技术领域technical field
本发明涉及图像识别领域，具体涉及一种基于多任务学习的卷积神经网络的人脸属性分析方法。The invention relates to the field of image recognition, in particular to a face attribute analysis method based on a multi-task learning convolutional neural network.
背景技术Background technique
传统的人脸图像分析技术往往只针对单个任务，如年龄估算、性别识别、种族分类等，针对人脸多属性分析时，需要分多次计算，非常消耗时间，很难达到实际需求。此外，单任务的人脸图像分析技术忽视了各个信息之间的联系，不能充分利用人脸图像中所蕴含的信息。人脸的面部特征在不同性别、不同种族之间是不一样的，如男女之间、黑白人种之间皮肤细腻程度、肤色、皮肤光亮程度等存在差异，并且皮肤的光亮程度、色泽、皱纹纹理等会随着年龄增长而发生相应的变化，其变化速度也随性别、种族而异。由此可见，各个人脸信息之间是紧密联系的，将各个任务进行独立学习在一定程度上会丢失很多有用的信息，从而降低模型的泛化能力。Traditional face image analysis techniques are often only for a single task, such as age estimation, gender recognition, race classification, etc. For multi-attribute analysis of faces, it needs to be calculated in multiple times, which is very time-consuming and difficult to meet actual needs. In addition, the single-task face image analysis technology ignores the connection between various information and cannot make full use of the information contained in the face image. The facial features of the human face are different between different genders and different races. For example, there are differences in skin fineness, skin color, and skin lightness between men and women, black and white, and skin lightness, color, and wrinkles. Texture, etc. will change with age, and the speed of change also varies with gender and race. It can be seen that the face information is closely related, and learning each task independently will lose a lot of useful information to a certain extent, thereby reducing the generalization ability of the model.
发明内容Contents of the invention
为了解决现有技术中的上述问题，本发明提出一种基于多任务学习的卷积神经网络的人脸属性分析方法，提高了人脸多属性分析时的计算速度和模型的泛化能力。In order to solve the above-mentioned problems in the prior art, the present invention proposes a face attribute analysis method based on a multi-task learning convolutional neural network, which improves the calculation speed and the generalization ability of the model during face multi-attribute analysis.
本发明提出的基于多任务学习的卷积神经网络的人脸属性分析方法，包括单任务模型分析、多任务模型训练和人脸属性判断三部分；The face attribute analysis method based on the multi-task learning convolutional neural network proposed by the present invention includes three parts: single-task model analysis, multi-task model training and face attribute judgment;
单任务模型分析：Single task model analysis:
步骤A1，将各年龄人脸图像的原始样本进行人脸关键点检测，并进行人脸对齐后按照预设尺寸裁剪生成包含人脸图像的新样本；In step A1, the original samples of face images of different ages are subjected to face key point detection, and after face alignment, they are cropped according to a preset size to generate new samples containing face images;
步骤A2，利用步骤A1生成的新样本，分别训练年龄估算网络、性别识别网络、种族分类网络三个单任务卷积神经网络，比较各网络的收敛速度，获取收敛速度最慢的一个单任务卷积神经网络的权值；Step A2, using the new samples generated in step A1, train three single-task convolutional neural networks of age estimation network, gender recognition network, and race classification network, compare the convergence speed of each network, and obtain the single-task volume with the slowest convergence speed The weight of the product neural network;
多任务模型训练：Multi-task model training:
步骤B1，构建多任务卷积神经网络，该网络共有三个任务输出，分别对应年龄估算、性别识别和种族分类，三个任务都采用softmax损失函数作为目标函数；所述多任务卷积神经网络包括用于多任务学习中数据共享和信息交换的共享部分、以及用于计算上述三个任务输出的独立部分；利用步骤A2获取的单任务卷积神经网络的权值初始化多任务卷积神经网络的共享部分，形成初始化后的多任务卷积神经网络；Step B1, constructing a multi-task convolutional neural network, the network has three task outputs, respectively corresponding to age estimation, gender recognition and race classification, and the three tasks all use the softmax loss function as the objective function; the multi-task convolutional neural network Including a shared part for data sharing and information exchange in multi-task learning, and an independent part for calculating the output of the above three tasks; use the weights of the single-task convolutional neural network obtained in step A2 to initialize the multi-task convolutional neural network The shared part forms an initialized multi-task convolutional neural network;
步骤B2，利用步骤A1中生成的新样本，训练多任务卷积神经网络，得到训练好的多任务卷积神经网络模型；Step B2, using the new samples generated in step A1 to train the multi-task convolutional neural network to obtain the trained multi-task convolutional neural network model;
人脸属性判断：Face attribute judgment:
步骤C1，对所输入图片进行人脸检测，判断是否包含人脸图像，如包含则对输入图像进行人脸关键点检测，并进行人脸对齐，然后按照预设尺寸裁剪生成包含人脸图像的新图片；Step C1, perform face detection on the input image, determine whether it contains a face image, if yes, perform face key point detection on the input image, and perform face alignment, and then crop according to a preset size to generate a face image containing new picture;
步骤C2，将步骤C1所得新图片，输入到步骤B2得到的多任务卷积神经网络模型，进行年龄估算、性别识别和种族分类。Step C2, input the new picture obtained in step C1 into the multi-task convolutional neural network model obtained in step B2 to perform age estimation, gender identification and race classification.
优选的，步骤A1具体包括以下内容：Preferably, step A1 specifically includes the following:
步骤A11，选取各年龄人脸图像作为原始样本；Step A11, selecting face images of various ages as original samples;
步骤A12，对所选取的原始样本进行人脸关键点检测，得到两个关键点；Step A12, performing face key point detection on the selected original samples to obtain two key points;
步骤A13，按照两个关键点的位置及其连线对原始样本进行人脸图像的对齐，所述人脸图像的对齐包括对原始样本的旋转、缩放、平移；Step A13, aligning the face images of the original samples according to the positions of the two key points and their connection lines, the alignment of the face images includes rotation, scaling, and translation of the original samples;
步骤A14，将步骤A13中对齐后的样本按照预设尺寸裁剪生成包含人脸图像的新样本。Step A14, cropping the aligned samples in step A13 according to a preset size to generate a new sample containing a face image.
优选的，步骤A2中在分别训练年龄估算网络、性别识别网络、种族分类网络三个单任务卷积神经网络时，学习率、学习策略等条件完全一致。Preferably, in step A2, when training the three single-task convolutional neural networks of the age estimation network, the gender recognition network, and the race classification network, the conditions such as the learning rate and the learning strategy are completely consistent.
优选的，步骤B1中多任务卷积神经网络的共享部分为多任务网络的底层部分，包括数据输入以及卷积层和池化层。Preferably, the shared part of the multi-task convolutional neural network in step B1 is the bottom part of the multi-task network, including data input, convolutional layer and pooling layer.
优选的，步骤B1中多任务卷积神经网络的独立部分为：年龄估算、性别识别、种族分类三个任务独立的网络结构，每个独立网络结构拥有独立的卷积层、pooling层和全连接层。Preferably, the independent parts of the multi-task convolutional neural network in step B1 are three task-independent network structures: age estimation, gender recognition, and race classification, each independent network structure has an independent convolutional layer, pooling layer, and full connection layer.
优选的，多任务卷积神经网络总损失函数为：Preferably, the total loss function of the multi-task convolutional neural network is:
lmulti-task＝α·lage+β·lgender+γ·lracelmulti-task = α·lage +β·lgender +γ·lrace
其中lmulti-task为多任务网络的总损失，α、β、γ分别为预设的三个任务的权重系数，lage、lgender、lrace分别为多任务卷积神经网络中的年龄估算损失、性别识别损失、种族分类损失。Among them, lmulti-task is the total loss of the multi-task network, α, β, and γ are the weight coefficients of the three preset tasks, and lage , lgender , and lrace are the age estimates in the multi-task convolutional neural network. loss, gender recognition loss, race classification loss.
优选的，步骤B2中训练多任务卷积神经网络的方法为：Preferably, the method for training a multi-task convolutional neural network in step B2 is:
步骤B21，从步骤A1生成的新样本中随机抽取m张图像，输入到在步骤B1中构建并已初始化的多任务卷积神经网络，进行多任务同步训练；Step B21, randomly extract m images from the new samples generated in step A1, input them to the multi-task convolutional neural network constructed and initialized in step B1, and perform multi-task synchronous training;
步骤B22，多任务卷积神经网络前向传递，分别计算年龄估算损失lage、性别识别损失lgender和种族分类损失lrace；Step B22, forwarding the multi-task convolutional neural network to calculate age estimation loss lage , gender identification loss lgender and race classification loss lrace ;
步骤B23，计算多任务卷积神经网络的总损失lmulti-task；Step B23, calculating the total loss lmulti-task of the multi-task convolutional neural network;
步骤B24：判断网络训练是否收敛，若收敛则停止训练并得到多任务卷积神经网络模型，否则执行步骤B25；Step B24: Determine whether the network training is convergent, if it is convergent, stop the training and obtain the multi-task convolutional neural network model, otherwise execute step B25;
步骤B25：采用反向传播算法计算网络各参数梯度，采用随机梯度下降法更新网络参数权值；返回步骤B21。Step B25: Use the backpropagation algorithm to calculate the gradient of each parameter of the network, and use the stochastic gradient descent method to update the weight of the network parameters; return to step B21.
优选的，步骤C1具体包括以下内容：Preferably, step C1 specifically includes the following:
步骤C11，对所输入的图片检测其是否包含人脸，若不包含人脸则放弃该张图片，否则进入步骤C12；Step C11, check whether the input picture contains a human face, if it does not contain a human face, discard the picture, otherwise enter step C12;
步骤C12，对所输入的图片进行人脸关键点检测，得到两个关键点；Step C12, performing face key point detection on the input image to obtain two key points;
步骤C13，按照上述关键点的位置及其连线对原始图片进行人脸图像的对齐，所述人脸图像的对齐包括对原始图片的旋转、缩放、平移；Step C13, aligning the face images of the original picture according to the positions of the key points and their connections, the alignment of the face images includes rotation, scaling, and translation of the original picture;
步骤C14，将步骤C13中对齐后的图片按照预设尺寸裁剪生成包含人脸图像的新图片。In step C14, the aligned pictures in step C13 are cropped according to a preset size to generate a new picture containing a face image.
