Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The primary goal of man is to progress and grow in the field he chooses and communication is one of the key aspects for this growth. As we are aware that some of the people in this world are unable to speak/hear to convey their thoughts and feelings. The purpose of this system was to make a way for the common man to understand what the mute are trying to convey. One solution could be the presence of an interpreter but his is highly impractical in daily life. There has been many research work which have been conducted in this field but most of them have developed a system which captures the isolated images of hands. The system that has been proposed here is implemented with the MediaPipe holistic framework which upon capturing the videos of the signs, extracts the skeletal keypoints of the face, pose, left and right hands which is very helpful to collect more accurate data. Adding to this the LSTM model has helped in processing and classifying the short videos of signs and OpenCV module has been crucial to capture all the videos required for the system. It was found that this system, might be quite slow to recognize the signs given a larger dataset, it was more accurate as the background lights, colours of skin getting merged with the background did not matter as it was the case with some of the other systems. For the dataset that was trained, the accuracy was around 97% and this system has a great scope for improvement in the future for recognizing many signs and can also be made into an application to the mobile phones.
Keywords:
Indian Sign Language (ISL), Mediapipe, LSTM and OpenCV
Cite Article:
"Sign Language Interpreter using Deep Learning Techniques", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.7, Issue 6, page no.691 - 696, June-2022, Available :http://www.ijrti.org/papers/IJRTI2206113.pdf
Downloads:
000205334
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator