Open AccessInvariant Hand Gesture Recognition System
Author(s) -
G. N. Balaji,
S. V. Suryanarayana,
C. Veeramani
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i4.6.21196
Subject(s) - gesture , gesture recognition , computer science , artificial intelligence , computer vision , preprocessor , support vector machine , histogram , segmentation , feature extraction , histogram of oriented gradients , invariant (physics) , pattern recognition (psychology) , image (mathematics) , mathematics , mathematical physics
Hand gesture recognition plays a vital role in numerous applications, which can run from mobile phones to 3D analysis of anatomy and from gaming to medicinal science. In a large portion of research applications and current business hand gestures recognition, has been implemented by utilizing either vision based or sensor-based gloves strategies where hues, paperclips of synthetic substances are used on to capture the gestures. Another essential issue associated with vision-based procedures is illuminated conditions. The threshold used for the segmentation is changed based on the light variations. A system is proposed in this paper, which extracts the gesture part from the hand image by preprocessing, followed by extraction of orientation histogram based feature is done. Further, in order to recognize the gestures, the extracted HOG feature vectors are provide for support vector machine (SVM). The proposed system is tested with 84 images and it outperforms with an accuracy of 94.04%.