技术领域Technical Field
本发明属于智能理疗仪领域，尤其涉及一种基于人工智能的理疗仪控制系统。The present invention belongs to the field of intelligent physiotherapy instruments, and in particular relates to a physiotherapy instrument control system based on artificial intelligence.
背景技术Background Art
理疗仪为现代医疗设备，用于帮助患者缓解疼痛、舒缓肌肉紧张、促进血液循环等，通过特定的电疗方式，如电刺激、超声波、磁疗等，来达到治疗作用。Physiotherapy devices are modern medical equipment used to help patients relieve pain, relieve muscle tension, promote blood circulation, etc. They achieve therapeutic effects through specific electrotherapy methods such as electrical stimulation, ultrasound, magnetic therapy, etc.
传统的理疗仪虽然能够进行简单的参数控制，但面临一些技术上的局限性，例如无法根据患者的个体差异和治疗感受快速调整治疗模式和参数，导致治疗效果不尽如人意，其次，现有理疗仪需要人工调整参数和模式，操作复杂，容易出错，并且增加了医护人员的工作负担。Although traditional physical therapy devices can perform simple parameter control, they face some technical limitations. For example, they cannot quickly adjust treatment modes and parameters according to individual differences and treatment perceptions of patients, resulting in unsatisfactory treatment results. Secondly, existing physical therapy devices require manual adjustment of parameters and modes, which is complicated to operate, prone to errors, and increases the workload of medical staff.
发明内容Summary of the invention
有鉴于现有技术的上述缺陷，本发明提出一种基于人工智能的理疗仪控制系统，本发明设计的技术方案包括：In view of the above-mentioned defects of the prior art, the present invention proposes a physiotherapy instrument control system based on artificial intelligence. The technical solution designed by the present invention includes:
传感模块、识别模块、智能控制模块、理疗模块和安全模块；Sensing module, identification module, intelligent control module, physical therapy module and safety module;
所述传感模块用于实时采集患者面部图像，并将所述患者面部图像下发至所述识别模块；The sensor module is used to collect the patient's facial image in real time and send the patient's facial image to the recognition module;
所述识别模块用于对所述患者面部图像进行分类辨别，并将分类辨别结果下发至所述智能控制模块；The recognition module is used to classify and identify the patient's facial image, and send the classification and identification results to the intelligent control module;
所述智能控制模块用于根据所述分类辨别结果和预设治疗方案对理疗仪的工作模式和参数进行调整，并驱动所述理疗模块；The intelligent control module is used to adjust the working mode and parameters of the physiotherapy instrument according to the classification and identification results and the preset treatment plan, and drive the physiotherapy module;
所述理疗模块用于根据调整后的治疗方案对患者进行治疗；The physical therapy module is used to treat the patient according to the adjusted treatment plan;
所述安全模块用于监测理疗仪的工作状况和患者的生理参数，处理异常情况并保护患者安全。The safety module is used to monitor the working condition of the physical therapy device and the physiological parameters of the patient, handle abnormal situations and protect the patient's safety.
优选地，所述分类辨别结果包括悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶共七种情绪。Preferably, the classification and identification results include seven emotions, namely sadness, happiness, surprise, neutrality, fear, anger and disgust.
优选地，所述对所述患者面部图像进行分类辨别包括：Preferably, the classifying and identifying the patient's facial image includes:
将所述患者面部图像进行点云转换，转换为患者面部点云，预设二维平面并基于目标检测算法选取预设二维平面的中心框，将所述患者面部点云映射至预设二维平面，计算所述患者面部点云的关键特征到所述中心框的距离，基于所述关键特征到所述中心框的距离计算患者面部图像与患者面部图像样本的相似值，基于相似值进行分类辨别。The patient's facial image is converted into a patient's facial point cloud by point cloud conversion, a two-dimensional plane is preset and a center frame of the preset two-dimensional plane is selected based on a target detection algorithm, the patient's facial point cloud is mapped to the preset two-dimensional plane, the distance from the key feature of the patient's facial point cloud to the center frame is calculated, and based on the distance from the key feature to the center frame, a similarity value between the patient's facial image and a patient's facial image sample is calculated, and classification and identification are performed based on the similarity value.
