Title :
Bank Check Image Binarization Based on Signal matching
Author :
Honggang, Zhang ; Guang, Chen ; Gang, Liu ; Jun, Guo
Author_Institution :
Sch. of Inf. Eng., Beijing Univ. of Posts & Telecommun.
Abstract :
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
Keywords :
cheque processing; feature extraction; image matching; iterative methods; signal sources; bank check image binarization; image projection function; information extraction; iterative threshold; signal matching; signal source; Automation; Data mining; Humans; Image analysis; Image edge detection; Iterative algorithms; Law; Legal factors; Lighting; Seals; Projection function; Signal matching; binarization; printed Chinese bank check date;
Conference_Titel :
Information, Communications and Signal Processing, 2005 Fifth International Conference on
Conference_Location :
Bangkok
Print_ISBN :
0-7803-9283-3
DOI :
10.1109/ICICS.2005.1689294