优选的，步骤C2具体包括以下内容：Preferably, step C2 specifically includes the following:
步骤C21，将步骤C1得到的新图片输入到已经训练好的多任务卷积神经网络，进行人脸多属性分析；Step C21, input the new picture obtained in step C1 into the multi-task convolutional neural network that has been trained, and perform face multi-attribute analysis;
步骤C22，得到年龄概率p1(i)，最终年龄估算结果为各年龄的数学期望值，其中输出结点个数为k+1个，i为输出节点序号，a(i)为输出节点i对应的年龄数值；In step C22, the age probability p1(i) is obtained, and the final age estimation result is the mathematical expectation value of each age, The number of output nodes is k+1, i is the serial number of the output node, and a(i) is the age value corresponding to the output node i;
步骤C23，得到性别类别概率p2(i)，最终性别识别结果为概率最大的性别，gender_pre＝argmaxip2(i)，其中i为性别类别序号；Step C23, obtain the gender category probability p2(i), the final gender recognition result is the gender with the highest probability, gender_pre=argmaxi p2(i), where i is the gender category serial number;
步骤C24，得到种族类别概率p3(i)，最终种族分类结果为概率最大的种族，race_pre＝argmaxip3(i)，其中i为种族类别序号。Step C24, get the race category probability p3(i), the final race classification result is the race with the highest probability, race_pre=argmaxi p3(i), where i is the race category number.
优选的，步骤A12和步骤C12所述的两个关键点为两眼中心点和上嘴唇中心点。Preferably, the two key points described in step A12 and step C12 are the center point of the two eyes and the center point of the upper lip.
本发明通过单任务模型分析、多任务模型训练，然后利用训练好的多任务学习的卷积神经网络对人脸多种属性(年龄、性别、种族)进行判断，提高了人脸多属性分析时的计算速度和模型的泛化能力。The present invention analyzes the multi-task model and trains the multi-task model, and then uses the trained multi-task learning convolutional neural network to judge the multiple attributes (age, gender, race) of the human face, thereby improving the performance of multiple attribute analysis of the human face. The calculation speed and the generalization ability of the model.
附图说明Description of drawings
图1为本实施例的步骤A1流程示意图；Fig. 1 is a schematic flow chart of step A1 of the present embodiment;
图2为本实施例的步骤A2流程示意图；Fig. 2 is the schematic flow chart of step A2 of the present embodiment;
图3为本实施例的多任务卷积神经网络框架示意图；FIG. 3 is a schematic diagram of the multi-task convolutional neural network framework of the present embodiment;
图4为本实施例的步骤B2流程示意图；Fig. 4 is the schematic flow chart of step B2 of the present embodiment;
图5为本实施例的步骤C1流程示意图；FIG. 5 is a schematic flow chart of step C1 of this embodiment;
图6为本实施例的步骤C2流程示意图。FIG. 6 is a schematic flow chart of step C2 of this embodiment.
具体实施方式detailed description
下面参照附图来描述本发明的优选实施方式。本领域技术人员应当理解的是，这些实施方式仅仅用于解释本发明的技术原理，并非旨在限制本发明的保护范围。Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.
本发明基于多任务学习的卷积神经网络的人脸属性分析方法，先进行单任务训练，找出收敛最慢的网络；再将训练好的收敛最慢的网络模型的权值赋给多任务卷积神经网络的共享部分，再进行多任务同步训练；这一步赋权值的工作会使多任务训练变得容易，可以很大程度上减小多任务网络针对收敛最慢任务的训练难度，使各个任务的收敛步调基本一致。The face attribute analysis method of the convolutional neural network based on multi-task learning in the present invention first performs single-task training to find out the network with the slowest convergence; then assigns the weight of the trained network model with the slowest convergence to the multi-task The shared part of the convolutional neural network, and then perform multi-task synchronization training; this step of weight assignment will make multi-task training easier, and can greatly reduce the training difficulty of the multi-task network for the slowest convergence task. Make the convergence pace of each task basically the same.
本发明包括单任务模型分析、多任务模型训练和人脸属性判断三部分；The present invention includes three parts: single-task model analysis, multi-task model training and face attribute judgment;
单任务模型分析：Single task model analysis:
步骤A1，将各年龄人脸图像的原始样本进行人脸关键点检测，并进行人脸对齐后按照预设尺寸裁剪生成包含人脸图像的新样本；In step A1, the original samples of face images of different ages are subjected to face key point detection, and after face alignment, they are cropped according to a preset size to generate new samples containing face images;
步骤A2，利用步骤A1生成的新样本，分别训练年龄估算网络、性别识别网络、种族分类网络三个单任务卷积神经网络，比较各网络的收敛速度，获取收敛速度最慢的一个单任务卷积神经网络的权值；Step A2, using the new samples generated in step A1, train three single-task convolutional neural networks of age estimation network, gender recognition network, and race classification network, compare the convergence speed of each network, and obtain the single-task volume with the slowest convergence speed The weight of the product neural network;
多任务模型训练：Multi-task model training:
步骤B1，构建多任务卷积神经网络，该网络共有三个任务输出，分别对应年龄估算、性别识别和种族分类，三个任务都采用softmax损失函数作为目标函数；所述多任务卷积神经网络包括用于多任务学习中数据共享和信息交换的共享部分、以及用于计算上述三个任务输出的独立部分；利用步骤A2获取的单任务卷积神经网络的权值初始化多任务卷积神经网络的共享部分，形成初始化后的多任务卷积神经网络；Step B1, constructing a multi-task convolutional neural network, the network has three task outputs, respectively corresponding to age estimation, gender recognition and race classification, and the three tasks all use the softmax loss function as the objective function; the multi-task convolutional neural network Including a shared part for data sharing and information exchange in multi-task learning, and an independent part for calculating the output of the above three tasks; use the weights of the single-task convolutional neural network obtained in step A2 to initialize the multi-task convolutional neural network The shared part forms an initialized multi-task convolutional neural network;
步骤B2，利用步骤A1中生成的新样本，训练多任务卷积神经网络，得到训练好的多任务卷积神经网络模型；Step B2, using the new samples generated in step A1 to train the multi-task convolutional neural network to obtain the trained multi-task convolutional neural network model;
人脸属性判断：Face attribute judgment:
步骤C1，对所输入图片进行人脸检测，判断是否包含人脸图像，如包含则对输入图像进行人脸关键点检测，并进行人脸对齐，然后按照预设尺寸裁剪生成包含人脸图像的新图片；Step C1, perform face detection on the input image, determine whether it contains a face image, if yes, perform face key point detection on the input image, and perform face alignment, and then crop according to a preset size to generate a face image containing new picture;
步骤C2，将步骤C1所得新图片，输入到步骤B2得到的多任务卷积神经网络模型，进行年龄估算、性别识别和种族分类。Step C2, input the new picture obtained in step C1 into the multi-task convolutional neural network model obtained in step B2 to perform age estimation, gender identification and race classification.
如图1所示，本实施例中步骤A1具体包括以下内容：As shown in Figure 1, step A1 in this embodiment specifically includes the following contents:
步骤A11，选取各年龄人脸图像作为原始样本；Step A11, selecting face images of various ages as original samples;
步骤A12，对所选取的原始样本进行人脸关键点检测，得到两个关键点；Step A12, performing face key point detection on the selected original samples to obtain two key points;
步骤A13，按照两个关键点的位置及其连线对原始样本进行人脸图像的对齐，所述人脸图像的对齐包括对原始样本的旋转、缩放、平移；Step A13, aligning the face images of the original samples according to the positions of the two key points and their connection lines, the alignment of the face images includes rotation, scaling, and translation of the original samples;
步骤A14，将步骤A13中对齐后的样本按照预设尺寸裁剪生成包含人脸图像的新样本。Step A14, cropping the aligned samples in step A13 according to a preset size to generate a new sample containing a face image.
如图2所示，本实施例中步骤A2分别训练年龄估算网络、性别识别网络、种族分类网络三个单任务卷积神经网络时，学习率、学习策略等条件完全一致。本实施例中得出三个任务的收敛速度最慢的为年龄估算任务，性别识别任务和种族分类任务收敛速度大致相同，所以获取收敛最慢的年龄估算任务网络模型的权值。As shown in Figure 2, when step A2 in this embodiment trains the three single-task convolutional neural networks of the age estimation network, the gender recognition network, and the race classification network, the conditions such as the learning rate and learning strategy are exactly the same. In this embodiment, it is concluded that the slowest convergence speed of the three tasks is the age estimation task, and the convergence speed of the gender recognition task and the race classification task is roughly the same, so the weight of the age estimation task network model with the slowest convergence is obtained.
如图3所示为本实施例多任务卷积神经网络框架图。FIG. 3 is a frame diagram of a multi-task convolutional neural network in this embodiment.
本实施例中，步骤B1中多任务卷积神经网络的共享部分为多任务网络的底层部分，包括数据输入以及卷积层和池化层；共享部分实现多任务学习中数据共享、信息交换；三个任务信息共享，有助于提高模型的泛化能力。如图3所示，本实施例的共享层包括输入、卷积层1、池化层1、卷积层2、池化层2、卷积层3、卷积层4。In this embodiment, the shared part of the multi-task convolutional neural network in step B1 is the bottom part of the multi-task network, including data input, convolutional layer and pooling layer; the shared part realizes data sharing and information exchange in multi-task learning; The information sharing of the three tasks helps to improve the generalization ability of the model. As shown in FIG. 3 , the shared layer in this embodiment includes an input, a convolutional layer 1 , a pooling layer 1 , a convolutional layer 2 , a pooling layer 2 , a convolutional layer 3 , and a convolutional layer 4 .
