A novel approach for ISL alphabet recognition using Extreme Learning Machine
- PDF / 1,078,101 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 97 Downloads / 239 Views
ORIGINAL RESEARCH
A novel approach for ISL alphabet recognition using Extreme Learning Machine Anand Kumar1 • Ravinder Kumar2
Received: 5 December 2019 / Accepted: 26 September 2020 Bharati Vidyapeeth’s Institute of Computer Applications and Management 2020
Abstract Deaf and dumb people use sign language as a tool for communication. As per the 2011 census in India, hearing impaired and speech disabled population is 1,998,692 and 5,072,914 respectively (Disabled persons in India, https://www.mospi.gov.in). Normal hearing people do not learn sign language and thus there is a big communication gap between them and deaf and dumb people. Sign language interpreters can fill this gap but it is a very costly affair to hire them. Indian Sign Language (ISL) consists of signs which are made with two hands while other sign languages like American Sign Language consists of signs made with single hand. This work proposes an automatic and efficient computer vision based system to recognize ISL alphabet which can assist this communication. It can further be used as a module of complete ISL recognition system. Phases in ISL alphabet recognition are image acquisition, preprocessing, segmentation, feature extraction and classification. All 26 ISL alphabet have been considered for testing with average accuracy of 80.76%. Results show that the accuracy of 100% is achieved when similar alphabet {C, L, M, N, R, U,Y} are excluded from testing dataset. Keywords Indian Sign Language (ISL) Computer vision Image acquisition Preprocessing Segmentation Feature extraction Classification & Anand Kumar [email protected] Ravinder Kumar [email protected] 1
USIC&T (Formerly USIT), GGSIPU, Dwarka, Delhi, India
2
Skill Faculty of Engineering & Technology, Shri Vishwakarma Skill University, Gurugram, Haryana, India
1 Introduction Children born with profound hearing loss (more than 90 decibels) who are not intervened for fitting of hearing aids/cochlear implant in the early age have inadequate verbal language. If they are totally deaf and dumb, then sign language is the only option left with them for communication. It is also used by person with inadequate speech. Normal persons do not know sign language. Hence it is very difficult for the deaf and dumb person to communicate his message to normal hearing person. Sign language interpreters are used to cover this communication gap but it is very costly to hire them. This demands the design of a vision based Human Computer Interface (HCI) system which can act as the interpreter. In this work, a computer vision based system to recognize ISL alphabet is designed which can further be used as a module of complete ISL recognition system. Deaf and dumb children are taught Indian Sign Language as a tool in total communication approach. Signs in ISL are made using various hand positions, facial expressions and body/hand gestures. The static signs do not involve movement of hands whereas dynamic signs involve movement of hands. There are many nouns and verbs for which either no sign
Data Loading...
