Image Database Indexing Using JPEG Coefficients

Image database indexing is used for e'cient retrieval of images in response to a query expressed as an example image. The query image is processedto extract information that is matchedagainst the index to provide pointers to similar images. We present a technique that facilitates content similarity-basedretrieval of JPEG-compressedimages without 8rst having to uncompress them. The technique is based on an index developed from a subset of JPEG coe'cients and a similarity measure to determine the di9erence between the query image and the images in the database. This methodo9ers substantial e'ciency as images are processedin compressedformat, information that was derivedduring the original compression of the images is reused, and extensive early pruning is possible. Initial experiments with the index have provided encouraging results. The system outputs a set of ranked images in the database with respect to the query using the similarity measure, andcan be limitedto output a speci8ednumber of matchedimages by changing the thresholdmatch. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.