Hand Gesture Based Control of Robotic Hand using Raspberry Pi Processor
Asian Journal of Scientific Research
A Novel approach has been proposed in this paper for the control of an intelligent hand which can mimic the natural movement of the human hand. Implementing such intellectual hand finds its application in humanoid as well as personal robots. In this paper vision-based interaction techniques are used to track the motion of the fingers and to extract the motion of the hand gesture accurately and promptly. Accuracy and effectiveness plays the key role for real time motion based applications.
... applications. Raspberry pi processor is used to control the entire set up which has a camera module attached in it, to capture the motion. Face subtraction, skin color detections are used to characterize the hand in the video. Mean shift algorithm is used to track the motion of the finger. The mechanical structure and the ratio between number of actuators and number of Degrees Of Freedoms (DOFs) have been optimized in order to cope with the strict size and weight constraints that are typical application of artificial hands for the implication of humanoid robotics. The proposed hand has a structure similar to that of the natural hand featuring articulated fingers (every finger with 4 degree of freedom) which is controlled by DC motors.