A COMPARISON OF DEEP LEARNING BASED ARCHITECTURE WITH A CONVENTIONAL APPROACH FOR FACE RECOGNITION PROBLEM

Authors : Fatıma Zehra ÜNAL

Pages : 129-149

Doi:10.33769/aupse.529575

View : 14 | Download : 3

Publication Date : 2019-12-01

Article Type : Research Paper

Abstract :This paper addresses a new approach for face recognition problem based on deep learning strategy. In order to verify the performance of the proposed approach, it is compared with a conventional face recognition method by using various comprehensive datasets.  The conventional approach employs Histogram of Gradient insert ignore into journalissuearticles values(HOG); algorithm to extract features and utilizes a multi-class Support Vector Machine insert ignore into journalissuearticles values(SVM); classifier to train and learn the classification. On the other hand, the proposed deep learning based approaches employ a Convolutional Neural Network insert ignore into journalissuearticles values(CNN); based architecture and also offer both a SVM and Softmax classifiers respectively for the classification phase. Results reveal that the proposed deep learning architecture using Softmax classifier outperform conventional method by a substantial margin. As well as, the deep learning architecture using Softmax classifier also outperform SVM in almost all cases.
Keywords : Convolutional Neural Network, Deep Learning, Face Recognition, Fine Tuning, Softmax