Human Face Recognition

Human Face Recognition

Author Name : Iram Naim, Pankaj

ABSTRACT

Face recognition is an important application of Image processing owing to it's use in many fields. The paper presented here was developed after study of various face recognition methods and their efficiencies.In this majorpaperan approach is given for the detection and recognition of human faces and describes a working, near-real time face recognition system that recognizes the person with the help of eigenfaces of known individuals. Our approach treats faces recognition as a two –dimensional problem, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-d characteristic views. This approach is known as principal of component analysis. The face space is define by the “Eigencore ” ,which are Eigenvector of the set of faces.Eigenfaces (and eigenimages) are created using a mathematical technique called Principal Components Analysis (PCA).All images are grayscale (intensity levels of gray are taken as image features).There are variations in facial expression (open/closed eyes,smiling/non-smiling). There should uniformity in the images' size,resolution, and brightness ,a dark homogeneous background and the subject is photographed in an upright, frontal position. The recognition process relies on a training phase involving multiple facial images, with associated names.The approach has advantage over other face recognition schemes in its speed, simplicity, learning capacity and relative insensitive to small or gradual change in the face images.