Welcome to the InfoSci Platform
Reference Hub1
EarLocalizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild

EarLocalizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild

Aman Kamboj, Rajneesh Rani, Aditya Nigam
Copyright: © 2019 |Pages: 23
ISBN13: 9781522575252|ISBN10: 1522575251|EISBN13: 9781522575269
DOI: 10.4018/978-1-5225-7525-2.ch006
Cite Chapter Cite Chapter

MLA

Kamboj, Aman, et al. "EarLocalizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild." Design and Implementation of Healthcare Biometric Systems, edited by Dakshina Ranjan Kisku, et al., IGI Global, 2019, pp. 137-159. https://doi.org/10.4018/978-1-5225-7525-2.ch006

APA

Kamboj, A., Rani, R., & Nigam, A. (2019). EarLocalizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild. In D. Kisku, P. Gupta, & J. Sing (Eds.), Design and Implementation of Healthcare Biometric Systems (pp. 137-159). IGI Global. https://doi.org/10.4018/978-1-5225-7525-2.ch006

Chicago

Kamboj, Aman, Rajneesh Rani, and Aditya Nigam. "EarLocalizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild." In Design and Implementation of Healthcare Biometric Systems, edited by Dakshina Ranjan Kisku, Phalguni Gupta, and Jamuna Kanta Sing, 137-159. Hershey, PA: IGI Global, 2019. https://doi.org/10.4018/978-1-5225-7525-2.ch006

Export Reference

Mendeley
Favorite

Abstract

With much concern over security, it has become essential to maintain the identity and track of an individual's activities in the modern healthcare sector. Although there are biometric authentication systems based on different modalities, recognition of a person using the ear has gained much attention as ears are unique. Ear localization is a first step for ear-based biometric authentication systems, and this needs to be accurate, since it plays a crucial role in the overall performance of the system. The localization of ear in the side face images captured in the wild possess great challenges due to varying angles, light, scale, background clutter, blur and occlusion, etc. In this chapter, the authors have proposed EarLocalizer model to localize the ear, which is inspired by Faster-RCNN. The model is evaluated on two wild ear databases, UBEAR-II and USTB-III, and has achieved an accuracy of 95% and 99.08%, respectively, at IOU (Intersection over Union) = 0.5. The results of the proposed model signify that the model is invariant to the environmental conditions.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.