The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

The Modified ART1 Network using Multiresolution Mergence : Mixed Character Recognition

다중 해상도 병합을 이용한 수정된 적응 공명 이론 신경망: 혼합 문자 인식 적용

  • Published : 2007.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

As Information Technology growing, the character recognition application plays an important role in the ubiquitous environment. In this paper, we propose the Modified ART1 network using Multiresolution Mergence to the problems of the character recognition. The approach is based on the unsupervised neural network and multiresolution. In order to decrease noises and to increase the classification rate of the characters, we propose the multiresolution mergence strategy using both high resolution and low resolution information. Also, to maximize the effect of multiresolution mergence, we use a modified ART1 method with a different similarity measure. Our experimental results show that the classification rate of character is quite increased as well as the performance of the propose algorithm in conjunction with the similarity measure is improved comparing to the conventional ART1 algorithm in this application.

최근 정보기술의 발달과 함께 문자 인식의 중요성이 높아지고 있다. 특히, 유비쿼터스 시대가 도래하면서 개인휴대용 정보 단말기, 태블릿 PC 등 유비쿼터스 컴퓨팅 장비가 급속도로 대중화 되고 있다. 이에 사람마다 다양한 필체로 인한 문제가 발생하고 있으며, 인식률을 높일 수 있는 문자 인식에 대한 연구가 필요한 실정이다. 본 연구에서는 다중 해상도 병합을 이용한 수정된 적응 공명 이론 신경망을 제안한다. 이는 자율 학습 신경망과 다중 해상도의 관점에서 접근하여 문자 인식 문제에 적용시켜 본 것이다. 노이즈와 문자 특성 정보를 구별하고 인식률을 높이기 위해 고해상도와 저해상도 정보를 같이 이용하는 다중 해상도 병합 방법을 제안한다. 또한, 다중 해상도 병합 방법의 효과를 극대화할 수 있는 적응 공명 이론 신경망의 유사도 측정 방법을 제안하여 기존의 방법보다 우수한 실험 결과를 제시하였다.