优选地，所述患者面部点云的关键特征包括眼睛、嘴巴、鼻子、脸颊和下巴。Preferably, key features of the patient's facial point cloud include eyes, mouth, nose, cheeks and chin.
优选地，所述计算所述患者面部点云的关键特征到所述中心框的距离，公式如下：Preferably, the distance from the key feature of the patient's facial point cloud to the center frame is calculated using the following formula:
式中，(xi，yi)为患者面部点云的关键特征坐标，(x′，y′)为中心框坐标，w为中心框宽度，h为中心框高度。Where (xi ,yi ) is the key feature coordinates of the patient's facial point cloud, (x′, y′) is the center frame coordinate, w is the center frame width, and h is the center frame height.
优选地，所述计算患者面部图像与患者面部图像样本的相似值，公式如下：Preferably, the similarity value between the patient's facial image and the patient's facial image sample is calculated using the following formula:
式中，n为关键特征的数量，Di为患者面部图像的第i关键特征点云到所述中心框的距离，D‘i为患者面部图像样本的第i关键特征点云到所述中心框的距离。Wherein, n is the number of key features,Di is the distance from the i-th key feature point cloud of the patient's facial image to the center frame, and D'i is the distance from the i-th key feature point cloud of the patient's facial image sample to the center frame.
优选地，所述基于相似值进行分类辨别包括：Preferably, the classification and identification based on similarity values includes:
比较患者面部图像与患者面部图像样本的相似值，找到当前患者面部图像最高的相似值对应的患者面部图像样本，所述对应的患者面部图像样本对应的情绪作为分类辨别结果输出。Compare the similarity values of the patient's facial image with those of the patient's facial image samples, find the patient's facial image sample corresponding to the highest similarity value of the current patient's facial image, and output the emotion corresponding to the corresponding patient's facial image sample as the classification and identification result.
优选地，所述理疗模块包括但不限于热疗模块、电疗模块和负压模块，通过对超声波、低频脉冲和负压的控制实现对患者的智能理疗。Preferably, the physiotherapy module includes but is not limited to a thermal therapy module, an electrotherapy module and a negative pressure module, and realizes intelligent physiotherapy for the patient by controlling ultrasound, low-frequency pulses and negative pressure.
优选地，所述安全模块还包括存储单元，所述存储单元用于对治疗过程中的数据进行备份，以防止数据丢失或损坏，必要时恢复备份数据。Preferably, the safety module further comprises a storage unit, which is used to back up data during the treatment process to prevent data loss or damage, and to restore the backup data when necessary.
有益效果：本申请通过传感模块采集的面部图像，识别模块可以对患者进行个性化分类和辨识。这使得智能控制模块能够根据患者的实际情况和需求，调整理疗仪的工作模式和参数。另外智能控制模块能够实时处理传感模块传来的数据，并根据识别模块的分类结果进行即时调整。这种即时性可以确保治疗过程中的效果最大化，适应患者状态的变化。Beneficial effects: The recognition module can perform personalized classification and identification of patients through facial images collected by the sensor module. This enables the intelligent control module to adjust the working mode and parameters of the physiotherapy device according to the actual situation and needs of the patient. In addition, the intelligent control module can process the data transmitted by the sensor module in real time and make instant adjustments based on the classification results of the recognition module. This immediacy can ensure the maximum effect of the treatment process and adapt to changes in the patient's condition.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是本发明一个较佳实施例的结构示意图。FIG1 is a schematic structural diagram of a preferred embodiment of the present invention.
具体实施方式DETAILED DESCRIPTION
下面对本发明的实施例作详细说明，下述的实施例在以本发明技术方案为前提下进行实施，给出了详细的实施方式和具体的操作过程，但本发明的保护范围不限于下述的实施例。The embodiments of the present invention are described in detail below. The following embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operation processes are given, but the protection scope of the present invention is not limited to the following embodiments.
