Form Analysis by Neural Classification of Cells
Our aim in this paper is to present a generic approach for linearly combining multi neural classifier for cell analysis of forms. This approach can be applied in a preprocessing step in order to highlight the different kind of information filled in the form and to determine the appropriate treatment. Features used for the classification are relative to the text orientation and to its character morphology. Eight classes are extracted among numeric, alphabetic, vertical, horizontal, capitals, etc. Classifiers are multi-layered perceptrons considering firstly global features and refining the classification at each step by looking for more precise features. The recognition rate of the classifiers for 3. 500 cells issued from 19 forms is about 91%.
KeywordsHide Layer Form Analysis Text Line Black Area Black Pixel
- 3.ISHITANI Y., Model Matching Based on Association Graph for Form Image Understanding, in Proceedings of ICDAR'95: 3rd International Conference on Document Analysis and Recognition, Montréal, Canada, 1995, pp. 287–292.Google Scholar
- 4.YUAN J., TANG Y. Y. and SUEN C. Y., Four Directional Adjacency Graphs (FDAG) and Their Application in Locating Fields in Forms, in Proceedings of ICDAR'95: 3rd International Conference on Document Analysis and Recognition, Montréal, Canada, 1995, pp.752–755.Google Scholar
- 5.HIRAYAMA Y., Analysing Form Images by Using Line-Shared-Adjacent Cell Relations, in Proceedings of ICPR'96: 13th International Conference on Pa ttern Recognition, 1996, pp.768–772.Google Scholar
- 6.SHIMOTSUJI S. and ASANO M., Form Identification based on Cell Structure, in Proceedings of ICPR'96: 13th International Conference on Pattern Recognition, 1996, pp.793–797.Google Scholar
- 7.TUROLLA E. BELAÏD Y. and BELAÏD A., Form item extraction based on line searching, in Graphics Recognition: Methods and Applications, Lecture Not es in Computer Science, Vol. 1072, 1996, pp. 69–79.Google Scholar