HIGH ACCURACY FACE REORGANIZATION BY PCA - SVDJournal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.5, No. 11)
Publication Date: 2016-11-30
Authors : Rahul Jain; Sanjay Kumar;
Page : 5-10
Keywords : Face Recognition; Principle Component Analysis (PCA); Eigenface; Covariance matrix; Face database.;
Face Detection or Reorganization is a Part of biomedical technology which is working for the many applications like Banking, Human - Computer interaction, Implementation Security, Retrieval of Data Base, etc. Base paper is using Principal Component Analysis (PCA) for Face Detection. PCA is a methodology for the Face Detection which is using for reducing the variable in th e Face Reorganization. The image in the training set can be represented as linear combination of Eigen Vector which is called by "Eigen Faces". From the Covariance Matrix, we can get the Eigen Vectors of training Image set called the basic function. For Fa ce Reorganization in PCA method, the test image is projected onto subspace with the help of Eigen Faces and the for Face Reorganization. Distance will measure such as Euclidean distance. All the test images will check by this method for Face Reorganization . In this Research , we are improving the Accuracy of the Face reorganization system by use PCA+SVD .We are taking the training data sets of different faces for recognize the face . From the result session, we can see the Accuracy of face detection . Accu racy is getting increase as we apply PCA+SVD.
Other Latest Articles
Last modified: 2016-11-07 17:50:35