Pose-robust face recognition with Huffman-LBP enhanced by Divide-and-Rule strategy. (June 2018)

• Record Type: Journal Article
• Authors: Zhou, Li-Fang; Du, Yue-Wei; Li, Wei-Sheng; Mi, Jian-Xun; Luan, Xiao
• Is Part Of: Pattern recognition. Volume 78(2018:Jun.)
• Page Start: 43
• Page End: 55
• Publication Date: 2018-06
• Subjects: Face recognition across pose -- LBP -- Huffman -- Divide-and-Rule strategy; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.01.003
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel LBP-like feature is proposed which takes the contribution of contrast value into consideration by Huffman coding. The Divide-and-Rule strategy is applied to both face representation and classification with the goal of improving the robustness to pose variation. Face representation via Region Selection Factor (RSF) is suggested in our method to treat the face images of different poses specifically rather than generally. In order to further make the method tolerate the rotations, we perform the face classification at the patch-level using a patchbased SRC fusion classification strategy. Abstract: Face recognition in harsh environments is an active research topic. As one of the most important challenges, face recognition across pose has received extensive attention. LBP feature has been used widely in face recognition because of its robustness to slight illumination and pose variations. However, due to the way of pattern feature calculation, its effectiveness is limited by the big rotations. In this paper, a new LBP-like feature extraction is proposed which modifies the code rule by Huffman. Besides, a Divide-and-Rule strategy is applied to both face representation and classification, which aims to improve recognition performance across pose. Extensive experiments on CMU PIE database, FERET database and LFW database are conducted to verify the efficacy of the proposed method. The experimental results show that our method significantly outperforms other approaches.