人民币冠字码识别技术的分析与实现.docxVIP

ABSTRACT With the development of automation science and technology, the use of machines to replace human labor becomes inevitable. In recent years, the character recognition technology (OCR technology) matures, cuiTency codes identification is an important application of OCR technology. Currency codes identification becomes an important indicator in the new Chinese Standard of next generation ATM this year, bank institutions request that currency codes identification should become available for ATM at the end of 2013. In this context, codes identification has become a pressing technology of ATM. The puipose of this paper is based on the characteristics of currency codes, to develop a system suitable for RMB crown recognition. Because of the images collected in this article are complete images of the currency, rather than merely Crown codes part of the image. To get the prefix zone image, this paper first obtained the tilt angle of the image by tilt angle measuring, followed by mapping and accurate positioning based on cross, for prefix regional localization and correction completed in the same time. Some codes uneven strokes is not clear, the paper uses binarization algorithm based on broad line detection, effective structural characteristics of the reserved characters, and achieves good binary effect. In order to extract the codes to a single character effectively, this paper presents an adaptive sliding-window method, this method has high efficiency, good robustness, effectively solves breaking character and touching character segmentation problems. Because the currency characters only contain arabic numerals and letters of the alphabet, characters set is small and the structure is relatively simple. In terms of character feature extraction, firstly extract the character grid feature, peripheral and border crossing, then compare them, finally chose the character grid feature,the feature is simple and versatile. Regarding the choice of a classifier, the paper uses