Share Email Print

Proceedings Paper

Feature extraction inspired by visual cortex mechanisms
Author(s): Xing Du; Weiguo Gong; Weihong Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Motivated by the mechanisms of mammalian primary visual cortex (V1), we propose a hierarchical model of feature extraction for object recognition. The proposed model consists of two layers, each of which emulates the functions of V1 simple cells and complex cells respectively. Filters learned from training images are applied at every position of the input image to get an edge feature representation. Then a maximum pooling operation is taken to increase shiftinvariance of the feature. Experiments on face recognition and crop-wise object detection show that our model is competitive with the state-of-the-art biologically-inspired method.

Paper Details

Date Published: 26 February 2010
PDF: 6 pages
Proc. SPIE 7546, Second International Conference on Digital Image Processing, 75460M (26 February 2010); doi: 10.1117/12.852798
Show Author Affiliations
Xing Du, Chongqing Univ. (China)
Weiguo Gong, Chongqing Univ. (China)
Weihong Li, Chongqing Univ. (China)

Published in SPIE Proceedings Vol. 7546:
Second International Conference on Digital Image Processing
Kamaruzaman Jusoff; Yi Xie, Editor(s)

© SPIE. Terms of Use
Back to Top