Face recognition using contourlet-based features and hybrid PSO-neural model

Performance Evaluation of Hybrid Swarm Intelligence Techniques for Extraction and Recognition of Facial Features

“…Recently PSO has been applied as an effective optimizer in many domains such as training artificial neural networks, linear constrained function optimization, wireless network optimization, and data clustering [2]. PSO is a population based stochastic optimization method which involves a number of particles flying around in the search space, where the position of each particle signifies a possible solution to the optimization problem [1]. ii.…”

“…The face recognition system can be defined as a 3 step process. The "feature extraction" is considered as a preclassification step in most image classification systems [1]. To recognize a face of a person, some features are to be extracted from the selected image.…”

“…are considered as the special features. In most of the cases, the extracted features play an important role in the performance of face recognition systems because they need to be selected with great care and can affect the further work [1]. As the images of persons are usually changed because of their expressions or are rotated and scaled, it is advisable to define (or design) the features of image so that these features always remain unchanged because of the above said changes.…”