本实施例中，步骤B1中多任务卷积神经网络的独立部分为：年龄估算、性别识别、种族分类三个任务独立的网络结构，每个独立网络结构拥有独立的卷积层、pooling层(池化层)和全连接层，用于训练出更加专一的特征。如图3所示，本实施例的独立部分为三个分支，分别用于年龄估算、性别识别、种族分类的计算和输出，对应的年龄估算分支包括年龄卷积层5、年龄池化层5、年龄全连接层6，性别估算分支包括性别卷积层5、性别池化层5、性别全连接层6，种族估算分支包括种族卷积层5、种族池化层5、种族全连接层6。In this embodiment, the independent parts of the multi-task convolutional neural network in step B1 are three task-independent network structures: age estimation, gender recognition, and race classification, each independent network structure has an independent convolutional layer and a pooling layer ( Pooling layer) and fully connected layer are used to train more specific features. As shown in Figure 3, the independent parts of this embodiment are three branches, which are used for the calculation and output of age estimation, gender recognition, and race classification respectively. The corresponding age estimation branches include age convolution layer 5 and age pooling layer 5 , Age fully connected layer 6, gender estimation branch includes gender convolutional layer 5, gender pooling layer 5, gender fully connected layer 6, race estimation branch includes race convolutional layer 5, race pooling layer 5, race fully connected layer 6 .
本实施例中，单任务网络结构也可以看做是多任务网络的一部分，只是把其它任务的独立部分去掉了，例如单任务年龄网络的结构是将多任务网络中性别和种族两个任务的独立部分去掉。In this embodiment, the single-task network structure can also be regarded as a part of the multi-task network, but the independent parts of other tasks are removed. The independent part is removed.
本实施例中，多任务卷积神经网络总损失函数如公式(1)所示：In this embodiment, the total loss function of the multi-task convolutional neural network is shown in formula (1):
lmulti-task＝α·lage+β·lgender+γ·lrace (1)lmulti-task = α·lage +β·lgender +γ·lrace (1)
其中lmulti-task为多任务网络的总损失，α、β、γ分别为预设的三个任务的权重系数，lage、lgender、lrace分别为多任务卷积神经网络中的年龄估算损失、性别识别损失、种族分类损失。Among them, lmulti-task is the total loss of the multi-task network, α, β, and γ are the weight coefficients of the three preset tasks, and lage , lgender , and lrace are the age estimates in the multi-task convolutional neural network. loss, gender recognition loss, race classification loss.
本实施例中，步骤B2中训练多任务卷积神经网络的方法如图4所示，包括：In this embodiment, the method for training a multi-task convolutional neural network in step B2 is shown in Figure 4, including:
步骤B21，从步骤A1生成的新样本中随机抽取m张图像，输入到在步骤B1中构建并已初始化的多任务卷积神经网络，进行多任务同步训练；Step B21, randomly extract m images from the new samples generated in step A1, input them to the multi-task convolutional neural network constructed and initialized in step B1, and perform multi-task synchronous training;
步骤B22，多任务卷积神经网络前向传递，分别计算年龄估算损失lage、性别识别损失lgender和种族分类损失lrace；Step B22, forwarding the multi-task convolutional neural network to calculate age estimation loss lage , gender identification loss lgender and race classification loss lrace ;
步骤B23，计算多任务卷积神经网络的总损失lmulti-task；Step B23, calculating the total loss lmulti-task of the multi-task convolutional neural network;
步骤B24：判断网络训练是否收敛，若收敛则停止训练并得到多任务卷积神经网络模型，否则执行步骤B25；Step B24: Determine whether the network training is convergent, if it is convergent, stop the training and obtain the multi-task convolutional neural network model, otherwise execute step B25;
步骤B25：采用反向传播算法计算网络各参数梯度，采用随机梯度下降法(Stochastic Gradient Descent,SGD)更新网络参数权值；返回步骤B21。Step B25: Use the backpropagation algorithm to calculate the gradient of each parameter of the network, and use the stochastic gradient descent method (Stochastic Gradient Descent, SGD) to update the network parameter weights; return to step B21.
本实施例中，步骤C1具体如图5所示，包括：In this embodiment, step C1 is specifically shown in Figure 5, including:
步骤C11，对所输入的图片检测其是否包含人脸，若不包含人脸则放弃该张图片，否则进入步骤C12；Step C11, check whether the input picture contains a human face, if it does not contain a human face, discard the picture, otherwise enter step C12;
步骤C12，对所输入的图片进行人脸关键点检测，得到两个关键点；Step C12, performing face key point detection on the input image to obtain two key points;
步骤C13，按照上述关键点的位置及其连线对原始图片进行人脸图像的对齐，所述人脸图像的对齐包括对原始图片的旋转、缩放、平移；Step C13, aligning the face images of the original picture according to the positions of the key points and their connections, the alignment of the face images includes rotation, scaling, and translation of the original picture;
步骤C14，将步骤C13中对齐后的图片按照预设尺寸裁剪生成包含人脸图像的新图片。In step C14, the aligned pictures in step C13 are cropped according to a preset size to generate a new picture containing a face image.
本实施例中，步骤C2具体如图6所示，包括：In this embodiment, step C2 is specifically shown in Figure 6, including:
步骤C21，将步骤C1得到的新图片输入到已经训练好的多任务卷积神经网络，前向传递，进行人脸多属性分析；Step C21, input the new picture obtained in step C1 into the multi-task convolutional neural network that has been trained, and pass it forward to perform face multi-attribute analysis;
步骤C22，得到年龄概率p1(i)，最终年龄估算结果为各年龄的数学期望值，其中输出结点个数为k+1个，i为输出节点序号，a(i)为输出节点i对应的年龄数值；In step C22, the age probability p1(i) is obtained, and the final age estimation result is the mathematical expectation value of each age, The number of output nodes is k+1, i is the serial number of the output node, and a(i) is the age value corresponding to the output node i;
步骤C23，得到性别类别概率p2(i)，最终性别识别结果为概率最大的性别，gender_pre＝argmaxip2(i)，其中i为性别类别序号；Step C23, obtain the gender category probability p2(i), the final gender recognition result is the gender with the highest probability, gender_pre=argmaxi p2(i), where i is the gender category serial number;
步骤C24，得到种族类别概率p3(i)，最终种族分类结果为概率最大的种族，race_pre＝argmaxip3(i)，其中i为种族类别序号。Step C24, get the race category probability p3(i), the final race classification result is the race with the highest probability, race_pre=argmaxi p3(i), where i is the race category number.
本实施例中，步骤A12和步骤C12所述的两个关键点为两眼中心点和上嘴唇中心点，步骤A14或C14所述的预设尺寸的分辨率为224*224。In this embodiment, the two key points described in step A12 and step C12 are the center point of the two eyes and the center point of the upper lip, and the resolution of the preset size described in step A14 or C14 is 224*224.
本领域技术人员应该能够意识到，结合本文中所公开的实施例描述的各示例的方法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明电子硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以电子硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。本领域技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。Those skilled in the art should be able to realize that the method steps described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the possibility of electronic hardware and software For interchangeability, in the above description, the composition and steps of each example have been generally described according to their functions. Whether these functions are performed by electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may implement the described functionality using different methods for each particular application, but such implementation should not be considered as exceeding the scope of the present invention.
至此，已经结合附图所示的优选实施方式描述了本发明的技术方案，但是，本领域技术人员容易理解的是，本发明的保护范围显然不局限于这些具体实施方式。在不偏离本发明的原理的前提下，本领域技术人员可以对相关技术特征作出等同的更改或替换，这些更改或替换之后的技术方案都将落入本发明的保护范围之内。So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings, but those skilled in the art will easily understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610856231.1ACN106529402B (en) | 2016-09-27 | 2016-09-27 | The face character analysis method of convolutional neural networks based on multi-task learning |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610856231.1ACN106529402B (en) | 2016-09-27 | 2016-09-27 | The face character analysis method of convolutional neural networks based on multi-task learning |
| Publication Number | Publication Date |
|---|---|
| CN106529402Atrue CN106529402A (en) | 2017-03-22 |
| CN106529402B CN106529402B (en) | 2019-05-28 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610856231.1AActiveCN106529402B (en) | 2016-09-27 | 2016-09-27 | The face character analysis method of convolutional neural networks based on multi-task learning |
| Country | Link |
|---|---|
| CN (1) | CN106529402B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133948A (en)* | 2017-05-09 | 2017-09-05 | 电子科技大学 | Image blurring and noise evaluating method based on multitask convolutional neural networks |
| CN107247947A (en)* | 2017-07-07 | 2017-10-13 | 北京智慧眼科技股份有限公司 | Face character recognition methods and device |
| CN107463888A (en)* | 2017-07-21 | 2017-12-12 | 竹间智能科技（上海）有限公司 | Face mood analysis method and system based on multi-task learning and deep learning |
| CN107545243A (en)* | 2017-08-07 | 2018-01-05 | 南京信息工程大学 | Yellow race's face identification method based on depth convolution model |
| CN107590460A (en)* | 2017-09-12 | 2018-01-16 | 北京达佳互联信息技术有限公司 | Face classification method, apparatus and intelligent terminal |
| CN107742107A (en)* | 2017-10-20 | 2018-02-27 | 北京达佳互联信息技术有限公司 | Face image classification method, device and server |
| CN107844781A (en)* | 2017-11-28 | 2018-03-27 | 腾讯科技（深圳）有限公司 | Face character recognition methods and device, electronic equipment and storage medium |
| CN107844784A (en)* | 2017-12-08 | 2018-03-27 | 广东美的智能机器人有限公司 | Face identification method, device, computer equipment and readable storage medium storing program for executing |
| CN107886073A (en)* | 2017-11-10 | 2018-04-06 | 重庆邮电大学 | A kind of more attribute recognition approaches of fine granularity vehicle based on convolutional neural networks |
| CN107958444A (en)* | 2017-12-28 | 2018-04-24 | 江西高创保安服务技术有限公司 | A kind of face super-resolution reconstruction method based on deep learning |
