Earticle

초록

영어

Dark images are acquired under low light level condition and they have some weakness about image contrast and distortion of color. However, the most studies about dark image tried not to recover colors of the image, but to improve the image contrast. For this reason, we propose the method combined with the tone mapping and MSRCR in order to recovering the original color. We consider the tone mapping to control brightness of the image and the MSRCR to recover the original color. As experimental images, we employed synthesized images, created from the Barnard’s data set. We also consider the Euclidean distance and the angular error between images as the evaluation factors. The performance of the proposed method was evaluated by two experiments. First, we carried out the performance comparison of our method and some well-known color constancy methods. Secondly, we analyzed the performance according to change parameters of MSRCR. The experimental results tell us that the proposed method is more suitable for recovering the color of the dark images than the other methods.

목차

Abstract
 1. Introduction
 2. Proposed Tone Mapping Method
 3. Color Restoration by MSRCR
 4. Experiment
  4.1. Experimental Data
  4.2. Evaluation Factors
  4.3. Performance Evaluation
 5. Conclusion
 Acknowledgements
 References

키워드

저자

• Woo-Ram Lee [ Dept. Of Computer Eng., College of Electrical and Computer Eng., Chungbuk National Univ., Cheongju, Chungbuk, 316-768, Republic of Korea ]
• Dong-Guk Hwang [ Dept. Of Computer Eng., College of Electrical and Computer Eng., Chungbuk National Univ., Cheongju, Chungbuk, 316-768, Republic of Korea ]
• Byoung-Min Jun [ Dept. Of Computer Eng., College of Electrical and Computer Eng., Chungbuk National Univ., Cheongju, Chungbuk, 316-768, Republic of Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Software Engineering and Its Applications

• 간기

  월간

• pISSN

  1738-9984

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605