单一光照颜色恒常性计算研究进展

Advances Research on Color Constancy Computation under Single Illuminant

单一光照颜色恒常性计算研究是目前计算机视觉、机器学习等领域中最热门的研究课题之一。算法的合理性直接影响到自动白平衡等应用效果。目前颜色恒常性计算的方法多种多样,将其划分为无监督、有监督、算法的融合和颜色不变性描述的颜色恒常性计算方法。着重介绍了4类典型的颜色恒常性计算方法,分析了各自的优缺点。最后就颜色恒常性计算的性能评价方法以及发展趋势做了简单的论述。

Advances in color constancy computation under a signal illumination is one of the most popular topics in the computer vision and machine learning.The effect of image automatic white balancing and other applications is directly affected by the reasonableness of the algorithm.Currently,the existing methods on color constancy methods are various.This paper divided color constancy into the unsupervised,the supervised,the algorithms fusion and color invariant description.This paper highlighted four typical color constancy computation ways and analyzed their advantages and disadvantages respectively.Finally,we discussed the evaluation methods and trends of color constancy computation simply.