| Presentation | 1994/9/22 Automatic document recognition system for general use Yasuto Ishitani, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A new form image understanding method based on model matching is proposed in this paper to realize OCR which can read various forms. The outline of this method is described as follows.First,ruled lines are extracted from the input image of a form.After that, several lines forming a table are grouped in one and it is recognized as a data which corresponds to the table.These lines and tables are basic features for understanding a form which also has feature attributes,and relationships between them.Each feature in an input form image is expected to conespond to a feature in a model form which is described as structured features.This correspondence is represented by a node in a association graph where an arc represents compatible correspondences established on the basis of feature relationships.The best match is determined by the largest clique in the association graph.A missing correspondence is automatically detected if this matching result is incomplete.In this case,correct solution of the matching is estimated by an iterative algorithm which uses correct correspondence already established near by this troubled portion. Experimental results show the method is robust and effective for poor quality document images and also for various styles in forms. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | document structure understanding / model matching / association graph / maximal clique / forms processing / document image processing |
| Paper # | PRU94-34 |
| Date of Issue |
| Conference Information | |
| Committee | PRU |
|---|---|
| Conference Date | 1994/9/22(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Understanding (PRU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic document recognition system for general use |
| Sub Title (in English) | |
| Keyword(1) | document structure understanding |
| Keyword(2) | model matching |
| Keyword(3) | association graph |
| Keyword(4) | maximal clique |
| Keyword(5) | forms processing |
| Keyword(6) | document image processing |
| 1st Author's Name | Yasuto Ishitani |
| 1st Author's Affiliation | Research and Development Center,Toshiba Corporation() |
| Date | 1994/9/22 |
| Paper # | PRU94-34 |
| Volume (vol) | vol.94 |
| Number (no) | 242 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |