Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Detection and Remove Algorithm of B/W Line Scratch on Old Film by Linear Recursive Curve Trace

선형 회귀곡선 추적을 이용한 고전 필름의 흑,백 라인 스크래치 검출과 제거 알고리즘

  • 이강현 (조선대학교 전자공학과)
  • Published : 2007.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

According to the increased demand of high quality multimedia content, it needs to recover an old movies. But the film of old movie is damaged with line scratches and dust. In this paper, the detection and restoration algorithm of B/W line scratch is proposed. Our scheme estimates and interpolates the damaged partial information of line scratch using the linear recursive curve trace which consider the intensity values of left and right region of line scratch and then median filtering processed. As a result, the film image PSNR 44.68 with B/W line scratch is increased up to 48.60 and the intensity of the interpolate pixel is approached about 14 against the pixel of original image.

고화질의 멀티미디어 콘텐츠 수요 증가에 따라서 고전영화의 복원이 필요하다. 그러나 고전영화의 필름은 라인 스크래치와 먼지에 의해서 영상이 많이 훼손되어 있다. 본 논문에서는 필름상의 흑, 백 라인 스크래치를 검출하여 복원하는 알고리즘을 제안한다. 제안된 알고리즘은 라인 스크래치 좌우 영역의 밝기 값을 고려하여 선형회귀 곡선 추적과 미디언 필터링으로 라인 스크래치 부분의 손상된 부분정보를 추정, 보간한다. 그 결과 흑, 백 라인 스크래치가 있는 PSNR 44.68인 필름영상을 48.60으로 향상시켰으며, 보간된 픽셀은 원 영상 픽셀에 14정도의 밝기 차로 접근되었다.

Keywords

References

  1. V. Bruni, D. Vitulano and A. Kokaram, 'Line scratches detection and restoration via light diffraction,' Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the 3rd International Symposium on, Volume 1, pp.5-10 Vol.1, 18-20 Sept. 2003
  2. V. Bruni, D. Vitulano and A. Kokaram, 'Fast removal of line scratches in old movies,' Pattern Recognition ICPR 2004 Proceedings of the 17th International Conference on, Volume 4, pp. 827-830, Aug. 2004
  3. L. Joyeux, S. Boukir and B. Besserer, 'Film line scratch removal using Kalman filtering and Bayesian restoration,' Applications of Computer Vision, 2000, Fifth IEEE Workshop on, pp. 8-13, 4-6 Dec. 2000
  4. V. Bruni and D. Vitulano, 'A generalized model for scratch detection,' Image Processing, IEEE Transactions on, Volume 13, Issue 1, pp. 44-50, Jan. 2004 https://doi.org/10.1109/TIP.2003.817231
  5. 김경태, 김은이, '신경망 기반의 텟처 분류기를 이용한 스크래치 검출,' 대한전자공학회 CI 43권 제 6호, pp. 26-33, 2006. 11
  6. L. Joyeux, S. Boukir and B. Besserer, 'Film line scratch removal using Kalman filtering and Bayesian restoration,' Applications of Computer Vision, 2000, Fifth IEEE Workshop on, pp. 8-13, 4-6 Dec. 2000
  7. L. Maddalena, 'Efficient methods for scratch removal in image sequences,' Image Analysis and Processing, 2001. Proceedings. 11th International Conference on, pp. 547-552, 26-28 Sept. 2001
  8. V. Bruni and D. Vitulano, 'Scratch detection via underdamped harmonic motion,' Pattern Recognition, 2002. Proceedings. 16th International Conference on, Volume 3, pp. 887-890, 11-15 Aug. 2002
  9. Shih, T. K., Lin, L. H. and Wonjun Lee, 'Detection and Removal of Long Scratch Lines in Aged Films,' Multimedia and Expo, 2006 IEEE International Conference on, pp. 477-480, July 2006
  10. L. Maddalena, 'Efficient methods for scratch removal in image sequences,' Image Analysis and Processing, 2001. Proceedings. 11th International Conference on, pp. 547-552, 26-28 Sept. 2001