Seow Ming-Jung, Asari Vijayan K
Electrical and Computer Engineering Department, Old Dominion University, Norfolk, VA 23529, USA.
Neural Netw. 2009 Jan;22(1):91-9. doi: 10.1016/j.neunet.2008.09.010. Epub 2008 Oct 9.
In this paper, we propose the concept of a manifold of color perception through empirical observation that the center-surround properties of images in a perceptually similar environment define a manifold in the high dimensional space. Such a manifold representation can be learned using a novel recurrent neural network based learning algorithm. Unlike the conventional recurrent neural network model in which the memory is stored in an attractive fixed point at discrete locations in the state space, the dynamics of the proposed learning algorithm represent memory as a nonlinear line of attraction. The region of convergence around the nonlinear line is defined by the statistical characteristics of the training data. This learned manifold can then be used as a basis for color correction of the images having different color perception to the learned color perception. Experimental results show that the proposed recurrent neural network learning algorithm is capable of color balance the lighting variations in images captured in different environments successfully.
在本文中，我们通过实证观察提出了颜色感知流形的概念，即在感知相似环境中图像的中心-环绕特性在高维空间中定义了一个流形。可以使用一种基于新型递归神经网络的学习算法来学习这种流形表示。与传统递归神经网络模型不同，在传统模型中记忆存储在状态空间中离散位置的吸引不动点上，而所提出的学习算法的动力学将记忆表示为一条非线性吸引线。围绕非线性线的收敛区域由训练数据的统计特征定义。然后，这个学习到的流形可以用作对具有与学习到的颜色感知不同的颜色感知的图像进行颜色校正的基础。实验结果表明，所提出的递归神经网络学习算法能够成功地对在不同环境中捕获的图像中的光照变化进行颜色平衡。
