Seven Staged Identity Recognition System Using Kinect V.2 Sensor
Seyed Muhammad Hossein Mousavi, Atiye Ilanloo · 2022
By employing artificial intelligence techniques and algorithms such as color and depth image processing, signal processing, machine learning, evolutionary algorithms and fuzzy systems, an identity recognition expert system with approximate recognition accuracy of 99% is proposed. Available identity recognition systems mostly are in three stages which may lead to some security problems, so it is decided to make a robust system. Proposed system uses Kinect Version 2 sensor in order to conduct 7 main stages of recognition. The system includes following stages of recognition and estimation which are, face and voice recognition, finger print recognition, iris recognition, gesture recognition, sex detection and age estimation. By adding macro lens to the sensor, recognition accuracy for fingerprint and iris increases significantly. All efforts on this project were to achieve the highest potential out of available techniques. The system is learning based and has high precision and could be well used in industrial purposes. By installing macro lens on Kinect sensor, the system could compete with other expensive identification systems. It has to be mention that proposed system works well in the pure darkness ass Kinect sensor supports the infrared spectrum.