Local Gabor Characteristic Integrated with LDP for Face Recognition with One Training Sample
Traditional methods get low recognition accuracy in the condition of only one training sample. A new face recognition method based on local Gabor phase characteristic and locality dispersing projection (LGP/LDP) is proposed. In our proposed method, according to the good spatial position and orientation of Gabor filter, a Gabor filter with four frequencies and six orientations is firstly applied to filter face images. Based on Daugmans method and the local Exclusive-or (XOR) pattern, local Gabor patterns are then extracted to form the characteristic images. Finally, LDP is used to project the characteristic images of each spatial position and orientation into low dimensional space. Neighbor classifier is adopted and the classified information is fused to get the recognition result. Experimental results show that our method consistently outperforms other recognition method based on Principal Component Analysis (PCA), LDP and local Gabor phase characteristic integrated with PCA (LGP/PCA).
face recognition local gabor phase characteristic characteristic fusion locality dispersing projection
JIANG Yan-xia REN Bo
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Techno School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Techno
国际会议
重庆
英文
121-125
2011-01-21（万方平台首次上网日期，不代表论文的发表时间）