Image indexing and retrieval in JPEG compressed domain based on vector quantization

This paper presents a new and effective image indexing technique that extracts features from JPEG compressed images. Using vector quantization techniques (VQ) and a codebook generated using a K-means clustering algorithm, the proposed technique is able to create an effective histogram from DCT coefficients, which are the major components of JPEG. The proposed method only needs to do partial decoding, therefore it can accelerate the work of indexing images. Experimental results show that its retrieval performance is higher compared with those of other methods from pixel and compressed domains. All experiments confirm the effectiveness and efficiency of the proposed method.