CN102693409B - Method for quickly identifying two-dimension code system type in images - Google Patents
Method for quickly identifying two-dimension code system type in imagesDownload PDFInfo
- Publication number
- CN102693409B CN102693409BCN201210156118.4ACN201210156118ACN102693409BCN 102693409 BCN102693409 BCN 102693409BCN 201210156118 ACN201210156118 ACN 201210156118ACN 102693409 BCN102693409 BCN 102693409B
- Authority
- CN
- China
- Prior art keywords
- image
- quick response
- code
- response code
- dimensional code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription48
- 230000008569processEffects0.000claimsabstractdescription17
- 238000012545processingMethods0.000claimsabstractdescription12
- 238000012549trainingMethods0.000claimsabstractdescription12
- 239000000284extractSubstances0.000claimsabstractdescription5
- 238000009499grossingMethods0.000claimsabstractdescription3
- 238000010606normalizationMethods0.000claimsabstract3
- 238000001914filtrationMethods0.000claimsabstract2
- 230000004044responseEffects0.000claimsdescription14
- 238000004422calculation algorithmMethods0.000claimsdescription3
- 238000004364calculation methodMethods0.000claimsdescription2
- 238000006243chemical reactionMethods0.000claims2
- HUTDUHSNJYTCAR-UHFFFAOYSA-NancymidolChemical compoundC1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1HUTDUHSNJYTCAR-UHFFFAOYSA-N0.000claims1
- 230000013011matingEffects0.000claims1
- 238000013341scale-upMethods0.000claims1
- 238000005259measurementMethods0.000abstractdescription4
- 238000007635classification algorithmMethods0.000abstractdescription2
- 238000012937correctionMethods0.000abstractdescription2
- 238000013528artificial neural networkMethods0.000description3
- 238000010586diagramMethods0.000description3
- 238000000605extractionMethods0.000description2
- 230000006870functionEffects0.000description2
- 239000011159matrix materialSubstances0.000description2
- 230000007246mechanismEffects0.000description2
- 238000012567pattern recognition methodMethods0.000description2
- 238000003672processing methodMethods0.000description2
- 238000012706support-vector machineMethods0.000description2
- 230000006399behaviorEffects0.000description1
- 230000009286beneficial effectEffects0.000description1
- 230000010365information processingEffects0.000description1
- 230000001537neural effectEffects0.000description1
- 238000003909pattern recognitionMethods0.000description1
- 238000007781pre-processingMethods0.000description1
- 230000009467reductionEffects0.000description1
- 238000011160researchMethods0.000description1
Images
Landscapes
- Image Analysis (AREA)
- Character Discrimination (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明属于数字图像处理、计算机视觉和模式识别方法，特别是涉及二维码图像中码制类型的快速识别方法。 The invention belongs to digital image processing, computer vision and pattern recognition methods, in particular to a fast recognition method for code system types in two-dimensional code images.
背景技术Background technique
二维条码（2-dimensional bar code）是指在一维条码的基础上扩展出另一维具有可读性的条码。一维条码的宽度记载着数据，而其长度没有记载数据。二维条码的长度、宽度均记载着数据。二维条码有一维条码没有的“定位点”和“容错机制”。容错机制在即使没有辨识到全部的条码、或是说条码有污损时，也可以正确地还原条码上的信息。目前，出现了许多种类的二维条码，其中较常用的码制有：Data Matrix, QR Code, PDF417等。二维条码具有储存量大、保密性高、追踪性高、抗损性强、备援性大、成本便宜等特性，这些特性特别适用于表单、安全保密、追踪、证照、存货盘点、资料备援等方面。 Two-dimensional barcode (2-dimensional barcode) refers to a barcode that expands on the basis of one-dimensional barcode and has another dimension with readability. The width of a one-dimensional barcode records data, but its length does not record data. Data is recorded in both the length and width of the two-dimensional barcode. Two-dimensional barcodes have "locating points" and "fault tolerance mechanisms" that one-dimensional barcodes do not have. The fault-tolerant mechanism can correctly restore the information on the barcode even if all the barcodes are not recognized or the barcode is defaced. At present, there are many types of two-dimensional barcodes, among which the more commonly used code systems are: Data Matrix, QR Code, PDF417, etc. Two-dimensional barcodes have the characteristics of large storage capacity, high confidentiality, high traceability, strong damage resistance, large redundancy, and low cost. These characteristics are especially suitable for forms, security and confidentiality, tracking, licenses, inventory, data backup aid etc.
