PROJECT TITLE :

Robust fingertip detection in a complex environment - 2016

ABSTRACT:

Fingertip detection includes a broad application in Gesture Recognition and finger tracking. It is conjointly an vital foundation of human-pc interaction systems. However, most algorithms are appropriate for straightforward conditions with low accuracy because the hand could be a nonrigid object, and its look model is advanced. To deal with the challenging downside of accurately detecting fingertips in a very advanced environment, we propose a unique and strong fingertip detection algorithm during this paper. In contrast to existing ways, our study requires no special device or mark, and users are free to move their hands. Via dense optical flow and a skin filter, we tend to perform complete hand region segmentation in a very complicated surroundings. We find the most worth of the native centroid distance outside the centroid circles and determine fingertips. Our algorithm performs favorably compared with common hand region segmentation and fingertip detection methods. Thorough experimentation proves that our proposed algorithm is effective and robust.