Face recognition is one of the most crucial component in computer vision and human interaction. Our project’s main concern is to mark attendance using face recognition with highest efficiency. Face recognition system consist of principal component analysis(PCA)[3] which is used to reduce the dimension of an image by feature extraction on the basis of illumination, intensity of particular region of common behavior identify in particular object. The algorithm calculate eigen value and eigenvector from covariance matrix of a training image set. The most variant data to a particular region is known as first principal component and component orthogonal to first principal component is known as second principal component. Face recognition is done by using support vector machine algorithm[1]. the input data as an image is matched with our application database and matched information will circulate to relative mentor .Haar cascade classifier is used to classify the various component of the images . The eye blinking motion will be detected to ensuring about real face not an face from any photograph.