表格型票据图像手写体特殊符号的混合检测算法  

Hybrid Detection Approach for Handwritten Specific Symbol in Form Bill Image

作　　者：宋晓宁[1,2,3] 刘梓[1,2] 於东军[1] 杨静宇[1] 陈天雨[3] 

机构地区：[1]南京理工大学计算机科学与工程学院,江苏南京210094 [2]江苏尚博信息科技有限公司博士后工作站,江苏无锡214072 [3]江苏科技大学计算机科学与工程学院,江苏镇江212003

出　　处：《南京理工大学学报》2012年第6期909-914,共6页Journal of Nanjing University of Science and Technology

基　　金：国家自然科学基金(61100116);中国博士后科学基金(2011M500926);江苏省自然科学基金(BK2012700);江苏省博士后科学基金(1102063C);人工智能四川省重点实验室开放基金(2012RZY02)

摘　　要：为了解决表格型票据图像定位区域中手写体勾符号的判定问题,该文提出一种混合检测算法并应用在表格型票据图像处理中。提出基于稀疏表示的形态学链码跟踪算法从而准确标记票据的外围轮廓。提出一种最优轴投影测度算法,完成外围轮廓角点坐标检测并对其进行倾角修正。根据标准模板库中的框线特征进行模板匹配,确定特殊字符所在的定位区域,利用空间卷积算法获得勾符号的判断标准。该文算法对表格型票据图像处理具有通用性,并能有效降低大规模多种类票据内容的定位与识别难度。实际银行支票图像测试证明了算法的有效性和鲁棒性。To solve the problem of recognition for handwritten tick symbols filled in form bill images, a hybrid detection approach is presented for form bill image processing. A chain code algorithm based on the sparse representation is proposed by using the morphological method to describe the external contour of form bills. An optimal-axis projection estimation algorithm is proposed for angular coordinate detection of frame lines and angle correction. By means of the frame line characteristics of standard template, the form areas of special characters are determined by template matching, and the judgment criterion of tick symbol is obtained by using the spatial convolution algorithm. This algorithm has generality for form bill image processing, and can decrease the difficulty of location and identification of large-scale multiple bill images. Detection results from the practical form bill images from banks demonstrate the effectiveness of the proposed method.

关 键 词：票据图像处理 表格型文档 手写体 特殊符号 目标检测 稀疏表示 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]