Face Patterns Analysis and Recognition System Based on Quantum Neural Network QNN

International Journal of Interactive Mobile Technologies

Jaafar SadiqQateef¹  Abdul Hadi M. Alaidi²  Roa'a M.Al_airaji³  IbtisamA. Aljazaery³  Haider Th.Salim Alrikabi⁴ 

[1]Computer Science Department, College of Education and Pure Sciences, Wasit University, Wasit, Iraq

[2]College of computer science and information technology, Wasit University

[3]University of Babylon, Babylon, Iraq

[4]Wasit University/ College of Engineering

关键词: Artificial Intelligence, Facial Recognition, Feature Extraction, QNN, PCA. How to work with this template;   

DOI  :  10.3991/ijim.v16i08.30107

来源: DOAJ

【 摘 要 】

The past few years have witnessed a huge increase in the application of facial recognition, detection, and analysis technology. However, face recognition systems remain the most popular among the general public. The facial recognition system can detect the presence of a face when exposed to one. The accuracy and fairness that can be derived from such systems necessitate their use, because humans, particularly security personnel can be tired and target the wrong person as a suspect. However, artificial intelligence systems that are properly trained are capable of efficiently identifying and classifying faces without errors. In this work, the use of Matlab language was employed in building a software system that is capable of recognizing and differentiating different face patterns. The proposed system is equipped with a camera that serves as the practical aspect of the software that captures different shots that are sent to the theoretical part of a special program that is designed to recognize faces by comparing them with a database stored within the program. The practical part of the work involved the use of Quantum Neural Network. In this work, the training dataset is made up of features vectors that were obtained from a well-known set of face images of different people. Here, Principle Component Analysis (PCA) was used for the extraction of feature vectors from images and then prepared for the next training step. The experimental results revealed that efficient face recognition can be achieved through the use of well-trained Quantum Network.

【 授权许可】

Unknown