Title :
Background learning for robust face recognition
Author :
Singh, R.K. ; Rajagopalan, A.N.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Madras, India
Abstract :
In this paper, we propose a robust face recognition technique based on the principle of eigenfaces. The traditional eigenface recognition (EFR) method works quite well when the input test patterns are cropped faces. However, when confronted with recognizing faces embedded in arbitrary backgrounds, the EFR method fails to discriminate effectively between faces and background patterns, giving rise to many false alarms. In order to improve robustness in the presence of background, we argue in favor of learning the distribution of background patterns. A background space is constructed from the background patterns and this space together with the face space is used for recognizing faces. The proposed method outperforms the traditional EFR technique and gives very good results even on complicated scenes.
Keywords :
computer vision; eigenvalues and eigenfunctions; face recognition; learning (artificial intelligence); background learning; background patterns; background scene; background space; eigenfaces; face detection; face recognition; Face detection; Face recognition; Humans; Image databases; Image reconstruction; Layout; Pattern recognition; Robustness; Testing;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1047992