Direct Processing of Document Images in Compressed Domain
Mohammed Javed, P. Nagabhushan, B.B. Chaudhuri

TL;DR
This paper explores methods to directly process compressed document images, enabling feature extraction, segmentation, and font size detection without decompression, thus saving computational resources in large-scale document analysis.
Contribution
It introduces novel algorithms for direct processing of run-length compressed documents, including segmentation and font size detection, validated with experimental data.
Findings
Successful direct feature extraction from compressed data
Effective segmentation of text lines, words, and characters in compressed domain
Accurate font size detection at text line level
Abstract
With the rapid increase in the volume of Big data of this digital era, fax documents, invoices, receipts, etc are traditionally subjected to compression for the efficiency of data storage and transfer. However, in order to process these documents, they need to undergo the stage of decompression which indents additional computing resources. This limitation induces the motivation to research on the possibility of directly processing of compressed images. In this research paper, we summarize the research work carried out to perform different operations straight from run-length compressed documents without going through the stage of decompression. The different operations demonstrated are feature extraction; text-line, word and character segmentation; document block segmentation; and font size detection, all carried out in the compressed version of the document. Feature extraction methods…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