通过手机或相机摄像头拍摄包含二维码的图像，利用数字图像处理技术进行识别，是国内外对二维条码的主要研究方向。由于目前存在多种二维码码制，在进行二维码识别解码前，先要对码制进行识别，然后才能根据码制规则进行解码处理。通常的处理方式是根据各种码制规则，逐一扫描图像中二维码的寻像图形，根据寻像图形的搜索结果确定码制类型，如国标《快速响应矩阵码 QR Code》中提供的参数方法是，在整幅图像中搜索QR码的寻像图形，QR码寻像图形的特点是各元素相当宽度的比例是1:1:3:1:1，在水平和垂直方向进行探测，找出三个这种类型的寻像图形，即确定出其为QR码。当码制类型较多时，逐一进行匹配搜索的效率较低，此外，这种方法对图像分辨率的要求较高，降低了二维码处理的整体速度。 It is the main research direction of two-dimensional barcodes at home and abroad to take images containing two-dimensional codes through mobile phones or cameras, and use digital image processing technology to identify them. Due to the existence of various two-dimensional code code systems, before performing two-dimensional code recognition and decoding, the code system must be identified first, and then the decoding process can be performed according to the code system rules. The usual processing method is to scan the image-finding graphics of the two-dimensional code in the image one by one according to various code system rules, and determine the code system type according to the search results of the image-finding graphics, such as the parameters provided in the national standard "Quick Response Matrix Code QR Code" The method is to search for the image-finding pattern of the QR code in the entire image. The characteristic of the image-finding pattern of the QR code is that the ratio of the width of each element is 1:1:3:1:1. It is detected in the horizontal and vertical directions to find If three image-finding patterns of this type are displayed, it is determined to be a QR code. When there are many types of code systems, the efficiency of matching and searching one by one is low. In addition, this method has high requirements on image resolution, which reduces the overall speed of two-dimensional code processing.
图像目标识别技术的关键环节是特征提取与目标分类。特征提取可采用多种方法，常见的有轮廓特征，傅里叶描述子，小波特征等。其中轮廓特征和傅里叶描述子仅考虑了目标边界的图像信息，对噪声非常敏感，影响识别率。小波特征是将模板图像变换到小波域中的识别特征，能够在保持目标空间关系的同时，描述图像中的频率结构信息，与基于边界信息的特征相比，具有较好的适应性。在提取了目标特征后，就要对特征进行分类，以辨识出目标的模式类别。常见的分类识别方法包括，K最近邻法、支持向量机、以及神经网络等。其中，支持向量机能够较好地解决小样本、非线性性及高维模式识别问题，但方法较为复杂，计算量大。神经网络是模拟动物神经网络行为，通过调整内部大量神经节点之间的相关连接关系，达到信息处理的目的，能够解决很多非线性问题，但其有很多没有解决的理论问题，使得在实际应用中存在很多困难。K最近邻(k-Nearest Neighbor，KNN)算法是在多维空间中找到与未知样本最近邻的Ｋ个点 ,并根据这Ｋ个点的类别来判断未知样本的类，由于K最近邻法理论成熟且使用简单，因此被广泛应用于模式分类问题。 The key links of image target recognition technology are feature extraction and target classification. A variety of methods can be used for feature extraction, the common ones are contour features, Fourier descriptors, wavelet features, etc. Among them, the contour feature and Fourier descriptor only consider the image information of the target boundary, which is very sensitive to noise and affects the recognition rate. The wavelet feature is the recognition feature that transforms the template image into the wavelet domain. It can describe the frequency structure information in the image while maintaining the target spatial relationship. Compared with the feature based on boundary information, it has better adaptability. After extracting the target features, it is necessary to classify the features to identify the pattern category of the target. Common classification recognition methods include K nearest neighbor method, support vector machine, and neural network. Among them, the support vector machine can better solve the problems of small samples, nonlinearity and high-dimensional pattern recognition, but the method is more complicated and the amount of calculation is large. Neural network is to simulate the behavior of animal neural network. By adjusting the relevant connections between a large number of internal neural nodes to achieve the purpose of information processing, it can solve many nonlinear problems, but there are many unsolved theoretical problems, which makes There are many difficulties. The K-Nearest Neighbor (KNN) algorithm is to find the K points closest to the unknown sample in the multi-dimensional space, and judge the class of the unknown sample according to the category of the K points. Since the K-Nearest Neighbor method is mature And it is easy to use, so it is widely used in pattern classification problems.
