Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Mosaic Detection Based on Edge Projection in Digital Video

비디오 데이터에서 에지 프로젝션 기반의 모자이크 검출

  • 장석우 (안양대학교 디지털미디어학과) ;
  • 허문행 (안양대학교 디지털미디어학과)
  • Received : 2016.01.08
  • Accepted : 2016.05.12
  • Published : 2016.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

In general, mosaic blocks are used to hide some specified areas, such as human faces and disgusting objects, in an input image when images are uploaded on a web-site or blog. This paper proposes a new algorithm for robustly detecting grid mosaic areas in an image based on the edge projection. The proposed algorithm first extracts the Canny edges from an input image. The algorithm then detects the candidate mosaic blocks based on horizontal and vertical edge projection. Subsequently, the algorithm obtains real mosaic areas from the candidate areas by eliminating the non-mosaic candidate regions through geometric features, such as size and compactness. The experimental results showed that the suggested algorithm detects mosaic areas in images more accurately than other existing methods. The suggested mosaic detection approach is expected to be utilized usefully in a variety of multimedia-related real application areas.

웹 사이트나 블로그 등에 사진을 업로드 할 때 특정인의 초상권을 보호하기 위해 사람의 얼굴을 블러링하거나 타인에게 혐오감을 주지 않기 위해 혐오스러운 물건들을 모자이크 처리하는 경우가 많이 있다. 본 논문에서는 다양하게 입력되는 영상에서 일정한 영역들을 가리기 위해 사용한 격자형 모자이크 영역들을 에지 프로젝션을 기반으로 정확하게 검출하는 새로운 알고리즘을 제안한다. 제안된 알고리즘에서는 먼저 입력 영상으로부터 캐니 에지를 검출하고, 수평과 수직 에지 프로젝션을 이용해 모자이크의 후보 영역들을 검출한다. 그런 다음, 크기나 밀집도 등의 기하학적인 특징들을 사용해 모자이크의 후보 영역들을 효과적으로 필터링함으로써 최종적으로 실제 모자이크 영역들을 검출한다. 실험 결과에서는 제안된 알고리즘이 입력되는 다양한 영상으로부터 모자이크 블록에 해당하는 영역들을 기존의 다른 검출 방법에 비해 보다 정확하게 검출한다는 것을 보여준다. 본 논문에서 제안된 모자이크 검출 방법은 개인 정보 블로킹, 영상 복원 및 후처리 등과 같은 멀티미디어 콘텐츠와 관련된 여러 가지 실제 응용분야에서 매우 유용하게 활용될 것으로 기대한다.

