디지털융복합연구 (Journal of Digital Convergence)

  • 제14권5호
  • /
  • Pages.263-271
  • /
  • 2016
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

칼라 상관관계 역투영법을 적용한 효율적인 객체 지역화 기법

Efficient Object Localization using Color Correlation Back-projection

  • 이용환 (스마트모바일학과, 극동대학교) ;
  • 조한진 (스마트모바일학과, 극동대학교) ;
  • 이준환 (스마트모바일학과, 극동대학교)
  • 투고 : 2016.03.18
  • 심사 : 2016.05.20
  • 발행 : 2016.05.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이미지 내에서 객체를 검출하고 해당 위치를 추출하는 지역화 기법은 컴퓨터 비전에서 많이 활용되는 기술이다. 기존 연구들은 하나의 객체를 대상으로 위치 검출을 수행하지만, 실제 사진에서는 다수의 유사 객체를 포함하는 경우가 많기 때문에, 활용에 한계가 있다. 이러한 문제를 해결하기 위해, 본 논문에서는 이미지 인식을 위해 객체 지역화의 새로운 알고리즘을 제안한다. 제안 알고리즘은 YCbCr 색채 성분에서 코렐로그램 역투영 기법을 활용하여 객체 지역화 문제를 해결한다. 제안 알고리즘에서는 질의 이미지의 객체가 포함되는 이미지의 위치를 검출할 수 있으며, 다수의 유사 객체가 존재할 경우 포함되는 객체 개수 정보 없이도 유사 후보 객체의 영역과 위치를 검출할 수 있다. 제안 알고리즘의 성능을 평가할 실험 결과, 기존에 연구된 방법에 비해, 21%의 성능 향상을 보였다. 이러한 결과를 통해, 색상 코렐로그램이 히스토그램 기법보다 성능적 우위를 보였다. 본 논문의 주요 공헌은 색 공간과 공간-색상 정보를 통해 객체 지역화 문제를 해결할 수 있는 또다른 기술을 제시한 것으로 학문적 기여를 검증하였다.

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

키워드

참고문헌

  1. Kyoungro Yoon, Youngseop Kim, Je-Ho Park, Jaime Delgado, Akio Yamada, Frederic Dufaux, Ruben Tous, "JPSearch: New International Standard Providing Interoperable Framework for Image Search and Sharing", Signal Processing: Image Communication, vol.27, issue.7, pp.709-721, 2012. https://doi.org/10.1016/j.image.2012.05.001
  2. P. Radhakrishnan, A. Clementking, "Determination of Object Similarity Closure using Shared Neighborhood Connectivity", Journal of the Korea Convergence Society, vol.5, no.3, pp.41-44, 2014. https://doi.org/10.15207/JKCS.2014.5.3.041
  3. Roger M. Dufour, Eric L. Mill, Nikolas P. Galatsanos, "Template Matching based Object Recognition with Unknown Geometric Parameters", IEEE Transactions on Image Processing, vol.11, no.12, pp.1385-1396, 2002. https://doi.org/10.1109/TIP.2002.806245
  4. Sanghyuk Lee, "Grouping DNA Sequence with Similarity Mearure and Application", Journal of the Korea Convergence, vol.4, no.3, pp.35-41, 2013.
  5. Vivek Jain, Neha Sahu, "A Survey on Content based Image Retrieval", International Journal of Engineering Research and Applications, vol.3, issue.4, pp.1166-1169, 2013.
  6. Keyuri M. Zinzuvadia, Bhavesh A. Tanawala, Keyur N. Brahmbhatt, "A Survey on Feature based Image Retrieval using Classification and Relevance Feedback Techniques", International Journal of Innovative Research in Computer and Communication Engineering, vol.3, issue.1, pp.508- 513, 2015.
  7. Olga Russakovsky, Yuanqing Lin, Kai Yu, Li Fei-Fei, "Object-centric Spatial Pooling for Image Classification", Lecture Notes in Computer Science, vol.7573, pp.1-15, 2012.
  8. Kevin Murphy, Antonio Torralba, Daniel Eaton, William Freeman, "Object Detection and Location using Local and Global Features", Lecture Notes in Computer Science, vol.4170, pp.382-400, 2006.
  9. John R. Smith, "Integrated Spatial and Feature Image Systems: Retrieval, Analysis and Compression", Ph.D. Thesis, Columbia University, USA, 1997.
  10. Hong-Hee Kim, Jae-Heung Lee, "Development of a License Plate Recognition System using Template Matching Method in Embedded System", Journal of Institute of Korean Electrical and Electronics Engineers, vol.15, no.4, pp.274-280, 2011.
  11. Tali Delel, Shaul Oron, Michael Rubinstein, Shai Avidan, William T. Freeman, "Best-Buddies Similarity for Robust Template Matching", International Conference on Computer Vision and Pattern Recognition, pp.2021-2029, 2015.
  12. Hee-June Han, Jong-Yun Lee, "Algorithm of Converged Corner Detection-based Segmentation in the Data Matrix Barcode", Journal of the Korea Convergence, vol.6, no.1, pp.7-16, 2015. https://doi.org/10.15207/JKCS.2015.6.1.007
  13. Alper Yilmaz, Omar Javed, Mubarak Shah, "Object Tracking: A Survey", ACM Computing Surveys, vol.38, issue.4, no.13, pp.1-45, 2006. https://doi.org/10.1145/1132952.1132953
  14. Sanghyuk Lee, Yujia Zhai, "Relation between Certainty and Uncertainty with Fuzzy Entropy and Similarity Measure", Journal of the Korea Convergence Society, vol.5, no.4, pp.155-161, 2014. https://doi.org/10.15207/JKCS.2014.5.4.155
  15. Christoph H. Lampert, Matthew B. Blaschko, Thomas Hofmann, "Beyond Sliding Windows: Object Localization by Efficient Subwindow Search", IEEE Conference on Computer Vision and Pattern Recognition, pp.1-8, 2008.
  16. Jamal Malki, Nozha Boujemaa, Chahab Naster, Alexandre Winter, "Region Queries without Segmentation for Image Retrieval by Content", Lecture Notes in Computer Science, vol.1614, pp.115-122, 2002.
  17. Michael Wirth, Ryan Zaremba, "Flame Region Detection based on Histogram Backprojection", Canadian Conference Computer and Robot Vision, pp.167-174, 2010.
  18. Jing Huang, S. Ravi Kumar, Mandar Mitra, Wei Jing Zhu, Ramin Zabih, "Spatial Color Indexing and Applications" International Journal of Computer Vision, vol.35, no.3, pp.245-268, 1999. https://doi.org/10.1023/A:1008108327226
  19. Jong-Hun Park, Gang-Seong Lee, Sang-Hun Lee, "A Study on the Convergence Technique enhaced GrabCut Algorithm using Color Histogram and Modified Sharpening Filter", Journal of the Korea Convergence Society, vol.6, no.5, pp.1-8, 2015.
  20. Mika Rautiainen, Timo Ojala, "Color Correlograms in Image and Video Retrieval", Finnish Conference on Artificial Intelligence, pp.1-10, 2002.
  21. Jing Huang, S. Ravi Kumar, Mandar Mitra, Wei0Jing Zhu, Ramin Zabih, "Image Indexing using Color Correlograms", IEEE Conference on Computer Vision and Pattern Recognition, pp.762-768, 1997.