A Human Identity Recognition System Based on Kinect Skeletal Tracking and ANN Classifier

We proposed a novel method of people recognition based on the structure of bones, which is detected by Kinect sensor for skeletal tracking. By using 3D depth image achieved by Kinect, body's skeleton information is extracted as 20 joints with joint coordinates, from which body's skeletal features are calculated into different length ratio between each bone. Later these features are processed by a BP artificial neural network (ANN) classifier to differentiate several samples. The results show a high accuracy up to 98% test samples, which indicate that the body's skeletal features can provide the effective judgment in people recognition.