Premium
Indian Sign Language Recognition Using Machine Learning Techniques
Author(s) -
Sahoo Ashok Kumar
Publication year - 2021
Publication title -
macromolecular symposia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.257
H-Index - 76
eISSN - 1521-3900
pISSN - 1022-1360
DOI - 10.1002/masy.202000241
Subject(s) - computer science , sign language , naive bayes classifier , sign (mathematics) , numeral system , classifier (uml) , arabic numerals , artificial intelligence , wearable computer , feature extraction , speech recognition , sign system , pattern recognition (psychology) , natural language processing , support vector machine , mathematical analysis , philosophy , linguistics , mathematics , communication , sociology , embedded system
Automatic conversion of sign language to text or speech is indeed helpful for interaction between deaf or mute people with people who even do not have knowledge of sign language. This is the demand of current times to develop an automatic system to convert ISL signs to normal text and vice versa. This will be beneficial for both communities to express their fillings to one another in accessing publicly available facilities like ticketing, banking services, traffic signals, etc. A new feature extraction and selection technique using structural features and some of the best available classifiers are proposed to recognize ISL signs for better communication for computer‐human interface. This paper narrates a system for automatic recognition of ISL immobile numeric signs, in which a standard digital camera was only used to acquire the signs, no wearable devices are required to capture electrical signals. The system is intended to convert isolated digit signs into text, that is, each entered sign image should contain precisely one numeric sign. To recognize ISL sign images in real time environment, a sign database containing ISL digits is created which contains 5000 images, 500 images for each numeral sign (0‐9). Among two classifiers, the k‐Nearest Neighbor outperforms the Naive Bayes classifier in stipulations of classification accuracy.