Multifunctional method for identifying hand gestures

Abstract

The invention provides a vision-based multifunctional method for identifying hand gestures, which comprises the following steps of: firstly, extracting a hand part region from the background by background subtraction; secondly, carrying out fingertip detection on the extracted hand part region to determine the number of single fingertips contained in the hand gestures; meanwhile, acquiring the outline of the hand part region and describing the outline of the hand part region through improved shape context descriptors; afterwards, introducing a directed acyclic support vector fleet to classify the extracted improved shape context descriptors; after classifying, comparing the number of fingers of a hand form, to which the improved shape context descriptors belong, with the detection result of the fingertip, if the number is matched with the result, outputting the final judgment result; and otherwise, refusing the judgment. The vision-based multifunctional method can be better applied to man-machine interaction, mobile equipment and sing language input.

Description

technical field [0001] The invention relates to a sign language recognition method, which can be used in many fields such as human-computer interaction, sign language letter input, mobile device control and game design, and also helps the disabled to better use the current advanced electronic equipment and integrate into modern in life. technical background [0002] In 2002, the Department of Engineering Science at Oxford University completed the recognition of 46 letters and symbols of sign language. [0003] In 2003, the Department of Computer Science of the University of California, Santa Barbara developed the HandVu system, which can locate and distinguish gestures, and designed its related applications, which achieved good results. [0004] The difficulties existing in the prior art have the following points: [0005] First, the difficulty of hand region tracking. The main reason is that hand tracking is often difficult to achieve when the background is complex. Acq...

AI Technical Summary

Problems solved by technology

[0006] Second, the difficulty in expressing the hand region

Because the human hand is a multi-joint deformable object, the features collected at different angles are not the same, and due to the existence of occlusion, it is very difficult to express the features of the hand area.

Images