期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2015
卷号：20
期号：1
页码：45-49
DOI：10.14445/22312803/IJCTT-V20P109
出版社：Seventh Sense Research Group
摘要：The face biometric based person identification plays a major role in wide range of applications such as surveillance and online image search. The first stage starts with face detection will used to obtain face images, which also have the normalized intensity, which are uniform in size and also the shape and only the face region Here granular computing and spatial features will presented to match the face images in the various illumination changes. The Gaussian operator also generates a sequence of low pass filter images by convolving each of constituent images with a 2D Gaussian kernel. By this granulation method, facial features are segregated at dissimilar resolutions to provide edge details, noise, level of smoothness, and presence of blurriness in a face image. In this features extraction, WLD descriptor represents an image as a histogram of differential excitations and gradient locations, and several interesting properties like robustness to noise and illumination transforms, effective detection of edges and powerful image representation.