| CN108021863A (en)* | 2017-11-01 | 2018-05-11 | 平安科技（深圳）有限公司 | Electronic device, the character classification by age method based on image and storage medium |
| CN108171254A (en)* | 2017-11-22 | 2018-06-15 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
| CN108197525A (en)* | 2017-11-20 | 2018-06-22 | 中国科学院自动化研究所 | Face image synthesis method and device |
| CN108229503A (en)* | 2018-01-04 | 2018-06-29 | 浙江大学 | A kind of feature extracting method for clothes photo |
| CN108256482A (en)* | 2018-01-18 | 2018-07-06 | 中科视拓（北京）科技有限公司 | A kind of face age estimation method that Distributed learning is carried out based on convolutional neural networks |
| CN108345832A (en)* | 2017-12-28 | 2018-07-31 | 新智数字科技有限公司 | A kind of method, apparatus and equipment of Face datection |
| CN108416327A (en)* | 2018-03-28 | 2018-08-17 | 京东方科技集团股份有限公司 | A kind of object detection method, device, computer equipment and readable storage medium storing program for executing |
| CN108509041A (en)* | 2018-03-29 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | Method and apparatus for executing operation |
| CN108537193A (en)* | 2018-04-17 | 2018-09-14 | 厦门美图之家科技有限公司 | Ethnic attribute recognition approach and mobile terminal in a kind of face character |
| CN108564097A (en)* | 2017-12-05 | 2018-09-21 | 华南理工大学 | A kind of multiscale target detection method based on depth convolutional neural networks |
| CN108665065A (en)* | 2018-04-25 | 2018-10-16 | 清华大学 | Processing method, device, equipment and the storage medium of task data |
| CN108734146A (en)* | 2018-05-28 | 2018-11-02 | 北京达佳互联信息技术有限公司 | Facial image Age estimation method, apparatus, computer equipment and storage medium |
| CN108764048A (en)* | 2018-04-28 | 2018-11-06 | 中国科学院自动化研究所 | Face critical point detection method and device |
| CN108764207A (en)* | 2018-06-07 | 2018-11-06 | 厦门大学 | A kind of facial expression recognizing method based on multitask convolutional neural networks |
| CN108764203A (en)* | 2018-06-06 | 2018-11-06 | 四川大学 | A kind of pedestrian's quantitative analysis and display systems towards urban planning |
| CN108875932A (en)* | 2018-02-27 | 2018-11-23 | 北京旷视科技有限公司 | Image-recognizing method, device and system and storage medium |
| CN108960283A (en)* | 2018-05-30 | 2018-12-07 | 北京市商汤科技开发有限公司 | Classification task incremental processing method and device, electronic equipment and storage medium |
| CN109063759A (en)* | 2018-07-20 | 2018-12-21 | 浙江大学 | A kind of neural network structure searching method applied to the more attribute forecasts of picture |
| CN109086837A (en)* | 2018-10-24 | 2018-12-25 | 高嵩 | User property classification method, storage medium, device and electronic equipment based on convolutional neural networks |
| CN109145987A (en)* | 2018-08-21 | 2019-01-04 | 厦门美图之家科技有限公司 | model generating method and device |
| CN109145798A (en)* | 2018-08-13 | 2019-01-04 | 浙江零跑科技有限公司 | A kind of Driving Scene target identification and travelable region segmentation integrated approach |
| CN109242516A (en)* | 2018-09-06 | 2019-01-18 | 北京京东尚科信息技术有限公司 | The single method and apparatus of processing service |
| CN109299487A (en)* | 2017-07-25 | 2019-02-01 | 展讯通信（上海）有限公司 | Neural network model, accelerator, modeling method and device, medium and system |
| CN109325398A (en)* | 2018-06-30 | 2019-02-12 | 东南大学 | A face attribute analysis method based on transfer learning |
| CN109359562A (en)* | 2018-09-29 | 2019-02-19 | 佳都新太科技股份有限公司 | Target identification method, device, target identification equipment and storage medium |
| CN109359499A (en)* | 2017-07-26 | 2019-02-19 | 虹软科技股份有限公司 | A method and apparatus for face classification |
| CN109426262A (en)* | 2017-08-25 | 2019-03-05 | 福特全球技术公司 | Shared processing to deep neural network |
| CN109472193A (en)* | 2018-09-21 | 2019-03-15 | 北京飞搜科技有限公司 | Method for detecting human face and device |
| CN109508654A (en)* | 2018-10-26 | 2019-03-22 | 中国地质大学（武汉） | Merge the human face analysis method and system of multitask and multiple dimensioned convolutional neural networks |
| CN109522824A (en)* | 2018-10-30 | 2019-03-26 | 平安科技（深圳）有限公司 | Face character recognition methods, device, computer installation and storage medium |
| CN109522872A (en)* | 2018-12-04 | 2019-03-26 | 西安电子科技大学 | A kind of face identification method, device, computer equipment and storage medium |
| CN109583277A (en)* | 2017-09-29 | 2019-04-05 | 大连恒锐科技股份有限公司 | Gender judgment method for barefoot or stocking foot based on CNN |
| CN109583431A (en)* | 2019-01-02 | 2019-04-05 | 上海极链网络科技有限公司 | A kind of face Emotion identification model, method and its electronic device |
| CN109598184A (en)* | 2017-09-30 | 2019-04-09 | 北京图森未来科技有限公司 | A kind for the treatment of method and apparatus of multi-split task |
| CN109697395A (en)* | 2017-10-24 | 2019-04-30 | 华为技术有限公司 | Thingness prediction technique, device and equipment |
| CN109727071A (en)* | 2018-12-28 | 2019-05-07 | 中国科学院半导体研究所 | Advertising recommendation method and system |
| CN109871814A (en)* | 2019-02-22 | 2019-06-11 | 成都旷视金智科技有限公司 | Estimation method, device, electronic equipment and the computer storage medium at age |
| WO2019109526A1 (en)* | 2017-12-06 | 2019-06-13 | 平安科技（深圳）有限公司 | Method and device for age recognition of face image, storage medium |
| CN109886154A (en)* | 2019-01-30 | 2019-06-14 | 电子科技大学 | Pedestrian appearance attribute recognition method based on multi-dataset joint training based on Inception V3 |
| CN109893095A (en)* | 2019-03-11 | 2019-06-18 | 常州市贝叶斯智能科技有限公司 | A kind of intelligent robot system of body composition detection and analysis |
| CN109947960A (en)* | 2019-03-08 | 2019-06-28 | 南京信息工程大学 | The construction method of face multi-attribute joint estimation model based on depth convolution |
| CN109993102A (en)* | 2019-03-28 | 2019-07-09 | 北京达佳互联信息技术有限公司 | Similar face retrieval method, apparatus and storage medium |
| CN110033481A (en)* | 2018-01-10 | 2019-07-19 | 北京三星通信技术研究有限公司 | Method and apparatus for carrying out image procossing |
| CN110046571A (en)* | 2019-04-15 | 2019-07-23 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110069994A (en)* | 2019-03-18 | 2019-07-30 | 中国科学院自动化研究所 | Face character identifying system, method based on face multizone |
| CN110084216A (en)* | 2019-05-06 | 2019-08-02 | 苏州科达科技股份有限公司 | Human face recognition model training and face identification method, system, equipment and medium |
| CN110111246A (en)* | 2019-05-15 | 2019-08-09 | 北京市商汤科技开发有限公司 | A kind of avatars generation method and device, storage medium |
| CN110163269A (en)* | 2019-05-09 | 2019-08-23 | 北京迈格威科技有限公司 | Model generating method, device and computer equipment based on deep learning |
| CN110232352A (en)* | 2019-06-12 | 2019-09-13 | 东北大学 | A kind of improved method of the multitask concatenated convolutional neural network model for recognition of face |
| CN110263756A (en)* | 2019-06-28 | 2019-09-20 | 东北大学 | A kind of human face super-resolution reconstructing system based on joint multi-task learning |
| CN110287836A (en)* | 2019-06-14 | 2019-09-27 | 北京迈格威科技有限公司 | Image classification method, device, computer equipment and storage medium |
| CN110334735A (en)* | 2019-05-31 | 2019-10-15 | 北京奇艺世纪科技有限公司 | Multitask network generation method, device, computer equipment and storage medium |
| CN110348416A (en)* | 2019-07-17 | 2019-10-18 | 北方工业大学 | A multi-task face recognition method based on multi-scale feature fusion convolutional neural network |
| CN110395257A (en)* | 2018-04-20 | 2019-11-01 | 北京图森未来科技有限公司 | A lane line instance detection method and device, automatic driving vehicle |
| CN110427795A (en)* | 2019-01-28 | 2019-11-08 | 厦门瑞为信息技术有限公司 | A kind of property analysis method based on head photo, system and computer equipment |
| CN110444214A (en)* | 2017-11-24 | 2019-11-12 | 深圳市腾讯计算机系统有限公司 | Speech processing model training method, device, electronic equipment and storage medium |
| CN110503072A (en)* | 2019-08-29 | 2019-11-26 | 南京信息工程大学 | Face age estimation method based on multi-branch CNN architecture |
| CN110516512A (en)* | 2018-05-21 | 2019-11-29 | 北京中科奥森数据科技有限公司 | Training method, pedestrian's attribute recognition approach and the device of pedestrian's attributive analysis model |
| CN110584654A (en)* | 2019-10-09 | 2019-12-20 | 中山大学 | Multi-mode convolutional neural network-based electrocardiosignal classification method |
| CN110709856A (en)* | 2017-05-31 | 2020-01-17 | 宝洁公司 | System and method for determining apparent skin age |
| US20200065563A1 (en)* | 2018-08-21 | 2020-02-27 | Software Ag | Systems and/or methods for accelerating facial feature vector matching with supervised machine learning |
| CN110874587A (en)* | 2019-12-26 | 2020-03-10 | 浙江大学 | Face characteristic parameter extraction system |
| WO2020078214A1 (en)* | 2018-10-19 | 2020-04-23 | 北京市商汤科技开发有限公司 | Child state analysis method and apparatus, vehicle, electronic device and storage medium |
| CN111191675A (en)* | 2019-12-03 | 2020-05-22 | 深圳市华尊科技股份有限公司 | Pedestrian attribute recognition model implementation method and related device |
| WO2020114118A1 (en)* | 2018-12-07 | 2020-06-11 | 深圳光启空间技术有限公司 | Facial attribute identification method and device, storage medium and processor |
