The developed system titled “I Know You (IKY)” is a face recognition system having the capability to detect the face, add the face to the learning set and finally use those faces from the learning set to recognize the input face. Technique used for detection and recognition of the face in this application is Principle Component Analysis (PCA). The main idea behind the use of PCA for the face recognition is to construct a large 1-D vector of pixel from 2-D facial images. And then express those large 1-D vectors of pixel into the compact principle components of the feature space. This can be called eigenspace projection. Eigen space is calculated by identifying the Eigen vectors of the covariance matrix derived from the set of facial images (vectors). Now the face images is transformed into a small set of characteristic feature images called “Eigen faces”, which are the principle components of the initial training set of face images. Finally recognition is performed by projecting the new image into the faces space and then classifying the face by calculating its position in the face space and comparing its position with the position of known faces in the training set. The comparison of the new face and faces in the training set is done by comparing Euclidian distance. The face for which the Euclidian distance from new (unknown) face is minimum is the best match of the unknown face. Hence the new face is recognized.

Share with your friends


Post Your Comment

Please Login to Comment