本发明设计了一种基于人工智能的理疗仪控制系统，技术方案包含以下步骤，具体包括：The present invention designs a physical therapy instrument control system based on artificial intelligence, and the technical solution comprises the following steps, specifically including:
传感模块、识别模块、智能控制模块、理疗模块和安全模块；Sensing module, identification module, intelligent control module, physical therapy module and safety module;
传感模块用于实时采集患者面部图像，并将患者面部图像下发至识别模块；The sensor module is used to collect the patient's facial image in real time and send the patient's facial image to the recognition module;
识别模块用于对患者面部图像进行分类辨别，并将分类辨别结果下发至智能控制模块；The recognition module is used to classify and identify the patient's facial image and send the classification and identification results to the intelligent control module;
智能控制模块用于根据分类辨别结果和预设治疗方案对理疗仪的工作模式和参数进行调整，并驱动理疗模块；The intelligent control module is used to adjust the working mode and parameters of the physiotherapy instrument according to the classification and identification results and the preset treatment plan, and drive the physiotherapy module;
理疗模块用于根据调整后的治疗方案对患者进行治疗；The physiotherapy module is used to treat patients according to the adjusted treatment plan;
安全模块用于监测理疗仪的工作状况和患者的生理参数，处理异常情况并保护患者安全。The safety module is used to monitor the working status of the physiotherapy device and the patient's physiological parameters, handle abnormal situations and protect the patient's safety.
优选地，分类辨别结果包括悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶共七种情绪。Preferably, the classification and identification results include seven emotions, namely sadness, happiness, surprise, neutrality, fear, anger and disgust.
优选地，对患者面部图像进行分类辨别包括：Preferably, classifying and identifying the patient's facial image includes:
将患者面部图像进行点云转换，转换为患者面部点云，预设二维平面并基于目标检测算法选取预设二维平面的中心框，将患者面部点云映射至预设二维平面，计算患者面部点云的关键特征到中心框的距离，基于关键特征到中心框的距离计算患者面部图像与患者面部图像样本的相似值，基于相似值进行分类辨别。The patient's facial image is converted into a point cloud of the patient's facial point cloud, a two-dimensional plane is preset and the center frame of the preset two-dimensional plane is selected based on the target detection algorithm, the patient's facial point cloud is mapped to the preset two-dimensional plane, the distance from the key features of the patient's facial point cloud to the center frame is calculated, and the similarity value between the patient's facial image and the patient's facial image sample is calculated based on the distance from the key features to the center frame, and classification and identification are performed based on the similarity value.
优选地，患者面部点云的关键特征包括眼睛、嘴巴、鼻子、脸颊和下巴。Preferably, key features of the patient's facial point cloud include eyes, mouth, nose, cheeks and chin.
优选地，计算患者面部点云的关键特征到中心框的距离，公式如下：Preferably, the distance from the key features of the patient's facial point cloud to the center frame is calculated using the following formula:
式中，(xi，yi)为患者面部点云的关键特征坐标，(x′，y′)为中心框坐标，w为中心框宽度，h为中心框高度。Where (xi ,yi ) is the key feature coordinates of the patient's facial point cloud, (x′, y′) is the center frame coordinate, w is the center frame width, and h is the center frame height.
具体的，中心框坐标为中心框中心点的坐标，而基于目标检测算法选取预设二维平面的中心框包括事先准备一个包含不同情绪(悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶)的面部表情图像数据集，使用深度学习技术，如卷积神经网络(CNN)，训练一个面部表情分类模型。该模型能够从图像中准确识别面部表情，包括悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶情绪，在训练集上运行训练好的情绪分类模型，对每张图像进行情绪分类。然后，基于每种情绪，手动在图像上标注一个矩形框作为中心框，中心框准确地包围面部表情的主要特征，并且框的中心应该与面部的中心位置对齐。Specifically, the center box coordinates are the coordinates of the center point of the center box, and the center box of the preset two-dimensional plane is selected based on the target detection algorithm, including preparing a facial expression image dataset containing different emotions (sadness, happiness, surprise, neutrality, fear, anger and disgust) in advance, and using deep learning technology, such as convolutional neural network (CNN), to train a facial expression classification model. The model can accurately identify facial expressions from images, including sadness, happiness, surprise, neutrality, fear, anger and disgust, and run the trained emotion classification model on the training set to classify emotions for each image. Then, based on each emotion, a rectangular box is manually marked on the image as the center box. The center box accurately surrounds the main features of the facial expression, and the center of the box should be aligned with the center position of the face.