| CN111291253A (en)* | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Model training method, consultation recommendation method, device and electronic equipment |
| CN111325108A (en)* | 2020-01-22 | 2020-06-23 | 中能国际建筑投资集团有限公司 | Multitask network model, using method, device and storage medium |
| CN111339818A (en)* | 2019-12-18 | 2020-06-26 | 中国人民解放军第四军医大学 | A face multi-attribute recognition system |
| CN111373419A (en)* | 2017-10-26 | 2020-07-03 | 奇跃公司 | Gradient Normalization System and Method for Adaptive Loss Balancing in Deep Multitask Networks |
| CN111369615A (en)* | 2020-02-21 | 2020-07-03 | 苏州优纳医疗器械有限公司 | Cell nucleus central point detection method based on multitask convolutional neural network |
| CN111401294A (en)* | 2020-03-27 | 2020-07-10 | 山东财经大学 | Multitask face attribute classification method and system based on self-adaptive feature fusion |
| CN111507263A (en)* | 2020-04-17 | 2020-08-07 | 电子科技大学 | A face multi-attribute recognition method based on multi-source data |
| CN111539452A (en)* | 2020-03-26 | 2020-08-14 | 深圳云天励飞技术有限公司 | Image recognition method and device for multitask attributes, electronic equipment and storage medium |
| CN111598000A (en)* | 2020-05-18 | 2020-08-28 | 中移（杭州）信息技术有限公司 | Multitask-based face recognition method, device, server and readable storage medium |
| CN111598600A (en)* | 2019-02-21 | 2020-08-28 | 虹软科技股份有限公司 | Multimedia information pushing method and system and terminal equipment |
| CN111626087A (en)* | 2019-02-28 | 2020-09-04 | 北京市商汤科技开发有限公司 | Neural network training and eye opening and closing state detection method, device and equipment |
| CN111626115A (en)* | 2020-04-20 | 2020-09-04 | 北京市西城区培智中心学校 | Face attribute identification method and device |
| CN111626303A (en)* | 2020-05-29 | 2020-09-04 | 南京甄视智能科技有限公司 | Sex and age identification method, sex and age identification device, storage medium and server |
| CN111680547A (en)* | 2020-04-27 | 2020-09-18 | 北京百度网讯科技有限公司 | Recognition method, device, electronic device and storage medium of traffic countdown board |
| CN112052734A (en)* | 2020-07-31 | 2020-12-08 | 北京奇艺世纪科技有限公司 | Role characteristic identification network generation method, role characteristic identification device, role characteristic identification equipment and role characteristic identification medium |
| CN112085540A (en)* | 2020-09-27 | 2020-12-15 | 湖北科技学院 | Advertising intelligent push system and method based on artificial intelligence technology |
| CN112149449A (en)* | 2019-06-26 | 2020-12-29 | 北京华捷艾米科技有限公司 | Face attribute recognition method and system based on deep learning |
| CN112163676A (en)* | 2020-10-13 | 2021-01-01 | 北京百度网讯科技有限公司 | Multi-task service prediction model training method, device, equipment and storage medium |
| CN112333545A (en)* | 2019-07-31 | 2021-02-05 | Tcl集团股份有限公司 | Television content recommendation method, system, storage medium and smart television |
| WO2021031566A1 (en)* | 2019-08-21 | 2021-02-25 | 五邑大学 | Multi-task learning-based facial beauty prediction method |
| CN112784916A (en)* | 2021-01-29 | 2021-05-11 | 西安电子科技大学 | Air target micro-motion parameter real-time extraction method based on multitask convolutional network |
| CN112825122A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Ethnicity judgment method, ethnicity judgment device, ethnicity judgment medium and ethnicity judgment equipment based on two-dimensional face image |
| CN112825117A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Behavior attribute judgment method, behavior attribute judgment device, behavior attribute judgment medium and behavior attribute judgment equipment based on head features |
| CN112825119A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Face attribute judgment method and device, computer readable storage medium and equipment |
| CN112906668A (en)* | 2021-04-07 | 2021-06-04 | 上海应用技术大学 | Face information identification method based on convolutional neural network |
| US20210174066A1 (en)* | 2017-11-09 | 2021-06-10 | Beijing Dajia Internet Information Technology Co., Ltd. | Method and device for age estimation |
| CN113095211A (en)* | 2021-04-08 | 2021-07-09 | 第六镜科技(成都)有限公司 | Image processing method and system and electronic equipment |
| CN113420768A (en)* | 2021-08-24 | 2021-09-21 | 深圳市信润富联数字科技有限公司 | Core category determination method and device, electronic equipment and storage medium |
| WO2021237727A1 (en)* | 2020-05-29 | 2021-12-02 | Siemens Aktiengesellschaft | Method and apparatus of image processing |
| CN114005166A (en)* | 2021-11-25 | 2022-02-01 | 浩云科技股份有限公司 | A face recognition method and device based on multi-task learning |
| CN114038044A (en)* | 2021-11-23 | 2022-02-11 | 携程旅游信息技术（上海）有限公司 | Face gender and age recognition method, device, electronic device and storage medium |
| WO2022052021A1 (en)* | 2020-09-11 | 2022-03-17 | 京东方科技集团股份有限公司 | Joint model training method, object information processing method, apparatus, and system |
| WO2022061726A1 (en)* | 2020-09-25 | 2022-03-31 | Intel Corporation | Method and system of multiple facial attributes recognition using highly efficient neural networks |
| CN114332914A (en)* | 2021-11-29 | 2022-04-12 | 中国电子科技集团公司电子科学研究院 | Personnel feature identification method, device and computer-readable storage medium |
| CN114467121A (en)* | 2019-11-27 | 2022-05-10 | 华为技术有限公司 | A perceptual network and image processing method |
| CN114495215A (en)* | 2022-01-14 | 2022-05-13 | 山东新一代信息产业技术研究院有限公司 | A unified multi-task learning method for interactive robots based on attention mechanism |
| CN114529731A (en)* | 2020-10-30 | 2022-05-24 | 北京眼神智能科技有限公司 | Face feature point positioning and attribute analysis method and device, storage medium and equipment |
| CN114821538A (en)* | 2022-05-19 | 2022-07-29 | 北京地平线机器人技术研发有限公司 | Training method and device of multi-task model |
| US11521021B2 (en) | 2019-04-09 | 2022-12-06 | Hitachi, Ltd. | Object recognition system and object recognition method |
| US11675876B2 (en) | 2020-10-28 | 2023-06-13 | International Business Machines Corporation | Training robust machine learning models |
| CN117079337A (en)* | 2023-10-17 | 2023-11-17 | 成都信息工程大学 | High-precision face attribute feature recognition device and method |
| CN119580318A (en)* | 2024-10-28 | 2025-03-07 | 广州像素数据技术股份有限公司 | A modular face attribute structure analysis method, device, equipment and medium |
| CN114495215B (en)* | 2022-01-14 | 2025-10-10 | 山东新一代信息产业技术研究院有限公司 | Unified multi-task learning method for interactive robots based on attention mechanism |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12300036B2 (en) | 2022-02-15 | 2025-05-13 | Ford Global Technologies, Llc | Biometric task network |
| US12406484B2 (en) | 2022-02-15 | 2025-09-02 | Ford Global Technologies, Llc | Biometric task network |
| US11776323B2 (en) | 2022-02-15 | 2023-10-03 | Ford Global Technologies, Llc | Biometric task network |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824054A (en)* | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded depth neural network-based face attribute recognition method |
| CN105469041A (en)* | 2015-11-19 | 2016-04-06 | 上海交通大学 | Facial point detection system based on multi-task regularization and layer-by-layer supervision neural networ |
| US20160140436A1 (en)* | 2014-11-15 | 2016-05-19 | Beijing Kuangshi Technology Co., Ltd. | Face Detection Using Machine Learning |
| CN105760859A (en)* | 2016-03-22 | 2016-07-13 | 中国科学院自动化研究所 | Method and device for identifying reticulate pattern face image based on multi-task convolutional neural network |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824054A (en)* | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded depth neural network-based face attribute recognition method |
| US20160140436A1 (en)* | 2014-11-15 | 2016-05-19 | Beijing Kuangshi Technology Co., Ltd. | Face Detection Using Machine Learning |
| CN105469041A (en)* | 2015-11-19 | 2016-04-06 | 上海交通大学 | Facial point detection system based on multi-task regularization and layer-by-layer supervision neural networ |
| CN105760859A (en)* | 2016-03-22 | 2016-07-13 | 中国科学院自动化研究所 | Method and device for identifying reticulate pattern face image based on multi-task convolutional neural network |
| Title |
|---|
| 邵蔚元 等: "多任务学习及卷积神经网络在人脸识别中的应用", 《计算机工程与应用》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133948A (en)* | 2017-05-09 | 2017-09-05 | 电子科技大学 | Image blurring and noise evaluating method based on multitask convolutional neural networks |
| CN107133948B (en)* | 2017-05-09 | 2020-05-08 | 电子科技大学 | Image blurring and noise evaluation method based on multitask convolution neural network |
| CN110709856B (en)* | 2017-05-31 | 2023-11-28 | 宝洁公司 | System and method for determining apparent skin age |
| CN110709856A (en)* | 2017-05-31 | 2020-01-17 | 宝洁公司 | System and method for determining apparent skin age |
| CN107247947A (en)* | 2017-07-07 | 2017-10-13 | 北京智慧眼科技股份有限公司 | Face character recognition methods and device |
| CN107247947B (en)* | 2017-07-07 | 2021-02-09 | 智慧眼科技股份有限公司 | Face attribute identification method and device |
| CN107463888A (en)* | 2017-07-21 | 2017-12-12 | 竹间智能科技（上海）有限公司 | Face mood analysis method and system based on multi-task learning and deep learning |
| CN107463888B (en)* | 2017-07-21 | 2020-05-19 | 竹间智能科技（上海）有限公司 | Face emotion analysis method and system based on multi-task learning and deep learning |
