A Novel FPGA-based Hand Gesture Recognition System

  title={A Novel FPGA-based Hand Gesture Recognition System},
  author={Chao-Tang Li and Wenhui Chen},
  journal={Journal of Convergence Information Technology},
There are many applications using hand gesture as a nature control interface, such as humanmachine interaction and interactive entertainment. With the advancement of computer vision and machine learning, the development of vision-based hand gesture recognition systems has received more and more attention in recent years. However, much previous research was focused on software algorithms running on a PC-based platform, which makes it inapplicable to real-time applications. In this study, a… 

Figures and Tables from this paper

Real-time implementation of vision-based unmarked static hand gesture recognition with neural networks based on FPGAs
A real-time vision-based unmarked hand sign recognition system with neural network (Self-Organizing Maps) based on FPGA that can accomplish the whole hand recognition task in real time with a high accuracy.
FPGA Design For Location Independent Hand Posture Recognition System
The work is to develop a design that supports realtime FPGA implementation using onboard camera and is designed for robustness against change in location of input image.
Appearance-based gesture recognition in the compressed domain
This work proposes a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques that improves both the computational efficiency and the memory requirement of the previous DTW-based K-NN gesture classifiers.
Static Hand Sign Recognition System with Som-Hebb Classifier Implemented in FPGA
A hybrid network consisting of self-organizing map (SOM) and Hebbian network is used for hand sign recognition, designed to recognize 24 ASL hand signs and coded in VHDL using Matlab and Modelsim.
Novel FPGA Implementation of Hand Sign Recognition System With SOM–Hebb Classifier
  • H. Hikawa, Keishi Kaida
  • Computer Science
    IEEE Transactions on Circuits and Systems for Video Technology
  • 2015
The system was designed to recognize 24 American sign language hand signs, and its feasibility was verified through both simulations and experiments, and it could accomplish recognition at a speed of 60 frames/s, while achieving an accuracy of 97.1%.
A Light-powered, "Always-On", Smart Camera with Compressed Domain Gesture Detection
An energy-efficient camera-based gesture recognition system powered by light energy for "always on" applications that can find wide applications in "always-on" vision systems such as in surveillance, robotics and consumer electronics with touch-less operation.
Optimizing hardware design for Human Action Recognition
An FPGA-based HAR feature extraction for near camera processing using fixed-point data representation and arithmetic is implemented and shows that by re-training the classifier with reduced data precision, the classification performs as well as the original double-precision floating-point.
A Light-Powered Smart Camera With Compressed Domain Gesture Detection
Owing to its fully self-powered operation, the proposed system can find wide applications in “always-on” vision systems, such as in surveillance, robotics, and consumer electronics with touch-less operation.
SOC integration for video processing application
This paper presents the integration of greyscale conversion into a complete camera system using Nios II software build tools for Eclipse, and the proposed greyscalesale conversion system is designed using the C programming language in Eclipse.


An FPGA-Based Smart Camera for Gesture Recognition in HCI Applications
GestureCam is presented, an FPGA-based smart camera built from scratch that can recognize simple hand gestures and has shown promising real-time performance and is being tested in several desktop HCI (Human Computer Interface) applications.
Vision-Based Human-Computer System Using Hand Gestures
  • Yun Liu, P. Zhang
  • Computer Science
    2009 International Conference on Computational Intelligence and Security
  • 2009
The AdaBoost algorithm was adopted to detect the user’ s hand automatically from the video stream which is based on Haar-like features as the representation of hand gestures and a Multi-class Support Vector Machines was used to training and recognition the hand gesture based on the Hu invariant moments features.
Vision-based remote control system by motion detection and open finger counting
Experimental results show that the shape of open fingers exhibits strong features for determining correct gesture states and the use of stable features on consecutive frames yields robust and accurate performance regardless of operating conditions.
Hand Mouse: Real Time Hand Motion Detection System Based on Analysis of Finger Blobs
A fast, computationally inexpensive solution which uses any type of computer video camera to control a cursor through hand movements and gesticulations is proposed.
Dynamic hand gesture recognition using a CNN model with 3D receptive fields
A pattern recognition model for dynamic hand gesture recognition that combines a convolutional neural network with a weighted fuzzy min-max neural network and a feature analysis technique utilizing the WFMM algorithm is proposed.
A generic framework for the design of visual-based gesture control interface
This study presented a generic framework for the design of a human machine interface based on visual-based hand gesture recognition techniques and Experimental results showed that the proposed approach is feasible for practical applications.
Gesture Recognition for Human-Computer Interaction (HCI)
A new technique for static hand gesture recognition, for the Human-Computer Interaction (HCI) based on shape analysis is presented, designed to be a simple and robust gestural interface prototype for various PC applications.
Visual understanding of dynamic hand gestures
Computer Vision on FPGAs: Design Methodology and its Application to Gesture Recognition
  • M. Sen, I. Corretjer, W. Wolf
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops
  • 2005
A design methodology for generating efficient, target specific Hardware Description Language (HDL) code from an algorithm through the use of coarse-grain reconfigurable dataflow graphs as a representation to guide the designer is developed.