Subspace ensemble learning via totally-corrective boosting for gait recognition

详细信息    查看全文

• 作者：Guangkai Ma^a ; ¹ ; Author Vitae ; Yan Wang^b ; ¹Author Vitae ; Ligang Wu^aAuthor Vitae
• 关键词：Subspace learning ; Totally-corrective boosting ; Ensemble learning ; Gait recognition
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：8 February 2017
• 年：2017
• 卷：224
• 期：Complete
• 页码：119-127
• 全文大小：1045 K
• 卷排序：224

文摘

Human identification at a distance has recently become a hot research topic in the fields of computer vision and pattern recognition. Since gait patterns can operate from a distance without subject cooperation, gait recognition has most widely been studied to address this problem. In this paper, a subspace ensemble learning using totally-corrective boosting (SEL_TCB) framework and its kernel extension are proposed for gait recognition. In this framework, multiple subspaces are iteratively learned with different weight distributions on the triplet set using totally-corrective technology, in order to preserve the proximity relationships among instance triplets. Further, we extend the SEL_TCB framework to the kernel SEL_TCB (KSEL_TCB) framework which can deal with the nonlinear manifold of data. We compare our method with the recently published gait recognition approaches on USF HumanID Database. Experimental results indicate that the proposed method achieves highly competitive performance against the state-of-the-art gait recognition approaches.