Sign Language Recognition System For Differently Abled Person

Data science

Nonverbal communication, such as sign language, uses outward body movements to convey key messages either simultaneously and concurrently with spoken words or in place of speech. The hands, face, or other body parts can move when using the performance of different neural network models in this area to obtain balanced neural network models, which not only recognize sign languages with good accuracy but also runs on lower-end embedded systems and smartphones with acceptable speed. This would help develop real-time and portable sign language. In contrast to gestures, which convey a specific language recognition system. Messages, pure expressive displays, proxemics, and displays of shared attention are examples of physical nonverbal communication. Culture-specific gestures can communicate significantly different meanings in various social or cultural contexts. The goal of this research is to develop a Deep Learning algorithm that can categorize photos of various sign languages, including alphabetic and numeric images. The accuracy of hand gesture types classification using CNNs is higher than that of the suggested and existing algorithms, according to a comparison it gives more accuracy than the ANN algorithm where ANN doesn’t contain any hidden layers so the accuracy will be lesser. In CNN AlexNet consists of eight layers five convolutional layers, two fully-connected hidden layers, and one fully-connected output layer. Whereas the AlexNet in ANN contains only eight convolution layers. It increases the accuracy.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.