|Table of Contents|

Hybrid Detection Approach for Handwritten Specific Symbol in Form Bill Image

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2012年06期
Page:
0-
Research Field:
Publishing date:

Info

Title:
Hybrid Detection Approach for Handwritten Specific Symbol in Form Bill Image
Author(s):
SONG Xiaoning 123LIU Zi 12YU Dongjun1YANG Jingyu1CHEN Tianyu 3
1.School of Computer Science and Engineering,NUST,Nanjing 210094,China;2.Postdoctoral Research Center, Jiangsu Sunboon Information Technology Co.,Ltd.,Wuxi 214072,China;3.School of Computer Science and Engineering,Jiangsu University of Science and Technology,Zhenjiang 212003,China
Keywords:
bill image processingform bill imagehandwritingspecific symbolstarget detectionsparse representation
PACS:
TP391.41
DOI:
-
Abstract:
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.

References:

[1]Aggarwal N,Karl W C.Line detection in images through regularized Hough transform[J].IEEE Trans on Image Processing,2006,15(3):582-591. 
[2]Zheng Yefeng,Li Huiping,Doermann D.A parallelline detection algorithm based on HMM decoding[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(5):777-792. 
[3]Nacken P.A metric for line segments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(12):1312-1318.
[4]张重阳.票据自动处理系统中的预处理技术研究[D].南京:南京理工大学计算机科学与技术学院,2004.
[5]张艳,郁生阳,张重阳,等.表格型票据中框线检测与去除算法[J].计算机研究与发展,2008,45(5):909-914. Zhang Yan,Yu Shengyang,Zhang Chongyang,et al.Extraction and removal of frame line in form bill[J].Journal of Computer Research and Development,2008,45(5):909-914.
[6]张艳,张重阳,郁生阳,等.基于框线检测的票据图像分类方法[J].南京理工大学学报,2007,31(4):409-413. Zhang Yan,Zhang Chongyang,Yu Shengyang,et al.Bill image classification method based on line detection[J].Journal of Nanjing University of Science and Technology,2007,31(4):409-413.
[7]邓承志.图像稀疏表示理论及其应用研究[D].武汉:华中科技大学电子与信息工程系,2008.
[8]封晓强,何铁军.基于量子进化算法的交通图像稀疏分解[J].南京理工大学学报,2010,34(1):40-45. Feng Xiaoqiang,He Tiejun.Sparse decomposition for traffic images using quantuminspired evolutionary algorithms[J].Journal of Nanjing University of Science and Technology,2010,34(1):40-45.
[9]Song Xiaoning,Yang Xibei,Yang Jingyu,et al.Discriminant analysis approach using fuzzy fourfold subspaces model[J].Neurocomputing,2010,73(10):2255-2265.
[10]Isabelle B.Duality vs.adjunction for fuzzy mathematical morphology and general form of fuzzy erosions and dilations[J].Fuzzy Sets and Systems,2009,160(13):1858-1867.
[11]Liu Y K,Borut .An efficient chain code with Huffman coding[J].Pattern Recognition,2005,38(4):553-557.
[12]Xu Xiangyang,Xu Shengzhou,Jin Lianghai,et al.Characteristic analysis of Otsu threshold and its applications[J].Pattern Recognition Letters,2011,32(7):956-961.

Memo

Memo:
-
Last Update: 2012-12-29