Sequential Belief-Based Fusion of Manual and Non-manual Information for Recognizing Isolated Signs

Authors:
Oya Aran;Thomas Burger;Alice Caplier;Lale Akarun
Affiliations:
Dep. of Computer Engineering, Bogazici University, Istanbul, Turkey 34342;France Telecom R&D, 28 ch. Vieux Chêêêne, Meylan, France;GIPSA-lab, Grenoble cedex 1, France 38031;Dep. of Computer Engineering, Bogazici University, Istanbul, Turkey 34342
Venue:
Gesture-Based Human-Computer Interaction and Simulation
Year:
2009

Citing 7
Cited 1

The transferable belief model

Artificial Intelligence
Automatic Detection of Relevant Head Gestures in American Sign Language Communication

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Robust Real-Time Face Detection

International Journal of Computer Vision
Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling Hesitation and Conflict: A Belief-Based Approach for Multi-class Problems

ICMLA '06 Proceedings of the 5th International Conference on Machine Learning and Applications
SignTutor: An Interactive System for Sign Language Tutoring

IEEE MultiMedia
Effect of colorspace transformation, the illuminance component, and color modeling on skin detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Towards automatic annotation of sign language dictionary corpora

TSD'11 Proceedings of the 14th international conference on Text, speech and dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work aims to recognize signs which have both manual and non-manual components by providing a sequential belief-based fusion mechanism. We propose a methodology based on belief functions for fusing extracted manual and non-manual features in a sequential two-step approach. The belief functions based on the likelihoods of the hidden Markov models are used to decide whether there is an uncertainty in the decision of the first step and also to identify the uncertainty clusters. Then we proceed to the second step which utilizes only the non-manual features within the identified cluster, only if there is an uncertainty.