Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation

被引：6
作者：
Banic, Nikola [1 ]
Loncaric, Sven [1 ]
机构：
[1] Univ Zagreb, Fac Elect Engn & Comp, Unska 3, HR-10000 Zagreb, Croatia
来源：
JOURNAL OF IMAGING | 2018年 / 4卷 / 11期
关键词：
chromaticity; color constancy; gray-edge; gray-world; green; illumination estimation; shades-of-gray; standard deviation; unsupervised learning; white balancing;
D O I：
10.3390/jimaging4110127
中图分类号：
TB8 [摄影技术];
学科分类号：
0804 ;
摘要：
In the image processing pipeline of almost every digital camera, there is a part for removing the influence of illumination on the colors of the image scene. Tuning the parameter values of an illumination estimation method for maximal accuracy requires calibrated images with known ground-truth illumination, but creating them for a given sensor is time-consuming. In this paper, the green stability assumption is proposed that can be used to fine-tune the values of some common illumination estimation methods by using only non-calibrated images. The obtained accuracy is practically the same as when training on calibrated images, but the whole process is much faster since calibration is not required and thus time is saved. The results are presented and discussed. The source code website is provided in Section Experimental Results.
引用
收藏
页数：11
相关论文
共 47 条
  • [1] Bani N., COLOR CONSTANCY IMAG
  • [2] Banic Nikola, 2015, 10th International Conference on Computer Vision Theory and Applications (VISAPP 2015). Proceedings, P136
  • [3] Banic Nikola, 2015, 10th International Conference on Computer Vision Theory and Applications (VISAPP 2015). Proceedings, P129
  • [4] Banic N., 2013, P 2 CROATIAN COMPUTE, P3
  • [5] Banic N, 2015, INT SYMP IMAGE SIG, P131, DOI 10.1109/ISPA.2015.7306046
  • [6] Banic N, 2014, IEEE IMAGE PROC, P605, DOI 10.1109/ICIP.2014.7025121
  • [7] Color Cat: Remembering Colors for Illumination Estimation
    Banic, Nikola
    Loncaric, Sven
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (06) : 651 - 655
  • [8] Banic N, 2014, INT CONF DIGIT SIG, P345, DOI 10.1109/ICDSP.2014.6900684
  • [9] A comparison of computational color constancy algorithms - Part I: Methodology and experiments with synthesized data
    Barnard, K
    Cardei, V
    Funt, B
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2002, 11 (09) : 972 - 984
  • [10] Fast Fourier Color Constancy
    Barron, Jonathan T.
    Tsai, Yun-Ta
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6950 - 6958
12345