Abstract
In this paper, an automatic method to detect the presence of on-line erasures/scribbles/corrections/over-writing in
the address block of various types of subscription and utility payment forms is presented. The proposed approach
employs bottom-up segmentation of the address block. Heuristic rules based on structural features are used to
automate the detection process. The algorithm is applied on a large dataset of 5,780 real world document forms of
200 dots per inch resolution. The proposed algorithm performs well with an average processing time of 108
milliseconds per document with a detection accuracy of 98.96%.
Original language | English |
---|---|
Title of host publication | Proceedings of IAENG International Conference on Imaging Engineering |
Place of Publication | Hong Kong |
Publisher | International Association of Engineers |
Pages | 650-654 |
Number of pages | 5 |
ISBN (Print) | 9789889867188 |
Publication status | Published - 2008 |
Event | International MultiConference of Engineers and Computer Scientists 2008 - Hong Kong, Hong Kong Duration: 19 Mar 2008 → 21 Mar 2008 http://www.iaeng.org/IMECS2008/ |
Conference
Conference | International MultiConference of Engineers and Computer Scientists 2008 |
---|---|
Abbreviated title | IMECS 2008 |
Country/Territory | Hong Kong |
City | Hong Kong |
Period | 19/03/08 → 21/03/08 |
Internet address |
Keywords
- offline scribble detection
- document image analysis
- document form processing
- address correction detection