Face Recognition Based On Image Sparse Representation And Singular Value Decomposition

. With the rapid development of computer technology and graphics technology, the computer patternrecognition problem which based on the face image has become a hot issue in recent years. Compared with otherbiometric identification technology, iris and finger prints for example, face recognition technology hastheadvantages of naturalness and imperceptibility. Therefore, face recognition has a broadprospect of application inidentity recognition, camera surveillance and so on.People have researched for over decades of time on face recognition, although some headway has been madeboth in theory and practical, the existing face recognition methodis limited in applications. There’s many elementsmake face recognition inaccurate,such as he selection of face feature,the quantities of training samples,theinfluence of light and shade,the change of posture,etc. Compared with other face recognition method, the onebased on sparse representation has a better recognition rate and robustness, but in the situation of less trainingsamples and characteristic vector dimension, the recognition rate is not ideal. Based on this kind of situation,amethod of face recognition based on singular value decomposition and sparse representation is brought in thispaper.The main work:1, First of all, an extraction method based both on global and local feature is brought forward while itsalgorithm principle is elaborated. This method is piecemeal the face image to get local characteristics in eachblock by using singular value decomposition,then get global characteristics by using singular value decompositionon global image.2, Secondly, a specific calculation process of face recognition based singular value decomposition and sparserepresentation is introduced.3, Finally,a specific method of solving sparse solution is introduced.The choices for the singular values ofglobal image and sub image has be discussed. By doing the experiment on YALE face database and analyzing theresults which come from the method that brought forward in this paper between the one come from the methodthat literature used, proves the method in this paper effective and stable.