Face recognition based on Kinect. Issue 4 (November 2016)

• Record Type: Journal Article
• Authors: Li, Billy; Mian, Ajmal; Liu, Wanquan; Krishna, Aneesh
• Is Part Of: Pattern analysis and applications. Volume 19:Issue 4(2016:Nov.)
• Page Start: 977
• Page End: 987
• Publication Date: 2016-11
• Subjects: Face recognition -- Kinect Sensor -- 3D face images -- Gabor feature -- LDA; Pattern recognition systems -- Periodicals; Pattern perception -- Periodicals; 006.4
• DOI: 10.1007/s10044-015-0456-4
• Languages: English
• ISSNs: 1433-7541

Abstract

Abstract In this paper, we present a new algorithm that utilizes low-quality red, green, blue and depth (RGB-D) data from the Kinect sensor for face recognition under challenging conditions. This algorithm extracts multiple features and fuses them at the feature level. A Finer Feature Fusion technique is developed that removes redundant information and retains only the meaningful features for possible maximum class separability. We also introduce a new 3D face database acquired with the Kinect sensor which has released to the research community. This database contains over 5, 000 facial images (RGB-D) of 52 individuals under varying pose, expression, illumination and occlusions. Under the first three variations and using only the noisy depth data, the proposed algorithm can achieve 72.5 % recognition rate which is significantly higher than the 41.9 % achieved by the baseline LDA method. Combined with the texture information, 91.3 % recognition rate has achieved under illumination, pose and expression variations. These results suggest the feasibility of low-cost 3D sensors for real-time face recognition.