We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
MediaPipe Frame and Convolutional Neural Networks-Based Fingerspelling Detection in Mexican Sign Language.
- Authors
Sánchez-Vicinaiz, Tzeico J.; Camacho-Pérez, Enrique; Castillo-Atoche, Alejandro A.; Cruz-Fernandez, Mayra; García-Martínez, José R.; Rodríguez-Reséndiz, Juvenal
- Abstract
This research proposes implementing a system to recognize the static signs of the Mexican Sign Language (MSL) dactylological alphabet using the MediaPipe frame and Convolutional Neural Network (CNN) models to correctly interpret the letters that represent the manual signals coming from a camera. The development of these types of studies allows the implementation of technological advances in artificial intelligence and computer vision in teaching Mexican Sign Language (MSL). The best CNN model achieved an accuracy of 83.63% over the sets of 336 test images. In addition, considering samples of each letter, the following results are obtained: an accuracy of 84.57%, a sensitivity of 83.33%, and a specificity of 99.17%. The advantage of this system is that it could be implemented on low-consumption equipment, carrying out the classification in real-time, contributing to the accessibility of its use.
- Subjects
CONVOLUTIONAL neural networks; COMPUTER vision; ARTIFICIAL intelligence; SIGN language; PROGRAMMING languages
- Publication
Technologies (2227-7080), 2024, Vol 12, Issue 8, p124
- ISSN
2227-7080
- Publication type
Article
- DOI
10.3390/technologies12080124