Downloads: 131 | Views: 188
Case Studies | Computer Science & Engineering | India | Volume 6 Issue 4, April 2017
Study on Recognizing the Human Face under Invariant Pose, Illumination and Expression using LBP, LoG and SVM
Abstract: Face recognition system uses human face for the identification of the person. Face recognition is a very difficult task there is no separate method that provide an accurate and efficient solution in all the situations like the face image with different pose, illumination and expressions. Local Binary Pattern (LBP) and Laplacian of Gaussian (LoG) operators. Support Vector Machine classifier is used to recognize the human face. The LoG algorithm is used to preprocess the image to detect the edges of the face image to get the image information. The LBP operator divides the face image into several blocks to generate the features information on pixel level by creating LBP labels for all the blocks of image is obtained by concatenating all the individual local histograms. Support Vector Machine classifier (SVM) is used to classify the image. The algorithm performance is verified under the constraints like illumination, expression and pose variation.
Keywords: Face Recognition, Local Binary Pattern, Laplacian of Gaussian, histogram, illumination, pose angle, expression variations, SVM
Edition: Volume 6 Issue 4, April 2017,
Pages: 957 - 959