Fast progressive image retrieval schemes based on updating enhanced equal-average equal-variance K nearest neighbour search in vector quantised feature database

This paper concerns with the problem of how to retrieve the images similar to the query image as fast as possible. The feature space is vector quantized to obtain several clusters, each cluster being denoted by a codeword. The feature vectors in each cluster are sorted in the ascending order of their mean values. The online image retrieval for a given query image is then progressively performed from its nearest cluster to its farthest cluster to find the first K nearest neighbors of the query feature vector as soon as possible. Experimental results show that the proposed retrieval methods can largely speed up the retrieval process.