Face Recognition Technology

Face Recognition Based on Genetic Algorithms For Feature Correlation

Download now Matlab source code
Requirements: Matlab, Matlab Image Processing Toolbox.

Human face recognition is currently a very active research area with focus on ways to perform robust and reliable biometric identification. Face recognition, the art of matching a given face to a database of known faces, is a non-intrusive biometric method that dates back to the 1960s. In efforts going back to far earlier times, people have tried to understand which facial features help us perform recognition tasks, such as identifying a person, deciding on an individual's age and gender, and classifying facial expression and even beauty. A recognition system has to be invariant both to external changes, like environmental light, partial occlusions and the person's position and distance from the camera, and internal deformations, like facial expression and aging. Because most commercial applications use large databases of faces, recognition systems have to be computationally efficient. We have developed a code to perform face identification using a Genetic algorithm-optimized Minimum Average Correlation Energy (MACE) filtering technique. The performances of the proposed algorithm are evaluated using Facial Expression Database collected at the Advanced Multimedia Processing Lab at Carnegie Mellon University (CMU). Database consists of 13 subjects, each with 75 images. The size of each image is 64×64 pixels, with 256 grey levels per pixel. A 5×5 filter has been designed using genetic algorithms. With GA Feature Correlation we have achieved an EER equal to 3.70%.

Index Terms: Matlab, source, code, correlation, filters, face, recognition, identification, system, MACE, GA, genetic, algorithm.

Release 1.0 Date 2011.07.08
Major features:

• One-to-many (1:N) face identification
• One-to-one (1:1) face verification
• Code for genetic algorithm optimization
• High recognition rate
• Fast and optimized implementation
• Easy and intuitive GUI
• Demo code (protected P-files) available for performance evaluation