Pose Invariant Face Recognition using PCA

Both face detection and recognition are very curious areas in the field of image analysis, computer vision and pattern recognition that has received a big deal of attention over the last few years. It has been widely used for the purpose of security and forensic science for identify of an individual e.g. at the place of video surveillance, airports, traffic, terrorist attacks.To analyze the information of face images: faster, robust and efficient face detection and recognition algorithms are required. This system has been facing problems in recognizing subjects of varying poses, illumination conditions, facial expressions, and face occlusions. Due to variation in pose relative to camera certain features like smile, open eyes or mouth, left side or right side of mouth or eyes, occluded mouth or eyes can’t be detected and extracted properly. It will be a critical task to detect a person with varying poses in vertical direction. In this work we present,face detection is performed by skin tone. Through PCA extract features and system is getting trained and tested. For face recognition process, Euclidean distance is measured and based on that minimum distance face is recognized.