另外，对于患者面部点云的关键特征到中心框的距离，使用指数函数作为距离度量，计算简单且高效。指数函数的特性使得距离值能够很好地反映特征点与中心框中心之间的相对位置关系，同时避免了复杂的计算过程。公式中的指数衰减函数能够有效地处理不同位置的面部特征点到中心框的距离，即使特征点位置稍微偏离中心框，也能得到合理的距离值。这种适应性使得公式在实际应用中更为可靠和稳定。能够有效、高效地计算患者面部点云的关键特征与中心框的距离。In addition, for the distance from the key features of the patient's facial point cloud to the center frame, an exponential function is used as the distance metric, which is simple and efficient to calculate. The characteristics of the exponential function enable the distance value to well reflect the relative position relationship between the feature point and the center of the center frame, while avoiding the complicated calculation process. The exponential decay function in the formula can effectively handle the distance from facial feature points at different positions to the center frame, and even if the position of the feature point deviates slightly from the center frame, a reasonable distance value can be obtained. This adaptability makes the formula more reliable and stable in practical applications. It can effectively and efficiently calculate the distance between the key features of the patient's facial point cloud and the center frame.
优选地，计算患者面部图像与患者面部图像样本的相似值，公式如下：Preferably, the similarity value between the patient's facial image and the patient's facial image sample is calculated using the following formula:
式中，n为关键特征的数量，Di为患者面部图像的第i关键特征点云到中心框的距离，D‘i为患者面部图像样本的第i关键特征点云到中心框的距离。Where n is the number of key features,Di is the distance from the i-th key feature point cloud of the patient's facial image to the center frame, and D'i is the distance from the i-th key feature point cloud of the patient's facial image sample to the center frame.
优选地，基于相似值进行分类辨别包括：Preferably, classification and identification based on similarity values includes:
比较患者面部图像与患者面部图像样本的相似值，找到当前患者面部图像最高的相似值对应的患者面部图像样本，对应的患者面部图像样本对应的情绪作为分类辨别结果输出。Compare the similarity values of the patient's facial image with those of the patient's facial image samples, find the patient's facial image sample corresponding to the current patient's facial image with the highest similarity value, and output the emotion corresponding to the corresponding patient's facial image sample as the classification and identification result.
