Color constancy based on local space average color
Color constancy based on local space average color
复制标题
DOI：
10.1007/s00138-008-0126-2
复制
发表时间：
2009-07-01
影响因子：
3.3
通讯作者：
Ebner, Marc
中科院分区：
文献类型：
--
作者：
Ebner, Marc
从对象反射的光因使用的光源类型而异。然而，对于人类观察者来说，物体的颜色似乎大致是恒定的。根据反射光计算颜色常量描述符的能力称为颜色恒定。为了解决颜色恒定的问题，必须做一些假设。一种常见的假设是，平均而言，世界是灰色的。我们解决了颜色恒定的问题，并重点讨论了使用空间平均颜色来实现颜色恒定。我们建议使用局部空间平均颜色，而不是计算全局空间平均颜色，因为光源在图像中经常变化。我们讨论了几种不同的计算局部空间平均颜色的方法。在一个目标识别任务上对不同算法以及相关算法的性能进行了评估。基于局部空间平均颜色的算法简单，但对颜色恒定问题非常有效。这样的算法特别适合于对象识别任务。
Light, which is reflected from an object, varies with the type of illuminant used. Nevertheless, the color of an object appears to be approximately constant to a human observer. The ability to compute color constant descriptors from reflected light, is called color constancy. In order to solve the problem of color constancy, some assumptions have to be made. One frequently made assumption is that on average, the world is gray. We address the problem of color constancy and focus on the use of space average color for color constancy. Instead of computing global space average color we suggest to use local space average color as the illuminant frequently varies across an image. We discuss several different methods on how to compute local space average color. The performance of the different algorithms as well as related algorithms is evaluated on an object recognition task. Algorithms based on local space average color are simple, yet highly effective for the problem of color constancy. Such algorithms are particularly suited for object recognition tasks.