A generalized block truncation coding algorithm for image compression

Abstract

Block Truncation Coding is a recently developed approach to image compression whose design is specified by the appropriate moment preserving quantizer. In this paper we show how the basic Block Truncation Coding algorithm can be generalized to include a family of moment preserving quantizers with the potential for improved performance. We then illustrate by way of example that such improvement is indeed possible from the standpoint of peak signal to noise ratio. There is a subclass of this family of moment preserving quantizers for which practical difficulties in implementation exist; however, we show that frequently we can avoid this subclass and still obtain good performance.