Document compression using rate-distortion optimized segmentation
- 1 April 2001
- journal article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 10 (2), 460-474
- https://doi.org/10.1117/1.1344590
Abstract
Effective document compression algorithms require that scanned document images be first segmented into regions such as text, pictures, and background. In this paper, we present a multilayer compression algorithm for document images. This compression al- gorithm first segments a scanned document image into different classes, then compresses each class using an algorithm specifically designed for that class. Two algorithms are investigated for seg- menting document images: a direct image segmentation algorithm called the trainable sequential MAP (TSMAP) segmentation algo- rithm, and a rate-distortion optimized segmentation (RDOS) algo- rithm. The RDOS algorithm works in a closed loop fashion by apply- ing each coding method to each region of the document and then selecting the method that yields the best rate-distortion trade-off. Compared with the TSMAP algorithm, the RDOS algorithm can of- ten result in a better rate-distortion trade-off, and produce more ro- bust segmentations by eliminating those misclassifications which can cause severe artifacts. At similar bit rates, the multilayer com- pression algorithm using RDOS can achieve a much higher subjec- tive quality than state-of-the-art compression algorithms, such as DjVu and SPIHT. © 2001 SPIE and IS&T. (DOI: 10.1117/1.1344590)Keywords
This publication has 17 references indexed in Scilit:
- Weighted universal bit allocation: optimal multiple quantization matrix codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Rate-distortion methods for image and video compressionIEEE Signal Processing Magazine, 1998
- The emerging JBIG2 standardIEEE Transactions on Circuits and Systems for Video Technology, 1998
- High quality document image compression with “DjVu”Journal of Electronic Imaging, 1998
- Check image compression using a layered coding methodJournal of Electronic Imaging, 1998
- Dynamic approach to visual data compressionIEEE Transactions on Circuits and Systems for Video Technology, 1997
- A new, fast, and efficient image codec based on set partitioning in hierarchical treesIEEE Transactions on Circuits and Systems for Video Technology, 1996
- A multiscale random field model for Bayesian image segmentationIEEE Transactions on Image Processing, 1994
- Rate-distortion optimal fast thresholding with complete JPEG/MPEG decoder compatibilityIEEE Transactions on Image Processing, 1994
- Color quantization of imagesIEEE Transactions on Signal Processing, 1991