Imaged document text retrieval without OCR (2002)
Cached
Download Links
- [www.comp.nus.edu.sg]
- [www.comp.nus.edu.sg]
- [www.comp.nus.edu.sg]
- DBLP
Other Repositories/Bibliography
| Venue: | IEEE Trans. Pattern Analysis and Machine Intelligence |
| Citations: | 22 - 9 self |
BibTeX
@ARTICLE{Tan02imageddocument,
author = {Chew Lim Tan and Ieee Computer Society and Weihua Huang and Zhaohui Yu and Yi Xu},
title = {Imaged document text retrieval without OCR},
journal = {IEEE Trans. Pattern Analysis and Machine Intelligence},
year = {2002},
volume = {24},
pages = {838--844}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
AbstractÐWe propose a method for text retrieval from document images without the use of OCR. Documents are segmented into character objects. Image features, namely, the Vertical Traverse Density (VTD) and Horizontal Traverse Density (HTD), are extracted. An n-gram based document vector is constructed for each document based on these features. Text similarity between documents is then measured by calculating the dot product of the document vectors. Testing with seven corpora of imaged textual documents in English and Chinese as well as images from UW1 database confirms the validity of the proposed method. Index TermsÐDocument image analysis, document vector, text similarity, text retrieval. æ 1
