FACE RECOGNITION ACROSS NON-UNIFORM MOTION BLUR, ILLUMINATION, AND POSE
Author(s):
M.Ramesh kumari
Keywords:
Face recognition, SVM, Matlab
Abstract
Face recognition algorithms perform very unreliably when the pose of the probe face is different from the stored face typical feature vectors vary more with pose than with identity. In the existing Approaches for performing face recognition in the presence of blur are based on the convolution model and cannot handle non-uniform blurring situations that frequently arise from tilts and rotations in hand-held cameras. In this project, we propose a face recognition algorithm that is robust to non-uniform motion blur arising from relative motion between the camera and the subject. Our project addresses the problem of recognizing faces across blur and illumination. Taken a set of images obtained by Dataset which is called as probe image and gallery images. Each synthesize gallery image, obtained the nine bases each synthesize gallery image find the optimal TSF and illumination coefficients. Transform the synthesize gallery images. Compare the LBP features of the probe images with those of the transformed gallery images and also to classify the SVM classifier both gallery and probe images which performs almost as fast as the recognition method to find the closest match.
Article Details
Unique Paper ID: 147004
Publication Volume & Issue: Volume 5, Issue 3
Page(s): 47 - 53
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024