Gesture recognition based on an improved local sparse representation classification algorithm

Yang He, Gongfa Li, Yajie Liao, Ying Sun, Jianyi Kong, Guozhang Jiang, Du Jiang, Bo Tao, Shuang Xu, Honghai Liu

Research output: Contribution to journalArticlepeer-review

288 Downloads (Pure)


The sparse representation classification method has been widely concerned and studies in pattern recognition because of its good recognition effect and classification performance. Using the minimized l1 norm to solve the sparse coefficient, all the training samples are selected as the redundant to calculate, but the computational complexity is higher. Aiming at the problem of high computational complexity of the l1 norm based solving algorithm, l2 norm local sparse representation classification algorithm is proposed. This algorithm uses the minimum l2 norm method to select the local dictionary. Then the minimum l1 norm is used in the dictionary to solve sparse coefficients for classifying them, and the algorithm is used to verify the gesture recognition on the constructed gesture database. The experimental results show that the algorithm can effectively reduce the calculation time while ensuring the recognition rate, and the performance of the algorithm is slightly better than KNN-SRC algorithm.
Original languageEnglish
Number of pages12
JournalCluster Computing
Early online date10 Oct 2017
Publication statusEarly online - 10 Oct 2017


  • gesture recognition
  • l2 norm
  • sparse representation
  • classification algorithm


Dive into the research topics of 'Gesture recognition based on an improved local sparse representation classification algorithm'. Together they form a unique fingerprint.

Cite this