Improving color constancy by selecting suitable set of training images
Improving color constancy by selecting suitable set of training images
复制标题
通过选择合适的训练图像集来提高颜色稳定性
DOI：
10.1364/oe.27.025611
复制
发表时间：
2019-09-02
期刊：
影响因子：
3.8
通讯作者：
Li, Yong-Jie
中科院分区：
文献类型：
--
作者：
Gao, Shao-Bing;Zhang, Ming;Li, Yong-Jie
基于回归的颜色恒常性（CC）方法具有非常简单的实现，最近通过将校正矩阵应用于一些基于低水平的CC算法的结果而获得了非常有竞争力的性能。然而，大多数基于回归的方法，例如，校正矩（CM），对所有测试图像应用相同的校正矩阵。考虑到捕获的图像颜色通常由各种因素（例如，光源和表面反射率），在不考虑图像之间的内在差异的情况下对不同的测试图像应用相同的校正显然不够合理。在这项工作中，我们首先从数学上分析了可能影响基于回归的CC性能的关键因素，然后我们设计了原则性规则来自动选择合适的训练图像，以学习每个测试图像的最佳校正矩阵。利用该策略，原始的基于回归的CC（例如，CM）明显得到了改进，以在四个广泛使用的基准数据集上获得更具竞争力的性能。我们还表明，尽管这项工作的重点是改进基于回归的CM方法，但所提出的自动训练数据选择策略的一个值得注意的方面是它适用于解决颜色恒定性问题的几种代表性的基于回归的方法。(C)根据OSA开放获取出版协议的条款，2019年美国光学学会
With very simple implementation, regression-based color constancy (CC) methods have recently obtained very competitive performance by applying a correction matrix to the results of some low level-based CC algorithms. However, most regression-based methods, e.g., Corrected Moment (CM), apply a same correction matrix to all the test images. Considering that the captured image color is usually determined by various factors (e.g., illuminant and surface reflectance), it is obviously not reasonable enough to apply a same correction to different test images without considering the intrinsic difference among images. In this work, we first mathematically analyze the key factors that may influence the performance of regression-based CC, and then we design principled rules to automatically select the suitable training images to learn an optimal correction matrix for each test image. With this strategy, the original regression-based CC (e.g., CM) is clearly improved to obtain more competitive performance on four widely used benchmark datasets. We also show that although this work focuses on improving the regression-based CM method, a noteworthy aspect of the proposed automatic training data selection strategy is its applicability to several representative regression-based approaches for the color constancy problem. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement