Article Preview
Top1. Introduction
In the world of almost 7 billion people more than 500 million suffer from some physical, sensory or mental disability states United Nations organization as on December 3, 2019. Their lives are often hampered by some disabilities which turns down them full participation in society and even their enjoyment of equal rights and opportunities. Sign language is used commonly for the deaf and the dumb. Sign language is an efficient alternative to talking, where the former is replaced by hand gestures. Hand gestures are combination of hand shapes, orientations and movement of the hands, alignments of the fingers and positioning of the palm which are used to express gracefully a conveyer's thoughts. Signs are used to communicate words and sentences to audience. Our objective is to optimize an algorithm for recognition of hand gestures with reasonable accuracy, where the input to the pattern recognition system will be given from the hand.
Gesture recognition aims to recognize meaningful movements of human bodies, and is of utmost importance in intelligent human computer or robot interactions. Hand gesture recognition system has got good attention now-a-days because of easy interaction between human and machine. The focus of developing hand gesture is to enhance the communication between the humans and the computer for conveying various information, which will help accomplishing multiple task. It is an efficient way of interacting with machines making it more popular and applicable for many purposes. The hands, arms, body and face are used for gesture recognition to perceive critical demeanours of movement by a human. Gesture recognition is mainly applicable for video conferencing, sign language recognition, distance learning as well as in forensic identification. Hand gesture recognition research has been gaining more and more popular among worldwide researchers. Hand gesture recognition has become an important research topic in human-computer interaction (Hu et. al., 2019; Li et. al., 2018; Patil et. al., 2018; Soe et. al., 2018; & Chaikhumpha et. al., 2018).
Hand gesture recognition system provides us an innovative, natural, and user friendly way of interaction with the computer which is more familiar to the human beings. Generally, the process of vision based hand gesture can be divided into four stages: sample image capturing, image pre-processing, feature analysis and parameter extraction, classification and recognition. Wherein, feature extraction aims to find out a feature or a set of features which can describe the specified hand gesture uniquely and help in better classification. The most commonly used features of static hand gesture include: gradient histogram, image subspace projection, and shape features. The traditional gradient histogram is easy to calculate and implement, it has the invariance of translation but not rotation. Image subspace projection is able to remove the correlation of higher-order statistics and make relatively comprehensive representation of the local features of training sample images, but it very much relies on the position scale and rotation. Shape based features such as contour, silhouette, fingertips are free of translation, size and rotation of hand gesture, and feature extraction algorithm based on shape is most commonly used currently.
The main contributions in this paper are it introduces a series of fingertip related features based on convex defect detection; presents a real time system for hand gesture recognition on the basis of detection of some meaningful shape-based features; combines browser control with recognized hand gestures and evaluates the effectiveness of the system. This hand gesture recognition system is an efficient system which will be able to control the browser via the recognized hand gestures i.e. different hand gestures will be used to open different sites. The concept behind the detection of hand gestures based on shape features and the controlling capability to open corresponding web sites are described in system design section.
The remainder of this paper are organized as follows: Related work section summarized the works that has been carried out related to gesture recognition. Experimental design section explains the proposed hand gesture recognition system, experimental results section describes the implementation details of the proposed method and the results obtained. Result analysis section presents the analysis of experimental results along with the conclusions drawn and the next section concludes the work.