Introduction: With the rapid development of information acquisition technology and sensor technology, there are more and more research experiments using computer vision technology to identify micro-expressions. In these experiments, the dimensionality of the actual acquired image data is getting higher and higher, how to describe the image effectively and convenient for subsequent processing has become one of the problems that need to be solved urgently in the fields of image processing, pattern recognition, and machine learning. Among the many existing methods, sparse algorithms have become the focus of current research due to their advantages of good robustness, generalization ability and strong anti-interference ability. This article was included in the PRICAI 2016 conference to discuss spontaneous micro-expression recognition based on the lean K-SVD algorithm. Title: Spontaneous Micro-expression Recognition Based on Scrambled K-SVD Algorithm Abstract: Micro-expression recognition has always been a challenging issue in computer vision because it is too subtle, but it is often difficult to hide. This paper presents a sparse K-SVD algorithm (RK-SVD) to learn sparse dictionaries for spontaneous micro-expression recognition. In RK-SVD, taking into account reconstruction errors and classification errors, the variance of sparse coefficients is minimized to handle similarity similarity and heterogeneity. The K-SVD algorithm and the stochastic gradient descent algorithm are used for optimization. Finally, a separate overcomplete dictionary and an optimal linear classifier are learned at the same time. The experimental results are based on two spontaneous micro-expression databases, CASME and CASME II, indicating that the new algorithm outperforms other advanced algorithms. Keywords: K-SVD correlation; dictionary learning; micro-expression recognition The first author introduction: Hao Zheng Nanjing Xiaozhuang College, School of Information Engineering, Key Laboratory of Trusted Cloud Computing and Big Data Analysis; Southeast University, School of Computer Science and Engineering, Key Laboratory of Computer Networks and Information Integration Ministry of Education; Provincial Key Laboratory of New Software Technology. Via PRICAI 2016 Paper original file download Lei Feng Network Press: This article by Lei Feng network (search "Lei Feng network" public number concern) exclusive compilation, without permission prohibited reprint! Hongkong Onice Limited , https://www.ousibangvape.com