发明内容Contents of the invention
本发明的目的是提供一种快速的图像中二维码码制识别方法，可作为二维码识别解码的预处理步骤，以提高二维码图像处理的整体效率。 The purpose of the present invention is to provide a fast two-dimensional code system recognition method in an image, which can be used as a preprocessing step for two-dimensional code recognition and decoding, so as to improve the overall efficiency of two-dimensional code image processing.
本发明的目的是这样实现的：一种快速的图像中二维码码制识别方法，主要包括两个过程，即学习训练过程与分类识别过程。 The object of the present invention is achieved in the following way: a fast two-dimensional code system recognition method in an image mainly includes two processes, that is, a learning training process and a classification and recognition process.
学习训练过程包括以下步骤： The learning training process includes the following steps:
1.1）通过采集各种类型、各种版本的二维码图像，建立用于学习训练的样本图像集；1.1) Establish a sample image set for learning and training by collecting various types and versions of two-dimensional code images;
1.2）对于每一个样本图像，将其转换成灰度图像后，进行高斯平滑滤波，去除图像中的噪声，然后根据图像的灰度分布信息，采用最大类间方差方法进行二值化处理，在得到的二值图像中，二维码的黑色模块为前景，其余部分为背景；1.2) For each sample image, after converting it into a grayscale image, Gaussian smoothing filter is performed to remove the noise in the image, and then according to the grayscale distribution information of the image, the maximum inter-class variance method is used for binarization processing. In the obtained binary image, the black module of the two-dimensional code is the foreground, and the rest is the background;
1.3）分别在水平和垂直方向上扫描二值化图像的前景边界，得到二维码的外边界点集，采用旋转卡壳法计算点集的最小覆盖矩形，根据最小覆盖矩形的方位角度，旋转图像以使二维码处于水平状态，从而实现二维码的水平矫正；1.3) Scan the foreground boundary of the binarized image in the horizontal and vertical directions respectively to obtain the outer boundary point set of the two-dimensional code, and use the rotation jamming method to calculate the minimum covering rectangle of the point set, and rotate the image according to the azimuth angle of the minimum covering rectangle So that the two-dimensional code is in a horizontal state, so as to realize the horizontal correction of the two-dimensional code;
1.4）对于水平矫正后的图像，以旋转后的最小覆盖矩形为边界，提取出二维码的图像区域。考虑到二维码的边角部分包含了大部分具有区分性的特征，对二维码区域按照一定的比例系数进行分块，选取其中处于边角部分的分块，组合成新的样本图像，并对其进行归一化处理，得到归一化样本图像；1.4) For the horizontally rectified image, the image area of the QR code is extracted with the rotated minimum coverage rectangle as the boundary. Considering that the corners of the two-dimensional code contain most of the distinguishing features, the two-dimensional code area is divided into blocks according to a certain ratio factor, and the blocks at the corners are selected to form a new sample image. and normalize it to obtain a normalized sample image;
1.5）对每个归一化的样本图像进行快速小波变换，将得到小波变换系数作为特征，进而建立用于后续分类的小波特征样本集；1.5) Fast wavelet transform is performed on each normalized sample image, and the wavelet transform coefficients are obtained as features, and then a wavelet feature sample set for subsequent classification is established;
分类识别过程包括以下步骤：The classification recognition process includes the following steps:
2.1）对待识别的二维码图像，按照步骤1.2）至步骤1.5）的方式提取图像的小波特征；2.1) For the two-dimensional code image to be recognized, extract the wavelet feature of the image according to steps 1.2) to 1.5);
2.2）建立基于特征分布加权的距离度量模型；将待识别特征与样本特征进行逐点匹配，并将所有点匹配的加权和作为特征之间的距离，其中权重的设置方式是，给处于不同空间位置的点赋予不同的权重，越靠近区域中心的点权重越低，越靠近二维码边缘的点权重越高；2.2) Establish a weighted distance measurement model based on feature distribution; match the features to be identified with the sample features point by point, and use the weighted sum of all point matches as the distance between features, where the weights are set in different spaces. Different weights are given to the points of the position, the closer to the center of the area, the lower the weight, and the closer to the edge of the QR code, the higher the weight;
2.3）采用K最近邻分类算法进行码制类型识别，根据步骤2.2）中定义的距离度量模型，选择距离最近的K个特征样本，这些样本大多数属于的码制类型即为待识别图像的类型。2.3) Use the K-nearest neighbor classification algorithm to identify the code system type. According to the distance measurement model defined in step 2.2), select the K feature samples with the closest distance. The code system type that most of these samples belong to is the type of image to be recognized .
