Design and development of a DSP processor based reconfigurable hand Gesture Recognition System for real time applications

In this paper, a reconfigurable hand Gesture Recognition System (GRS) has been designed and developed for multiple applications using vision based techniques. Image is acquired from the camera and processed using a DSP processor in real time. Processing involves image segmentation and palm extraction techniques for extracting palm shaped objects from the background image and gesture recognition technique for recognizing the input gestures. The recognized gesture is transmitted from the DSP processor to the receiver wirelessly for controlling the end-user application. The development of an effective static GRS devoid of training data, multiple cameras, markers, bulky computing device and gloves constitutes the original contribution of the research. The developed reconfigurable GRS has a balanced mix of implementation of advanced technologies for robust applications resulting in enhanced end-user product appreciation. Overall, the developed reconfirgurable GRS exhibits desirable features of robustness, portability and cost effectiveness. The experimental results for chosen hand gestures, show a recognition rate of around 97%.