15-11-2012, 03:33 PM
Face recognition via sparse representation
Face recognition.pdf (Size: 89.55 KB / Downloads: 42)
Abstract
This topic deals with automatic recognition of human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. It introduces a new mathematical framework for classification and recognition problems. The basic idea is to cast recognition as a sparse representation problem, utilizing new mathematical tools from compressed sensing and l1 minimization. The system uses tools from sparse representation to align a test face image to a set of frontal training images. This new framework provides new insights into two crucial issues in face recognition- feature extraction and robustness to occlusion as well as occlusion. This technology can be used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems. One key advantage of face recognition is that it does not require aid (or consent) from the test subject. Properly designed systems installed in airports, multiplexes, and other public places can identify individuals among the crowd whereas other biometrics like fingerprints, iris scans, and speech recognition cannot perform this kind of mass identification.