具体的，计算患者面部图像与患者面部图像样本的相似值的公式需要事先准备一个包含不同情绪(悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶)的面部表情图像数据集，每个样本图像也转换成点云数据，并计算关键特征点到中心框的距离，使用公式计算患者面部图像与每个样本图像之间的相似值，样本图像有7种情绪(悲伤、高兴、惊讶、中性、恐惧、愤怒和厌恶)，计算患者图像与这7种情绪样本图像的相似值，比较计算出的相似值，找到最高的相似值对应的情绪类型，假设最高相似度对应的情绪类型是“高兴”，那么就可以判断患者面部图像表现出的情绪是“高兴”。对于患者面部图像与患者面部图像样本的相似值的公式，相比传统余弦函数，公式中的余弦函数以及绝对值的求和部分不仅考虑了特征点之间的距离差异的大小(即绝对值部分)，还考虑了它们的方向性(即余弦函数部分)。这种综合考虑使得相似值E更能够全面地衡量两个面部图像在结构上的相似性，而不仅仅是简单地计算距离的总和或平均值。相较于传统的单一距离度量方法，能够更全面地捕捉面部图像的结构特征，提高了相似性评估的精确度和适用性。Specifically, the formula for calculating the similarity between the patient's facial image and the patient's facial image sample requires a facial expression image dataset containing different emotions (sadness, happiness, surprise, neutrality, fear, anger, and disgust) to be prepared in advance. Each sample image is also converted into point cloud data, and the distance from the key feature point to the center box is calculated. The formula is used to calculate the similarity between the patient's facial image and each sample image. The sample image has 7 emotions (sadness, happiness, surprise, neutrality, fear, anger, and disgust). The similarity between the patient's image and the sample images of these 7 emotions is calculated, and the calculated similarity values are compared to find the emotion type corresponding to the highest similarity value. Assuming that the emotion type corresponding to the highest similarity is "happy", it can be judged that the emotion expressed by the patient's facial image is "happy". For the formula for the similarity between the patient's facial image and the patient's facial image sample, compared with the traditional cosine function, the cosine function and the sum of the absolute values in the formula not only consider the size of the distance difference between the feature points (i.e., the absolute value part), but also consider their directionality (i.e., the cosine function part). This comprehensive consideration enables the similarity value E to more comprehensively measure the structural similarity between two facial images, rather than simply calculating the sum or average of the distances. Compared with the traditional single distance measurement method, it can capture the structural characteristics of facial images more comprehensively and improve the accuracy and applicability of similarity assessment.
另外，智能控制模块根据分类辨别结果和预设治疗方案对理疗仪的工作模式和参数进行调整的方式如下：1、情绪识别与治疗匹配：根据传感模块采集的面部图像，识别模块会将患者的情绪分类为悲伤、高兴、惊讶、中性、恐惧、愤怒或厌恶等七种情绪之一。智能控制模块事先设定了针对每种情绪的理疗方案。2、参数调整：一旦识别模块确定了患者的情绪状态，智能控制模块会根据预设的治疗方案选择相应的工作模式和参数。例如，对于悲伤情绪可能会选择轻柔舒缓的理疗模式，而对于愤怒可能会选择放松和安抚的治疗方式。3、实时调整与反馈：智能控制模块能够实时地根据传感模块的数据调整理疗仪的输出。这包括调整理疗仪的频率、强度、治疗时间等参数，以确保理疗的效果最大化和对患者情绪的有效响应。4、个性化适应：智能控制模块的能力在于根据每个患者当前的情绪状态进行个性化调整，而不是简单地依赖于固定的治疗模式。这种个性化适应能够提高治疗的效果和患者的舒适度。In addition, the intelligent control module adjusts the working mode and parameters of the physiotherapy instrument according to the classification results and the preset treatment plan as follows: 1. Emotion recognition and treatment matching: Based on the facial images collected by the sensor module, the recognition module will classify the patient's emotions into one of seven emotions, such as sadness, happiness, surprise, neutrality, fear, anger or disgust. The intelligent control module pre-sets the physiotherapy plan for each emotion. 2. Parameter adjustment: Once the recognition module determines the patient's emotional state, the intelligent control module will select the corresponding working mode and parameters according to the preset treatment plan. For example, a gentle and soothing physiotherapy mode may be selected for sadness, while a relaxing and soothing treatment method may be selected for anger. 3. Real-time adjustment and feedback: The intelligent control module can adjust the output of the physiotherapy instrument in real time according to the data of the sensor module. This includes adjusting the parameters of the physiotherapy instrument such as frequency, intensity, and treatment time to ensure the maximum effect of physiotherapy and effective response to the patient's emotions. 4. Personalized adaptation: The ability of the intelligent control module lies in making personalized adjustments based on the current emotional state of each patient, rather than simply relying on a fixed treatment mode. This personalized adaptation can improve the effect of treatment and the comfort of the patient.
