REAL-TIME AMERICAN SIGN LANGUAGE RECOGNITION WITH NEURAL NETWORKS

2021 ◽  
Vol 1 (10) ◽  
pp. 263-272
Author(s):  
Mohd Arifullah ◽  
Fais Khan ◽  
Yash Handa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
American Sign Language ◽  
Sign Language ◽  
Image Recognition ◽  
Time Signal ◽  
American Sign ◽  
Language Recognition ◽  
Sign Language Recognition ◽  
Information Sets

Actual-time signal language translator is a crucial milestone in facilitating communication among the deaf community and the general public. Introducing the development and use of yanked sign Language Spelling Translator (ASL) based on the convolutional neural network. We use the pre-skilled Google Net architecture educated inside the ILSVRC2012 database, in addition to the ASL database for Surrey University and Massey university ASL to apply gaining knowledge of switch in this task. We have developed a sturdy version that constantly separates the letters a-e from the original users and any other that separates the spaced characters in maximum cases. Given the limitations of the information sets and the encouraging consequences acquired, we are assured that with similarly studies and further facts, we can produce a totally customized translator for all ASL characters. Keywords: Sign Language, Image Recognition, American Sign Language, Expressions signals, CNN

scholarly journals A Real-Time American Sign Language Recognition System using Convolutional Neural Network for Real Datasets

TEM Journal ◽  
2020 ◽  
pp. 937-943
Author(s):  
Rasha Amer Kadhim ◽  
Muntadher Khamees
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
American Sign Language ◽  
Real Time ◽  
Sign Language ◽  
Recognition System ◽  
High Accuracy ◽  
American Sign ◽  
Language Recognition ◽  
Sign Language Recognition

In this paper, a real-time ASL recognition system was built with a ConvNet algorithm using real colouring images from a PC camera. The model is the first ASL recognition model to categorize a total of 26 letters, including (J & Z), with two new classes for space and delete, which was explored with new datasets. It was built to contain a wide diversity of attributes like different lightings, skin tones, backgrounds, and a wide variety of situations. The experimental results achieved a high accuracy of about 98.53% for the training and 98.84% for the validation. As well, the system displayed a high accuracy for all the datasets when new test data, which had not been used in the training, were introduced.

scholarly journals Optimization of Convolutional Neural Networks Architectures Using PSO for Sign Language Recognition

Axioms ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 139
Author(s):  
Jonathan Fregoso ◽  
Claudia I. Gonzalez ◽  
Gabriela E. Martinez
Keyword(s):  
Neural Networks ◽  
Objective Function ◽  
American Sign Language ◽  
Sign Language ◽  
Convolutional Neural Networks ◽  
Network Performance ◽  
Recognition Rate ◽  
American Sign ◽  
Language Recognition ◽  
Sign Language Recognition

This paper presents an approach to design convolutional neural network architectures, using the particle swarm optimization algorithm. The adjustment of the hyper-parameters and finding the optimal network architecture of convolutional neural networks represents an important challenge. Network performance and achieving efficient learning models for a particular problem depends on setting hyper-parameter values and this implies exploring a huge and complex search space. The use of heuristic-based searches supports these types of problems; therefore, the main contribution of this research work is to apply the PSO algorithm to find the optimal parameters of the convolutional neural networks which include the number of convolutional layers, the filter size used in the convolutional process, the number of convolutional filters, and the batch size. This work describes two optimization approaches; the first, the parameters obtained by PSO are kept under the same conditions in each convolutional layer, and the objective function evaluated by PSO is given by the classification rate; in the second, the PSO generates different parameters per layer, and the objective function is composed of the recognition rate in conjunction with the Akaike information criterion, the latter helps to find the best network performance but with the minimum parameters. The optimized architectures are implemented in three study cases of sign language databases, in which are included the Mexican Sign Language alphabet, the American Sign Language MNIST, and the American Sign Language alphabet. According to the results, the proposed methodologies achieved favorable results with a recognition rate higher than 99%, showing competitive results compared to other state-of-the-art approaches.

American sign language recognition and training method with recurrent neural network

2021 ◽  
Vol 167 ◽  
pp. 114403
Author(s):  
C.K.M. Lee ◽  
Kam K.H. Ng ◽  
Chun-Hsien Chen ◽  
H.C.W. Lau ◽  
S.Y. Chung ◽  
...  
Keyword(s):  
Neural Network ◽  
American Sign Language ◽  
Sign Language ◽  
Recurrent Neural Network ◽  
American Sign ◽  
Training Method ◽  
Language Recognition ◽  
Sign Language Recognition ◽  
And Training
Sign in / Sign up

Export Citation Format

Share Document