International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022
p-ISSN: 2395-0072
www.irjet.net
SILINGO – SIGN LANGUAGE DETECTION/ RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS Rudransh Kush1, Tanisha Chaudhary2, Shubham Gautam3, Sai Suvam Patnaik4 1,2,3,4Student,
Department of Computer Science and Engineering, Bennett University, Greater Noida, Uttar Pradesh, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – Sign Language is a medium for conversation
first language and primary mode of communication. Sign Language is still not used in India at huge scale and is very limited to communities and NGOs working for empowerment of blind and deaf people. It is also not a universal language as many countries have different sign language interpretations contrary to common perception.
used by the deaf and mute people that focuses on hand gestures, movements, and expressions. The hearing and speech impaired individuals have difficulty in conveying their thoughts and messages to the people. Recognizing a Sign Language is a topic of deep research and will help people who can’t understand sign language and break down this communication barrier between deaf/dumb/mute people with other people. Sign Language Recognition using Hand Gesture is a System which presents a novel, organic, interactive, and easy to use method of engaging with computers that is more recognizable to homo sapiens. Human-machine interface, language of sign, and immersive game technology are all examples of applications for gesture recognition. People who are not deaf, on the other hand, find it difficult or impossible to converse with deaf people. They must depend on an interpreter, which is both costly and inconvenient for the persons trying to converse with deaf/mute/dumb people. This project aims to provide a method that can employ the abilities of layers of Convolutional Neural Network (CNN) to detect and identify hand signs taken in real time using a device with camera.
Figure 1: Sign Language As a result, the ineffective communication between the hearing majority and the Deaf and silent people is expanding decade after decade. Written communication takes time and is only possible when people are seated or standing still or both sides have knowledge of a common language. Like, if a person is Bengali and the other person tries to communicate in Hindi then it would result in a complete failure. So, considering English as not a regional language and is an official language of India and is taught in every school it, it would be good to make a sign language recognition project which translates sign language to English words. While walking or moving, written communication might be awkward. In addition, the Deaf and mute community is less adept at writing a spoken language. The fundamental goal of a hand sign recognition system is to create a human-CNN classifier interface in which the recognized signs can be utilized to convey meaningful information or to give inputs to a machine without having to touch physical knobs and dials on that machine. Our project's main goal is to raise the bar and make progress in the field of sign language recognition. We're concentrating on detecting signals and motions as quickly as possible. There are two essential steps that must be followed in order to build an automated recognition system for human behaviours in spatialtemporal data. The first and most important step is to take the frame sequences and accurately extract characteristics from them. As a consequence, we'll obtain a representation
Key Words: Sign Language, Convolutional Neural Network (CNN), sign, gestures, deaf and mute people, TensorFlow, smoothing, normalization, feature extraction, ASL, classification Impact Statement - Sign Language Recognition and Detection using AI is one of the most demanding tools which can help in creating a smooth communication using AI and ML between two or more human beings using CNN (Convolutional Neural Network) algorithm. It is very helpful tool, and it will help in boosting the number of mute and deaf people to be actively part of workforce. It’s often come to known that a deaf/mute person was rejected from a job because of difficulty in communication. This tool will break all such barriers for deaf and mute community and will let them put forward their thoughts without any hesitation. Nothing can limit talent and ideas from such creative minds to be discarded and thus, this tool gives them a voice which they were wanting since birth.
1. INTRODUCTION Sign language is a lingually complete and highly visualspatial language. For deaf and mute people, it is usually their
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 3640