优选地，理疗模块包括但不限于热疗模块、电疗模块和负压模块，通过对超声波、低频脉冲和负压的控制实现对患者的智能理疗。Preferably, the physiotherapy module includes but is not limited to a thermal therapy module, an electrotherapy module and a negative pressure module, and intelligent physiotherapy for the patient is achieved through the control of ultrasound, low-frequency pulses and negative pressure.
优选地，安全模块还包括存储单元，存储单元用于对治疗过程中的数据进行备份，以防止数据丢失或损坏，必要时恢复备份数据。Preferably, the safety module further comprises a storage unit, which is used to back up the data during the treatment process to prevent data loss or damage, and to restore the backup data when necessary.
以上详细描述了本发明的较佳具体实施例。应当理解，本领域的普通技术无需创造性劳动就可以根据本发明的构思作出诸多修改和变化。因此，凡本技术领域中技术人员依本发明的构思在现有技术的基础上通过逻辑分析、推理或者有限的试验可以得到的技术方案，皆应在由权利要求书所确定的保护范围内。The preferred specific embodiments of the present invention are described in detail above. It should be understood that ordinary technicians in the field can make many modifications and changes based on the concept of the present invention without creative work. Therefore, all technical solutions that can be obtained by technicians in the technical field based on the concept of the present invention through logical analysis, reasoning or limited experiments on the basis of the prior art should be within the scope of protection determined by the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410798484.2ACN118830843B (en) | 2024-06-20 | 2024-06-20 | A physical therapy instrument control system based on artificial intelligence |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410798484.2ACN118830843B (en) | 2024-06-20 | 2024-06-20 | A physical therapy instrument control system based on artificial intelligence |
| Publication Number | Publication Date |
|---|---|
| CN118830843Atrue CN118830843A (en) | 2024-10-25 |
| CN118830843B CN118830843B (en) | 2025-02-11 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410798484.2AActiveCN118830843B (en) | 2024-06-20 | 2024-06-20 | A physical therapy instrument control system based on artificial intelligence |
| Country | Link |
|---|---|
| CN (1) | CN118830843B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008151471A1 (en)* | 2007-06-15 | 2008-12-18 | Tsinghua University | A robust precise eye positioning method in complicated background image |
| CN101650777A (en)* | 2009-09-07 | 2010-02-17 | 东南大学 | Corresponding three-dimensional face recognition method based on dense point |
| US20140313303A1 (en)* | 2013-04-18 | 2014-10-23 | Digimarc Corporation | Longitudinal dermoscopic study employing smartphone-based image registration |
| CN107929950A (en)* | 2017-11-08 | 2018-04-20 | 中国科学院苏州生物医学工程技术研究所 | The multi-modal physical therapeutic system of intelligent three-dimensionalization and its control method |
| CN109858547A (en)* | 2019-01-29 | 2019-06-07 | 东南大学 | A kind of object detection method and device based on BSSD |
| KR20200055811A (en)* | 2018-11-06 | 2020-05-22 | 숙명여자대학교산학협력단 | Facial emotional recognition apparatus for Identify Emotion and method thereof |
| CN111222474A (en)* | 2020-01-09 | 2020-06-02 | 电子科技大学 | An Arbitrary Scale Small Object Detection Method in High Resolution Images |
| CN111914794A (en)* | 2020-08-17 | 2020-11-10 | 长春大学 | Novel deep learning-based physiotherapy instrument system design method |
| WO2021121302A1 (en)* | 2019-12-19 | 2021-06-24 | 华为技术有限公司 | Video collection control method, electronic device, and computer-readable storage medium |
| CN113180944A (en)* | 2021-04-26 | 2021-07-30 | 张远瑞 | Intelligent system therapeutic instrument |
| CN113368403A (en)* | 2021-06-24 | 2021-09-10 | 深圳市恒康泰医疗科技有限公司 | Intelligent physiotherapy system capable of improving cardio-pulmonary function |
