DocumentCode
2021527
Title
An Efficient Thresholding Algorithm for Brazilian Bank Checks
Author
Mello, Carlos A B ; Bezerra, Byron L D ; Zanchettin, Cleber ; Macário, Valmir
Author_Institution
Univ. of Pernambuco, Recife
Volume
1
fYear
2007
fDate
23-26 Sept. 2007
Firstpage
193
Lastpage
197
Abstract
It is present herein an algorithm for thresholding images of bank checks. These images have complex background elements. Some of these patterns make very hard to distinguish between the text and the texture pattern defined by the bank. For the binarizing process, an adaptive global thresholding algorithm is proposed based on ROC curves and it is compared to several well-known algorithms. The images generated by the new algorithm achieved a hit rate of 97% for recognition of the CMC7 code.
Keywords
bank data processing; image texture; Brazilian bank check; adaptive thresholding algorithm; image texture; Entropy; Histograms; Image converters; Image generation; Image processing; Image recognition; Ink; Iterative algorithms; Law; Legal factors;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location
Parana
ISSN
1520-5363
Print_ISBN
978-0-7695-2822-9
Type
conf
DOI
10.1109/ICDAR.2007.4378702
Filename
4378702
Link To Document