The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Image Retrieval Using Rearranged Color Histogram

재배열 칼라 히스토그램을 이용한 영상 검색

  • 안영은 (조선대학교 자유전공학부) ;
  • 이강준 (조선대학교 소프트웨어융합공학과) ;
  • 박종안 (조선대학교 정보통신공학과)
  • Received : 2015.12.08
  • Accepted : 2016.01.10
  • Published : 2016.01.31
⟨ Previous Next ⟩

Abstract

This paper proposes an image retrieval system using rearranged color histogram for content based image retrieval. And analyze the performance by using a JPEG 3,000 image of different sizes composed of the database. The proposed algorithm is evenly divided a histogram extracted from the RGB color image with 16 pins. By rearranging the values in the histogram bin 16 divided by size and then mapped to the area value and a new characteristic value of 1-16. And by applying the correlogram to the image feature values are mapped to the table constitutes the feature character. Compare using this feature table to the query image and database image. In simulation that use the 3,000 JPEG image database, the method presents that the recall property is improved by 0.21 and more than the standard color histogram algorithm.

본 논문에서는 내용 기반 영상 검색을 위해 재배열 칼라 히스토그램을 이용한 영상 검색 시스템을 제안하였다. 그리고 서로 다른 크기의 JPEG 영상 3,000개로 구성된 데이터베이스를 이용하여 성능을 분석 하였다. 제안된 알고리즘은 RGB 칼라 영상에서 추출된 히스토그램을 16개의 빈으로 균일하게 분할하고, 분할된 16개 빈 안에 있는 히스토그램 값들을 크기순으로 재정렬 한 후 공간 값이자 새로운 특징값인 1~16으로 사상한다. 그리고 특징값으로 사상된 영상에 코렐로그램을 적용하여 특징자 테이블을 구성하고, 이 특징자 테이블을 이용하여 데이터베이스 내의 영상과 질의 영상을 비교 검색한다. 제안된 검색 시스템은 칼라 히스토그램만을 사용한 시스템보다 리콜(Recall)이 0.21 큰 것으로 보아 영상 검색 성능이 더 우수함을 확인하였다.

Keywords

Acknowledgement

Supported by : 조선대학교

References

  1. T. Gevers and A. W. M. Smeulders, "PicToSeek : Combining color and shape invariant features for image retrieval", IEEE Transactions on Image Processing, Vol. 9, No. 1, pp. 102-119, Jan. 2000. https://doi.org/10.1109/83.817602
  2. V. Mezaris, I. Kompatsiaris, and M. G. Strintzis, "Region-Based Image Retrieval Using an Object Ontology and Relevance Feedback", EURASIP Journal on Applied Signal Processing, Vol. 6, pp. 886-901, June 2004.
  3. D. Neumann, K. and R. Gegenfurtner, "Image Retrieval and Perceptual Similarity", ACM Transactions on Applied Perception, Vol. 3, No. 1, pp. 31-47, Jan. 2006. https://doi.org/10.1145/1119766.1119769
  4. J. A. Park, S. K. Kang, I. H. Jeong, W. Rasheed, S. J. Park and Y. E. An, "Web based image retrieval system using HSI color indexes", Third International Conference on Intelligent Computing, ICIC 2007, Vol. 1, pp. 21-24, Aug. 2007.
  5. K. M, Wong, K. W. Cheung, and L. M Po, "MIRROR: an interactive content based image retrieval system", Proceedings of ISCAS, Vol. 2, pp. 1541-1544, May 2005.
  6. R. Schettini, G. Ciocca, and S. Zuffi, "A survey of methods for colour image indexing and retrieval in image databases", L. W. MacDonald and M. R. Luo, Editors, Color imaging science: exploiting digital media, Wiley, J. & Sons Ltd, 2001.
  7. B. Di, "An efficient image retrieval approach base on color clustering", Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Vol. 1, pp. 214-220, Nov. 2007.
  8. A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain, "Content-based image retrieval at the end of the early years", IEEE Transactions of Pattern Analysis and Machine Intelligence, Vol. 22, No. 12, pp. 1349-1380, Dec. 2000. https://doi.org/10.1109/34.895972
  9. B. Fishbain and M. Mehrubeoglu, "Guest Editirial of the Special Issue on Real-time Vision-based Motion Analysis and Intelligent Transportation Systems", Journal of Real-Time Image Processing, Vol. 5, No. 4, pp. 213-214, Dec. 2010. https://doi.org/10.1007/s11554-010-0180-7
  10. M. Patel, S. Lal, D. Kavanagh and P. Rossiter, "Fatigue Detection Using Computer Vision", International Journal of Electronics and Telecommunications, Vol. 56, No. 4, pp. 457-461, Nov. 2010. https://doi.org/10.2478/v10177-010-0062-8
  11. J. A. Park and T. S. Park, "Using Intrinsic Object Attributes for Incremental Content Based Image Retrieval with Histograms", Journal of Korean Institute of Information Technology, Vol. 5, No. 3, pp. 17-24, Sep. 2007.
  12. J. Huang, S. R. Kumar, M. Mitra, W. J. Zhu, and R. Zabi, "Image Indexing using color correlograms", Computer Vision and Pattern Recognition, IEEE Computer Society Conference on San Juan, pp. 762-768, June 1997.