DOI QR코드

DOI QR Code

Image Restoration for Character Recognition

문자 인식을 위한 영상 복원

  • Yoo, Suk Won (Dept. of Computer Science, SeoKyeong University)
  • 유석원 (서경대학교 컴퓨터과학과)
  • Received : 2018.05.15
  • Accepted : 2018.07.25
  • Published : 2018.08.31

Abstract

Because of the mechanical problems of input camera equipment, image restoration process is performed in order to minimize recognition errors due to the noise problem generated in test data image. The image restoration method resolves the noise problem by examining the numbers and positions of the Direct neighbors and the Indirect neighbors for each pixel constituting the test data. As a result, satisfactory recognition result can be obtained by eliminating the noise problem generated in the test data through the image restoration process as much as possible and also by calculating the differences between the learning data and the test data in the area unit, thereby reducing the possibility of recognition error by the noise problem.

영상 기기의 기계적인 문제로 인해 실험 데이터에 발생한 잡음으로 인한 인식 오류를 최소화하기 위해서 영상복원 과정을 거친다. 영상 복원 방법은 실험 데이터를 구성하는 각각의 픽셀에 대해 Direct Neighbor와 Indirect Neighbor의 개수와 위치를 조사해서 잡음을 해결한다. 결과적으로, 영상 복원 과정을 통해 실험 데이터에 발생한 잡음을 최대한 제거하고, 영역 단위로 학습 데이터와 실험 데이터의 차이를 계산해서 잡음에 의한 인식 오류 가능성을 낮춤으로써 만족할만한 인식 결과를 얻을 수 있다.

Keywords

References

  1. J. Parker, Algorithms for Image Processing and Computer Vision, Wiley, pp. 137-175, 2010.
  2. C. Chen, L. Pau, P Wang, Handbook of Pattern Recognition and Computer Vision, World Scientific, pp. 61-84, 1993.
  3. T. Adali, S. Haykin, Adaptive Signal Processing, John Wiley & Sons, pp. 40-58, 2010.
  4. E. Hall, Computer Image Processing and Recognition, Academic Press, pp. 76-153, 1979.
  5. F. Shih, Image Processing and Mathematical Morphology, CRC Press, pp. 25-35, 2009.
  6. Y. Yang, S. Lee, “An Object Tracking Method for Studio Cameras by OpenCV-based Python Program,” Journal of Convergence on Culture Technology(JCCT), Vol. 4, No. 1, pp. 291-297, 2018. https://doi.org/10.17703/JCCT.2018.4.1.291
  7. G. Dougherty, Digital Image Processing for Medical Application, Cambridge, pp. 155-189, 2009
  8. S. Yoo, “Character Recognition Algorithm using Accumulation Mask,” International Journal of Advanced Culture Technology(IJACT), Vol. 6, No. 2, pp. 123-128, 2018. https://doi.org/10.17703/IJACT.2018.6.2.123