Lifting Wavelet Based Cognitive Vision System

Abstract

This paper presents a cognitive vision system based on the learning of lifting wavelets. The learning process consists of four steps: 1. Extract training and query object images automatically from adjacent video frames using our proposed cosine-maximization method; 2. Compute autocorrelation vectors from the extracted training images, and their discriminant vectors by linear discriminant analysis; 3. Map the autocorrelation vectors onto the discriminant vector space to obtain feature vectors; 4. Learn lifting parameters in the feature vectors using the idea of discriminant analysis. The recognition of a query object is performed by measuring cosine distance between its feature vector and the feature vectors for training object images. Our experimental results on vehicle types recognition show that the proposed system performs better than the discriminant analysis of original images.