The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지

Fast Thinning Algorithm based on Improved SOG($SOG^*$)

개선된 SOG 기반 고속 세선화 알고리즘($SOG^*$)

  • 이찬희 (부경대학교 전자계산학과) ;
  • 정순호 (부경대학교 컴퓨터멀티미디어공학부)
  • Published : 2001.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose Improved Self-Organized Graph(Improved SOG：$SOG^*$)thinning method, which maintains the excellent thinning results of Self-organized graph(SOG) built from Self-Organizing features map and improves the performance of modified SOG using a new incremental learning method of Kohonen features map. In the experiments, this method shows the thinning results equal to those of SOG and the time complexity O((logM)3) superior to it. Therefore, the proposed method is useful for the feature extraction from digits and characters in the preprocessing step.

본 논문은 기존의 신경망을 이용한 세선화 방법 중에서 자기 구성 그래프(Self-Organized Graph：SOG) 세선화 기법의 우수한 세선화 결과를 유지하면서, 수행 속도를 향상시키기 위하여 Kohonen Features Map의 새로운 점증 기법을 변형된 SOG에 적용한 개선된 SOG(Improved SOG：$SOG^*$) 세선화 기법을 제안한다. 실험 결과로써 숫자와 문자 모두 기존의 SOG와 같은 우수한 세선화 결과를 나타내며, O((logM)3)의 시간 복잡도를 가지는 속도 향상을 이루었다. 따라서 본 논문에서 제안한 방법은 숫자 또는 문자 인식에 있어 특징 추출의 빠른 전처리 과정으로 사용할 수 있다.

Keywords

References

  1. Keiji Yamada, 'Inverse Recall Neural Network Model and Feedback Pattern Recognition,' IEEE international Conference on Neural Networks, pp.399-406, 1993 https://doi.org/10.1109/ICNN.1993.298590
  2. Lianwen JIN, Kwokping CHAN and Bingzheng XU, 'OffLine Chinese Handwriting Recognition using Multi-Stage Neural Network Architecture,' IEEE International Conference on Neural Networks, pp.3083-3088, 1995 https://doi.org/10.1109/ICNN.1995.487276
  3. 방극준, 조남신, 강창언, 홍대식, '필기체 숫자인식을 위한 병렬 자구성 계층 신경회로망', 전자공학회논문지, 제33권 B편 제7호, pp.1193-1202, 1996
  4. 이성환, '패턴 인식의 원리 2', 홍릉과학출판사, 1997
  5. 이성환, '문자 인식 이론과 실제 II', 홍릉과학출판사, 1997
  6. Holt, C. M., A. Stewart, 'A parallel thinning algorithm with fine grain subtasking,' Parallel Comput. 10, pp.329-334, 1989 https://doi.org/10.1016/0167-8191(89)90105-1
  7. L. Lam., S. Lee and C. Y. Suen, 'Thinning methodologies-a comprehensive survey,' IEEE Trans. Pattern Analysis and Machine Intelligence, 14(9), pp.869-885, 1992 https://doi.org/10.1109/34.161346
  8. P. Ahmed, 'A neural network based dedicated thinning method.' Pattern Recognition, 16, pp.585-590, 1995 https://doi.org/10.1016/0167-8655(95)80004-D
  9. M. Altuwaijri, M. Bayoumi, 'A New Thinning Algorithm for Arabic Characters Using Self-Organizing Network,' Circuits and Systems, ISCAS '95, IEEE International Symposium on, Vol.3, pp.1824-1827, 1995 https://doi.org/10.1109/ISCAS.1995.523769
  10. John Cowell, Fiaz Hussain, 'Thinning Arabic Characters for Feature Extraction,' IEEE Information Visualization, Proceedings, Fifth International Conference, pp.181-185, 2001 https://doi.org/10.1109/IV.2001.942056
  11. Majid M. Altuwaijri, Magdy A. Bayoumi, 'A Thinning Algorithm for Arabic Characters Using ART2 Neural Network,' IEEE Transactions on Circuits and Systems-II, Vol.45, No.2, 1998 https://doi.org/10.1109/82.661669
  12. J. E. Dayhoff, 'Neural Network Architectures,' Van Nostrand Reinhold, 1990
  13. S.Haykin, 'Neural Networks,' Prentice Hall, 1994
  14. Y. P. JUN, H. S. Yoon, J. W. CHO, 'L* Learning : A Fast Self-Organizing Feature Map Learning Algorithm Based on Incremental Ordering,' IEICE Trans. INF & SYST., Vol.E76-D, No.6, June, 1993
  15. I. Gyoun, P. Albrecht, Y. Le Cun, J. Denker, W. Hubbard, 'Design of a Neural Network Character Recognizer for a Touch Terminal,' Pattern Recognition, Vol.24, No.2, pp.105-119, 1991 https://doi.org/10.1016/0031-3203(91)90081-F