Adaptive Skin Colour Segmentation For Sign Language Recognition

Pankaj Prajapati, Alok Mishra


In this paper sign language recognition system is implemented via hand gesture recognition system. For detecting hand it is very important to separate out the hand in various light condition and in cluttered background. Hand gesture can be captured by any simple camera. So RGB to YCbCr conversion is used for an adaptive skin colour segmentation. The ability of this adaptive skin colour segmentation is it can segment the out the skin region so well with very poor light conditions and whatever background except skin colour background. After that Median filter is used to remove the background noise and smoothen the edges of hand. Then Hu’s Moment is calculated for extracting necessary feature. Database of hand gestures is created for 26 alphabets and trained using Artificial Neural Network(ANN).The accuracy of the system is better than previous work because of adaptive method for skin colour segmentation.  Feature scope of this work is real time hand gesture recognition for sign language recognition.

Full Text:


Copyright (c) 2020 Pankaj Prajapati, Alok Mishra

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


All published Articles are Open Access at 

Paper submission: