Design and Implementation of Deep Learning Based Contactless Authentication System Using Hand Gestures

Abstract

Hand gestures based sign language digits have several contactless applications. Applications include communication for impaired people, such as elderly and disabled people, health-care applications, automotive user interfaces, and security and surveillance. This work presents the design and implementation of a complete end-to-end deep learning based edge computing system that can verify a user contactlessly using ‘authentication code’. The ‘authentication code’ is an ‘n’ digit numeric code and the digits are hand gestures of sign language digits. We propose a memory-efficient deep learning model to classify the hand gestures of the sign language digits. The proposed deep learning model is based on the bottleneck module which is inspired by the deep residual networks. The model achieves classification accuracy of 99.1% on the publicly available sign language digits dataset. The model is deployed on a Raspberry pi 4 Model B edge computing system to serve as an edge device for user verification. The edge computing system consists of two steps, it first takes input from the camera attached to it in real-time and stores it in the buffer. In the second step, the model classifies the digit with the inference rate of 280 ms, by taking the first image in the buffer as input.

Design and Implementation of a Rural Social Security System Based on Deep Learning

“…However, the aging of the rural population in our country is extremely serious, the population is relatively dense, and farmers are unable to carry out their daily lives due to medical treatment, which increase the burden on farmers [8]. Therefore, my country's current agricultural social security system mainly includes aging and medical care, with the focus on the construction of the rural social pension and cooperative medical system [9]. Agricultural cultural relics insurance refers to the provision of pensions to farmers who have reached the retirement age in accordance with relevant laws and regulations of our country [10].…”

Hand gesture recognition algorithm combining hand-type adaptive algorithm and effective-area ratio for efficient edge computing

“…45,46 However, the optimal features are unknown in many cases, resulting in a significant variation of the performance of the classifier depending on the selected features. Some deep learning algorithms are large in scale and require high hardware performance [47][48][49] and require a large number of training samples. Some deep networks require both training and GPU support for online deployment, which pose high hardware demand and thus is not conducive to small, embedded artificial intelligence systems.…”

Event-Driven Deep Learning for Edge Intelligence (EDL-EI)

“…The parameters for the filters are given by w (l) i,j,k , while the sigmoid activation equation for sequential activation is described by σ(x (l) i,j,k ). The final step illustrated by Equations ( 10) and (11), is entirely interconnected.…”

“…For example, recent work has presented an edge-computing-based deep-learning model based on the fog/edge-computing paradigm [ 10 ]. Additionally, some recent deep-learning solutions have shown interesting applications, including a hand-gesture authentication system with edge-based deep learning [ 11 ].…”