Keywords

References

  1. H. Duan, Y. Peng, G. Min, X. Xiang, W. Zhan, and H. Zou, "Distributed In-Memory Vocabulary Tree for Real-Time Retrieval of Big Data Images," Ad Hoc Networks, Vol. 35, pp. 137-148, December 2015. DOI: http://dx.doi.org/10.1016/j.adhoc.2015.05.006
  2. D. Rim, M. K. Hasan, F. Puech, and C. J. Pal, "Learning from Weakly Labeled Faces and Video in the Wild," Pattern Recognition, Vol. 48, No. 3, pp. 759-771, March 2015. DOI: http://dx.doi.org/10.1016/j.patcog.2014.09.016
  3. L. Yin, Q. Cheng, Z. Wang, and Z. Shao, "Big Data for Pedestrian Volume: Exploring the Use of Google Street View Images for Pedestrian Counts," Applied Geography, Vol. 63, pp. 337-345, September 2015. DOI: http://dx.doi.org/10.1016/j.apgeog.2015.07.010
  4. D. Guo, J. Tang, Y. Cui, J. Ding, and C. Zhao, "Saliency-based Content-Aware Lifestyle Image Mosaics," Journal of Visual Communication and Image Representation, Vol. 26, pp. 192-199, January 2015. DOI: http://dx.doi.org/10.1016/j.jvcir.2014.11.011
  5. S.-W. Jang and M. Jung, "Detection of Harmful Content Using Multilevel Verification in Visual Sensor Data," Wireless Personal Communications, Springer, pp. 1-16, August 2015.
  6. Z. Wei, J. Lin, L. Zhang, and S. Song, "Mosaic Defect Detection Based on Macro Block Solid Edge Detection," Research Journal of Applied Science, Engineering and Technology, No. 5, Vol. 13, pp. 3549-3553, April 2013. https://doi.org/10.19026/rjaset.5.4486
  7. Y.-J. Park, G.-S. Choi, and J.-J. Park, "A Study on Grid Mosaic Detection for Identifying Image Harmfulness," In Proc. of the Korea Society of Industrial Information Systems, pp. 1-5, June 2015.
  8. J. Liu, L. Huang, and J. Lin, "An Image Mosaic Block Detection Method Based on Fuzzy C-Means Clustering," In Proc. of the IEEE International Conference on Computer Research and Development (ICCRD), Vol. 1, pp. 237-240, March 2011. DOI: http://dx.doi.org/10.1109/ICCRD.2011.5764011
  9. X. Huang, H. Ma, and H. Yuan, "Video Mosaic Block Detection Based on Template Matching and SVM," In Proc. of the IEEE International Conference for Young Computer Scientist (ICYCS), pp. 1082-1086, November 2008. DOI: http://dx.doi.org/10.1109/icycs.2008.69
  10. S.-F. Sun, S.-H. Han, G. Wang, Y.-C. Xu, and B.-J. Lei, "Mosaic Defect Detection in Digital Video," In Proc. of the IEEE Chinese Conference on Pattern Recognition (CCPR), pp. 1-5, October 2010. DOI: http://dx.doi.org/10.1109/ccpr.2010.5659234
  11. H.-I. Choi, Computer Vision, Hongrung Publishing Company, November 2012.
  12. S. H. Kim, G. J. So, "Block Based Extraction of Excessive Disparity Regions Using Automatic Binarization," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol. 5, No. 4, pp. 91-100, Aug. 2015. DOI: http://dx.doi.org/10.14257/AJMAHS.2015.08.56
  13. Y. M. Kang, K. H. Kim, M. R. Han, J. B. Kim, "A Study on the Business Strategies based on Big Data Analysis," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol. 5, No. 5, pp. 145-152, Oct. 2015. DOI: http://dx.doi.org/10.14257/AJMAHS.2015.10.14
  14. Young-Eun An, Ji-Min Lee, Won-Ii Yang, Young-Il Choi, Min-Hyuk Chang, "Object Retrieval Using the Corners Area Variability Based on Correlogram," The Journal of The Institute of Webcasting, Internet and Telecommunication, Vol. 11 No. 6, pp. 283-288, 2011.
  15. P. K. Rhee, Y. Z. Xu, H. C. Shin, Y. Shen, "Local Context based Feature Extraction for Efficient Face Detection," The Journal of The Institute of Webcasting, Internet and Telecommunication, Vol. 11 No. 1, pp. 185-191, 2011.
  16. Y.-S. Kim, J.-Y. Ahn, S.-B. Kim, K.-I. Hur, "A study on Robust Feature Image for Texture Classification and Detection," The Journal of The Institute of Webcasting, Internet and Telecommunication, Vol. 10 No. 5, pp. 133-138, 2010.
  17. D.-W. Kim, Y.-J. Song, A.-K. Kim, Y.-S. Hong, J.-H. Ahn, "Object Detection Method for The Wild Pig Surveillance System," The Journal of The Institute of Webcasting, Internet and Telecommunication, Vol. 10 No. 5, pp. 229-235, 2010.
  18. D. H. Kim, "SVD-based Image Enhancement Method using Weighted Average of Histogram Stretching and Equalization," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol.5, No.5, pp. 77-85, Oct. 2015. DOI: http://dx.doi.org/10.14257/AJMAHS.2015.10.01