In the emerging economy there is a new infrastructure, based on the internet, that is causing us to scrutinies most of our assumptions about the business. As a skin of networks - growing in ubiquity, robustness, bandwidth, and function - covers the skin of the planet, new models of how wealth is created are emerging.

Sunday, October 12, 2014

Face recognition system

Face recognition is a task that humans perform and effortlessly in daily lives. Face recognition has been studied for many years and has practical applications such as face-based access control system, security system and system automation based on computer vision.

The first automated face recognition system was developed by Takeo Kanade in his PhD thesis work in 1973. There was a dormant period in automatic face recognition until the work by Sirovich and Kirby on low dimensional face representation.

The systems generally include a database, known as gallery, consisting of facial images from a set of known subjects of interest.

It is one of the major biometric technologies, has become increasingly important owing to rapid advances in image capture devices (including surveillance cameras, camera in mobile phones), availability of huge amounts of face images on the web, and increased demands for higher security.

There have many efforts to design human face recognition systems some of which have employed artificial neural networks [TURK91] [SOL92] [CAST] [TOOL88] [MIDO88] {PERR90] and others [NAKA91] [WU90] [KAUF76] [WONG89], such as:
*Template matching of iso-density lines of subjects; faces
*Comparing of sizes/relative distance of facial features (nose, eyes, mouth) of subjects facial images

To build a reliable and robust face recognition system, one has to consider various issues:
*Computation and storage
*System engineering
*Security issue
Face recognition system

The most popular articles