Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Region-based Image retrieval using EHD and CLD of MPEG-7

MPEG-7의 EHD와 CLD를 조합한 영역기반 영상검색

  • Ryu Min-Sung (Department of Electronic Engineering, Dongguk University) ;
  • Won Chee Sun (Department of Electronic Engineering, Dongguk University)
  • Published : 2006.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a combined region-based image retrieval system using EHD(Edge Histogram Descriptor) and CLD(Color Layout Descriptor) of MPEG-7 descriptors. The combined descriptor can efficiently describe edge and color features in terms of sub-image regions. That is, the basic unit for the selection of the region-of-interest (ROI) in the image is the sub-image block of the EHD, which corresponds to 16 (i.e., $4{\times}4)$ non-overlapping image blocks in the image space. This implies that, to have a one-to-one region correspondence between ELE and CLD, we need to take an $8{\times}8$ inverse DCT (IDCT) for the CLD. Experimental results show that the proposed retrieval scheme can be used for image retrieval with the ROI based image retrieval for MPEG-7 indexed images.

본 논문에서는 영상의 에지와 칼라 분포를 부영상(sub-image)의 단위로 기술하기 위해 MPEG-7의 여러 가지 서술자 중 에지히스토그램 서술자(EHD: Edge Histogram Descriptor)와 컬러레이아웃 서술자(CLD: Color Layout Descriptor)를 조합한 영역기반 영상 검색 시스템을 제안한다. 영상 내의 관심영역 (ROI) 선택의 기본 단위는 영상 공간을 $16(4{\times}4)$개의 겹치지 않는 영역으로 분할한 EHD의 부영상 블록이다. 따라서 영상 특징 벡터에 대한 블록-대-블록의 일-대-일 대응 관계를 유지하기 위해 CLD의 기술자는 $8{\times}8$ 역 DCT (IDCT)를 통해 $4{\times}4$의 각 부영상에 대응하는 컬러 특징을 생성한다 제안된 방법이 MPEG-7의 기술자에 대해 관심영역기반 영상 검색에 적용될 수 있음을 실험을 통해 제시하였다.

Keywords

References

  1. ISO/IEC JTC 1/SC 29/WG 11 N4918'Text of ISO/IEC TR 15938-8 (Extraction and Use of MPEG-7 Descriptions)', July 2002, Klagenfurt
  2. B. S. Manjunath, P. Salembier, T. Sikora, Introduction to MPEG-7, pp.179, West Sussex. England, 2002
  3. 강희범, 원치선, 'MPEG-7 디스크립터들의 조합을 이용한 영상 검색', 방송공학회 논문지 제 8권 1호, pp91-100, 2003
  4. Zoran Stejic, Yasumi Takama, Kaoru Hirota, 'Relevance Feedback-Based Image Retrieval Interface Incorporating Region and Feature Saliency Patterns as Visualizable Image Similarity Criteria', IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS ,VOL 50, NO 5, OCTOBER 2003 https://doi.org/10.1109/TIE.2003.817497
  5. Feng Jing, Mingjing Li, Hong- Jiang Zhang, Bo Zhang, 'LEARNING REGION WEIGHING FROM RELEVANCE FEEDBACK IN IMAGE RETRIEVAL', IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002. Proceeding. (ICASSP'02), VOL 4,IV-4088-IV-4091 13-17 May 2002
  6. Yamamoto, H, Iwasa. H, Yokoya. N., Takemura, H, Content-based similarity retrieval of images based on spatial color distributions Image Analysis and Processing, 1999. Proceedings. International Conference on, 27-29 Sept. 1999 Pages: 951-956 https://doi.org/10.1109/ICIAP.1999.797718
  7. Carson, C., Belongie, S., Greenspan, H, Malik, J., Region-based image querying, Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries, 20 June 1997 Pages: 42-49 https://doi.org/10.1109/IVL.1997.629719
  8. Huseyin O., Chen T., Wu HR., Performance evaluation of multiple regions-of-interest query for accessing image databases, Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on, 2-4 May 2001 Pages: 300-303 https://doi.org/10.1109/ISIMP.2001.925393
  9. Kutics, A.; Nakajima, M.; Ieki, T. ; Mukawa, N. ; An object-based image retrieval system using an inhomogeneous diffusion model, Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on, Volume: 2, 24-28 Oct. 1999 Pages: 590-594 vol.2 https://doi.org/10.1109/ICIP.1999.822963
  10. Min-Sung Ryu, Soo-Jun Park, Chee Sun Won, ISO/IEC JTC1/SC29 M11641: 'Photo retrieval based on Region of Interest(ROI), VCE-5', 2005
  11. ISO/IEC JTC1/SC29/WG11/M6029, 'Subjective Evaluation of the MPEG-7 Retrieval Accuracy Measure(ANMRR)', Geneva, May 2000