DOI QR코드

DOI QR Code

A Study on Performance Improvement of Business Card Recognition in Mobile Environments

모바일 환경에서의 명함인식 성능 향상에 관한 연구

  • Shin, Hyunsub (Department of Computer Engineering, Graduate School of Information & Communications, Hanbat National University) ;
  • Kim, Chajong (Department of Computer Engineering, Hanbat National University)
  • Received : 2013.12.16
  • Accepted : 2014.01.20
  • Published : 2014.02.28

Abstract

In this paper, as a way of performance improvement of business card recognition in the mobile environment, we suggested a hybrid OCR agent which combines data using a parallel processing sequence between various algorithms and different kinds of business card recognition engines which have learning data. We also suggested an Image Processing Method on mobile cameras which adapts to the changes of the lighting, exposing axis and the backgrounds of the cards which occur depending on the photographic conditions. In case a hybrid OCR agent is composed by the method suggested above, the average recognition rate of Korean business cards has improved from 90.69% to 95.5% compared to the cases where a single engine is used. By using the Image Processing Method, the image capacity has decreased to the average of 50%, and the recognition has improved from 83% to 92.48% showing 9.4% improvement.

본 논문은 모바일 환경에서의 명함 인식 성능 향상을 위한 방안으로 서로 다른 알고리즘과 학습 데이터를 갖는 이종(異種)의 명함 인식 엔진을 병렬처리 하여 데이터를 결합하는 하이브리드 OCR 에이전트를 제안하였고, 모바일 카메라의 특성상 촬영자의 환경에 따라 변하는 조명, 촬영방향, 명함의 배경에 적응하는 모바일 카메라에서의 명함 이미지 전처리 기법을 제안하였다. 본 논문에서 제안한 방법으로 하이브리드 OCR 에이전트를 구성할 경우 단일 엔진을 구성하였을 때 보다 국문명함의 명함 인식률이 평균 90.69%에서 95.5%로 향상되었고, 이미지 전처리 기법을 적용함으로써 이미지 용량이 50% 수준으로 줄어들었으며 이미지 전처리 기법을 적용하기 전보다 인식률이 83%에서 92.48% 수준으로 약 9.4%의 향상 효과를 얻을 수 있었다.

Keywords

References

  1. Character and speech recognition, and future prospects related technologies Available: http://www.connectinglab.net/wordpress/?p=9608
  2. Mollah, A. F., Majumder, N., Basu, S., & Nasipuri, M. " Design of an Optical Character Recognition System for Camera-based Handheld Devices," in International Journal of Computer Science Issues, vol. 8, issue 4, no. 1, pp. 283-289, July, 2011.
  3. Beginning of Mobile Cloud Available: http://www.imaso. co.kr/?doc=bbs/gnuboard.php&bo_table=article&wr_id=38258
  4. Gao, Y., Jin, L., He, C., & Zhou, G. "Handwriting Character Recognition as a Service: A New Handwriting Recognition System Based on Cloud Computing," in International Conference on Document Analysis and Recognition, pp. 885-889, Beijing, Sept, 2011.
  5. Huerta-Canepa, G., & Lee, D., "A virtual cloud computing provider for mobile devices," in Proceedings of the 1st ACM Workshop on Mobile Cloud Computing & Services Social Networks and Beyond, New York: NY, pp. 1-5, 2010.
  6. Hyunsub, S., HIART Corporation, Cloud OCR business card information management system, KR1020120111954, 2013.
  7. Hsueh, M. "Interactive Text Recognition and Translation on a Mobile Device," University of California, Berkeley: CA, Technical Report UCB/EECS-2011-57, 2001.
  8. Blem, E., Menon, J., & Sankaralingam, K., "A detailed analysis of contemporary arm and x86 architectures," University of Wisconsin-Madison, Technical Report, Feb, 2013.
  9. Context switch Available: http://en.wikipedia.org/wiki/Context_switch
  10. Yeiyoung, J., Hyunsub, S., Chajong, K., "A Development of Mobile Camera Application for AvoidingShadows in Business Card from Smart Device," in Proceedings of the KIIT Summer Conference, pp. 306-311, 2013.
  11. Sauvola, J., & Pietikainen, M., "Adaptive document image binarization. Pattern Recognition", pp. 225-236, 2000.
  12. Hyunsub, S., Chajong, K., Injun, S., "A Study on the Business card Web Service for Smartphone," in Proceedings of the KIIT Autumn Conference, pp. 1-6, 2011.
  13. Miscellaneous Image Transformations Available: http://docs.opencv.org/modules/imgproc/doc/miscellaneous_transformations.html

Cited by

  1. A Study on the Automated Design of Business Card for Personal Information Leakage Prevention Using IT-based Convergent Service vol.10, pp.4, 2014, https://doi.org/10.7236/ijibc.2018.10.4.25
  2. Shell Template Offset 도면을 활용한 선체 곡판 형상 복원 방법에 관한 연구 vol.56, pp.1, 2014, https://doi.org/10.3744/snak.2019.56.1.066