Adaptive hierarchical architecture for visual recognition

Fok Hing Chi Tivive, University of Wollongong
Abdesselam Bouzerdoum, University of Wollongong
Son Lam Phung, University of Wollongong
Khan M. Iftekharuddin, University of Memphis

Article comments

Tivive, F., Bouzerdoum, A., Phung, S. & Iftekharuddin, K. M. (2010). Adaptive hierarchical architecture for visual recognition. Applied Optics, 49 (10), B1-B8.

Abstract

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 filters 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.