Automatic processing of information on cheques

In the business transactions of large corporations such as utility companies and banks, many cheques must be processed on a regular basis. In this paper, we describe algorithms currently under development to automatically process the information contained on them. These procedures are designed to preprocess the scanned image of a cheque, locate and extract different items of information from it, and produce recognition results for these items by classifiers developed for each function.

[1]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[2]  Ching Y. Suen,et al.  Cursive Script Recognition: A Sentence Level Recognition Scheme , 1994 .

[3]  Adam Krzyzak,et al.  Segmentation of handwritten digits using contour features , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[4]  Ching Y. Suen,et al.  A sequential method of extracting contour chains from an image , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[5]  Jing-Yu Yang,et al.  Algebraic feature extraction for image recognition based on an optimal discriminant criterion , 1993, Pattern Recognit..

[6]  D. Guillevic,et al.  Cursive script recognition: A fast reader scheme , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).