Symbolic Compression and Processing of Document Images
Abstract
In this paper we describe a compression and representation scheme which exploits the component-level redundancy found within a document image. The approach identifies patterns which appear repeatedly, represents similar patterns with a single prototype, stores the location of pattern instances and codes the residuals between the prototypes and the pattern instances. Using a novel encoding scheme, we provide a representation which facilitates scalable lossy compression and progressive transmission, and supports document image analysis in the compressed domain. We motivate the approach, provide details of the encoding procedures, report compression results and describe a class of document image understanding tasks which operate on the compressed representation.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1997
- Accession Number
- ADA458853
Entities
People
- Azriel Rosenfled
- David S. Doermann
- Omid Kia
- Rama Chellappa
Organizations
- University of Maryland