ICA filters for lighting invariant face recognition
ICA filters for lighting invariant face recognition
复制标题
DOI：
10.1109/icpr.2004.1334120
复制
发表时间：
2004-08
期刊：
影响因子：
--
通讯作者：
J. Fortuna;D. Capson
中科院分区：
文献类型：
--
作者：
J. Fortuna;D. Capson
利用独立成分分析（ICA）的滤波器的建设光照不变的人脸识别的影响。伊卡用于提供滤波器，该滤波器作为预处理步骤应用于数据库的低维PCA子空间表示。使用支持向量分类器对来自面部数据库的在不同照明下成像的测试面部进行分类。将伊卡预滤波识别结果与使用各种空间分辨率的LoG（高斯拉普拉斯）滤波器和无预滤波的识别结果进行了比较。伊卡预过滤器被证明是非常有效的，在选择性地减少对象和人脸识别中的照明方差的影响，而不需要调整过滤器的方向和空间分辨率的图像。
The use of ICA (independent component analysis) for the construction of filters for lighting invariant face recognition is investigated. ICA is used to provide filters which are applied as a pre-processing step to a low dimensional PCA subspace representation of the databases. Test faces imaged under varying illumination from a face database are classified using a support vector classifier. The ICA pre-filter recognition results are compared against those using LoG (Laplacian of Gaussian) filter of various spatial resolutions and no pre-filtering. The ICA pre-filters are shown to be very effective at selectively reducing the effect of illumination variance in object and face recognition without the need for tuning the filters to the orientations and spatial resolutions present in the images.