Description

Face recognition has been one of the most interesting and important research fields in the past two decades. The reasons comefrom the need of automatic recognitions and surveillance systems , the interest in human visual system on face recognition, and the design of human-computer interface, etc.we propose a novel technique of recognizing 3d face images using the face annotation.For initially we construct the 3d face images. In that images we detecting the face parts.The detected face parts is passed to ICP Feature Extraction. It is transformed to best match the reference. The algorithm iteratively revises the transformation needed to minimize the distance from the source to the reference point cloud.The extracted features passed to the recognition. Based on the Euclidean calculation, The result is predicted.In existing LDA is used for the feature extraction. The standard LDA can be seriously degraded if there are only a limited number of observations N compared to the dimension of the feature space n. LDA doesn’t change the location but only tries to provide more class separability and draw a decision region between the given classes. 3D reconstruction from multiple images is the creation of three-dimensional models from a set of images.It is the reverse process of obtaining 2D images from 3D scenes. We calculating the correct classification rate. It is identified based on the true positive and false positive of the recognition. Based on this accuracy we calculate the performance of our system.Here we have shown the 3d face recognition process with help of Euclidean distance and ICP features.It shows the better performance than the existing system