A medical axis transform algorithm for compression and vectorization of document images

Abstract

It is proposed that the medial axis transformation (MAT), being an invertible transformation, has value in lossless data compression, and, since the MAT conveys the line structure of an image, that it is also useful for vector conversion. To this end, some properties of the MAT are established and then exploited to devise a specialized chain-code representation. This MAT-based chain-code language captures any binary image but is particularly suited to line drawings. An extension of the language that can express chain-code sequences as linear and quadratic line segments under tunable error tolerance is described. The representation has achieved acceptable lossless data compression and significant additional compression for line drawings when vectorization is employed. As the error tolerance is increased, the amount of compression increases together with distortion. Thus, the method can be used to obtain a rate/distortion curve for binary images. >