Bank Check Image Binarization Based on Signal matching

In this paper, a method based on signal matching to binarize low signal-noise rate bank check image is proposed. This method can extract information from the check image interfered with both complex background and imprinted seal. With the prior knowledge, the image projection function without noise is the source signal, the projection function of image binarized by iterative threshold will match the source signal, and the threshold which projection function matches best is the optimum threshold. Experimental results showed that significant improvement in the binarization quality in comparison with other well-established algorithms

[1]  Anil K. Jain,et al.  Goal-Directed Evaluation of Binarization Methods , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Xu Wei.  Classification of Machine-Printed and Handwritten Texts Based on the Bayesian Judge , 2003 .

[3]  Amer Dawoud,et al.  Iterative multimodel subimage binarization for handwritten character segmentation , 2004, IEEE Transactions on Image Processing.

[4]  Emmanuel Augustin,et al.  Industrial bank check processing: the A2iA CheckReaderTM , 2001, International Journal on Document Analysis and Recognition.

[5]  Slawomir Wesolkowski,et al.  A comparison of research and production architectures for check reading systems , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[6]  Sebastiano Impedovo,et al.  Automatic Bankcheck Processing: A New Engineered System , 1997, Int. J. Pattern Recognit. Artif. Intell..

[7]  Jian Liu,et al.  Research on Chinese financial invoice recognition technology , 2003, Pattern Recognit. Lett..

[8]  Amer Dawoud,et al.  Iterative model-based binarization algorithm for cheque images , 2002, International Journal on Document Analysis and Recognition.

[9]  Yuan Yan Tang,et al.  Automatic Extraction of Baselines and Data from Check Images , 1997, Int. J. Pattern Recognit. Artif. Intell..

[10]  Minoru Okada.  Extraction of User Entered Components from A Personal Bankcheck Using Morphological Subtraction , 1997, Int. J. Pattern Recognit. Artif. Intell..

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

[12]  Ching Y. Suen,et al.  A recursive thresholding technique for image segmentation , 1998, IEEE Trans. Image Process..

[13]  Ching Y. Suen,et al.  Extraction of bankcheck items by mathematical morphology , 1999, International Journal on Document Analysis and Recognition.

[14]  J. R. Parker,et al.  Gray Level Thresholding in Badly Illuminated Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Sargur N. Srihari,et al.  Document Image Binarization Based on Texture Features , 1997, IEEE Trans. Pattern Anal. Mach. Intell..