Applying Specific Region Frequency and Texture Features on Content-based Image Retrieval

In this paper, a specific region called affine noisy invariant region is extracted from a query and database images to help accurate retrieval on different attacks. Then, only a 64x1 codebook based feature vector is obtained from this specific region applying vector quantization and codebook generation based on the Linde-Buzo-Gray algorithm, which reduces retrieval feature comparison calculations. Also a number of texture and frequency domain based features are computed and established for the region. Finally combination of these two groups of feature vectors improves the retrieval system efficiency. Besides, in order to optimize weighting combination coefficients of the feature vectors, the particle swarm optimization algorithm is applied. The experimental results show a real-time content-based image retrieval system with higher accuracy and acceptable retrieval time.