A new method for interaction recognition based on sparse representation of feature covariance matrices was presented.Firstly,the dense trajectories(DT)extracted from the video were clustered into different groups to e...A new method for interaction recognition based on sparse representation of feature covariance matrices was presented.Firstly,the dense trajectories(DT)extracted from the video were clustered into different groups to eliminate the irrelevant trajectories,which could greatly reduce the noise influence on feature extraction.Then,the trajectory tunnels were characterized by means of feature covariance matrices.In this way,the discriminative descriptors could be extracted,which was also an effective solution to the problem that the description of the feature second-order statistics is insufficient.After that,an over-complete dictionary was learned with the descriptors and all the descriptors were encoded using sparse coding(SC).Classification was achieved using multiple instance learning(MIL),which was more suitable for complex environments.The proposed method was tested and evaluated on the WEB Interaction dataset and the UT interaction dataset.The experimental results demonstrated the superior efficiency.展开更多
Aiming at technical difficulties in feature extraction for the inverse synthetic aperture radar （ISAR） target recognition, this paper imports the concept of visual perception and presents a novel method, which is ba...Aiming at technical difficulties in feature extraction for the inverse synthetic aperture radar （ISAR） target recognition, this paper imports the concept of visual perception and presents a novel method, which is based on the combination of non-negative sparse coding （NNSC） and linear discrimination optimization, to recognize targets in ISAR images. This method implements NNSC on the matrix constituted by the intensities of pixels in ISAR images for training, to obtain non-negative sparse bases which characterize sparse distribution of strong scattering centers. Then this paper chooses sparse bases via optimization criteria and calculates the corresponding non-negative sparse codes of both training and test images as the feature vectors, which are input into k neighbors classifier to realize recognition finally. The feasibility and robustness of the proposed method are proved by comparing with the template matching, principle component analysis （PCA） and non-negative matrix factorization （NMF） via simulations.展开更多
针对近红外光下采集的指静脉图像存在局部像素相似性强、单一方向识别效果差的问题,提出模板投票和多方向融合的指静脉识别方法。首先,提出基于模板投票的局部三值模式(template voting local three pattern,TVTP),充分利用局部多邻域...针对近红外光下采集的指静脉图像存在局部像素相似性强、单一方向识别效果差的问题,提出模板投票和多方向融合的指静脉识别方法。首先,提出基于模板投票的局部三值模式(template voting local three pattern,TVTP),充分利用局部多邻域点的信息,减少局部像素相似性;其次,指静脉图像中含有丰富的方向特征信息,提出多方向编码(multi-directional coding,MDC),获取图像中具有辨别力的方向特征,加强不同方向特征之间的鲁棒性,解决单一方向识别率差的问题;最后,利用分块直方图统计特征,并使用协同表示(collaborative representation,CR)进行分类,提高识别效率。实验结果证明,所提方法在SDUMLA数据集、USM数据集和THU-FVFDT2数据集上的识别率分别达到99.32%、99.73%和99.75%,与其他经典和新颖算法相比,不仅取得了更好的识别效果,还能同时满足实时性要求,具有应用价值。展开更多
数字化浪潮下,企业日益依赖机器人流程自动化(Robot Process Automation,RPA)技术来降低成本、提高效率,以保持竞争力。但流程中部分环节面临汉字点选验证码识别的难题,限制了自动化水平的进一步提高。现有研究方案存在数据集制作难度...数字化浪潮下,企业日益依赖机器人流程自动化(Robot Process Automation,RPA)技术来降低成本、提高效率,以保持竞争力。但流程中部分环节面临汉字点选验证码识别的难题,限制了自动化水平的进一步提高。现有研究方案存在数据集制作难度大、模型泛化性能差、模型复杂度与性能之间不平衡等问题。为此,提出一种数据集制作成本低、模型泛化性能好且轻量化的汉字点选验证码识别方法。具体而言:首先采用经过针对性改进的YOLOv8-n显著轻量化汉字检测模型,然后对汉字图片进行分割、矫正等预处理操作,接着采用泛化性强的PaddleOCR模型进行汉字识别,降低了场景迁移的成本,并通过识别概率矩阵得到最佳匹配结果,进一步提高了准确率。此外,设计了一种半自动的汉字检测数据集构建流程并公开了数据集。该研究旨在推动汉字点选验证码的自动识别技术的发展,促进企业流程自动化水平的提升。展开更多