| CN109299487A (en)* | 2017-07-25 | 2019-02-01 | 展讯通信（上海）有限公司 | Neural network model, accelerator, modeling method and device, medium and system |
| US11455831B2 (en) | 2017-07-25 | 2022-09-27 | Arcsoft Corporation Limited | Method and apparatus for face classification |
| CN109359499A (en)* | 2017-07-26 | 2019-02-19 | 虹软科技股份有限公司 | A method and apparatus for face classification |
| CN107545243A (en)* | 2017-08-07 | 2018-01-05 | 南京信息工程大学 | Yellow race's face identification method based on depth convolution model |
| CN109426262A (en)* | 2017-08-25 | 2019-03-05 | 福特全球技术公司 | Shared processing to deep neural network |
| CN107590460A (en)* | 2017-09-12 | 2018-01-16 | 北京达佳互联信息技术有限公司 | Face classification method, apparatus and intelligent terminal |
| CN107590460B (en)* | 2017-09-12 | 2019-05-03 | 北京达佳互联信息技术有限公司 | Face classification method, apparatus and intelligent terminal |
| CN109583277A (en)* | 2017-09-29 | 2019-04-05 | 大连恒锐科技股份有限公司 | Gender judgment method for barefoot or stocking foot based on CNN |
| CN109598184A (en)* | 2017-09-30 | 2019-04-09 | 北京图森未来科技有限公司 | A kind for the treatment of method and apparatus of multi-split task |
| CN109598184B (en)* | 2017-09-30 | 2021-08-24 | 北京图森未来科技有限公司 | Method and device for processing multi-segmented tasks |
| CN107742107A (en)* | 2017-10-20 | 2018-02-27 | 北京达佳互联信息技术有限公司 | Face image classification method, device and server |
| CN107742107B (en)* | 2017-10-20 | 2019-03-01 | 北京达佳互联信息技术有限公司 | Facial image classification method, device and server |
| WO2019076227A1 (en)* | 2017-10-20 | 2019-04-25 | 北京达佳互联信息技术有限公司 | Human face image classification method and apparatus, and server |
| US11417148B2 (en) | 2017-10-20 | 2022-08-16 | Beijing Dajia Internet Information Technology Co., Ltd. | Human face image classification method and apparatus, and server |
| CN109697395A (en)* | 2017-10-24 | 2019-04-30 | 华为技术有限公司 | Thingness prediction technique, device and equipment |
| CN111373419A (en)* | 2017-10-26 | 2020-07-03 | 奇跃公司 | Gradient Normalization System and Method for Adaptive Loss Balancing in Deep Multitask Networks |
| CN111373419B (en)* | 2017-10-26 | 2025-08-05 | 奇跃公司 | Gradient normalization system and method for adaptive loss balancing in deep multi-task networks |
| CN108021863A (en)* | 2017-11-01 | 2018-05-11 | 平安科技（深圳）有限公司 | Electronic device, the character classification by age method based on image and storage medium |
| US11587356B2 (en)* | 2017-11-09 | 2023-02-21 | Beijing Dajia Internet Information Technology Co., Ltd. | Method and device for age estimation |
| US20210174066A1 (en)* | 2017-11-09 | 2021-06-10 | Beijing Dajia Internet Information Technology Co., Ltd. | Method and device for age estimation |
| CN107886073B (en)* | 2017-11-10 | 2021-07-27 | 重庆邮电大学 | A fine-grained vehicle multi-attribute recognition method based on convolutional neural network |
| CN107886073A (en)* | 2017-11-10 | 2018-04-06 | 重庆邮电大学 | A kind of more attribute recognition approaches of fine granularity vehicle based on convolutional neural networks |
| CN108197525A (en)* | 2017-11-20 | 2018-06-22 | 中国科学院自动化研究所 | Face image synthesis method and device |
| CN108197525B (en)* | 2017-11-20 | 2020-08-11 | 中国科学院自动化研究所 | Face image generation method and device |
| CN108171254A (en)* | 2017-11-22 | 2018-06-15 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
| CN110444214A (en)* | 2017-11-24 | 2019-11-12 | 深圳市腾讯计算机系统有限公司 | Speech processing model training method, device, electronic equipment and storage medium |
| CN110444214B (en)* | 2017-11-24 | 2021-08-17 | 深圳市腾讯计算机系统有限公司 | Speech signal processing model training method, device, electronic device and storage medium |
| CN107844781A (en)* | 2017-11-28 | 2018-03-27 | 腾讯科技（深圳）有限公司 | Face character recognition methods and device, electronic equipment and storage medium |
| CN108564097B (en)* | 2017-12-05 | 2020-09-22 | 华南理工大学 | Multi-scale target detection method based on deep convolutional neural network |
| CN108564097A (en)* | 2017-12-05 | 2018-09-21 | 华南理工大学 | A kind of multiscale target detection method based on depth convolutional neural networks |
| WO2019109526A1 (en)* | 2017-12-06 | 2019-06-13 | 平安科技（深圳）有限公司 | Method and device for age recognition of face image, storage medium |
| CN107844784A (en)* | 2017-12-08 | 2018-03-27 | 广东美的智能机器人有限公司 | Face identification method, device, computer equipment and readable storage medium storing program for executing |
| CN108345832A (en)* | 2017-12-28 | 2018-07-31 | 新智数字科技有限公司 | A kind of method, apparatus and equipment of Face datection |
| CN107958444A (en)* | 2017-12-28 | 2018-04-24 | 江西高创保安服务技术有限公司 | A kind of face super-resolution reconstruction method based on deep learning |
| CN108229503A (en)* | 2018-01-04 | 2018-06-29 | 浙江大学 | A kind of feature extracting method for clothes photo |
| CN110033481A (en)* | 2018-01-10 | 2019-07-19 | 北京三星通信技术研究有限公司 | Method and apparatus for carrying out image procossing |
| CN108256482B (en)* | 2018-01-18 | 2021-06-25 | 中科视拓（北京）科技有限公司 | Face age estimation method for distributed learning based on convolutional neural network |
| CN108256482A (en)* | 2018-01-18 | 2018-07-06 | 中科视拓（北京）科技有限公司 | A kind of face age estimation method that Distributed learning is carried out based on convolutional neural networks |
| CN108875932A (en)* | 2018-02-27 | 2018-11-23 | 北京旷视科技有限公司 | Image-recognizing method, device and system and storage medium |
| CN108416327B (en)* | 2018-03-28 | 2022-04-29 | 京东方科技集团股份有限公司 | Target detection method and device, computer equipment and readable storage medium |
| CN108416327A (en)* | 2018-03-28 | 2018-08-17 | 京东方科技集团股份有限公司 | A kind of object detection method, device, computer equipment and readable storage medium storing program for executing |
| CN108509041A (en)* | 2018-03-29 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | Method and apparatus for executing operation |
| CN108537193A (en)* | 2018-04-17 | 2018-09-14 | 厦门美图之家科技有限公司 | Ethnic attribute recognition approach and mobile terminal in a kind of face character |
| CN110395257A (en)* | 2018-04-20 | 2019-11-01 | 北京图森未来科技有限公司 | A lane line instance detection method and device, automatic driving vehicle |
| CN110395257B (en)* | 2018-04-20 | 2021-04-23 | 北京图森未来科技有限公司 | A lane line instance detection method and device, and an automatic driving vehicle |
| CN108665065A (en)* | 2018-04-25 | 2018-10-16 | 清华大学 | Processing method, device, equipment and the storage medium of task data |
| CN108665065B (en)* | 2018-04-25 | 2020-08-04 | 清华大学 | Method, device and equipment for processing task data and storage medium |
| CN108764048B (en)* | 2018-04-28 | 2021-03-16 | 中国科学院自动化研究所 | Face key point detection method and device |
| CN108764048A (en)* | 2018-04-28 | 2018-11-06 | 中国科学院自动化研究所 | Face critical point detection method and device |
| CN110516512B (en)* | 2018-05-21 | 2023-08-25 | 北京中科奥森数据科技有限公司 | Training method of pedestrian attribute analysis model, pedestrian attribute identification method and device |
| CN110516512A (en)* | 2018-05-21 | 2019-11-29 | 北京中科奥森数据科技有限公司 | Training method, pedestrian's attribute recognition approach and the device of pedestrian's attributive analysis model |
| CN108734146A (en)* | 2018-05-28 | 2018-11-02 | 北京达佳互联信息技术有限公司 | Facial image Age estimation method, apparatus, computer equipment and storage medium |
| CN108960283B (en)* | 2018-05-30 | 2022-01-11 | 北京市商汤科技开发有限公司 | Classification task increment processing method and device, electronic equipment and storage medium |
| CN108960283A (en)* | 2018-05-30 | 2018-12-07 | 北京市商汤科技开发有限公司 | Classification task incremental processing method and device, electronic equipment and storage medium |
| CN108764203A (en)* | 2018-06-06 | 2018-11-06 | 四川大学 | A kind of pedestrian's quantitative analysis and display systems towards urban planning |
| CN108764207A (en)* | 2018-06-07 | 2018-11-06 | 厦门大学 | A kind of facial expression recognizing method based on multitask convolutional neural networks |
| CN108764207B (en)* | 2018-06-07 | 2021-10-19 | 厦门大学 | A facial expression recognition method based on multi-task convolutional neural network |
| CN109325398B (en)* | 2018-06-30 | 2020-10-09 | 东南大学 | Human face attribute analysis method based on transfer learning |
| WO2020001082A1 (en)* | 2018-06-30 | 2020-01-02 | 东南大学 | Face attribute analysis method based on transfer learning |
| CN109325398A (en)* | 2018-06-30 | 2019-02-12 | 东南大学 | A face attribute analysis method based on transfer learning |
| CN109063759A (en)* | 2018-07-20 | 2018-12-21 | 浙江大学 | A kind of neural network structure searching method applied to the more attribute forecasts of picture |
| CN109145798A (en)* | 2018-08-13 | 2019-01-04 | 浙江零跑科技有限公司 | A kind of Driving Scene target identification and travelable region segmentation integrated approach |
| CN109145798B (en)* | 2018-08-13 | 2021-10-22 | 浙江零跑科技股份有限公司 | Driving scene target identification and travelable region segmentation integration method |
| CN109145987B (en)* | 2018-08-21 | 2020-10-20 | 厦门美图之家科技有限公司 | Model generation method and device |
| CN109145987A (en)* | 2018-08-21 | 2019-01-04 | 厦门美图之家科技有限公司 | model generating method and device |
| US20200065563A1 (en)* | 2018-08-21 | 2020-02-27 | Software Ag | Systems and/or methods for accelerating facial feature vector matching with supervised machine learning |
