DOI QR코드

DOI QR Code

An Efficient Image Matching Scheme Based on Min-Max Similarity for Distorted Images

왜곡 영상을 위한 효과적인 최소-최대 유사도(Min-Max Similarity) 기반의 영상 정합 알고리즘

  • Heo, Young-Jin (Dept. of IT Engineering, Sookmyung Women's University) ;
  • Jeong, Da-Mi (Dept. of IT Engineering, Sookmyung Women's University) ;
  • Kim, Byung-Gyu (Dept. of IT Engineering, Sookmyung Women's University)
  • Received : 2019.09.24
  • Accepted : 2019.12.16
  • Published : 2019.12.31

Abstract

Educational books commonly use some copyrighted images with various kinds of deformation for helping students understanding. When using several copyrighted images made by merging or editing distortion in legal, we need to pay a charge to original copyright holders for each image. In this paper, we propose an efficient matching algorithm by separating each copyrighted image with the merged and edited type including rotation, illumination change, and change of size. We use the Oriented FAST and Rotated BRIEF (ORB) method as a basic feature matching scheme. To improve the matching accuracy, we design a new MIN-MAX similarity in matching stage. With the distorted dataset, the proposed method shows up-to 97% of precision in experiments. Also, we demonstrate that the proposed similarity measure also outperforms compared to other measure which is commonly used.

Keywords

Acknowledgement

Supported by : Korea Copyright Commission

This research project was supported by Ministry of Culture, Sports and Tourism (MCST) and from Korea Copyright Commission in 2019.

References

  1. The Copyright Law, http://www.law.go.kr/legislation/copyright-law (accessed September 16, 2019).
  2. Y. Choi, J. Kim, J. Lee, Y. Lee, G. Hong, and B. Kim, “Efficient Object Classification Scheme for Scanned Educational Book Image,” Journal of Digital Contents Society, Vol. 18, No. 7, pp. 1323-1331, 2017. https://doi.org/10.9728/dcs.2017.18.7.1323
  3. D. Jeong, Y. Choi, and B. Kim, "A Study on Image Retrieval Algorithm for Scanned Education Books," Proceeding of the Spring Conference of the Korea Multimedia Society, pp. 158-161, 2019.
  4. D. Lowe, “Distinctive Image Features from Scale-invariant Keypoints,” International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  5. R. Arandjelovi and A. Isserman, "Three Things Everyone Should Know to Improve Object Retrieval," Proceeding of Conference on Computer Vision and Pattern Recognition, pp. 2911-2918, 2012.
  6. D. Jeong, J. Kim, Y. Lee, and B. Kim, "Robust Weighted Keypoint Matching Algorithm for Image Retrieval," Proceeding of the 2018 the 2nd International Conference on Video and Image Processing, pp. 145-149, 2018.
  7. H. Bay, A. Ess, T. Tuytelaars, and V. Gool, “Speeded-up Robust Features(SURF),” Computer Vision and Image Understanding, Vol. 110, No. 3, pp. 346-359, 2008. https://doi.org/10.1016/j.cviu.2007.09.014
  8. L. Bo, L. Haibo, and S. Ulrik, "Scale-invariant Corner Keypoints," Proceeding of International Conference on Image Processing, pp. 5741-5745, 2014.
  9. L. Yang, L. Lingshan, W. Lianghao, L. Dongxia, and Z. Ming, "Fast SIFT Algorithm Based on Sobel Edge Detector," Proceeding of International Conference on Consumer Electronics, Communications and Networks, pp. 1820-1823, 2012.
  10. M. Calonder, V. Lepetit, C. Strecha, and P. Fua, "Brief: Binary Robust Independent Elementary Features," Proceeding of European Conference on Computer Vision, pp. 778-792, 2010.
  11. E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An Efficient Alternative to SIFT or SURF," Proceeding of IEEE International Conference on Computer Vision, pp. 2564-2571, 2011.
  12. K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask R-CNN," arXiv Preprint arXiv:1703.06870, 2017.
  13. S. Ren, K. He, R. Girshick, and J. Sun. "Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks," arXiv Preprint arXiv:1506.01497, 2015.
  14. T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, et al., "Microsoft COCO: Common Objects in Context," Proceeding of European Conference on Computer Vision, pp. 740-755, 2014.
  15. S. Amit, “Modern Information Retrieval: A Brief Overview,” Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, Vol. 24, No. 4, pp. 35-43, 2001.
  16. J. Wan, D. Wang, S. Hoi, P. Wu, Ji. Zhu, Y. Zhang, et al., "Deep Learning for Content-Based Image Retrieval: A Comprehensive Study," Proceeding of the 22nd ACM International Conference on Multimedia, pp. 157-166, 2014.
  17. W. Huang, L. Wu, H. Song, and Y. Wei, "RBRIEF: A Robust Descriptor Based on Random Binary Comparisons," Institution of Engineering and Technology Computer Vision, pp. 29-35, 2013.
  18. L. Li, L. Wu, and Y. Gao, "Improved Image Matching Method Based on ORB," Proceeding of the 17th IEEE/ACIS International Conference on Software Engineering, pp. 465-468, 2016.
  19. S. Eghbali and L. Tahvildari, "Fast Cosine Similarity Search in Binary Space with Angular Multi-index Hashing," Proceeding of the IEEE Transactions on Knowledge and Data Engineering, pp. 329-342, 2018.
  20. K.W. Kim, “Improvement of Retrieval Performance Using Adaptive Weighting of Key Frame Features,” Journal of Korea Multimedia Society, Vol. 17, No. 1, pp. 26-33, 2014. https://doi.org/10.9717/kmms.2014.17.1.026
  21. S.J. Lee, K.S. Lee, and B.G. Kim, “Binary Image Based Fast DoG Filter Using Zero-dimensional Convolution and State Machine LUTs,” Journal of Multimedia Information System, Vol. 5, No. 2, pp. 131-138, 2018. https://doi.org/10.9717/JMIS.2018.5.2.131
  22. L.K. Mudragada, K.S. Lee, and B.G. Kim, “Virtual Prototyping of Area-based Fast Image Stitching Algorithm,” Journal of Multimedia Information System, Vol. 6, No. 1, pp. 7-14, 2019. https://doi.org/10.33851/JMIS.2019.6.1.7