“Who are there in the movie” — The improved approach for person recognition from the movie

Even if automatic face recognition has shown great achievement for high-quality images under embarrassed conditions, for video-based recognition it is hard to achieve similar levels of performance. In this paper, two popular face recognition methods, the Eigenface and the Fisherface have been implemented and the simulated output of the same has been described. The Eigenface is the first method well thought-out as a successful method of face recognition. This method uses Principal Component Analysis to linearly project the image space to a low dimensional feature space. The Fisherface method is an improvement of the Eigenface method that it uses Fisher's Linear Discriminant Analysis for the dimensionality reduction. The Fisherfaces concept maximizes the ratio of between-class scatter to that of within-class scatter; therefore, it works better than PCA for intention of discrimination. The Fisherface is particularly useful when facial images have large variations in illumination and facial expression. In this paper, Fisherface methods respect to facial images having large illumination variations is examined over a more than 1,15,000 frames of various movies. The proposed face-recognition technique significantly outperforms traditional subspace-based approaches particularly in very low-dimensional representations; here the proposed method has been compared with the PCA based method in the same context with the base of videos.