We propose a new framework termed Keyblock for content-based image retrieval, which is a generalization of the text-based imformation retrieval technology in the image domain. In this framework, methods for extracting comprehensive image features are provided, which are based on the frequency of representative blocks, termed keyblocks, of the image database. Keyblocks, which are analogous to index terms in text document retrieval, can be constructed byn exploiting the vector quantization (VQ) method which as been used for image compression. By comp[aring the performance of our approach with the existing techiques using color feature and wavelet texture feature, the experimental results demonstrate the effectiveness of the framework in image retrieval.
展开▼
