Adaptive hierarchical architecture for visual recognition

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.