本发明的有益效果主要有以下两点： Beneficial effect of the present invention mainly contains following two points:
1、本发明提供的技术方案简便快捷，并通过提取二维码中最具区分性的特征区域，实现较高的识别率，能够兼顾处理的实时性和准确性；1. The technical solution provided by the present invention is simple and quick, and by extracting the most distinguishing feature area in the two-dimensional code, a higher recognition rate can be achieved, and the real-time and accuracy of processing can be taken into account;
2、识别方法仅利用了二维码的图像特征，不用考虑具体的码制规则，具有较好的普遍适用性，能够识别目前常见的二维码类型，仅要求二维码的外形为矩形。2. The recognition method only uses the image features of the two-dimensional code, without considering the specific code system rules, and has good universal applicability. It can recognize the current common two-dimensional code types, and only requires the shape of the two-dimensional code to be a rectangle.
本发明基于图像的目标识别技术，通过提取二维码中具有区分性的图像特征，应用模式识别方法，对二维码码制进行分类与识别，可以极大地提高码制识别效率。 The image-based target recognition technology of the present invention extracts distinguishable image features in two-dimensional codes and applies a pattern recognition method to classify and recognize two-dimensional code codes, thereby greatly improving code system recognition efficiency.
附图说明Description of drawings
图1是本发明所述方法的系统示意框图。 Fig. 1 is a schematic block diagram of the system of the method of the present invention.
图2是本发明方法在估计二维码区域的最小覆盖矩形的示意图（上边一个为原图，左下一个为边界点集，右下一个为估计的最小覆盖矩形）。 Fig. 2 is a schematic diagram of the method of the present invention in estimating the minimum covering rectangle of the two-dimensional code area (the upper one is the original image, the lower left one is the boundary point set, and the lower right one is the estimated minimum covering rectangle).
图3是本发明方法在选取图像分块的示意图。 Fig. 3 is a schematic diagram of selecting image blocks by the method of the present invention.
具体实施方式Detailed ways
下面结合附图具体描述本发明的实施方式。 Embodiments of the present invention will be specifically described below in conjunction with the accompanying drawings.
参照图1，具体介绍在图像中识别二维码码制类型的方法步骤，整个处理过程分为学习训练与分类识别，其中学习训练过程的步骤如下： Referring to Figure 1, the method steps of identifying the two-dimensional code type in the image are specifically introduced. The entire processing process is divided into learning training and classification recognition, wherein the steps of the learning training process are as follows:
步骤一：读取包含有二维码的训练图像，将其转化成256级的灰度图像，然后采用高斯函数生成的核进行滤波，以去除图像中存在的噪声。根据图像的灰度分布信息，采用大津法（即最大类间方差方法）进行二值化处理，使得二维码中的黑色模块为图像前景，图像其余部分为背景；Step 1: Read the training image containing the QR code, convert it into a 256-level grayscale image, and then use the kernel generated by the Gaussian function to filter to remove the noise in the image. According to the gray level distribution information of the image, the Otsu method (that is, the maximum inter-class variance method) is used for binarization processing, so that the black module in the two-dimensional code is the foreground of the image, and the rest of the image is the background;
步骤二：在水平方向上，分别从左向右、从右向左逐行扫描图像前景的外边界，得到图像垂直方向的外边界点。同样，在垂直方向上，分别从上向下、从下向上逐列扫描图像前景的外边界，得到图像水平方向的外边界点。根据得到的外边界点集，如图2中左下图所示，计算由这些点构成的凸包的对踵点对，进而得到该点集的最小覆盖矩形，如图2中右下图所示的白色矩形，将该矩形区域作为二维码区域；Step 2: In the horizontal direction, the outer boundary of the foreground of the image is scanned line by line from left to right and from right to left, respectively, to obtain the outer boundary points of the image in the vertical direction. Similarly, in the vertical direction, the outer boundary of the foreground of the image is scanned column by column from top to bottom and bottom to top to obtain the outer boundary points of the image in the horizontal direction. According to the obtained outer boundary point set, as shown in the lower left figure in Figure 2, calculate the antipodal point pairs of the convex hull formed by these points, and then obtain the minimum covering rectangle of the point set, as shown in the lower right figure in Figure 2 The white rectangle of , and use this rectangular area as the QR code area;
