Generation of Indian Sign Language Letters, Numbers, and Words

Yadav, AK and Kumar, N and Rathna, GN (2024) Generation of Indian Sign Language Letters, Numbers, and Words. In: International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024, 23 August 2024 - 24 August 2024, Hassan.

PDF IACIS_2024.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Sign language, which contains hand movements, facial expressions and bodily gestures, is a significant medium for communicating with hard-of-hearing people. A well-trained sign language community communicates easily, but those who don't know sign language face significant challenges. Recognition and generation are basic communication methods between hearing and hard-of-hearing individuals. Despite progress in recognition, sign language generation still needs to be explored. The Progressive Growing of Generative Adversarial Network (ProGAN) excels at producing high-quality images, while the Self-Attention Generative Adversarial Network (SAGAN) generates feature-rich images at medium resolutions. Balancing resolution and detail is crucial for sign language image generation. We are developing a Generative Adversarial Network (GAN) variant that combines both models to generate feature-rich, high-resolution, and class-conditional sign language images. Our modified Attention-based model generates high-quality images of Indian Sign Language letters, numbers, and words, outperforming the traditional ProGAN in Inception Score (IS) and Frechet Inception Distance (FID), with improvements of 3.2 and 30.12, respectively. Additionally, we are publishing a large dataset incorporating high-quality images of Indian Sign Language alphabets, numbers, and 129 words. © 2024 IEEE.

Item Type:	Conference Paper
Publication:	International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the publisher.
Keywords:	Adversarial machine learning; Convolutional neural networks; Image enhancement; Image quality; Recurrent neural networks, Adversarial networks; Convolutional neural network; Hard of hearings; High quality images; Indian sign languages; Neural-networks; Progressive growing network; Self-attention; Sign language; Sign language image, Generative adversarial networks
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation Division of Electrical Sciences > Electrical Communication Engineering Division of Electrical Sciences > Electrical Engineering
Date Deposited:	26 Nov 2024 16:12
Last Modified:	26 Nov 2024 16:12
URI:	http://eprints.iisc.ac.in/id/eprint/86976

Actions (login required)

View Item