영상분할과 다중 특징을 이용한 영역기반 영상검색 알고리즘 = Region-based Image Retrieval Algorithm Using Image Segmentation and Multi-Feature

국문 초록 (Abstract)

컴퓨터 기반의 영상 데이터베이스의 급격한 증가에 따라 영상 정보를 관리할 수 있는 시스템의 필요성이 증가하고 있다. 본 논문에서는 영상분할 알고리즘에 Active Contour, 칼라 특징으로 칼라 오토코렐로그램(Color Autocorrelogram), 질감 특징으로 CWT(Complex Wavelet Transform), 그리고 형태 특징으로 Hu 불변모멘트를 선택하여 이들을 효율적으로 추출하고 결합한 영역기반 다중 특징 영상검색 알고리즘을 제안한다. 칼라 오토코렐로 그램은 영상의 H(Hue), S(Saturation) 성분으로부터 추출 하였고, 질감 특징과 형태 및 위치 특징은 V(Value) 성분으로부터 추출하였다. 효율적인 유사도 측정을 위해 추출된 특징(오토코렐로그램, Hu 불변 모멘트, CWT 모멘트)을 결합하여 정확도와 재현율을 측정하였다. Corel DB 및 VisTex DB에 대한 실험 결과, 제안된 영상검색 알고리즘은 94.8%의 정확도와 90.7%의 재현율을 가지며 성공적으로 영상검색 시스템에 응용할 수 있다.

다국어 초록 (Multilingual Abstract)

The rapid growth of computer-based image database, necessity of a system that can manage an image information is increasing. This paper presents a region-based image retrieval method using the combination of color(autocorrelogram), texture(CWT moments) and shape(Hu invariant moments) features. As a color feature, a color autocorrelogram is chosen by extracting from the hue and saturation components of a color image(HSV). As a texture, shape and position feature are extracted from the value component. For efficient similarity computation, the extracted features(color autocorrelogram, Hu invariant moments, and CWT moments) are combined and then precision and recall are measured. Experiment results for Corel and VisTex DBs show that the proposed image retrieval algorithm has 94.8% precision, 90.7% recall and can successfully apply to image retrieval system.

목차 (Table of Contents)

• 요약
• Abstract
• Ⅰ. 서론
• Ⅱ. 제안된 영역기반 다중특징 영상검색 알고리즘
• Ⅲ. 실험 및 결과 검토
• Ⅳ. 결론
• 참고문헌
• 저자소개

참고문헌 (Reference)

1 이강현, "영상 분할을 이용한 영역기반 내용 검색 알고리즘" 대한전자공학회 44 (44): 1-11, 2007

2 J. R. Smith, "VisualSEEk: A fully automated contentbased image query system" 87-98, 1996

3 M.K.Hu, "Visual Pattern Recognition by Moment Invariants" IT-8 : 179-187, 1962

4 "VisTex DB [Online]"

5 Ivan W. S, "The Dual-Tree Complex Wavelet Transform" 123-151, 2005

6 R. M. Haralick, "Texture features for image classification,” IEEE Trans" IEEE Trans.Syst.Man Cybern 610-621, 1973

7 "Special issue on digital libraries" 18 (18): 1996

8 Michael Kass, "Snakes: Active contour models" 321-331, 1988

9 A.K.Jain and A.Vailaya, "Shape-based retrieval:A case study with trademark image database" 31 (31): 31-9, 1998

10 J. Z. Wang, "SIMPLIcity: Semantics-sensitive integrated matching for picture libraries" 23 (23): 947-963, 2001

11 C. H. Yao, "Retrieval of translated rotated and scaled colour textures" 36 : 913-929, 2002

12 M. Flickner, "Query by image and video content: The QBIC system" 28 (28): 23-32, 1995

13 T. Gevers, "PicToseek: combining colour and shape invariant features for image retrieval,”" 9 (9): 102-119, 000

14 T. Syeda-Mahmood, "On describing colour and shape information in images" 16 (16): 15-31, 2000

15 Chunming Li, "Level Set Evolution Without Re-initialization: A New Variational Formulation,”" IEEE Computer Society Conf. on Computer Vision and Pattern Recognition Proc 2005

16 Y. Rui, "Image retrieval: Current techniques, promising directions, and open issues" 10 (10): 39-62, 1999

17 A. K. Jain, "Image retrieval using colour and shape" 529-533, 1995

18 S. Liapis, "Image retrieval by colour and texture using chromaticity histograms and wavelet frames" 2000

19 J. Huang, "Image indexing using colour correlogram,” Proc. IEEE Conf. on Comput. Vis" 764 (764): 1997

20 Jing Huang, "Image indexing using color correlograms,” in Proc. of Recognition, pp"

21 Y. D. Chun, "Image Retrieval Using BDIP and BVLC Moments" 13 (13): 951-957, 2003

22 J. Li, "IRM: Integrated region matching for image retrieval" 147-156, 2000

23 S. Abbasi, "Curvature scale space in shape similarity retrieval" 1999

24 "Corel DB [Online]"

25 A. W. M. Smeulders, "Content-based image retrieval at the end of early years" 22 (22): 1340-1380, 2000

26 V. N. Gudivada, "Content based image retrieval systems" 28 (28): 18-22, 1995

27 C. Carson, "Blobworld: image segmentation using expectation maximization and its application to image querying" 24 (24): 1026-1038, 2002

28 Kian-Lee, "An Evaluation of Color-Spatial Retrieval Techniques for large Databases" 14 : 55-78, 2001

29 R. L. Kashyap, "A. Khotanzad, “Texture classification using features derived from random field models" 43-50, 1982

30 K. S. Thyagarajan, "A maximum likelihood approach to texture classification using wavelet transform" 640 : 640644-, 1994