步骤三：根据得到的最小覆盖矩形确定二维码的旋转角度，通过旋转图像使二维码处于水平状态。提取出二维码图像区域，对该区域进行分块，分块的尺寸范围设置为二维码基本模块的5~7倍。二维码图像中最具代表性的特征为寻像图形和辅助定位功能图形，这些图形主要分布于二维码的边缘区域，因此，选择靠近边缘区域的图像块，如图3中的白色矩形块所示，按照位置顺序组合为新的样本图像，减少图像的冗余信息，实现特征降维；Step 3: Determine the rotation angle of the two-dimensional code according to the obtained minimum coverage rectangle, and make the two-dimensional code horizontal by rotating the image. The image area of the QR code is extracted, and the area is divided into blocks, and the size range of the blocks is set to be 5 to 7 times that of the basic module of the QR code. The most representative features in the two-dimensional code image are image-finding graphics and auxiliary positioning function graphics. These graphics are mainly distributed in the edge area of the two-dimensional code. Therefore, the image blocks close to the edge area are selected, such as the white rectangle in Figure 3 As shown in the block, it is combined into a new sample image according to the order of position, reducing the redundant information of the image and realizing feature dimensionality reduction;
步骤四：对样本图像进行归一化处理，为了保证图像具有一定的可辨识性，归一化后的图像分辨率设置为180×180像素；利用快速小波变换算法，将归一化的样本图像变换至小波域，小波变换系数作为后续分类的特征模板。对于每种类型的二维码，采集各种版本的图像共100幅，然后按照步骤一至步骤四，得到每个样本的特征模板，从而建立特征样本集。Step 4: Normalize the sample image. In order to ensure that the image has a certain degree of identifiability, the normalized image resolution is set to 180×180 pixels; using the fast wavelet transform algorithm, the normalized sample image Transform to the wavelet domain, and the wavelet transform coefficients are used as feature templates for subsequent classification. For each type of two-dimensional code, a total of 100 images of various versions were collected, and then the feature template of each sample was obtained according to steps 1 to 4, so as to establish a feature sample set.
分类识别过程的步骤如下： The steps of the classification recognition process are as follows:
步骤一：对待识别的二维码图像，按照样本图像的处理方法，得到该图像的小波特征；Step 1: Obtain the wavelet feature of the image of the two-dimensional code image to be recognized according to the processing method of the sample image;
步骤二：建立基于特征分布加权的距离度量模型，用于度量两个小波特征之间的相似度。由于二维码的代表特征靠近图像边缘，因此在特征匹配时，给处于不同空间位置的特征分配不同的权重，越靠近图像边缘部分的特征分配的权重越高。特征的权重计算为该点到图像中心的欧式距离，权重归一化成介于0和1（即大于零和小于等于1）之间的一个数值。将待识别特征与样本特征逐点匹配，所有点匹配的加权和作为特征之间的距离；Step 2: Establish a weighted distance measurement model based on feature distribution, which is used to measure the similarity between two wavelet features. Since the representative features of the two-dimensional code are close to the edge of the image, different weights are assigned to features at different spatial positions during feature matching, and the closer to the edge of the image, the higher the weight assigned to the feature. The weight of the feature is calculated as the Euclidean distance from the point to the center of the image, and the weight is normalized to a value between 0 and 1 (that is, greater than zero and less than or equal to 1). Match the feature to be identified with the sample feature point by point, and the weighted sum of all point matches is used as the distance between the features;
步骤三：按照步骤二定义的距离模型，计算待识别图像的小波特征与训练集特征样本之间的距离，选择其中距离最近的K个邻居（取K=10），然后根据这K个邻居所属的码制类型，选择相同类型数最大的那个类型为识别结果。Step 3: According to the distance model defined in step 2, calculate the distance between the wavelet feature of the image to be recognized and the feature sample of the training set, select the K neighbors with the closest distance (take K=10), and then according to the K neighbors belong to The type of code system, select the type with the largest number of the same type as the recognition result.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210156118.4ACN102693409B (en) | 2012-05-18 | 2012-05-18 | Method for quickly identifying two-dimension code system type in images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210156118.4ACN102693409B (en) | 2012-05-18 | 2012-05-18 | Method for quickly identifying two-dimension code system type in images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102693409A CN102693409A (en) | 2012-09-26 |
| CN102693409Btrue CN102693409B (en) | 2014-04-09 |
Family
