A deep learning approach for person identification using ear biometrics
- PDF / 677,067 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 68 Downloads / 268 Views
A deep learning approach for person identification using ear biometrics Ramar Ahila Priyadharshini 1
&
Selvaraj Arivazhagan 1 & Madakannu Arun 1
Accepted: 1 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Automatic person identification from ear images is an active field of research within the biometric community. Similar to other biometrics such as face, iris and fingerprints, ear also has a large amount of specific and unique features that allow for person identification. In this current worldwide outbreak of COVID-19 situation, most of the face identification systems fail due to the mask wearing scenario. The human ear is a perfect source of data for passive person identification as it does not involve the cooperativeness of the human whom we are trying to recognize and the structure of ear does not change drastically over time. Acquisition of a human ear is also easy as the ear is visible even in the mask wearing scenarios. Ear biometric system can complement the other biometric systems in automatic human recognition system and provides identity cues when the other system information is unreliable or even unavailable. In this work, we propose a six layer deep convolutional neural network architecture for ear recognition. The potential efficiency of the deep network is tested on IITD-II ear dataset and AMI ear dataset. The deep network model achieves a recognition rate of 97.36% and 96.99% for the IITD-II dataset and AMI dataset respectively. The robustness of the proposed system is validated in uncontrolled environment using AMI Ear dataset. This system can be useful in identifying persons in a massive crowd when combined with a proper surveillance system. Keywords Ear recognition . Identification . Human . CNN
1 Introduction The demand for secured automated identity system has intensified the research in the fields of computer vision and intelligent systems. Most of the human identification systems make use of the biometrics because of their invariance over time, easiness to acquire, and uniqueness for each individual. The physical or behavioral traits including face, iris, fingerprint, palmprint, hand geometry, voice, and signature are the most commonly used biometrics for human identification. Many research works for the biometric systems have been implemented successfully and are now available for public use. These biometric systems are mostly used for human
* Ramar Ahila Priyadharshini [email protected] Selvaraj Arivazhagan [email protected] Madakannu Arun [email protected] 1
Centre for Image Processing and Pattern Recognition, Mepco Schlenk Engineering College, Sivakasi, India
authentication purposes. For human identification, most of this biometrics requires the cooperation from the corresponding human in order to acquire the biometric traits. Due to the current COVID-19 pandemic situation around the world, the entire human community is becoming a mask wearing community. Because of this reason, the face recognition systems suffer a lot and ther
Data Loading...
