Can I read A Hidden Markov Model approach for appearance-based 3D object recognition on EtoBox?

A Hidden Markov Model approach for appearance-based 3D object recognition by Manuele Bicego; Umberto Castellani; Vittorio Murino is a Computer Science article available to read on EtoBox.

What is A Hidden Markov Model approach for appearance-based 3D object recognition about?

In this paper, a new appearance-based 3D object classification method is proposed based on the Hidden Markov Model (HMM) approach. Hidden Markov Models are a widely used methodology for sequential data modelling, of growing importance in the last years. In the proposed approach, each view is subdivided in regular, partially overlapped sub-images, and wavelet coefficients are computed for each window. These coefficients are then arranged in a sequential fashion to compose a sequence vector, which is used to train a HMM, paying particular attention to the model selection issue and to the training procedure initialization. A thorough experimental evaluation on a standard database has shown promising results, also in presence of image distortions and occlusions, the latter representing one of the most severe problems of the recognition methods. This analysis suggests that the proposed approach represents an interesting alternative to classic appearance-based methods to 3D object classification.

Who reads A Hidden Markov Model approach for appearance-based 3D object recognition?

Author

Manuele Bicego; Umberto Castellani; Vittorio Murino

Publisher

Elsevier Science; Elsevier ; Elsevier BV (ISSN 0167-8655)

Published

2005

Language

EN

Field

Computer Science (Physical Sciences)