Face recognition using eigenfaces

ABSTARCT :

We tried to develop a real time face detection and recognition system which uses an “appearance-based” approach. For detection purpose we used Viola Jones algorithm. To recognize face we worked with Eigen Faces which is a PCA based algorithm. In a real time to recognize a face we need a data training set. For data training set we took five images of each person and manipulated the Eigen values to match the known individual.

EXISTING SYSTEM :

? Facial features are removed and implemented through algorithms which are proficient and some notifications are done to improve the existing algorithm models. ? When compared to previous existing algorithm the proposed algorithm takes less time to run the program. ? Efficient face recognition by using Eigen face approach is presented. ? The proposed protected system is able to perform user recognition. ? To evaluate the reasonability of this way to deal with face recognition, we created an example set of face pictures with certain varieties of lighting and direction.

DISADVANTAGE :

? Indexing schemes and other techniques were developed to cope up with these problems. ? Many problems there are a number of interesting features in Eigenface method. ? It solves the problem by maximizing the ratio between class scatter to within-class scatter. ? It can be more problematic when there are extreme changes in the pose, expression or the person is in disguise. ? These problems decrease the efficiency of the system. These problems can be somewhat manageable but not totally avoidable.

PROPOSED SYSTEM :

• An unsupervised pattern recognition scheme is proposed in this paper which is independent of excessive geometry and computation. • The proposed methods were tested on Olivetti and Oracle Research Laboratory (ORL) face database. • The proposed technique is coding and decoding of face images, emphasizing the significant local and global features. • The proposed method is independent of any judgment of features (open/closed eyes, different facial expressions, with and without Glasses). • The proposed technique is analyzed by varying the number of eigenfaces used for feature extraction.

ADVANTAGE :

? Eigenfaces is a crucial component for the performance of a facial recognition system. ? But the background can change in the real world scenarios; this will hamper the recognition performance. ? Eigen Faces are used for: i) to get the appropriate facial info and ii) Efficiently produce facial image. ? To get related information in facial image, we need to encode it efficiently and relate the face with a dataset of images encoded in the same way. ? To learn and recognize faces of the preferred personal, building up the characteristic features by practice is an efficient way. ? when the dimensions of the face space is smaller than the number of face classes only that time the recognition system is efficient.