Deep convolutional neural network-based effective model for 2D ear recognition using data augmentation

ABSTRACT

In the pandemic of COVID-19, identifying a person from their face became difficult due to wearing of mask. In regard to the given circumstances, the authors have remarkably put effort on identifying a person using 2D ear images based on deep convolutional neural network (CNNs). They investigated the challenges of limited data and varying environmental conditions in this regards. To deal with such challenges, the authors developed an augmentation-based light-weight CNN model using CPU enabled machine so that it can be ported into embedded devices. While applying data augmentation technique to enhance the quality and size of training dataset, the authors analysed and discussed the different augmentation parameters (rotation, flipping, zooming, and fill mode) that are effective for generating the large number of sample images of different variability. The model works well on constrained and unconstrained ear datasets and achieves good recognition accuracy. It also reduces the problem of overfitting.

KEYWORDS:

• Ear biometrics
• convolution neural network
• identification
• recognition
• feature extraction
• augmentaion
• constrained
• unconstrained

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Ravishankar Mehta

Ravishankar Mehta is a research scholar in the Department of Computer Science & Engineering at National Institute of Technology Jamshedpur. He received his B.Tech degree in CSE department from the West Bengal University of Technology and M.Tech degree in CSE department from Calcutta University. Currently, he is pursuing Ph.D. from NIT Jamshedpur under the supervision of Dr. Koushlendra Kumar Singh. His areas of research interest include Image Processing, Deep learning, Machine learning, Computer vision and Biometric system.

Koushlendra Kumar Singh

Dr. Koushlendra Kumar Singh is working as an Assistant Professor in the Deaprtment of Computer Science and Engineering at National Institute of Technology Jamshedpur, India. Dr. Singh received the Ph.D. degree in 2016 from the Indian Institute of Information Technology, Design Manufacturing, Jabalpur, India. He received the master degree from the same institute in Computer Science and Engineering discipline. He graduated the B.Tech in CSE Department from Bhagalpur College of Engineering, Bhagalpur. His current research interests include Image Processing, Biometrics, AI and ML and different applications of Fractional Derivatives. He is the recipient of Erasmus+International Mobility for teaching at TUC, Greece.