Title: Super resolution and recognition of unconstrained ear image
Authors: Anand Deshpande; Prashant Patavardhan; Vania V. Estrela
Addresses: Department of Electronics and Communication Engineering, Angadi Institute of Technology and Management, Belagavi, Karnataka, India ' Department of Electronics and Communication Engineering, School of Engineering, Dayanand Sagar University, Bengaluru, Karnataka, India ' Department of Telecommunications, Universidade Federal Fluminense, Brazil
Abstract: In this paper, a framework is proposed to super-resolve low resolution ear images and to recognise these images, without external dataset. This frame uses linear kernel co-variance function-based Gaussian process regression to super-resolve the ear images. The performance of the proposed framework is evaluated on UERC database by comparing and analysing the peak signal to noise ratio, structural similarity index matrix and visual information fidelity in pixel domain. The results are compared with the state-of-the-art-algorithms. The results demonstrate that the proposed approach outperforms the state-of-the-art super resolution approaches.
Keywords: super resolution; ear recognition; Gaussian process regression; GPR; peak signal to noise ratio; PSNR.
International Journal of Biometrics, 2020 Vol.12 No.4, pp.396 - 410
Received: 30 Mar 2019
Accepted: 14 Feb 2020
Published online: 29 Oct 2020 *