OBJECT RECOGNITION IN COMPRESSED IMAGERY

Image-based applications can save time and space by operating on compr essed data. The problem is that most mid- and high-level image operati ons, such as object recognition, are formulated as sequences of operat ions in the image domain. Such methods need direct access to pixel inf ormation as a starting point, but the pixel information in a compresse d image stream is not immediately accessible. In this paper we show ho w to perform object recognition directly on compressed images (JPEG) a nd index frames from video streams (MPEG I-frames) without recovering explicit pixel information. The approach uses eigenvectors constructed from compressed image data. Our performance results show that a five- fold speedup can be gained by using compressed data. (C) 1998 Elsevier Science B.V. All rights reserved.