Title: Hybrid dense matching features for cloud-based face recognition
Authors: T. Shreekumar; K. Karunakara
Addresses: Faculty of Computer Science and Engineering, Mangalore Institute of Technology and Engineering, Mijar, Moodabidre, India ' Faculty of Information Science and Engineering, Sri Siddartha Institute of Technology, Sri Siddhartha Academy of Higher Education, Tumakuru, India
Abstract: Cloud computing is a computing service done not on a local device but an internet connection to a data centre infrastructure. The cloud computing system also provides a scalability solution where cloud computing can increase the resources needed when doing larger data processing. In recent years, face bio-metric plays an important role in biometric authentication, where security is the primary concern. The two major difficulties to be addressed in face recognition are illumination and pose variation. This work proposes a cloud computing-based face recognition technique by consolidating four-patch LBP and the local landmark features to the acquired feature vector. After that, the SVM is utilised to recognise the individual. The feature set used for training and testing is also made available in the cloud. At some stage in the training phase, the kernel parameters of SVM are optimised with GWO to improve the recognition performance. This method yields a maximum recognition accuracy of 99.00% with LFW and 98.0% accuracy with YTF.
Keywords: local binary pattern; feature extraction; support vector machine; grey wolf optimisation; GWO; cloud computing.
International Journal of Cloud Computing, 2023 Vol.12 No.2/3/4, pp.399 - 423
Received: 16 Sep 2020
Accepted: 24 Feb 2021
Published online: 14 May 2023 *