الفهرس 
Literature OverviewOnly 14 pages are availabe for public view
 |  | from | 15 |  |  |
| | | from | 15 | | |
Abstract
Face recognition is a form of biometric identification that relies on data acquired from the face of an individual. This data, which can be either twodimensional or three dimensional in nature, is compared against a database of individuals. In recent years, face recognition has gained popularity among researchers all over the world. With applications ranging from security to entertainment, face recognition is an important subset of biometrics. In real world applications, it is desirable to have a stand-alone, embedded face recognition system. The reason is that such systems provide a higher level of robustness. Face recognition from video is one of the challenges problems in image processing that concerned with determining which part of an image contains face with its features such as eyes, nose, eyebrows and mouse. Some of these problems The person’s face is exposed to very different illumination conditions, Different size scales, Different face expressions, and People don’t look into the camera and show quite a lot of orientation. The main objective of this work is to recognize human faces from video with different backgrounds and different directions of faces. By treating with different videos that the proposed system uses genetic algorithm (GA) to achieve better recognition rates. Each frame in each video is normalized to the predefined scale, to make any comparison between the template and any given image of different size isn’t a problem, then GA starts searching of human faces in complex backgrounds and different directions of faces. Face recognition is achieved by employing template matching between a known face image and the converted image. GA is a blind search technique which is used for searching possible facial regions in video. GA is developed to provide efficient techniques for optimization and machine learning applications through application of principles of evolutionary biology to compute science such as inheritance, mutation, natural selection, and recombination. It is a heuristic method that uses the idea of survival of the fittest. Some advantages of GA that uses more individuals so that they are less likely to get struck in a local extreme and easy to implement a new chromosome and fitness function to solve a new problem.