| US20210353498A1 (en)* | 2017-05-31 | 2021-11-18 | Chien-Chi Wang | Control system for hand-controlled physiotherapy equipment and electrical stimulation mode |
| CN216211153U (en)* | 2021-08-11 | 2022-04-05 | 武汉中盛瑞邦光电有限公司 | Intelligent security device based on face recognition |
| CN115359521A (en)* | 2022-07-22 | 2022-11-18 | 平安科技（深圳）有限公司 | Face recognition method, device, equipment and storage medium |
| CN115439766A (en)* | 2022-09-23 | 2022-12-06 | 重庆邮电大学 | A UAV target detection method based on improved yolov5 |
| CN116440425A (en)* | 2023-06-19 | 2023-07-18 | 深圳市科医仁科技发展有限公司 | Intelligent adjusting method and system of LED photodynamic therapeutic instrument |
| US20230360350A1 (en)* | 2022-05-03 | 2023-11-09 | Ditto Technologies, Inc. | Systems and methods for scaling using estimated facial features |
| CN117315752A (en)* | 2023-09-26 | 2023-12-29 | 中移(苏州)软件技术有限公司 | Training method, device, equipment and medium for face emotion recognition network model |
| CN117581260A (en)* | 2021-05-31 | 2024-02-20 | 索尼半导体解决方案公司 | Face deformation compensation method, imaging device and storage medium for face depth image |
| US20240142994A1 (en)* | 2022-09-05 | 2024-05-02 | Al Incorporated | Stationary service appliance for a poly functional roaming device |
| CN118045289A (en)* | 2024-03-19 | 2024-05-17 | 深圳市宏强兴电子有限公司 | Safety protection device of physiotherapy equipment and physiotherapy equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008151471A1 (en)* | 2007-06-15 | 2008-12-18 | Tsinghua University | A robust precise eye positioning method in complicated background image |
| CN101650777A (en)* | 2009-09-07 | 2010-02-17 | 东南大学 | Corresponding three-dimensional face recognition method based on dense point |
| US20140313303A1 (en)* | 2013-04-18 | 2014-10-23 | Digimarc Corporation | Longitudinal dermoscopic study employing smartphone-based image registration |
| US20210353498A1 (en)* | 2017-05-31 | 2021-11-18 | Chien-Chi Wang | Control system for hand-controlled physiotherapy equipment and electrical stimulation mode |
| CN107929950A (en)* | 2017-11-08 | 2018-04-20 | 中国科学院苏州生物医学工程技术研究所 | The multi-modal physical therapeutic system of intelligent three-dimensionalization and its control method |
| KR20200055811A (en)* | 2018-11-06 | 2020-05-22 | 숙명여자대학교산학협력단 | Facial emotional recognition apparatus for Identify Emotion and method thereof |
| CN109858547A (en)* | 2019-01-29 | 2019-06-07 | 东南大学 | A kind of object detection method and device based on BSSD |
| WO2021121302A1 (en)* | 2019-12-19 | 2021-06-24 | 华为技术有限公司 | Video collection control method, electronic device, and computer-readable storage medium |
| CN111222474A (en)* | 2020-01-09 | 2020-06-02 | 电子科技大学 | An Arbitrary Scale Small Object Detection Method in High Resolution Images |
| CN111914794A (en)* | 2020-08-17 | 2020-11-10 | 长春大学 | Novel deep learning-based physiotherapy instrument system design method |
| CN113180944A (en)* | 2021-04-26 | 2021-07-30 | 张远瑞 | Intelligent system therapeutic instrument |
| CN117581260A (en)* | 2021-05-31 | 2024-02-20 | 索尼半导体解决方案公司 | Face deformation compensation method, imaging device and storage medium for face depth image |
| CN113368403A (en)* | 2021-06-24 | 2021-09-10 | 深圳市恒康泰医疗科技有限公司 | Intelligent physiotherapy system capable of improving cardio-pulmonary function |
| CN216211153U (en)* | 2021-08-11 | 2022-04-05 | 武汉中盛瑞邦光电有限公司 | Intelligent security device based on face recognition |
| US20230360350A1 (en)* | 2022-05-03 | 2023-11-09 | Ditto Technologies, Inc. | Systems and methods for scaling using estimated facial features |
| CN115359521A (en)* | 2022-07-22 | 2022-11-18 | 平安科技（深圳）有限公司 | Face recognition method, device, equipment and storage medium |
