Title :
HMM Based Eyebrow Recognition
Author :
Li, Yujian ; Li, Xingli
Author_Institution :
Beijing Univ. of Technol., Beijing
Abstract :
We study the problem of how to recognize a person only by his eyebrow based on hidden Markov models (HMM). By experiments on a small-scale eyebrow image database taken from 27 subjects, we show that our HMM-based eyebrow recognition method can achieve the highest accuracy of 92.6%, based on the relation of its accuracy to the number of observation symbols and that of states. Hence, we conclude that human eyebrow can work as a biometric with certain possibility and feasibility.
Keywords :
biometrics (access control); face recognition; hidden Markov models; biometric; eyebrow recognition; hidden Markov models; small-scale eyebrow image database; Biometrics; Character recognition; Eyebrows; Face recognition; Handwriting recognition; Hidden Markov models; Humans; Image recognition; Probability distribution; Speech recognition;
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing, 2007. IIHMSP 2007. Third International Conference on
Conference_Location :
Kaohsiung
Print_ISBN :
978-0-7695-2994-1
DOI :
10.1109/IIHMSP.2007.4457510
