We propose a new hierarchical architecture for visual pattern classification. The new architecture consists of a set of fixed, directional filters and a set of adaptive filters arranged in a cascade structure. The fixed filters are used to extract primitive features such as orientations and edges that are present in a wide range of objects, whereas the adaptive filters can be trained to find complex features that are specific to a given object. Both types of filter are based on the biological mechanism of shunting inhibition. The proposed architecture is applied to two problems: pedestrian detection and car detection. Evaluation results on benchmark data sets demonstrate that the proposed architecture outperforms several existing ones.
© 2010 Optical Society of America
Original Manuscript: October 2, 2009
Revised Manuscript: December 18, 2009
Manuscript Accepted: December 26, 2009
Published: January 28, 2010
Vol. 5, Iss. 8 Virtual Journal for Biomedical Optics
Fok H. C. Tivive, Abdesselam Bouzerdoum, Son Lam Phung, and Khan M. Iftekharuddin, "Adaptive hierarchical architecture for visual recognition," Appl. Opt. 49, B1-B8 (2010)