A Content-Based Image Retrieval Technique Using the Shape and Color Features of Objects

객체의 모양과 색상특징을 이용한 내용기반 영상검색 기법

  • 박종현 (목포대학교 전자공학과 정회원) ;
  • 박순영 (목포대학교 전자공학과 정회원) ;
  • 오일환 (목포대학교 전자공학과 정회원)
  • Published : 1999.10.01

Abstract

In this paper we present a content-based image retrieval algorithm using the visual feature vectors which describe the spatial characteristics of objects. The proposed technique uses the Gaussian mixture model(GMM) to represent multi-colored objects and the expectation maximization(EM) algorithm is employed to estimate the maximum likelihood(ML) parameters of the model. After image segmentation is performed based on GMM, the shape and color features are extracted from each object using Fourier descriptors and color histograms, respectively. Image retrieval consists of two steps: first, the shape-based query is carried out to find the candidate images whose objects have the similar shapes with the query image and second, the color-based query is followed. The experimental results show that the proposed algorithm is effective in image retrieving by using the spatial and visual features of segmented objects.

본 논문에서는 객체들의 공간적 특성이 반영된 시각적인 특징벡터를 이용한 내용기반 영상검색 알고리즘을 제안한다. 제안된 검색 기법은 여러 색상으로 이루어진 객체들을 표현하기 위하여 가우시안 혼성 모델을 적용하여 모델의 최대유사 파라미터는 EM 알고리즘을 사용하여 추정한다. GMM을 기반으로 하여 분할된 각 객체들로부터 Fourier descriptor의 색상 히스토그램을 사용하여 모양과 색상 특징을 추출하게 된다. 영상 검색은 두 단계로 구성되는데 첫 단계에서는 공간적인 모양 특성을 추출하여 모양이 유사한 객체들을 후보 영상으로 압축하게 되며 마지막으로 객체의 색상 히스토그램에 의하여 검색이 수행된다. 실험 결과 제안된 알고리즘은 분할된 객체의 공간적, 시각적 특징을 이용하여 효율적으로 검색을 수행할 수 있음을 보여준다.

Keywords

References

  1. Proceedings ICIP98 3 MPEG-7 standardization Activities M. Ibrahim Senzen;Richard J.Qia-n.
  2. Technical Report RJ 9951-57910 Automatic and semiautomatic methods for image annotation and retrieval in QBIC J. Ashley;R. Barber;M. Flickner;J. Hafner;D. Lee;W. Niblack;D. Petkovic
  3. In CVPR ‘97 Recognition of images in large in large databases using color and texture H. Greenspan;S. Belongie;C. Carson;J. Malik
  4. ACM Multimedia 96 Visual-SEEK: a fully automated conte-nt based image query system John R. Smith;Shi-Fu Chang
  5. Int. J. Comp. Vis. v.18 no.3 Photobook: Content-based manipulation of image databases A. Pentland;R. Picard;S.Sclaroff
  6. IEEE Computer Society Color and Texture Based Image Segmentation Using EM and Its Application to Content-Based Image Retrieval Serge Belongie;Chad Carson;Hayit Greenspan;jitendra Malik
  7. J. Royal Soc. Statist. Series B. no.1 Maximum likelihood from incomplete data via the EM algorithm A. P. Demper;N. M. Laird:D. J. Rubin
  8. Pattern Recognition in Practice Ⅳ Initializing the EM Algorithm for use in Gaussian Mixture Modeling Patricia McKenzie;Michael Alder
  9. IEEE Trans. Image Processing v.7 no.4 Prediction of Image Partitions Using Fourier Descriptors: Application to Segmentation-Based Coding Schemes F. Marques;B. Llorens;A. Gasull
  10. Image based Measurement Systems Ferdinand van der Heijden
  11. Pattern Recognition Letters v.16 no.3 Color matching for image Retrieval Babu M. Mehtre;Mohan S. Kankanhalli;A Desai Narasimhalu;Guo Chang Man
  12. SPIE 95 Similarity of Color Images Markus Stricker;Markus Orengo