Understanding the hand-gestures using Convolutional Neural Networks and Generative Adversial Networks

TL;DR

This paper presents a real-time hand gesture recognition system utilizing CNNs and GANs, incorporating hand tracking with Camshift, skin color detection, and adaptive techniques to improve accuracy across 36 gestures.

Contribution

It introduces a robust real-time hand gesture recognition system combining CNNs, GANs, and advanced tracking and filtering techniques for improved accuracy.

Findings

Effective recognition of 36 gestures including alphabets and digits

Robust hand tracking using Camshift and skin color analysis

Enhanced accuracy through adaptive thresholding and training image selection

Abstract

In this paper, it is introduced a hand gesture recognition system to recognize the characters in the real time. The system consists of three modules: real time hand tracking, training gesture and gesture recognition using Convolutional Neural Networks. Camshift algorithm and hand blobs analysis for hand tracking are being used to obtain motion descriptors and hand region. It is fairy robust to background cluster and uses skin color for hand gesture tracking and recognition. Furthermore, the techniques have been proposed to improve the performance of the recognition and the accuracy using the approaches like selection of the training images and the adaptive threshold gesture to remove non-gesture pattern that helps to qualify an input pattern as a gesture. In the experiments, it has been tested to the vocabulary of 36 gestures including the alphabets and digits, and results effectiveness of the approach.