Hand gesture recognition based on deep neural network
Publish place: The ninth international Conference on Knowledge and Technology of Mechanical, Electrical Engineering and Computer Of Iran
Publish Year: 1402
نوع سند: مقاله کنفرانسی
زبان: English
View: 64
This Paper With 5 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
DMECONF09_143
تاریخ نمایه سازی: 12 اردیبهشت 1403
Abstract:
Human hand gestures serve as a non-verbal mode of communication facilitating interaction between humans and computers. Due to their intuitive and natural nature, hand gestures are a key driving force inspiring researchers to enhance human-computer interaction by leveraging the unique capabilities of hands. In this paper, we propose a convolution neural network based on SE-Block for hand gesture recognition on a complex dataset that interprets and responds to hand movements in real time. Our data set includes ۱۶۰۰۰ binary images in ۸ classes. The obtained results show that the accuracy of the proposed network is less than similar deep neural networks. Keywords: Neural network, Hand Gesture recognition, SE-Block.
Authors
Hossein Gholamalinejad
Department of Computer Engineering, Bozorgmehr University of Qaenat, Qaen, Iran
Marziyeh Felahat
Department of Basic Sciences, Bozorgmehr University of Qaenat, Qaen, Iran