Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Fast Patch Retrieval for Example-based Super Resolution by Multi-phase Candidate Reduction

단계적 후보 축소에 의한 예제기반 초해상도 영상복원을 위한 고속 패치 검색

  • 박규로 (한동대학교 정보통신공학과) ;
  • 김인중 (한동대학교 전산전자공학부)
  • Received : 2009.01.14
  • Accepted : 2010.01.26
  • Published : 2010.04.15
Download PDF
⟨ Previous Next ⟩

Abstract

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

예제기반 초해상도 영상복원은 영상 패치의 대한 학습 및 검색을 통해 저해상도 영상으로부터 고해상도 영상을 복원하는 방법으로써 성능이 좋고 한 장의 저해상도 영상에 대하여도 적용 가능하다. 그러나 복원 과정에서 패치 검색에 많은 비교 연산이 요구되기 때문에 속도가 매우 느리다. 복원 속도를 향상시키기 위해서는 효과적인 패치 검색 알고리즘이 요구된다. 본 논문에서는 패치 검색에 사용 가능한 다양한 고차원 특징 검색 방법들을 실제 초해상도 영상복원 시스템에 적용하여 그 성능을 비교하였다. 또한 문자 인식 분야에서 성공적으로 적용되어왔으나 초해상도 영상복원에서는 사용되지 않았던 단계적 후보축소 방법을 패치 검색 단계에 적용할 것을 제안한다. 실험 결과 기존의 방법 중에서는 LSH가 가장 좋은성능을 나타내었다. 본 논문에서 제안한 단계적 후보 축소에 의한 패치 검색 방법은 LSH보다 더욱 우수하여 $1024{\times}1024$ 영상의 복원 시 LSH보다 최대 3.12배 빠른 복원 속도를 나타내었다.

Keywords

References

  1. M. E. Tipping and C. M. Bishop. "Bayesian image super-resolution," In S. Thrun S. Becker and K. Obermayer, editors, Advances in Neural Information Processing Systems 15, pp.1279-1286, MIT Press, Cambridge, MA, 2003.
  2. B. Battulga, "Anisotropic Total Variation Method for Text Image Super-Resolution," pp.1-34, Master Thesis, KAIST, 2007.
  3. L. C. Pickup, D. P. Capel, S. J. Roberts, and A. Zisserman, "Bayesian image super-resolution, continued," Advances in Neural Information Processing Systems 19, pp.1089-1096, Cambridge, Mass, USA, December 2006.
  4. William T. Freeman, Thouis R. Jones, Egon C Pasztor, "Example-Based Super-Resolution," IEEE Computer Graphics and Applications, vol.22, no.2, pp.56-65, March/April, 2002. https://doi.org/10.1109/38.988747
  5. Wang, Q., Tang, X., and Shum, H. "Patch Based Blind Image Super Resolution," In Proceedings of the Tenth IEEE international Conference on Computer Vision, 2005.
  6. Simon Baker, Takeo Kanade, "Limits on Super- Resolution and How to Break Them," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24, no.9, pp.1167-1183, September, 2002. https://doi.org/10.1109/TPAMI.2002.1033210
  7. J.Park, Y.Kwon, J.Kim, "An Example-Based Prior Model for Text Image Super-resolution," 8th International Conference on Document Analysis and Recognition (ICDAR2005), Seoul, Korea, pp.374-378, 2005.
  8. Kim, Sang-Wook, Charu Aggarwal, Philip Yu, "최근접 질의를 위한 고차원 인덱싱 방법", 한국정보과학회 논문지 : 데이타베이스, vol.28, no.4, pp.632-642, Dec. 2001.
  9. Bentley, J. L., "K-d trees for semidynamic point sets," In Proceedings of the Sixth Annual Symposium on Computational Geometry, SCG '90. ACM, New York, NY, 187-197. 1990.
  10. King-ip Lin, H. V. Jagadish, Christos Faloutsos, "The TV-tree: an index structure for high-dimensional data," VLDB, 1994.
  11. Roger Weber, Hans-J. Schek, Stephen Blott, "A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces," Proc. 24th Int. Conf. VLDB, pp.194-205, 1998.
  12. Jeffrey S. Beis, David G. Lowe, "Indexing without Invariants in 3D Object Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, no.10, pp. 1000-1015, Oct., 1999. https://doi.org/10.1109/34.799907
  13. Gionis, A., Indyk, P., and Motwani, R, "Similarity Search in High Dimensions via Hashing," In Proceedings of the 25th international Conference on Very Large Data Bases, Sep. 1999.
  14. Ching-Lin Liu, Ryuji Mine, Masashi Koga, "Building Compact Classifier for Large Character Set Recognition Using Discriminative Feature Extraction," icdar, pp.846-850, 2005.
  15. S. C. Ahalt, A. K. Krishnamurthy, P. Chen, and D. E. Melton. Competitive learning algorithms for vector quantization. Neural Networks, 3(3):277- 290, 1990. https://doi.org/10.1016/0893-6080(90)90071-R
  16. Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, "Image quality assessment: From error visibility to structural similarity," IEEE Transactions on Image Processing, vol.13, no.4, pp. 600-612, Apr. 2004. https://doi.org/10.1109/TIP.2003.819861