Evaluation of Person Recognition Accuracy based on OpenPose parameters

Recently, person recognition has become an active area of research because it finds large number of applications including defence and security. Person recognition is the ability to detect and recognize a person using a variety of techniques. Some of the techniques which are widely used for person recognition system are based on face recognition, fingerprint and retina scanning, use of gait, silhouette and human skeleton parameters. This paper has proposed an innovative approach to recognize the person by using the openpose keypoints and then evaluated the recognition accuracy based on number of OpenPose parameters in an indoor environment. The major advantage and motive of the proposed approach is that this method is a non-contact type method and does not need any interaction with the subject.