Face Recognition Using Deep Convolutional Network and One-shot Learning

International Journal of Computer Science and Engineering

© 2020 by SSRG - IJCSE Journal

Volume 7 Issue 4

Year of Publication : 2020

Authors : Joyassree Sen, Bappa Sarkar, Mst. Ashrafunnahar Hena, Md. Hafizur Rahman

10.14445/23488387/IJCSE-V7I4P107

How to Cite?

Joyassree Sen, Bappa Sarkar, Mst. Ashrafunnahar Hena, Md. Hafizur Rahman, "Face Recognition Using Deep Convolutional Network and One-shot Learning," SSRG International Journal of Computer Science and Engineering , vol. 7,  no. 4, pp. 23-29, 2020. Crossref, https://doi.org/10.14445/23488387/IJCSE-V7I4P107

Abstract:

Among the most successful application of images analysis and understanding, face recognition has recently received significant attention, especially during the past few years. Facial recognition technology (FRT) has emerged as an attractive solution to address many contemporary needs for identity and verification of identity claims. Face recognition is the identification of humans by the unique characteristics of their faces. FRT technology is the least intrusive and fastest bio-metric technology. It works with the most obvious individual identifier for the human face. With increasing security needs and with the advancement in technology extracting information has become much simpler. The system proposed in this paper uses the power of Convolution Neural Network (CNN) to encode the face and produce a vector matrix. Then we use tripled loss function to calculate the distance between input and trained image to predict the face.

Keywords:

CNN, FRT, ANN, Machine learning, Conv

References:

[1] Fei-Fei L, Fergus R, Perona P. “One-shot learning of object categories”. IEEE transactions on pattern analysis and machine intelligence. 2006 Feb 21;28(4):594-611.
[2] Gosavi VR, Sable GS, Deshmane AK. “Evaluation of feature extraction techniques using neural network as a classifier: a comparative review for face recognition”. Int. J. Sci. Res. Sci. Technol. 2018;4(2):1082-91.
[3] Lauzon FQ. “An introduction to deep learning”. In2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA) 2012 Jul 2 (pp. 1438-1439). IEEE.
[4] Balaji SA, Baskaran K. “Design and development of artificial neural networking (ANN) system using sigmoid activation function to predict annual rice production in Tamilnadu”. Ar Xiv preprint arXiv:1303.1913. 2013 Mar 8.
[5] Yegnanarayana B. “Artificial neural networks”. PHI Learning Pvt. Ltd.; 2009 Jan 14.
[6] Kutsuna T. “Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks”.
[7] Sharma A. “Understanding activation functions in neural networks”. Medium. com blog. 2017 Mar;30.
[8] Brownlee J. “Gentle introduction to the adam optimization algorithm for deep learning’. Machine Learning Mastery. 2017 Jul 3.
[9] Karpathy A. Stanford university cs231n: Convolutional neural networks for visual recognition. url: http://cs231n. stanford. edu/syllabus. html. 2018.
[10] Stewart M. “Simple introduction to convolutional neural networks”. Towards Data Science. 2019 Feb, 27.