Invariant object detection based on evidence accumulation and Gabor features

Abstract

In this paper. we propose an invariant object detection method based on evidence accumulation and the Gabor transforms feature. In contrast to conventional evidence accumulation methods, the proposed method uses Gabor transform features to detect object parts. Experimental results prove that our algorithm robustly detects arbitrary shaped objects in cluttered environments with invariance to translation, rotation, scaling and small deformation. (C) 2001 Elsevier Science B.V. All rights reserved.