ID=46858828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210156118.4AExpired - Fee RelatedCN102693409B (en) | 2012-05-18 | 2012-05-18 | Method for quickly identifying two-dimension code system type in images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102693409B (en) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294783B (en)* | 2013-05-16 | 2016-08-03 | 广州唯品会信息科技有限公司 | Product picture group technology and device |
| WO2015006911A1 (en)* | 2013-07-16 | 2015-01-22 | Intel Corporation | Techniques for low power visual light communication |
| CN103412906B (en)* | 2013-08-01 | 2017-06-20 | 百度在线网络技术（北京）有限公司 | Information transferring method and system |
| EP3157410B1 (en)* | 2014-06-20 | 2020-05-06 | Rambus Inc. | System for lensed and lensless optical sensing |
| WO2016037300A1 (en)* | 2014-09-10 | 2016-03-17 | Xiaoou Tang | Method and system for multi-class object detection |
| CN104298953A (en)* | 2014-10-27 | 2015-01-21 | 苏州睿新捷信息科技有限公司 | Method and system for recognizing barcodes in batches |
| CN104363400A (en)* | 2014-10-29 | 2015-02-18 | 广东欧珀移动通信有限公司 | A method and device for scanning a local two-dimensional code |
| CN105809094A (en)* | 2014-12-31 | 2016-07-27 | 研祥智能科技股份有限公司 | Bar code identification method based on machine vision |
| CN104899589B (en)* | 2015-05-12 | 2018-10-12 | 广州中大数码科技有限公司 | It is a kind of that the pretreated method of two-dimensional bar code is realized using threshold binarization algorithm |
| CN105262991B (en)* | 2015-10-12 | 2018-09-11 | 国家电网公司 | A kind of substation equipment object identifying method based on Quick Response Code |
| CN105260693B (en)* | 2015-12-01 | 2017-12-08 | 浙江工业大学 | A laser two-dimensional code positioning method |
| CN105868676A (en)* | 2016-06-13 | 2016-08-17 | 郝迎喜 | Improved two-dimension code region positioning system and positioning method thereof |
| CN106127093A (en)* | 2016-06-17 | 2016-11-16 | 广州中大微电子有限公司 | A kind of Quick Response Code identification chip and its implementation |
| CN107665324B (en)* | 2016-07-27 | 2020-08-28 | 腾讯科技（深圳）有限公司 | Image identification method and terminal |
| CN107273777A (en)* | 2017-04-26 | 2017-10-20 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of Quick Response Code identification of code type method matched based on slide unit |
| CN107220577A (en)* | 2017-05-12 | 2017-09-29 | 广州智慧城市发展研究院 | A kind of Quick Response Code localization method and system based on machine learning |
| CN107545259A (en)* | 2017-08-31 | 2018-01-05 | 华南理工大学 | A kind of Quick Response Code reconstructing method based on Da-Jin algorithm |
| CN108846664A (en)* | 2018-06-26 | 2018-11-20 | 刘晓英 | Mobile phone scan code system based on image procossing |
| CN109214225A (en)* | 2018-07-04 | 2019-01-15 | 青岛海信移动通信技术股份有限公司 | A kind of scan method, device, mobile terminal and the storage medium of figure bar code |
| CN110874540A (en)* | 2018-08-31 | 2020-03-10 | 北京意锐新创科技有限公司 | Method and device for reading bar code at all angles |
| CN110874542A (en)* | 2018-08-31 | 2020-03-10 | 北京意锐新创科技有限公司 | Method and device suitable for reading bar codes displayed by different carriers |
| CN109359497A (en)* | 2018-09-17 | 2019-02-19 | 四川长虹电器股份有限公司 | A kind of positioning and recognition methods in VAT invoice two-dimensional image code region |
| CN110147864B (en)* | 2018-11-14 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Method and device for processing coding pattern, storage medium and electronic device |
| CN109739233B (en)* | 2018-12-29 | 2022-06-14 | 歌尔光学科技有限公司 | AGV trolley positioning method, device and system |
| CN109800616A (en)* | 2019-01-17 | 2019-05-24 | 柳州康云互联科技有限公司 | A kind of two dimensional code positioning identification system based on characteristics of image |
| CN111507119B (en)* | 2019-01-31 | 2024-02-06 | 北京骑胜科技有限公司 | Identification code recognition method, identification code recognition device, electronic equipment and computer readable storage medium |
| CN110991201B (en)* | 2019-11-25 | 2023-04-18 | 浙江大华技术股份有限公司 | Bar code detection method and related device |