| US10747989B2 (en)* | 2018-08-21 | 2020-08-18 | Software Ag | Systems and/or methods for accelerating facial feature vector matching with supervised machine learning |
| CN109242516A (en)* | 2018-09-06 | 2019-01-18 | 北京京东尚科信息技术有限公司 | The single method and apparatus of processing service |
| CN109472193A (en)* | 2018-09-21 | 2019-03-15 | 北京飞搜科技有限公司 | Method for detecting human face and device |
| CN109359562A (en)* | 2018-09-29 | 2019-02-19 | 佳都新太科技股份有限公司 | Target identification method, device, target identification equipment and storage medium |
| US11403879B2 (en) | 2018-10-19 | 2022-08-02 | Beijing Sensetime Technology Development Co., Ltd. | Method and apparatus for child state analysis, vehicle, electronic device, and storage medium |
| WO2020078214A1 (en)* | 2018-10-19 | 2020-04-23 | 北京市商汤科技开发有限公司 | Child state analysis method and apparatus, vehicle, electronic device and storage medium |
| CN109086837A (en)* | 2018-10-24 | 2018-12-25 | 高嵩 | User property classification method, storage medium, device and electronic equipment based on convolutional neural networks |
| CN109508654A (en)* | 2018-10-26 | 2019-03-22 | 中国地质大学（武汉） | Merge the human face analysis method and system of multitask and multiple dimensioned convolutional neural networks |
| CN109522824A (en)* | 2018-10-30 | 2019-03-26 | 平安科技（深圳）有限公司 | Face character recognition methods, device, computer installation and storage medium |
| CN109522872A (en)* | 2018-12-04 | 2019-03-26 | 西安电子科技大学 | A kind of face identification method, device, computer equipment and storage medium |
| CN111291253B (en)* | 2018-12-06 | 2023-09-19 | 北京嘀嘀无限科技发展有限公司 | Model training method, consultation recommendation method and device and electronic equipment |
| CN111291253A (en)* | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Model training method, consultation recommendation method, device and electronic equipment |
| WO2020114118A1 (en)* | 2018-12-07 | 2020-06-11 | 深圳光启空间技术有限公司 | Facial attribute identification method and device, storage medium and processor |
| CN111291604A (en)* | 2018-12-07 | 2020-06-16 | 深圳光启空间技术有限公司 | Facial attribute recognition method, device, storage medium and processor |
| CN109727071A (en)* | 2018-12-28 | 2019-05-07 | 中国科学院半导体研究所 | Advertising recommendation method and system |
| CN109583431A (en)* | 2019-01-02 | 2019-04-05 | 上海极链网络科技有限公司 | A kind of face Emotion identification model, method and its electronic device |
| CN110427795A (en)* | 2019-01-28 | 2019-11-08 | 厦门瑞为信息技术有限公司 | A kind of property analysis method based on head photo, system and computer equipment |
| CN109886154A (en)* | 2019-01-30 | 2019-06-14 | 电子科技大学 | Pedestrian appearance attribute recognition method based on multi-dataset joint training based on Inception V3 |
| CN111598600A (en)* | 2019-02-21 | 2020-08-28 | 虹软科技股份有限公司 | Multimedia information pushing method and system and terminal equipment |
| CN109871814A (en)* | 2019-02-22 | 2019-06-11 | 成都旷视金智科技有限公司 | Estimation method, device, electronic equipment and the computer storage medium at age |
| CN111626087A (en)* | 2019-02-28 | 2020-09-04 | 北京市商汤科技开发有限公司 | Neural network training and eye opening and closing state detection method, device and equipment |
| CN109947960A (en)* | 2019-03-08 | 2019-06-28 | 南京信息工程大学 | The construction method of face multi-attribute joint estimation model based on depth convolution |
| CN109947960B (en)* | 2019-03-08 | 2024-01-23 | 南京信息工程大学 | Face multi-attribute joint estimation model construction method based on depth convolution |
| CN109893095A (en)* | 2019-03-11 | 2019-06-18 | 常州市贝叶斯智能科技有限公司 | A kind of intelligent robot system of body composition detection and analysis |
| CN110069994A (en)* | 2019-03-18 | 2019-07-30 | 中国科学院自动化研究所 | Face character identifying system, method based on face multizone |
| CN110069994B (en)* | 2019-03-18 | 2021-03-23 | 中国科学院自动化研究所 | Face attribute recognition system and method based on face multi-region |
| CN109993102B (en)* | 2019-03-28 | 2021-09-17 | 北京达佳互联信息技术有限公司 | Similar face retrieval method, device and storage medium |
| CN109993102A (en)* | 2019-03-28 | 2019-07-09 | 北京达佳互联信息技术有限公司 | Similar face retrieval method, apparatus and storage medium |
| US11521021B2 (en) | 2019-04-09 | 2022-12-06 | Hitachi, Ltd. | Object recognition system and object recognition method |
| CN110046571A (en)* | 2019-04-15 | 2019-07-23 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110084216A (en)* | 2019-05-06 | 2019-08-02 | 苏州科达科技股份有限公司 | Human face recognition model training and face identification method, system, equipment and medium |
| CN110084216B (en)* | 2019-05-06 | 2021-11-09 | 苏州科达科技股份有限公司 | Face recognition model training and face recognition method, system, device and medium |
| CN110163269A (en)* | 2019-05-09 | 2019-08-23 | 北京迈格威科技有限公司 | Model generating method, device and computer equipment based on deep learning |
| CN110111246B (en)* | 2019-05-15 | 2022-02-25 | 北京市商汤科技开发有限公司 | Virtual head portrait generation method and device and storage medium |
| WO2020228384A1 (en)* | 2019-05-15 | 2020-11-19 | 北京市商汤科技开发有限公司 | Virtual head portrait generation method and device, and storage medium |
| US11403874B2 (en) | 2019-05-15 | 2022-08-02 | Beijing Sensetime Technology Development Co., Ltd. | Virtual avatar generation method and apparatus for generating virtual avatar including user selected face property, and storage medium |
| CN110111246A (en)* | 2019-05-15 | 2019-08-09 | 北京市商汤科技开发有限公司 | A kind of avatars generation method and device, storage medium |
| CN110334735A (en)* | 2019-05-31 | 2019-10-15 | 北京奇艺世纪科技有限公司 | Multitask network generation method, device, computer equipment and storage medium |
| CN110334735B (en)* | 2019-05-31 | 2022-07-08 | 北京奇艺世纪科技有限公司 | Multitask network generation method and device, computer equipment and storage medium |
| CN110232352B (en)* | 2019-06-12 | 2022-11-25 | 东北大学 | Improvement method of multi-task cascade convolution neural network model for face recognition |
| CN110232352A (en)* | 2019-06-12 | 2019-09-13 | 东北大学 | A kind of improved method of the multitask concatenated convolutional neural network model for recognition of face |
| CN110287836A (en)* | 2019-06-14 | 2019-09-27 | 北京迈格威科技有限公司 | Image classification method, device, computer equipment and storage medium |
| CN110287836B (en)* | 2019-06-14 | 2021-10-15 | 北京迈格威科技有限公司 | Image classification method and device, computer equipment and storage medium |
| CN112149449A (en)* | 2019-06-26 | 2020-12-29 | 北京华捷艾米科技有限公司 | Face attribute recognition method and system based on deep learning |
| CN110263756A (en)* | 2019-06-28 | 2019-09-20 | 东北大学 | A kind of human face super-resolution reconstructing system based on joint multi-task learning |
| CN110348416A (en)* | 2019-07-17 | 2019-10-18 | 北方工业大学 | A multi-task face recognition method based on multi-scale feature fusion convolutional neural network |
| CN112333545A (en)* | 2019-07-31 | 2021-02-05 | Tcl集团股份有限公司 | Television content recommendation method, system, storage medium and smart television |
| WO2021031566A1 (en)* | 2019-08-21 | 2021-02-25 | 五邑大学 | Multi-task learning-based facial beauty prediction method |
| CN110503072A (en)* | 2019-08-29 | 2019-11-26 | 南京信息工程大学 | Face age estimation method based on multi-branch CNN architecture |
| CN110503072B (en)* | 2019-08-29 | 2023-05-26 | 南京信息工程大学 | Face age estimation method based on multi-branch CNN architecture |
| CN110584654A (en)* | 2019-10-09 | 2019-12-20 | 中山大学 | Multi-mode convolutional neural network-based electrocardiosignal classification method |
| CN112825117A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Behavior attribute judgment method, behavior attribute judgment device, behavior attribute judgment medium and behavior attribute judgment equipment based on head features |
| CN112825122A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Ethnicity judgment method, ethnicity judgment device, ethnicity judgment medium and ethnicity judgment equipment based on two-dimensional face image |
| CN112825119A (en)* | 2019-11-20 | 2021-05-21 | 北京眼神智能科技有限公司 | Face attribute judgment method and device, computer readable storage medium and equipment |
| CN114467121A (en)* | 2019-11-27 | 2022-05-10 | 华为技术有限公司 | A perceptual network and image processing method |
| CN111191675A (en)* | 2019-12-03 | 2020-05-22 | 深圳市华尊科技股份有限公司 | Pedestrian attribute recognition model implementation method and related device |
| CN111191675B (en)* | 2019-12-03 | 2023-10-24 | 深圳市华尊科技股份有限公司 | Pedestrian attribute identification model realization method and related device |
| CN111339818B (en)* | 2019-12-18 | 2023-06-06 | 中国人民解放军第四军医大学 | Face multi-attribute recognition system |
| CN111339818A (en)* | 2019-12-18 | 2020-06-26 | 中国人民解放军第四军医大学 | A face multi-attribute recognition system |
| CN110874587A (en)* | 2019-12-26 | 2020-03-10 | 浙江大学 | Face characteristic parameter extraction system |
| CN111325108A (en)* | 2020-01-22 | 2020-06-23 | 中能国际建筑投资集团有限公司 | Multitask network model, using method, device and storage medium |
| CN111325108B (en)* | 2020-01-22 | 2023-05-26 | 中能国际高新科技研究院有限公司 | Multitasking network model, using method, device and storage medium |
| CN111369615A (en)* | 2020-02-21 | 2020-07-03 | 苏州优纳医疗器械有限公司 | Cell nucleus central point detection method based on multitask convolutional neural network |
