Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

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

Extraction of Representative Color of Digital Images Using Histogram of Hue Area and Non-Hue Area

색상영역과 비색상영역의 히스토그램을 이용한디지털 영상의 대표색상 추출

  • Kwak, Nae-Joung (Hanbat National University Dept. Electronic engineering) ;
  • Hwang, Jae-Ho (Hanbat National University Dept. Electronic engineering)
  • 곽내정 (한밭대학교 전자공학과) ;
  • 황재호 (한밭대학교 전자공학과)
  • Published : 2010.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

There have been studied with activity about color standard due to extention of digital contents' application area. Therefore the studies in relation to the standard are needed to represent image's feature as color. Also the methods to extract color's feature to be apt to various application are needed. In this paper, we set the base color as 50 colors from Munsell color system, get the color histogram to show the characteristics of colors's distribution of a image, and propose the method to extract representative colors from the histogram. Firstly, we convert a input image of RGB color space to a image of HSI color space and split the image into hue area and non-hue area. To split hue area and non-hue area, we use a fixed threshold and a perception-function of color area function to reflect the subjective vision of human-being. We compute histograms from each area and then make a total histogram from the histogram of hue area and the histogram of hue area, and extract the representative colors from the histogram. To evaluate the proposed method, we made 18 test images, applied conventional methods and proposed method to them Also the methods are applied to public images and the results are analyzed. The proposed method represents well the characteristics of the colors' distribution of images and piles up colors' frequency to representative colors. Therefore the representative colors can be applied to various applications

디지털 콘텐츠의 응용분야가 확산되면서 디지털 콘텐츠의 색상을 표준화하기 위한 연구가 활발히 진행되고 있다. 따라서 색상을 이용한 영상의 특징을 표현하는 방법도 표준화에 준한 연구가 필요하다. 또한 다양한 응용분야에 사용될 수 있는 색상 특징을 추출하는 방법도 필요하다. 본 논문에서는 디지털 표색계의 근간이 되는 먼셀좌표계를 기본으로 하여 기준색상을 50색상으로 정의하고 영상 내 색상의 분포 특성을 알 수 있는 히스토그램을 구하고 영상을 대표할 수 있는 대표색상을 추출한다. 제안 방법의 성능을 평가하기 위해 18개의 실험영상을 만들어 기존의 방법과 제안방법을 적용하였으며 일반영상에도 적용하여 그 결과를 분석하였다. 제안방법을 적용한 결과영상은 영상 내에 존재하는 색상의 분포 특성을 잘 나타내주며 대표색상으로 빈도가 집중함으로 영상의 대표색상을 이용하여 다양한 응용분야에 적용이 가능하다.

Keywords

References

  1. J. C. Russ, The Image Processing Handbook, 2nd ed, Boca Raton, FL: CRC, 1995.
  2. R. C. Gonzalez, and R. E. Woods, Digital Image Processing, 2nd, Prentice Hall, 2002.
  3. A. Glassner, Principles of Digital Image Synthesis, ser. The Morgan Kaufman Series in Computer Graphics and Geometric Modeling. San Francisco, CA:Morgan-Kaufamann, 1995.
  4. M. Swain and D. Ballard, "Color Indexing," Int. J. Comput. Vision, vol. 7, no. 1, pp.11-32, 1991 https://doi.org/10.1007/BF00130487
  5. P. K. Sahoo, S. Soltani, A. K. C. Wong, and Y. C. Chen, "A Survey of thresholding techniques," Comput. Vis. Graph. Image Process., vol. 41, pp. 233-260. 1988. https://doi.org/10.1016/0734-189X(88)90022-9
  6. X.Wan and C.-C.Kuo, "Color distribution analysis and quantization for image retrieval," in SPIE Storage and Retrieval for Image and Video Databases IV, vol SPIE 2670, Feb, 1996, pp.9-16
  7. M. T. Orchard, C. A. Bouman, "Color quantization of images," IEEE Trans. Signal Process, vol. 39. no. 2, pp.2677-2690, 1991. https://doi.org/10.1109/78.107417
  8. M. Gervautz and W.Purgatathofer, A. Simple Method for Color Quantization: Octree Quantization:Octree Quantization, San Diego, CA: Academic, 1990.
  9. Xia Wan and C.-C. Jay Kuo, "A New Approach to Image Retireval With Hierarchical Color Clustring," IEEE Trans. Circuit and Sys. for Video Tech., vol. 8, no. 5 1998.
  10. G. A. Agoston, Color Theory and its Application in Art and Design, New York Springer- Verlag Berlin Heidelberg, 1979, pp.85-95
  11. 한국공업표준협회, KS A 0011 물체의 색이름, 1987.