التفاصيل البيبلوغرافية
العنوان: |
From Gestures to Words The Role of LSTM Networks in Real-Time Sign Language Interpretation |
المؤلفون: |
Ardra M P, Dr Paulin Paul |
المصدر: |
NCECA -2024, National Conference on Emerging Computer Applications, Kanjirappally, Kerala, 16-04-2024 |
بيانات النشر: |
Amal Jyothi College of Engineering Kanjirappally, Kottayam |
سنة النشر: |
2024 |
المجموعة: |
Zenodo |
مصطلحات موضوعية: |
sign language recognition, hearing and speech impairment, LSTM |
الوصف: |
— According to WHO, there are more than 466 million people around the world who has speech and hearing impairments. This accounts to almost 5% of the total world population. People who have speech and hearing impairments use sign language to communicate to the world. But people who are not educated in sign language, finds it difficult to comprehend the sign language. A system that can recognize these signs, can help them to comprehend the signs and communicate with the people with hearing and speech impairments. Most of the existing systems has been built upon static signs. Through this project, we are trying to build a system that can recognize the dynamic signs of Indian Sign Language. We had chosen 3 words, that are essential and is used on a daily basis. We had created the dataset with 30 videos for each of the signs. This model is trained using Long Short-Term Memory (LSTM). The model had an accuracy of 99.3%. |
نوع الوثيقة: |
conference object |
اللغة: |
unknown |
Relation: |
https://zenodo.org/communities/amaljyothi; https://doi.org/10.5281/zenodo.11523970; https://doi.org/10.5281/zenodo.11523971; oai:zenodo.org:11523971 |
DOI: |
10.5281/zenodo.11523971 |
الاتاحة: |
https://doi.org/10.5281/zenodo.11523971 |
Rights: |
info:eu-repo/semantics/openAccess ; Creative Commons Attribution 4.0 International ; https://creativecommons.org/licenses/by/4.0/legalcode |
رقم الانضمام: |
edsbas.FC847403 |
قاعدة البيانات: |
BASE |