Title :
Hidden Markov models for silhouette classification
Author :
Abd-Almageed, Wael ; Smith, Christopher
Author_Institution :
Electr. & Comput. Eng. Dept., New Mexico Univ., Albuquerque, NM, USA
Abstract :
In this paper, a new technique for object classification from silhouettes is presented. Hidden Markov models are used as a classification mechanism. Through a set of experiments, we show the validity of our approach and show its invariance under severe rotation conditions. Also, a comparison with other techniques that use hidden Markov models for object classification from silhouettes is presented.
Keywords :
hidden Markov models; image classification; object recognition; HMM; hidden Markov models; object classification; silhouette classification; Computer vision; Feature extraction; Fourier transforms; Hidden Markov models; Neural networks; Parameter estimation; Pattern recognition; Probability distribution; Shape measurement; Wavelet transforms;
Conference_Titel :
Automation Congress, 2002 Proceedings of the 5th Biannual World
Print_ISBN :
1-889335-18-5
DOI :
10.1109/WAC.2002.1049575
