DOI QR코드

DOI QR Code

Content-based Image Retrieval Using HSV Color and Edge Orientation

HSV 색상과 에지 방향을 이용한 내용기반 영상 검색

  • 송주환 (전주대학교 스마트미디어학과)
  • Received : 2018.04.07
  • Accepted : 2018.05.06
  • Published : 2018.05.31

Abstract

In this paper, we propose a content-based image retrieval system using hue and value of the HSV color model and edge orientation. The proposed algorithm converts an RGB color image into an HSV color image, and then finds the edge orientation using the hue and the value. The values, which are obtained by quantizing the hue, value, and edge orientation, respectively, are defined as feature vectors of the image. The feature vectors of each image are stored in the database and then compared with the feature vector of the input image. The retrieval performance was tested using 1000 images of Corel 1000 database. Experimental results show that the proposed method retrieves images more effectively than the standard color histogram method, the color difference histogram method, and the color corelogram method. The average precision for the top 20 was 0.06, 0.01, and 0.10 higher than the comparison methods.

논문에서는 HSV의 색상과 에지 방향을 이용한 내용기반 영상 검색 방법을 제안한다. 제안된 알고리즘은 RGB 색상의 영상을 HSV 색상의 영상으로 변환한 뒤 색조(Hue)와 명도(Value)를 이용하여 에지 방향을 구한다. 색조와 명도, 그리고 에지 방향을 각각 양자화 한 후 모은 값을 영상의 특징벡터로 정의한다. 각 영상의 특징벡터는 데이터베이스에 저장한 후 질의로 입력된 영상의 특징벡터와 비교하여 유사영상들을 검색한다. 사용한 영상은 Corel 1000 데이터베이스의 영상 1000개이고, 이를 사용하여 검색 성능을 분석하였다. 실험한 결과 제안된 방법을 색상 정보만을 이용한 방법과 색상 차에 대한 히스토그램을 이용한 방법, 색상에 대한 코렐로 그램을 이용한 방법과 비교하였더니 상위 20개에 대한 평균 정확률에 대한 비교 결과 제안 방법이 각각 0.06, 0.01, 0.10 더 높게 나와 더 우수함을 알 수 있었다.

Keywords

References

  1. Y. E. An, “Image Retrieval Using Rearranged Color Histogram,” Journal of KIIT, Vol. 14, No. 1, pp. 85-91, Jan. 2016.
  2. J. W. Song, “Content-based Image Retrieval using Histogram and Motif Correlogram of HSV Color Images,” Journal of KIIT, Vol. 14, No. 5, pp. 181-186, May 2016.
  3. M. J. Swain and D. H. Ballard, “Color indexing,” International Journal of Computer Vision, Vol. 7, No. 1, pp. 11-32, July 1991. https://doi.org/10.1007/BF00130487
  4. G. Pass and R. Zabih, "Histogram refinement for content-based image retrieval," IEEE Workshop on Applications of Computer vision, pp. 96-102, Dec. 1996.
  5. G. H. Liu and J. Y. Yang, "Content-based image retrieval using color difference histogram," Pattern Recognition 46, pp. 188-198, Jan. 2013. https://doi.org/10.1016/j.patcog.2012.06.001
  6. S. Murala and R. P. Maheshwari, “Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval,” IEEE Transactions on Image Processing, Vol. 21, No. 5, pp. 2874-2886, May 2012. https://doi.org/10.1109/TIP.2012.2188809
  7. S. M. Singh and K. Hemachandran, “Content-Based Image Retrieval using Color Moment and Gabor Texture Feature,” International Journal of Computer Science Issues, Vol. 9, No. 5, pp. 299-309, Sep. 2012.
  8. J. W. Song, “Content-based Image Retrieval using HSV Color and Uniform Local binary Patterns,” Journal of Korean Institute of Information Technology, Vol. 12, No. 6, pp. 169-174, June 2014.
  9. M. S. An, S. W. Ha, and D. S. Kang, “Object Tracking Method based on Particle Filter with Color and Texture Information,” Journal of Korean Institute of Information Technology, Vol. 8, No. 11, pp. 225-230, Nov. 2010.
  10. J. Li, J. Z. Wang, and G. Wiederhold, “SIMPLIcity: Semantics-sensitive Integrated Matching for Picture Libraries,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 9, pp. 947-963, Sep. 2001. https://doi.org/10.1109/34.955109
  11. A. N. Fierro-Radilla, G. Calderon-Auza, M. Nakano-Miyatake, and H. M. P?rez-Meana, "Motif Correlogram for Texture Image Retrieval," Intelligent Software Methodologies, Tools and Techniques, Vol. 532, pp. 496-505, Sep. 2015.

Cited by

  1. A Study on Vehicle Tracking System using Raspberry Pi vol.21, pp.5, 2020, https://doi.org/10.9728/dcs.2020.21.5.1009
  2. Image Analysis and Dimension Reduction for Color-texture Space using IOCLBP vol.19, pp.9, 2018, https://doi.org/10.14801/jkiit.2021.19.9.87