基金Project(51678075) supported by the National Natural Science Foundation of ChinaProject(2017GK2271) supported by the Science and Technology Project of Hunan Province,China
文摘A new method for interaction recognition based on sparse representation of feature covariance matrices was presented.Firstly,the dense trajectories(DT)extracted from the video were clustered into different groups to eliminate the irrelevant trajectories,which could greatly reduce the noise influence on feature extraction.Then,the trajectory tunnels were characterized by means of feature covariance matrices.In this way,the discriminative descriptors could be extracted,which was also an effective solution to the problem that the description of the feature second-order statistics is insufficient.After that,an over-complete dictionary was learned with the descriptors and all the descriptors were encoded using sparse coding(SC).Classification was achieved using multiple instance learning(MIL),which was more suitable for complex environments.The proposed method was tested and evaluated on the WEB Interaction dataset and the UT interaction dataset.The experimental results demonstrated the superior efficiency.
基金supported by the Prominent Youth Fund of the National Natural Science Foundation of China (61025006)
文摘Aiming at technical difficulties in feature extraction for the inverse synthetic aperture radar （ISAR） target recognition, this paper imports the concept of visual perception and presents a novel method, which is based on the combination of non-negative sparse coding （NNSC） and linear discrimination optimization, to recognize targets in ISAR images. This method implements NNSC on the matrix constituted by the intensities of pixels in ISAR images for training, to obtain non-negative sparse bases which characterize sparse distribution of strong scattering centers. Then this paper chooses sparse bases via optimization criteria and calculates the corresponding non-negative sparse codes of both training and test images as the feature vectors, which are input into k neighbors classifier to realize recognition finally. The feasibility and robustness of the proposed method are proved by comparing with the template matching, principle component analysis （PCA） and non-negative matrix factorization （NMF） via simulations.
文摘针对近红外光下采集的指静脉图像存在局部像素相似性强、单一方向识别效果差的问题,提出模板投票和多方向融合的指静脉识别方法。首先,提出基于模板投票的局部三值模式(template voting local three pattern,TVTP),充分利用局部多邻域点的信息,减少局部像素相似性;其次,指静脉图像中含有丰富的方向特征信息,提出多方向编码(multi-directional coding,MDC),获取图像中具有辨别力的方向特征,加强不同方向特征之间的鲁棒性,解决单一方向识别率差的问题;最后,利用分块直方图统计特征,并使用协同表示(collaborative representation,CR)进行分类,提高识别效率。实验结果证明,所提方法在SDUMLA数据集、USM数据集和THU-FVFDT2数据集上的识别率分别达到99.32%、99.73%和99.75%,与其他经典和新颖算法相比,不仅取得了更好的识别效果,还能同时满足实时性要求,具有应用价值。
文摘数字化浪潮下,企业日益依赖机器人流程自动化(Robot Process Automation,RPA)技术来降低成本、提高效率,以保持竞争力。但流程中部分环节面临汉字点选验证码识别的难题,限制了自动化水平的进一步提高。现有研究方案存在数据集制作难度大、模型泛化性能差、模型复杂度与性能之间不平衡等问题。为此,提出一种数据集制作成本低、模型泛化性能好且轻量化的汉字点选验证码识别方法。具体而言:首先采用经过针对性改进的YOLOv8-n显著轻量化汉字检测模型,然后对汉字图片进行分割、矫正等预处理操作,接着采用泛化性强的PaddleOCR模型进行汉字识别,降低了场景迁移的成本,并通过识别概率矩阵得到最佳匹配结果,进一步提高了准确率。此外,设计了一种半自动的汉字检测数据集构建流程并公开了数据集。该研究旨在推动汉字点选验证码的自动识别技术的发展,促进企业流程自动化水平的提升。
