Face Recognition System

440 Words2 Pages
Biometric Face Recognition Systems Biometric face recognition system is an application for automatically identifying a person from the data that collected before from video sources. This is a common application for many companies nowadays. It is also the prevalence of mobile smartphone and successful implementation in visa applications and in criminal and military investigations. The main challenge for face recognition, as with any non-contact biometric, continues to be compensation for unconstrained individuals and environments and the use of low quality sensors. For example, face recognition on a low resolution video image taken outdoors with harsh shadows continues to be challenge, but a high resolution studio, booking photograph taken with controlled pose, lighting and background now performs well for many applications. The measured error rate in face recognition has continued to drop by half every two years. Other advances in face recognition include recognizing faces in a crowd and three-dimensional face recognition. This contributes to improved understanding of how biometrics can best be used for operational applications and provide tools to address known technological gaps. Automated face recognition is a relatively new concept. Developed in the 1960’s, the first semi-automated system for face recognition required the administrator to locate features on the photographs before it calculated distances and ratios to a common reference point, which were then compared to reference data. In the 70’s, Goldstein, Harmon, and Lesk used 21 specific subjective markers such as hair color and lip thickness to automate the recognition. The problem with both of these early solutions was that the measurements and locations were manually computed. In 1988, Kirby and Sirovic applied principle component analysis, a standard linear algebra technique, to the face

More about Face Recognition System

Open Document