Compression-based template matching

Abstract

Textual image compression is a method of both lossy and lossless image compression that is particularly effective for images containing repeated sub-images, notably pages of text (Mohiuddin et al., 1984; Witten et al., 1992). The process comprises three main steps: • Extracting all the characters from an image; • Building a library that contains one representative for each character class; • Compressing the image with respect to the library.