Browse > Article

Destination Address Block Location on Machine-printed and Handwritten Korean Mail Piece Images  

정선화 (한국전자통신연구원)
장승익 (한국전자통신연구)
임길택 (한국전자통신연구)
남윤석 (한국전자통신연구원)
Publication Information
Journal of KIISE:Software and Applications / v.31, no.1, 2004 , pp. 8-19 More about this Journal
Abstract
In this paper, we propose an efficient method for locating destination address block on both of machine-Printed and handwritten Korean mail piece images. The proposed method extracts connected components from the binary mail piece image, generates text lines by merging them, and then groups the text fines into nine clusters. The destination address block is determined by selecting some clusters. Considering the geometric characteristics of address information on Korean mail piece, we split a mail piece image into nine areas with an equal size. The nine clusters are initialized with the center coordinate of each area. A modified Manhattan distance function is used to compute the distance between text lines and clusters. We modified the distance function on which the aspect ratio of mail piece could be reflected. The experiment done with live Korean mail piece images has demonstrated the superiority of the Proposed method. The success rate for 1, 988 testing images was about 93.56%.
Keywords
Machine-printed address; Handwritten address; Destination address block location; Address reading system;
Citations & Related Records
연도 인용수 순위
  • Reference
1 순로구분 자동처리 시스템 개발-최종 연구개발보고서, 정보통신부, 2001
2 이성환, 김은순, '주소 및 성명에서의 한글인식을 위한 효율적인 오인식 교정 알고리즘', 한국정보과학회 논문지, 제20권, 제5호, pp. 729-738, 1993
3 원유헌, 함경수 등, '필기 한글인식을 위한 오류 후처리 기법', 한국정보학회 춘계 학술발표 논문집, pp. 829-836, 1993
4 S.H. Jeong, K.T. Lim and Y.S. Nam, 'A Combination Method of Two Classifiers Based on the Information of Confusion,' Proceedings of the 8th International Workshop on Frontiers in Hand-writing Recognition, pp. 519-523, Niagara-on-the Lake Ontario,Canada, 2002   DOI
5 A.K. Jain and S.K. Bhattachrjee, 'Address Block Location on Envelopes Using Gabor Filters: Supervised Method,' Proceedings of the 11th International Conference on Pattern Recognition, Vol. 2, pp. 264-267, 1992   DOI
6 이관용, 권진욱, 이일병, '단어 수준의 음절 공기 확률을 이용한 한글 주소 인식', 한국정보과학회 논문지, 제25권, 제12호, pp. 1758-1768, 1998
7 B. Yu, A.K. Jain and M. Mohiuddin, 'Address Block Location on Complex Mail Pieces,' Proceedings of the 4th International Conference on Document Analysis and Recognition, pp. 897-901, Ulm,Germany, 1997   DOI
8 M. Wolf, H. Nieman and W. Schmidt, 'Fast Address Block Location on Handwritten and Machine Printed Mail Piece Images,' Proceedings of the 4th International Conference on Document Analysis and Recognition, pp. 753-757, Ulm,Germany, 1997   DOI
9 권진욱, 이일병 등, '한글주소인식 시스템', 한국정보과학회 춘계 학술발표 논문집, pp. 529-532, 1997
10 김수형, '최소거리분류 및 사전기반 후처리의 강결합에 의한 필기한글 주소열의 인식', 한국정보과학회 논문지, 제25권, 제8호, pp. 1195-1205, 1998
11 N. Otsu, 'A Threshold Selection Method from Gray-level Histogram,' IEEE Transactions on Systems,Man, and Cybernetics, Vol. 9, pp. 62-66, 1979   DOI   ScienceOn
12 W. Chanpongsaeng, P. Kumhom and K. Chamnongthai, 'Locating Destination Address Block on Tahi Envelopes,' Proceedings of the 5th Symposium on National Language Processing, Hua Hin,Thailand, 2002
13 S.W. Lee and K.C. Kim, 'Locating Destination Address Block on Handwritten Korean Envelopes,' Proceedings of the 12th International Conference on Pattern Recognition, pp. 619-621, Jerusalem, Israel, 1994   DOI
14 N. Nakajiman, T. Tsuchiya, T. Kamimura and K. Yamada, 'Analysis of Address Layout on Japanese Handwritten Mail - A Hierarchical Process of Hypothesis Verification,' Proceedings of the 13th International Conference on Pattern Recognition, pp. 726-731, Vienna,Austria, 1996   DOI
15 A.P. Whichello and H. Yan, 'Locating Address Block and Postcodes in Mail-piece Images,' Proceedings of the 13th International Conference on Pattern Recognition, pp. 716-720, Vienna, Austria, 1996   DOI
16 J. Xue, X. Ding, C. Liu, S. Pan and H. Kong, 'Destination Address Block Location on Hand-written Chinese Envelope,' Proceedings of the 5th International Conference on Document Analysis and Recognition, pp. 737-740, 1999   DOI