Author Login IJIRT Partner Network (IPN) Login

Sign Language To Text Generation Using CNN And LSTM

  • Unique Paper ID: 167592
  • Volume: 11
  • Issue: 3
  • PageNo: 1592-1597
  • Abstract:
  • Language barriers remain a significant challenge, particularly in the realm of sign language, which has not yet been fully addressed by translation technologies. This project aims to develop an end-to-end custom object detection system for real-time sign language translation. The system will utilize hand gesture recognition to detect, interpret, and translate sign language through advanced computer vision techniques. The core of the proposed solution involves a deep, multi-layered Convolutional Neural Network (CNN) designed to handle variations in hand gestures such as pose, orientation, location, and scale. The methodology includes capturing images using OpenCV and a webcam, annotating these images for object detection, training a TensorFlow model for sign language recognition, and implementing real-time gesture detection. Unlike traditional face detection methods, such as Haar-based classifiers that struggle with occlusions or variations in pose, the CNN-based approach offers greater flexibility and accuracy, benefiting from its ability to adapt through extensive training data.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 3
  • PageNo: 1592-1597

Sign Language To Text Generation Using CNN And LSTM

Related Articles

Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry