Independent component analysis applied to feature extraction from colour and stereo images
Independent component analysis applied to feature extraction from colour and stereo images
复制标题
DOI：
10.1088/0954-898x/11/3/302
复制
发表时间：
2000-08-01
影响因子：
7.8
通讯作者：
Hyvärinen, A
中科院分区：
文献类型：
--
作者：
Hoyer, PO;Hyvärinen, A
以前的工作表明，独立成分分析（伊卡）应用于自然图像数据的特征提取产生类似于Gabor函数和简单细胞感受野的功能。本文认为，包括色彩和立体声信息的影响。颜色的包含导致特征被划分为单独的红色/绿色、蓝色/黄色和亮/暗通道。另一方面，立体图像数据导致被调谐到各种视差的双目感受野。这些结果与观察到的初级视皮层中简单细胞的特性之间的相似性进一步证明了视觉皮层神经元执行某种类型的冗余减少的假设，这是伊卡最初的动机之一。此外，伊卡提供了从彩色和立体图像中提取特征的原则性方法;这些特征可用于图像处理操作，如去噪和压缩，以及模式识别。
Previous work has shown that independent component analysis (ICA) applied to feature extraction from natural image data yields features resembling Gabor functions and simple-cell receptive fields. This article considers the effects of including chromatic and stereo information. The inclusion of colour leads to features divided into separate red/green, blue/yellow, and bright/dark channels. Stereo image data, on the other hand, leads to binocular receptive fields which are tuned to various disparities. The similarities between these results and the observed properties of simple cells in the primary visual cortex are further evidence for the hypothesis that visual cortical neurons perform some type of redundancy reduction, which was one of the original motivations for ICA in the first place. In addition, ICA provides a principled method for feature extraction from colour and stereo images; such features could be used in image processing operations such as denoising and compression, as well as in pattern recognition.