| US20240142994A1 (en)* | 2022-09-05 | 2024-05-02 | Al Incorporated | Stationary service appliance for a poly functional roaming device |
| CN115439766A (en)* | 2022-09-23 | 2022-12-06 | 重庆邮电大学 | A UAV target detection method based on improved yolov5 |
| CN116440425A (en)* | 2023-06-19 | 2023-07-18 | 深圳市科医仁科技发展有限公司 | Intelligent adjusting method and system of LED photodynamic therapeutic instrument |
| CN117315752A (en)* | 2023-09-26 | 2023-12-29 | 中移(苏州)软件技术有限公司 | Training method, device, equipment and medium for face emotion recognition network model |
| CN118045289A (en)* | 2024-03-19 | 2024-05-17 | 深圳市宏强兴电子有限公司 | Safety protection device of physiotherapy equipment and physiotherapy equipment |
| Title |
|---|
| 余冰;胡新荣;程露;: "基于Kinect的面部表情获取与识别方法研究", 科技创业月刊, no. 08, 25 April 2016 (2016-04-25)* |
| 吴嘉琪;景丽萍;: "基于集成人脸对距离学习的跨年龄人脸验证", 模式识别与人工智能, no. 12, 15 December 2017 (2017-12-15)* |
| 成亚玲;谭爱平;张敏;: "混合多距离图像的线性判别分析人脸识别算法", 系统仿真学报, no. 09, 8 September 2016 (2016-09-08)* |
| Publication number | Publication date |
|---|---|
| CN118830843B (en) | 2025-02-11 |
| Publication | Publication Date | Title |
|---|---|---|
| CN113080855B (en) | A facial pain expression recognition method and system based on depth information | |
| CN116452855A (en) | Wound image classification and laser assisted treatment method based on deep learning | |
| CN109002846B (en) | Image recognition method, device and storage medium | |
| CN120000167A (en) | An intelligent pain detection and management system | |
| CN114983418A (en) | Feedback system for acquiring mental health condition | |
| CN106725341A (en) | A kind of enhanced lingual diagnosis system | |
| WO2021077480A1 (en) | Radiotherapy patient identity verification method and apparatus, and radiotherapy device | |
| CN118782212A (en) | A social simulation digital intervention system based on virtual reality | |
| CN118830843B (en) | A physical therapy instrument control system based on artificial intelligence | |
| CN115758119A (en) | Paralytic patient monitoring system based on brain-computer interface and motion recognition | |
| CN119606324A (en) | A system and method for analyzing oral function rehabilitation training after oral and maxillofacial surgery | |
| CN112164436A (en) | Artificial intelligence real-time medical scheme adjusting system and method based on face recognition | |
| CN115054829B (en) | Intelligent plasma brush system, implementation method and device thereof, and storage medium | |
| CN118800394A (en) | Ultrasonic medical parameter adaptive optimization system and method based on artificial intelligence | |
| CN118490165A (en) | Anesthetic state assessment method and system based on EEG data analysis | |
| CN118644819B (en) | Video monitoring management method and system for face care | |
| CN119746278A (en) | A portable red light therapy device | |
| CN118893639B (en) | Nursing robot control method and robot system | |
| CN116077071B (en) | Intelligent rehabilitation massage method, robot and storage medium | |
| CN118846412B (en) | Intelligent multi-parameter optimized ultrasonic therapeutic device and optimized control system | |
| CN116186575B (en) | A method for processing breast sampling data based on machine learning | |
| CN118248316A (en) | Cardiopulmonary resuscitation guidance method and system based on remote communication | |
| CN118711796B (en) | AI-based oral sedation treatment auxiliary monitoring method, system and medium | |
| CN115741728A (en) | Intelligent epidemic prevention robot | |
| CN119499555A (en) | A red light therapy device capable of online calibration |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 |