Sign Language Recognition: A Comparative Analysis of Deep Learning Models

Premkumar, Aswathi; Krishna, Ravi; Chanalya, Nikita; Meghadev, C.; Varma, Utkrist Arvind; Anjali, T; Rani, Shikha

doi:10.1007/978-981-16-6723-7_1

Cited by 15 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By utilizing this existing knowledge, the model can adapt more quickly and effectively to the new task, leading to improved performance and reduced training time compared to starting training from scratch. A research paper titled "Sign language recognition: A comparative analysis of deep learning models" published in 2022 (Premkumar et al, 2022), demonstrated a comparative study of a customized CNN and VGG16 models. The paper concluded that VGG16 was better where it delivered an accuracy of 99.56%, followed by customized CNN with an accuracy of 99.38%.…”

Section: Related Workmentioning

confidence: 99%

American Sign Language Classification using CNNs: A Comparative Study

Kumar Adhikari,

Neupane,

Mainali

et al. 2024

Int. J. Engin. Technol.

View full text Add to dashboard Cite

American Sign Language (ASL) classification is crucial in facilitating communication for individuals with hearing impairments. Traditional methods rely heavily on manual interpretation, which can be time-consuming and error-prone. Inspired by the success of deep learning techniques in image processing, the paper explores the application of Convolutional Neural Networks (CNNs) for ASL classification. The paper presents a CNN architecture tailored specifically for this task and investigates the effectiveness of transfer learning by leveraging four pre-trained models: VGG16, InceptionV3, ResNet50, and DenseNet121. A comparative analysis of these architectures has been presented in this paper. The experimental results show that the customized CNN model outperformed other models with a testing accuracy of 99.93% when provided with testing set images. Consequently, it is concluded that customized CNN outshines other models in accurately classifying sign languages.

show abstract

Section: Related Workmentioning

confidence: 99%