Fuzzy-Bayesian-Partnership Towards the Inference of Cheremes in Human Sign Languages

J.M. León Rojas, V. Masero, and M. Morales (Spain)

Keywords

Human-Computer Interaction, Bayesian Inference, Type2 Fuzzy Sets, Handshape recognition

Abstract

We characterize all the distinct ways one chereme (hand shape) of the Spanish Sign Language may be performed (the cheretypes). The solution is based on maximal sub relations of similarity among probability distributions, type 2 fuzzy sets, and Bayesian inference. Crisp evi dence consists of the normalized joint angle values com ing from sensor devices such as those mounted on in strumented gloves. We work with fuzzy-valued evidence describing cheremes and cheretypes as type 2 fuzzy sub sets of the whole collection of sensors in order to incor porate linguistic evidence into the system (an example of an input fuzzy grade is: “medium exed”). We integrate the multiple expert information identifying the “brute” cheretypes with maximal sub-relations of similarity. Us ing a fuzzy Bayesian scheme we rst estimate the likeli hood of crisp evidence from the likelihoods of linguistic evidence and then we compute the posterior probabili ties allowing the selection of the most probable and most relevant cheremes.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image