Recognition of static hand gestures of Indian sign language using CNN

• Main Authors: Reshna, S., Sajeena, A., Jayaraju, M.
• Format: Conference Proceeding
• Language: English
• Subjects: Gloves; Human communication; Image classification; Languages; Neural networks; Recognition; Sentences; Sign language; Vision systems; Words (language)
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0004485

Sign languages are natural languages used by hearing impaired people which use several means of expression for communication in day to day life. It relates letters, words, and sentences of a spoken language to gesticulations, enabling them to communicate among themselves. The deaf community can interact with normal people with an automation system that can associate signs to the words of speech. This will support them to enhance their abilities and make them aware of doing better for the mankind. A vision based system that provides a feasible solution to Indian Sign Language (ISL) recognition of static gestures is presented in this paper. The proposed method doesn’t require that signers wear gloves or any other marker devices to simplify the process of hand segmenting. After modeling and analysis of the input hand image, classification method is used to recognize the sign. The classification is done using Computational Neural networks(CNN). Detection using CNN is rugged to distortions such as change in shape due to camera lens, different lighting conditions, various poses, presence of occlusions, horizontal and vertical shifts, etc. We are able to recognize 5 ISL gestures with a recognition accuracy of 90.55 %.