scholarly journals Hand Motion Analysis using CNN

Hand motion detection and gesture recognition research has attracted large interest due to its wide range of applications in the field of Human computer interaction such as sign language recognition, 3D printing, virtual reality. There have been several approaches to create a robust algorithm to ease human computer interaction and perform in unfavourable environments.The real time recognition and learning of the model are big challenges. In this work, we use Convolutional Neural Network architecture to detect and classify hand motions, the region of interest of the image is passed through the neural network for the hand motion analysis and detection.Our system has achieved testing accuracy of 98%.

2020 ◽  
Vol 9 (5) ◽  
pp. 1873-1881
Author(s):  
Yohanssen Pratama ◽  
Ester Marbun ◽  
Yonatan Parapat ◽  
Anastasya Manullang

An image processing system that based computer vision has received many attentions from science and technology expert. Research on image processing is needed in the development of human-computer interactions such as hand recognition or gesture recognition for people with hearing impairments and deaf people. In this research we try to collect the hand gesture data and used a simple deep neural network architecture that we called model E to recognize the actual hand gestured. The dataset that we used is collected from kaggle.com and in the form of ASL (American Sign Language) datasets. We doing accuracy comparison with another existing model such as AlexNet to see how robust our model. We find that by adjusting kernel size and number of epoch for each model also give a different result. After comparing with AlexNet model we find that our model E is perform better with 96.82% accuracy.


Sign in / Sign up

Export Citation Format

Share Document