Skip to main content

Adaptive hierarchical architecture for visual recognition

Journal Article


Download full-text (Open Access)

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.

Publication Date


  • 2010

Citation


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

Scopus Eid


  • 2-s2.0-77954051885

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1825&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/814

Start Page


  • B1

End Page


  • B8

Volume


  • 49

Issue


  • 10

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.

Publication Date


  • 2010

Citation


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

Scopus Eid


  • 2-s2.0-77954051885

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1825&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/814

Start Page


  • B1

End Page


  • B8

Volume


  • 49

Issue


  • 10