An Efficient Method for Hand Gesture Recognition Using Robust Features Vector

Integration of technology for the Fourth Industrial Revolution (IR 4.0) has
increased the need for efficient methods for developing dynamic human
computer interfaces and virtual environments. In this context, hand gesture
recognition can play a vital role to serve as a natural mode of interactive
human machine interaction. Unfixed brightness, complex backgrounds, color
constraints, dependency on hand shape, rotation, and scale variance are the
challenging issues which have an impact on robust performance for the
existing methods as per outlined in previous researches. This research
presents an efficient method for hand gesture recognition by constructing a
robust features vector. The proposed method is performed in two phases,
where in the first phase the features vector is constructed by selecting interest
points at distinctive locations using a blob detector based on Hessian matrix
approximation. After detecting the area of the hand from the features vector,
edge detection is applied in the isolated hand followed by edge orientation
computation. After this, templates are generated using one and two
dimensional mapping to compare candidate and prototype images using
adaptive threshold. The proposed research performed extensive
experimentation, where a recognition accuracy rate of 98.33% was achieved
by it, which is higher as compared to previous research results. Experimental
results reveal the effectiveness of the proposed methodology in real time.