Keywords

References

  1. 조영임, '인공지능시스템', 홍릉과학출판사, pp. 7-164, 2003
  2. G. A. Carpenter, S. Grossberg, 'Adaptive pattern classification and universal receding, I : Parallel development and coding of neural feature detectors', Biological Cybernetics, Vol 23, pp. 121-134, 1976a https://doi.org/10.1007/BF00344744
  3. G. A. Carpenter, S. Grossberg, 'Adaptive pattern classification and universal receding, II : Feedback, expectation, olfaction, and illusions', Biological Cybernetics, Vol 23, pp. 187-202, 1976b https://doi.org/10.1007/BF00340335
  4. G. A. Carpenter, S. Grossberg, 'A massively parallel architecture for a self -organizing neural pattern recognition machine', Computer Vision, Graphics, and Image Processing, Vol 37, pp. 54-115, 1987a https://doi.org/10.1016/S0734-189X(87)80014-2
  5. G. A. Carpenter, S. Grossberg, 'ART2: Self-organization of stable category recognition codes for analog input patterns', Applied Optics, Vol 260, pp. 4919-4930, 1987b
  6. G. A. Carpenter, S. Grossberg, B. Rosen, 'Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system', Neural Networks, Vol 4, pp. 759 - 771, 1991a https://doi.org/10.1016/0893-6080(91)90056-B
  7. G. A. Carpenter, S. Grossberg, 'ART 3: hierarchical search using chemical transmitter in self-organizing pattern recognition architectures', Neural Networks, Vol 3, No 4, pp. 129 -152, 1990 https://doi.org/10.1016/0893-6080(90)90085-Y
  8. G. A. Carpenter, S. Grossberg, J. H. Reynolds, 'ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network', Neural Networks, Vol 4, pp. 565 - 588, 1991b https://doi.org/10.1016/0893-6080(91)90012-T
  9. G. A. Carpenter, S. Grossberg, N. Markuzon, J. H. Reynolds, D. B. Rosen, 'Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps', IEEE Transactions on Neural Networks, Vol 30, No 5, pp. 698 -713, 1992 https://doi.org/10.1109/72.159059
  10. E. E. Khin, A. Shrestha, R. Sadananda, 'ART1: Similarity Measures, Neural Processing Letters', Vol 6, pp, 109 -117, 1997 https://doi.org/10.1023/A:1009619908131
  11. T. Takaoka, M. Izumida, K. Murakami, 'A classification method to reduce the number of categories in ARTI', Systems and Computers in Japan, Vol 32, No 11, pp. 952-960, 2001 https://doi.org/10.1002/scj.1070
  12. L. Massey, 'On the quality of ART1 text clustering', Neural Networks, Vol 16, pp. 771 -778, 2003 https://doi.org/10.1016/S0893-6080(03)00088-1
  13. K-B. Kim, C-S. Park, 'An Enhanced Fuzzy Multilayer Perceptron', ICONIP 2004, LNCS 3316, pp. 977-982, Springer-Verlag Berlin Heidelberg 2004 https://doi.org/10.1007/b103766
  14. C. H. Dagli, P. Poshyanonda, 'New approaches to nesting rectangular patterns', Journal of Intelligent Manufacturing, Vol 8, pp. 177-190, 1997 https://doi.org/10.1023/A:1018517106992
  15. C. A. Chang, C. Y. Tsai, 'Using ART1 neural networks with destructive solid geometry for design retrieving systems', Computers in Industry, Vol 34, pp. 27-41, 1997 https://doi.org/10.1016/S0166-3615(96)00071-1
  16. C. B. Wang, Y. J. Chen, Y. M Chen, H. C. Chu, 'Application of ART neural network to development of technology for functional feature-based reference design retrieval', Computers in Industry, Vol 56, pp. 428 - 441, 2005 https://doi.org/10.1016/j.compind.2004.12.004
  17. F. L. Chen, S. F. Liu, 'A neural-network approach to recognize defect spatial pattern in semiconductor fabrication', IEEE Transactions on semiconductor manufacturing, Vol 13, No 3, pp, 366-373, 2000 https://doi.org/10.1109/66.857947
  18. S. F. Liu, F. L. Chen, W. B. Lu, 'Wafer bin map recognition using a neural network approach', int. j. prod. res., Vol 40, No 10, pp. 2207-2223, 2002 https://doi.org/10.1080/00207540210122275
  19. K-B. Kim, S-W. Jang, C-K. Kim, 'Recognition of Car License Plate by Using Dynamical Thresholding Method and Enhanced Neural Networks', CAIP 2003, LNCS 2756, pp. 309-319, Springer-Verlag Berlin Heidelberg 2003 https://doi.org/10.1007/b13427
  20. S. Rajasekaran, R. A. Raj, 'Image recognition using analog- ART1 architecture augmented with moment-based feature extractor', Neurocomputing, Vol 56, pp. 61-77, 2004 https://doi.org/10.1016/S0925-2312(03)00371-0
  21. F. D. Palma, G. D. Nicolao, G. Miraglia, E. Pasquinetti, F. Piccinini, 'Unsupervised spatial pattern classification of electrical-wafer-sorting maps in semiconductor manufacturing', Pattern Recognition Letters, Vol 26, pp. 1857-865, 2005 https://doi.org/10.1016/j.patrec.2005.03.007
  22. K-B. Kim, S-S. Kim, 'Hierarchical Recognition of English Calling Card by Using Multiresolution Images and Enhanced Neural Network', CIS 2005, Part I, LNAI 3801, pp. 785-792, Springer-Verlag Berlin Heidelberg 2005 https://doi.org/10.1007/11596448_116
  23. K-B. Kim, J-H. Cho, A-S. Oh, 'Recognition of English Business Cards Using Enhanced Hybrid Network, ISNN 2005, LNCS 3497, pp. 209-215, Springer-Verlag Berlin Heidelberg 2005 https://doi.org/10.1007/11427445_33
  24. K-B. Kim, S-S. Kim, 'Recognition of English Calling Card by Using Multiresolution Images and Enhanced ART1-Based RBF Neural Networks', ISNN 2006, LNCS 3972, pp. 299-305, Springer-Verlag Berlin Heidelberg 2006 https://doi.org/10.1007/11760023_44
  25. K-B. Kim, K-B. Sim, S-H. Ahn, 'Recognition of Concrete Surface Cracks Using the ART1-Based RBF Network', ISNN 2006, LNCS 3972, pp. 669-675, Springer-Verlag Berlin Heidelberg 2006 https://doi.org/10.1007/11760023_98
  26. F. Laurene, 'Fundamentals of neural networks : architectures, algorithms, and applications', Prentice-Hall, Inc. New Jersey, pp. 222-245, 1994