Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{167592,
        author = {Mariyam Mirza and Subramanian K.M and Sridhar Gummalla},
        title = {Sign Language To Text Generation Using CNN And LSTM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {1592-1597},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167592},
        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.},
        keywords = {},
        month = {September},
        }