Recognition of gestures in Pakistani sign language using fuzzy classifier

Authors:
Sumaira Kausar;M. Younus Javed;Shaleeza Sohail
Affiliations:
Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Pakistan;Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Pakistan;Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Pakistan
Venue:
ISCGAV'08 Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision
Year:
2008

Citing 3
Cited 1

Finger identification and hand posture recognition for human-robot interaction

Image and Vision Computing
Depth silhouettes for gesture recognition

Pattern Recognition Letters
Gesture recognition using quadratic curves

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I

Methodological foundation for sign language 3d motion trajectory analysis

IDA'12 Proceedings of the 11th international conference on Advances in Intelligent Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic recognition of sign language can be used as an efficient mean of communication with deaf people. In this paper, a fuzzy classifier to recognize alphabets of Pakistani sign language is proposed. In the proposed method, colored gloves are used to identify each finger-tip and joint. Angle between finger tip and corresponding finger joint is calculated and used to identify the position of each finger and then these positions are used to recognize the alphabet of sign language. Angles are provided as input to fuzzy inference system and then system identifies the position of each finger and on the basis of these positions defuzzification is performed. Results have shown that accuracy rate of the proposed system is quite high; only two signs out of thirty seven could not be recognized by the system correctly; all other 35 signs have been recognized accurately.