Hand Gesture Recognition Using Neural Networks and Image Processing
- 0 Collaborators
A technical paper for recognizing hand gestures using Image Processing Techniques, Sobel edge detection, Skin segmentation ,Data acquisition methods ,Feature Extraction of Neural Networks, Implementation of Neural Networks, Convolution Neural Networks(CNN). ...learn more
Project status: Published/In Market
Overview / Usage
● Smart Homes
● Home Automation using Gestures
● User Continence
● New approach to automate using hand gestures
Methodology / Approach
In our method we use neural networks to recognize different hand gestures’ neural network is a connection of interconnected nodes with 3 layers, input layer, hidden layer and output layer. The given input propagates through the network to provide the required output. First we have to train the neural network to recognize different hand gestures. So we give 100’s of sample images as different inputs to obtain the different outputs. The images of hand gestures are complex even though they are in grey scale. So the images are converted into binary image, hence the resolution also reduced to 20x30. So the no of input given to network is only 600.
Technologies Used
Software Tools
● MATLAB (Version R2015 a)
● Relevance – Simulation of the algorithm
Hardware Tools
● Logitech Quick Cam 300
● Capturing images and implementation of the idea
●Aurduino UNO
●Micro controller for controlling the appliances
Repository
https://github.com/TEJASNARAYANS