| CN111476053B (en)* | 2020-04-03 | 2022-03-01 | 支付宝(杭州)信息技术有限公司 | Identification method and device |
| CN112766012B (en)* | 2021-02-05 | 2021-12-17 | 腾讯科技（深圳）有限公司 | Two-dimensional code image recognition method and device, electronic equipment and storage medium |
| CN112560538B (en)* | 2021-02-26 | 2021-05-11 | 江苏东大集成电路系统工程技术有限公司 | Method for quickly positioning damaged QR (quick response) code according to image redundant information |
| CN113971680B (en)* | 2021-09-02 | 2025-04-04 | 上海准视智能信息技术有限公司 | A method, server, storage medium and system for locating arbitrary barcodes based on gray-level co-occurrence matrix |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6480627B1 (en)* | 1999-06-29 | 2002-11-12 | Koninklijke Philips Electronics N.V. | Image classification using evolved parameters |
| CN102236788A (en)* | 2010-04-20 | 2011-11-09 | 荣科科技股份有限公司 | Kilowatt-hour meter image automatic identification method |
| CN102254144A (en)* | 2011-07-12 | 2011-11-23 | 四川大学 | Robust method for extracting two-dimensional code area in image |
- 2012
- 2012-05-18CNCN201210156118.4Apatent/CN102693409B/ennot_activeExpired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6480627B1 (en)* | 1999-06-29 | 2002-11-12 | Koninklijke Philips Electronics N.V. | Image classification using evolved parameters |
| CN102236788A (en)* | 2010-04-20 | 2011-11-09 | 荣科科技股份有限公司 | Kilowatt-hour meter image automatic identification method |
| CN102254144A (en)* | 2011-07-12 | 2011-11-23 | 四川大学 | Robust method for extracting two-dimensional code area in image |
Non-Patent Citations (2)
| Title |
|---|
| 叶龙欢.复杂背景下的票据字符分割方法.《计算机应用》.2012,第32卷(第11期),3198－3120，3125. |
| 复杂背景下的票据字符分割方法;叶龙欢;《计算机应用》;20121101;第32卷(第11期);3198－3120，3125* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102693409A (en) | 2012-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102693409B (en) | Method for quickly identifying two-dimension code system type in images | |
| Su et al. | A fast forgery detection algorithm based on exponential-Fourier moments for video region duplication | |
| Tang et al. | 3D face recognition using local binary patterns | |
| CN102360421B (en) | Face identification method and system based on video streaming | |
| Hauagge et al. | Image matching using local symmetry features | |
| CN103324944B (en) | A False Fingerprint Detection Method Based on SVM and Sparse Representation | |
| Yao et al. | A new pedestrian detection method based on combined HOG and LSS features | |
| Pan et al. | Palmprint recognition using Gabor-based local invariant features | |
| CN102254144A (en) | Robust method for extracting two-dimensional code area in image | |
| CN107622489A (en) | Image tampering detection method and device | |
| Peng et al. | Recognition of low-resolution logos in vehicle images based on statistical random sparse distribution | |
| CN110298376A (en) | A kind of bank money image classification method based on improvement B-CNN | |
| Chen et al. | Robust text line segmentation for historical manuscript images using color and texture | |
| CN105550641B (en) | Age estimation method and system based on multi-scale linear differential texture features | |
| CN115238723A (en) | Local vertex detection method and device | |
| Liu et al. | Fingerprint indexing based on singular point correlation | |
| Zhou et al. | Histograms of categorized shapes for 3D ear detection | |
| Zhu et al. | A robust stamp detection framework on degraded documents | |
| Jia et al. | Palmprint identification using restricted fusion | |
| Zhang et al. | Palmprint identification combining hierarchical multi-scale complete LBP and weighted SRC | |
| Guo et al. | Image classification based on SURF and KNN | |
| CN110163182A (en) | A kind of hand back vein identification method based on KAZE feature | |
| CN113228105A (en) | Image processing method and device and electronic equipment | |
| Zhou et al. | Partial fingerprint indexing: a combination of local and reconstructed global features | |
| CN1936922A (en) | Shoe-print automatic matching method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20140409 |