Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지

Directional Feature Extraction of Handwritten Numerals using Local min/max Operations

Local min/max 연산을 이용한 필기체 숫자의 방향특징 추출

  • 정순원 ((주)니트젠 기술연구소) ;
  • 박중조 (경상대학교 전기전자공학부, ERI)
  • Published : 2009.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a directional feature extraction method for off-line handwritten numerals by using the morphological operations. Direction features are obtained from four directional line images, each of which contains horizontal, vertical, right-diagonal and left-diagonal lines in entire numeral lines. Conventional method for extracting directional features uses Kirsch masks which generate edge-shaped double line images for each direction, whereas our method uses directional erosion operations and generate single line images for each direction. To apply these directional erosion operations to the numeral image, preprocessing steps such as thinning and dilation are required, but resultant directional lines are more similar to numeral lines themselves. Our four [$4{\times}4$] directional features of a numeral are obtained from four directional line images through a zoning method. For obtaining the higher recognition rates of the handwrittern numerals, we use the multiple feature which is comprised of our proposed feature and the conventional features of a kirsch directional feature and a concavity feature. For recognition test with given features, we use a multi-layer perceptron neural network classifier which is trained with the back propagation algorithm. Through the experiments with the CENPARMI numeral database of Concordia University, we have achieved a recognition rate of 98.35%.

본 논문에서는 local min/max 연산을 이용한 필기체 숫자의 방향특징 추출 기법을 제안한다. 숫자의 방향특징은 숫자를 이루는 선에서 수평, 수직 및 두 대각방향인 4개 방향의 선들로 구성된 방향선분 영상으로부터 구해진다. Kirsch 마스크를 사용하는 기존의 방향특징 추출기법은 에지형태인 두 겹으로 된 방향선분 영상을 생성하는데 반해 본 논문에서 제시하는 방법은 방향성 수축연산을 사용하여 한 겹으로 된 방향선분 영상을 생성한다. 본 방향성 수축연산을 숫자영상에 적용하기 위해서는 먼저 세선화, 영상 팽창 등의 전처리가 필요하지만 이 방법은 숫자를 이루는 선 자체와 더욱 유사한 형태를 갖는 방향선분을 제공한다. 우리가 구하고자 하는 [$4{\times}4$] 크기인 4개의 방향특징은 4개의 방향선분 영상으로부터 조닝방법을 통해 구해진다. 보다 높은 필기체 숫자인식을 얻기 위해, 본 연구에서는 우리가 제안한 방향특징에 기존의 Kirsch 방향특징과 오목특징을 결합한 다중특징을 사용하였다. 본 숫자 특징에 의한 인식률을 테스트를 위해 오류역전파 알고리즘으로 학습되는 다층퍼셉트론 신경회로망을 인식기로 사용하였으며, Concordia 대학의 CENPARMI 숫자 데이터베이스를 사용하여 실험한 결과 98.35%의 인식률을 얻을 수 있었다.

Keywords

References

  1. Favata J. T. and Srikantan G., "A multiple feature/resolution approach to handprinted digit and character recognition", International Journal of Imaging Systems and Technology, Vol. 7, pp. 304-311, 1996. https://doi.org/10.1002/(SICI)1098-1098(199624)7:4<304::AID-IMA5>3.0.CO;2-C
  2. S. H. Lee, "Off-line Recognition of Totally Unconstrained Handwirtten Numerals Using Multilayer Cluster Neural Network", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 18, No. 6, pp. 648-652, 1996 https://doi.org/10.1109/34.506416
  3. S. Knerr and L. Personnaz and G. Dreyfus, "Hand written Digit Recognition by Neural networks with Single-layer Training", IEEE Trans. Neural Networks, Vol. 3, No. 6, pp. 962-968, 1992. https://doi.org/10.1109/72.165597
  4. Oivind Due Trier, Anil K. Jain and Torfinn Taxt, "Feature Extraction Methods for Character Recognition - A Survey", Pattern Recognition, Vol. 29, No. 4, pp. 641-662, 1996 https://doi.org/10.1016/0031-3203(95)00118-2
  5. K. M. Mohiuddin and J. Mao, "A Comparative Study of Different Classifiers for Handprinted Character Recognition", Pattern Recognition in practice IV, pp. 437-448, 1994.
  6. P. Gader, B. Forester et al, "Recognition of Hand-written Digits using Template and Model matching", Pattern Recognition, Vol. 24, No. 5, pp, 421-431, 1991. https://doi.org/10.1016/0031-3203(91)90055-A
  7. S. B. Cho, "Neural network Classifiers for Recognizing Totally Unconstrained Handwritten Numerals", IEEE Trans. on Neural Networks, Vol. 8, No. 1, pp. 43-53, 1997. https://doi.org/10.1109/72.554190
  8. Shi M., Fuiisawa Y., Wakabayashi T., Kimura F., "Handwritten numeral recognition using gradient and curvature of gray scale image", Pattern Recognition. Vol. 35, pp. 2051-2059, 2002. https://doi.org/10.1016/S0031-3203(01)00203-5
  9. Gorgevik D., Cakmakov D., "An Efficient Three-Stage Classifier for Handwritten Digit Recognition", Proceedings of 17th Int. Conference on Pattern Recognition, ICPR2004, IEEE Computer Society, Cambridge, UK, Vol. 4, pp, 507-510, 23-26 August 2004.
  10. G. L. Martin, J. A. Pittman, "Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning", Neural Computation. No. 3, pp. 258-267, 1991
  11. Yoh-Han Pao, Adaptive Pattern Recognition and Neural Networks, Addison- Wesley, 1989