School of Computer and Information Science, Chongqing Normal University, Chongqing, China

---

Abstract—Document image information systems are used more and more in government. Much redundant information in the document existed in such systems. That implies the research on the compression method based on the page-page statistical features is quite significant. Set Redundancy Compression (SRC) is such a technique that reduces the total entropy of the whole image set by utilizing the image page’s similarity. Compression-based Template Differential (CTD) is an improved SRC. The similar image set is constructed by the document template. The coding performance is improved by adding the template image into the Min-Max Differential (MMD) coding/decoding model. It proves theoretically that CTD’s coding performance is higher than MMD’s. It is demonstrated by experiments that both the CTD and MMD are benefit to increase the compression ratio of image set, however CTD increases more than MMD.

Index Terms—document image; set redundancy; image compression; template differential

[PDF]

Cite: Ping Yu and You Yang, "Document Set Redundancy Compression Method Using Template Differential," Journal of Software vol. 7, no. 5, pp. 1052-1058, 2012.