 |
    |
A New Biologically Inspired Color Image Descriptor
Jun Zhang1,2, Youssef Barhomi1, and Thomas Serre1
1Department of Cognitive Linguistic & Psychological Sciences Institute for Brain Sciences, Brown University, Providence, RI 02912, USA
zhangjun1126@gmail.com
youssef_barhomi@brown.edu
thomas_serre@brown.edu
2School of Computer & Information, Hefei University of Technology, Hefei, Anhui 230009, China
Abstract. We describe a novel framework for the joint processing of color and shape information in natural images. A hierarchical non-linear spatio-chromatic operator yields spatial and chromatic opponent channels, which mimics processing in the primate visual cortex. We extend two popular object recognition systems (i.e., the Hmax hierarchical model of visual processing and a sift-based bag-of-words approach) to incorporate color information along with shape information. We further use the framework in combination with the gist algorithm for scene categorization as well as the Berkeley segmentation algorithm. In all cases, the proposed approach is shown to outperform standard grayscale/shape-based descriptors as well as alternative color processing schemes on several datasets.
Keywords: image descriptor, color,
LNCS 7576, p. 312 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012