A novel illumination-robust local descriptor based on sparse linear regression

详细信息    查看全文

• 作者：Zuodong Yang^a ; ^b ; ^{yangzd13@mails.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yong Wu^a ; ^b ; ^{wuyong11@mails.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Wenteng Zhao^a ; ^b ; ^{zhaowt13@mails.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yicong Zhou^c ; ^{yicongzhou@umac.mo" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Zongqing Lu^a ; ^b ; ^{luzq@sz.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Weifeng Li^a ; ^b ; ^{Li.Weifeng@sz.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Qingmin Liao^a ; ^b ; ^{liaoqm@tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Face recognition ; Illumination-insensitive representation ; Local descriptor ; Sparse linear regression
• 刊名：Digital Signal Processing
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：48
• 期：Complete
• 页码：269-275
• 全文大小：1629 K

文摘

Robust face recognition under uncontrolled illumination conditions is an important problem for real face recognition systems. In this paper, we introduce a novel illumination-robust local descriptor named Sparse Linear Regression Binary (SLRB) descriptor. The SLRB descriptor is a bit string by binarizing the sparse linear regression coefficients in a local block. It is an illumination-insensitive descriptor based on the locally linear consistency assumption under the Lambertian reflectance model. We use the cosine similarity and Hamming similarity as the similarity measure for the SLRB descriptor of two different images respectively. Experimental results on the Extended Yale-B and CMU-PIE face database show a promising performance compared to the existing representative approaches.