Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inc...Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.展开更多
By combining the AdaBoost modular locality preserving projection （AMLPP） algorithm and the locally linear regression （LLR） algorithm, a novel pose-invariant algorithm is proposed to realize high-accuracy face reco...By combining the AdaBoost modular locality preserving projection （AMLPP） algorithm and the locally linear regression （LLR） algorithm, a novel pose-invariant algorithm is proposed to realize high-accuracy face recognition under different poses. In the training stage of this algorithm, the AMLPP is employed to select the crucial frontal blocks and construct effective strong classifier. According to the selected frontal blocks and the corresponding non-frontal blocks, LLR is then applied to learn the linear mappings which will be used to convert the non-frontal blocks to visual frontal blocks. During the testing of the learned linear mappings, when a non-frontal face image is inputted, the non-frontal blocks corresponding to the selected frontal blocks are extracted and converted to the visual frontal blocks. The generated virtual frontal blocks are finally fed into the strong classifier constructed by AMLPP to realize accurate and efficient face recognition. Our algorithm is experimentally compared with other pose-invariant face recognition algorithms based on the Bosphorus database. The results show a significant improvement with our proposed algorithm.展开更多
Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as costly devices,spec...Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as costly devices,specified postures, simple background, and stable illumination. In this paper, a contactless personal identification system is proposed based on matching hand geometry features and color features. An inexpensive Kinect sensor is used to acquire depth and color images of the hand. During image acquisition, no pegs or surfaces are used to constrain hand position or posture. We segment the hand from the background through depth images through a process which is insensitive to illumination and background. Then finger orientations and landmark points, like finger tips or finger valleys, are obtained by geodesic hand contour analysis. Geometric features are extracted from depth images and palmprint features from intensity images. In previous systems, hand features like finger length and width are normalized, which results in the loss of the original geometric features. In our system, we transform 2D image points into real world coordinates, so that the geometric features remain invariant to distance and perspective effects. Extensive experiments demonstrate that the proposed hand-biometric-based personal identification system is effective and robust in various practical situations.展开更多
经典LLE(Locally Linear Embedding)通过流形学习,能够得到嵌入在高维空间的低维流形.但是它与Isomap、Lapla-cian Eigenmaps一样,学习过程中没有用到先验知识.本文改进了LLE方法,充分利用先验类别信息,能够找到从高维空间到低维空间更...经典LLE(Locally Linear Embedding)通过流形学习,能够得到嵌入在高维空间的低维流形.但是它与Isomap、Lapla-cian Eigenmaps一样,学习过程中没有用到先验知识.本文改进了LLE方法,充分利用先验类别信息,能够找到从高维空间到低维空间更为合理的映射.最终使用一种线性近似的方法学习这种映射的显示表达.通过这种映射,可以比较好地解决人脸识别中的姿态问题.在FERET数据库上,当姿态变化从-60度到+60度,该方法达到了较高的识别率.展开更多
基金supported by the National Natural Science Foundation of China (No.31872399)Advantage Discipline Construction Project (PAPD,No.6-2018)of Jiangsu University。
文摘Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.
基金Supported by the National Natural Science Foundation of China(60772066)
文摘By combining the AdaBoost modular locality preserving projection （AMLPP） algorithm and the locally linear regression （LLR） algorithm, a novel pose-invariant algorithm is proposed to realize high-accuracy face recognition under different poses. In the training stage of this algorithm, the AMLPP is employed to select the crucial frontal blocks and construct effective strong classifier. According to the selected frontal blocks and the corresponding non-frontal blocks, LLR is then applied to learn the linear mappings which will be used to convert the non-frontal blocks to visual frontal blocks. During the testing of the learned linear mappings, when a non-frontal face image is inputted, the non-frontal blocks corresponding to the selected frontal blocks are extracted and converted to the visual frontal blocks. The generated virtual frontal blocks are finally fed into the strong classifier constructed by AMLPP to realize accurate and efficient face recognition. Our algorithm is experimentally compared with other pose-invariant face recognition algorithms based on the Bosphorus database. The results show a significant improvement with our proposed algorithm.
基金Project supported by the National Natural Science Foundation of China(Nos.61340046,60875050,and 60675025)the National High-Tech R&D Program(863)of China(No.2006AA04Z247)+1 种基金the Scientific and Technical Innovation Commission of Shenzhen Municipality(Nos.JCYJ20120614152234873,CXC201104210010A,JCYJ20130331144631730,and JCYJ20130331144716089)the Specialized Research Fund for the Doctoral Program of Higher Education,China(No.20130001110011)
文摘Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as costly devices,specified postures, simple background, and stable illumination. In this paper, a contactless personal identification system is proposed based on matching hand geometry features and color features. An inexpensive Kinect sensor is used to acquire depth and color images of the hand. During image acquisition, no pegs or surfaces are used to constrain hand position or posture. We segment the hand from the background through depth images through a process which is insensitive to illumination and background. Then finger orientations and landmark points, like finger tips or finger valleys, are obtained by geodesic hand contour analysis. Geometric features are extracted from depth images and palmprint features from intensity images. In previous systems, hand features like finger length and width are normalized, which results in the loss of the original geometric features. In our system, we transform 2D image points into real world coordinates, so that the geometric features remain invariant to distance and perspective effects. Extensive experiments demonstrate that the proposed hand-biometric-based personal identification system is effective and robust in various practical situations.
文摘经典LLE(Locally Linear Embedding)通过流形学习,能够得到嵌入在高维空间的低维流形.但是它与Isomap、Lapla-cian Eigenmaps一样,学习过程中没有用到先验知识.本文改进了LLE方法,充分利用先验类别信息,能够找到从高维空间到低维空间更为合理的映射.最终使用一种线性近似的方法学习这种映射的显示表达.通过这种映射,可以比较好地解决人脸识别中的姿态问题.在FERET数据库上,当姿态变化从-60度到+60度,该方法达到了较高的识别率.
