A fingertip detection method based on the top-hat transform

This paper presents a fingertip detection method that is based on the top-hat transform. A hand is assumed to be segmented in advance. The palm of the hand is obtained using the morphological opening. Fingertips are then obtained as the opening residue, the difference between the input image and the palm image. The performance of the approach is compared with three other techniques: (1) the convex hull algorithm, (2) Kanade-Lucas-Tomasi (KLT) feature tracker, and (3) the SUSAN corner detector. Simulation results show that the method (1) is ineffective to closed hands. The methods (2) and (3) respond falsely to many non-fingertip points. By contrast, the proposed method works well even when the hand is closed.