层次型金融票据图像分类方法

金融票据图像识别处理是当今的一个热点研究方向,而票据分类是其中重要的基础部分。针对种类繁多、数量巨大、版面复杂和噪声干扰严重的金融票据彩色图像,本文提出了一种基于二叉树决策的层次型票据类型匹配方法。该方法利用三个类型判断器:基于票据版面结构的松弛匹配、基于OCR 的票据标题识别和基于票据颜色的色彩分析,层次化的进行票据类型判断。实验表明,层次型金融票据图像分类方法具有良好的效果;基于该方法的银行票据识别处理系统已经广泛应用于各大银行的相关业务系统中。

A Hierarchical Method for Form Classification of Financial Document Images

Recently, financial document analysis and recognition is a hot research topic, and form classification is one of its fundamental parts. In this article, we introduce a hierarchical method for classifying financial documents using a binary tree decision. First, form classification is based on elastic matching of form structure shape. Then, OCR of document tides is performed. Thirdly, document color is re-confirmed. As a result, the sequent range of document types becomes more and more tighter. At last, the final decision of document types is performed by linear combination of the first two classifiers. Applicatious of financial document recognition systems based on this form classification method have been successfully and widely used.