| CN111539452B (en)* | 2020-03-26 | 2024-03-26 | 深圳云天励飞技术有限公司 | Image recognition method and device for multi-task attribute, electronic equipment and storage medium |
| CN111539452A (en)* | 2020-03-26 | 2020-08-14 | 深圳云天励飞技术有限公司 | Image recognition method and device for multitask attributes, electronic equipment and storage medium |
| CN111401294A (en)* | 2020-03-27 | 2020-07-10 | 山东财经大学 | Multitask face attribute classification method and system based on self-adaptive feature fusion |
| CN111507263B (en)* | 2020-04-17 | 2022-08-05 | 电子科技大学 | Face multi-attribute recognition method based on multi-source data |
| CN111507263A (en)* | 2020-04-17 | 2020-08-07 | 电子科技大学 | A face multi-attribute recognition method based on multi-source data |
| CN111626115A (en)* | 2020-04-20 | 2020-09-04 | 北京市西城区培智中心学校 | Face attribute identification method and device |
| CN111680547B (en)* | 2020-04-27 | 2024-01-12 | 阿波罗智能技术(北京)有限公司 | Traffic countdown sign recognition method and device, electronic equipment and storage medium |
| CN111680547A (en)* | 2020-04-27 | 2020-09-18 | 北京百度网讯科技有限公司 | Recognition method, device, electronic device and storage medium of traffic countdown board |
| CN111598000A (en)* | 2020-05-18 | 2020-08-28 | 中移（杭州）信息技术有限公司 | Multitask-based face recognition method, device, server and readable storage medium |
| WO2021237727A1 (en)* | 2020-05-29 | 2021-12-02 | Siemens Aktiengesellschaft | Method and apparatus of image processing |
| CN111626303A (en)* | 2020-05-29 | 2020-09-04 | 南京甄视智能科技有限公司 | Sex and age identification method, sex and age identification device, storage medium and server |
| CN111626303B (en)* | 2020-05-29 | 2021-04-13 | 南京甄视智能科技有限公司 | Sex and age identification method, sex and age identification device, storage medium and server |
| CN112052734B (en)* | 2020-07-31 | 2024-05-17 | 北京奇艺世纪科技有限公司 | Character characteristic recognition network generation method, character characteristic recognition network generation program, character characteristic recognition apparatus, device and medium |
| CN112052734A (en)* | 2020-07-31 | 2020-12-08 | 北京奇艺世纪科技有限公司 | Role characteristic identification network generation method, role characteristic identification device, role characteristic identification equipment and role characteristic identification medium |
| CN114556444A (en)* | 2020-09-11 | 2022-05-27 | 京东方科技集团股份有限公司 | Joint model training method and object information processing method, device and system |
| WO2022052021A1 (en)* | 2020-09-11 | 2022-03-17 | 京东方科技集团股份有限公司 | Joint model training method, object information processing method, apparatus, and system |
| US12147887B2 (en)* | 2020-09-11 | 2024-11-19 | Beijing Boe Technology Development Co., Ltd. | Method for training joint model, object information processing method, apparatus, and system |
| US20220327361A1 (en)* | 2020-09-11 | 2022-10-13 | Boe Technology Group Co., Ltd. | Method for Training Joint Model, Object Information Processing Method, Apparatus, and System |
| WO2022061726A1 (en)* | 2020-09-25 | 2022-03-31 | Intel Corporation | Method and system of multiple facial attributes recognition using highly efficient neural networks |
| CN112085540A (en)* | 2020-09-27 | 2020-12-15 | 湖北科技学院 | Advertising intelligent push system and method based on artificial intelligence technology |
| CN112163676B (en)* | 2020-10-13 | 2024-04-05 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for training multitasking service prediction model |
| CN112163676A (en)* | 2020-10-13 | 2021-01-01 | 北京百度网讯科技有限公司 | Multi-task service prediction model training method, device, equipment and storage medium |
| US11675876B2 (en) | 2020-10-28 | 2023-06-13 | International Business Machines Corporation | Training robust machine learning models |
| CN114529731A (en)* | 2020-10-30 | 2022-05-24 | 北京眼神智能科技有限公司 | Face feature point positioning and attribute analysis method and device, storage medium and equipment |
| CN114529731B (en)* | 2020-10-30 | 2024-07-12 | 北京眼神智能科技有限公司 | Face feature point positioning and attribute analysis method, device, storage medium and equipment |
| CN112784916A (en)* | 2021-01-29 | 2021-05-11 | 西安电子科技大学 | Air target micro-motion parameter real-time extraction method based on multitask convolutional network |
| CN112784916B (en)* | 2021-01-29 | 2022-03-04 | 西安电子科技大学 | Air target micro-motion parameter real-time extraction method based on multitask convolutional network |
| CN112906668B (en)* | 2021-04-07 | 2023-08-25 | 上海应用技术大学 | Face Information Recognition Method Based on Convolutional Neural Network |
| CN112906668A (en)* | 2021-04-07 | 2021-06-04 | 上海应用技术大学 | Face information identification method based on convolutional neural network |
| CN113095211B (en)* | 2021-04-08 | 2023-08-25 | 第六镜科技(成都)有限公司 | Image processing method, system and electronic equipment |
| CN113095211A (en)* | 2021-04-08 | 2021-07-09 | 第六镜科技(成都)有限公司 | Image processing method and system and electronic equipment |
| CN113420768A (en)* | 2021-08-24 | 2021-09-21 | 深圳市信润富联数字科技有限公司 | Core category determination method and device, electronic equipment and storage medium |
| CN114038044A (en)* | 2021-11-23 | 2022-02-11 | 携程旅游信息技术（上海）有限公司 | Face gender and age recognition method, device, electronic device and storage medium |
| CN114005166A (en)* | 2021-11-25 | 2022-02-01 | 浩云科技股份有限公司 | A face recognition method and device based on multi-task learning |
| CN114332914A (en)* | 2021-11-29 | 2022-04-12 | 中国电子科技集团公司电子科学研究院 | Personnel feature identification method, device and computer-readable storage medium |
| CN114495215A (en)* | 2022-01-14 | 2022-05-13 | 山东新一代信息产业技术研究院有限公司 | A unified multi-task learning method for interactive robots based on attention mechanism |
| CN114495215B (en)* | 2022-01-14 | 2025-10-10 | 山东新一代信息产业技术研究院有限公司 | Unified multi-task learning method for interactive robots based on attention mechanism |
| CN114821538A (en)* | 2022-05-19 | 2022-07-29 | 北京地平线机器人技术研发有限公司 | Training method and device of multi-task model |
| CN114821538B (en)* | 2022-05-19 | 2024-11-19 | 北京地平线机器人技术研发有限公司 | A training method and device for a multi-task model |
| CN117079337B (en)* | 2023-10-17 | 2024-02-06 | 成都信息工程大学 | A high-precision facial attribute feature recognition device and method |
| CN117079337A (en)* | 2023-10-17 | 2023-11-17 | 成都信息工程大学 | High-precision face attribute feature recognition device and method |
| CN119580318A (en)* | 2024-10-28 | 2025-03-07 | 广州像素数据技术股份有限公司 | A modular face attribute structure analysis method, device, equipment and medium |
| Publication number | Publication date |
|---|---|
| CN106529402B (en) | 2019-05-28 |
| Publication | Publication Date | Title |
|---|---|---|
| CN106529402A (en) | Multi-task learning convolutional neural network-based face attribute analysis method | |
| CN107679522B (en) | Multi-stream LSTM-based action identification method | |
| CN109508669B (en) | A Face Expression Recognition Method Based on Generative Adversarial Networks | |
| CN108510485B (en) | A reference-free image quality assessment method based on convolutional neural network | |
| CN105760835B (en) | A kind of gait segmentation and Gait Recognition integral method based on deep learning | |
| CN113673510B (en) | Target detection method combining feature point and anchor frame joint prediction and regression | |
| CN110276264B (en) | Crowd density estimation method based on foreground segmentation graph | |
| CN109902546A (en) | Face recognition method, device and computer readable medium | |
| CN110096156A (en) | Virtual costume changing method based on 2D image | |
| CN108710831A (en) | A kind of small data set face recognition algorithms based on machine vision | |
| CN107437099A (en) | A kind of specific dress ornament image recognition and detection method based on machine learning | |
| CN107704838A (en) | The attribute recognition approach and device of destination object | |
| CN110059598A (en) | The Activity recognition method of the long time-histories speed network integration based on posture artis | |
| CN107944386B (en) | Visual Scene Recognition Method Based on Convolutional Neural Network | |
| CN108961272A (en) | It is a kind of to fight the generation method for generating the skin disease image of network based on depth convolution | |
| CN110738161A (en) | A face image correction method based on improved generative adversarial network | |
| CN108717732B (en) | Expression tracking method based on MobileNet model | |
| CN111127309B (en) | Portrait style migration model training method, portrait style migration method and device | |
| CN113724354B (en) | Gray image coloring method based on reference picture color style | |
| CN114360018B (en) | Rendering method and device of three-dimensional facial expression, storage medium and electronic device | |
| CN114663593B (en) | Three-dimensional human body posture estimation method, device, equipment and storage medium | |
| CN112861659B (en) | Image model training method and device, electronic equipment and storage medium | |
| CN111445426B (en) | Target clothing image processing method based on generation of countermeasure network model | |
| CN108388905A (en) | A kind of Illuminant estimation method based on convolutional neural networks and neighbourhood context | |
| CN112446253A (en) | Skeleton behavior identification method and device |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |