Understanding the hand-gestures using Convolutional Neural Networks and Generative Adversial Networks
This work addresses the problem of real-time gesture recognition for human-computer interaction, but it appears incremental as it combines existing methods like CNNs and Camshift without introducing major innovations.
The paper tackles real-time hand gesture recognition by developing a system that uses Convolutional Neural Networks for training and recognition, along with hand tracking via Camshift algorithm and skin color analysis. It achieves effectiveness in recognizing a vocabulary of 36 gestures, including alphabets and digits, though no specific accuracy numbers are provided.
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.