We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Soft Biometrics Techniques - A Technical Review.
- Authors
Tomar, Suhail; Kumar, K. Senthil; Malathi, D.
- Abstract
Soft biometrics are a new form of biometric identification which use physical or behavioral traits that can be naturally described by humans. Soft biometric is not like other biometric approaches as it allows identification based totally upon verbal descriptions, and this bridges the semantic gap between biometrics and human description. The term semantic gap here means, the gap which exists between how machines and people recognize humans. Soft biometrics bridge this gap, allowing conversion between human descriptions and biometrics. Now a days the soft biometrics are used in surveillance purposes by allowing identification based on human descriptions. Soft biometrics traits include characteristics like height, weight, hair length, hair colour, marks, tattoos, gender etc. These traits can be described using human understandable labels and these labels can be used in human identification. One of the major advantage of soft biometrics is that it can be obtained at a distance without subject cooperation and knowledge even from the low quality video footage. In this paper, we have compared techniques used to implement the soft biometrics and also advantages of soft biometrics over hard biometrics. This paper briefly explains the techniques which can be useful in implementing the soft biometrics in real world scenario.
- Subjects
BIOMETRY; STATISTICS; BIOMATHEMATICS; SEMANTICS; COMPARATIVE linguistics
- Publication
International Journal of Advanced Research in Computer Science, 2014, Vol 5, Issue 7, p153
- ISSN
0976-5697
- Publication type
Article