Abstract: Face recognition has become a very popular field of research in computer vision, representing both a pattern recognition and biometric domain. It is preferable to many other biometric technologies because of its non-intrusive character and because it is very easy to use. Thus, facial recognition has a critical role in biometric systems and it is also attractive for numerous applications including visual surveillance, access control, robotics and security systems. Face detection and recognition represent two strongly-correlated computer vision processes. Face detection constitutes the first step for any automatic face recognition system. Although there has been a great amount of progress in face detection and recognition so far, numerous issues remain unsolved. In spite of several decades of extensive research the development of a computer-based artificial facial recognition system having capabilities comparable with those of human vision systems represents an unachieved goal. Research of human face detection has to confront many challenging problems, related to viewpoint, outdoor illumination, posing variation with large rotation angles, low image quality, low resolution, occlusion, and background changes in complex real-life scenes. Artificial face recognition is also quite difficult because of some factors, such as viewpoint, lighting conditions, facial expressions, aging effects and occlusions.
There are several known categories of face detection approaches: knowledge-based techniques, feature-based methods, appearance-based approaches and template matching methods. The template matching techniques have been the most investigated during our research. We proposed novel face detection approaches based on human skin identification. A skin detection algorithm based on explicitly defined regions is applied first, then a correlation-based template-matching process is performed on the detected skin regions. The most popular face recognition techniques include Eigenfaces, Fisherfaces, Linear Discriminant Analysis, Elastic Bunch Graph Matching, Hidden Markov Models, Gabor filtering and Dynamic Link Matching neuronal model. During our research we considered original facial recognition techniques based on Eigenfaces and Gabor filters. Our Eigenface-based approach is based on the influential work of Turk and Pentland, proposed in 1991. A continuous differential model for face fature extraction is provided, then the mathematical model is discretized. The second recognition technique uses Gabor filtering in the feature extraction stage. It applies a set of 2D Gabor filters, at various frequencies, orientations and standard deviations, on the facial images. An automatic supervised classifier is used in both face authentication cases.

Brief Biography of the Speaker:
Dr. Tudor Barbu is currently Senior Researcher II at the Institute of Computer Science of the Romanian Academy, Ia?i branch. He is the coordinator of an image and video processing research collective at this institute. Mr. Barbu has a PhD degree in Computer Science, awarded by the Faculty of Automatic Control and Computers of the University “Politehnica” of Bucharest.
He possess a remarkable research profile. In the last decade he published two books and four book chapters as single or main author. Also, dr. Tudor Barbu published more than 60 articles in prestigious international journals and volumes of international scientific events (conferences, symposiums and workshops). His prolific scientific activity also includes more than 30 research reports, elaborated with the institute research team coordinated by him or related to various research projects. His scientific publications have numerous citations, according to Google-Academic.
In recent years he also coordinated various research directions in 6 projects based on contracts/grants. Dr. Tudor Barbu received also several awards for his research results, the most important being the Romanian Academy Prize “Gheorghe Cartianu”, in the Information Science and Technology domain, awarded on December 18, 2008. He is member of several conference scientific committees and also member of scientific and technical committee and editorial review boards of some journals. He is the Editor in Chief of a book. His main scientific areas of interest are: digital media (audio, video and image) signal processing and analysis, pattern recognition, computer vision, multimedia information storage, indexing and retrieval, and biometric authentication using voice, face and digital fingerprint recognition.