Harris feature vector descriptor

• DOI: 10.1109/icmlc.2010.5581008
• Publication Date: 2010-09-22T15:57:54Z
• Authors: Xu-Guang Wang; Jie Su; Hai-Yan Cheng
• Keywords: Feature (linguistics); Feature vector; Point distribution model

This paper defines a new image feature called Harris vector, which is able to describe the gradient distribution in an effective way. By computing mean and standard deviation of vector local region, novel descriptors are constructed for matching invariable rigid transformation linear intensity change. Experimental evidence suggests that descriptor point has good adaptability slight view changing, JPEG compression nonlinear changing intensity, besides, line performs well too.