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.
%0 Journal Article
%1 deshpande2020super
%A Deshpande, Anand
%A Patavardhan, Prashant
%A Estrela, Vania V
%A Estrela, V. V.
%A Estrela, Vania Vieira
%A Estrela, Vania
%D 2020
%I InternationVol. 12: , Issue. 4, : Pagehttps://doi.org/10.1504/IJBM.2020~…
%J International Journal of Biometrics
%K GPR Gaussian_process_recognition PSNR biomedical_engineering computer_vision ear_recognition healthcare image_analysis image_database image_processing image_retrieval imported myown peak_signal-to-noise_ratio super-resolution
%N 4
%P 396--410
%R 10.1504/IJBM.2020.110813
%T Super resolution and recognition of unconstrained ear image
%V 12
%X 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.
@article{deshpande2020super,
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.},
added-at = {2021-04-21T12:10:35.000+0200},
author = {Deshpande, Anand and Patavardhan, Prashant and Estrela, Vania V and Estrela, V. V. and Estrela, Vania Vieira and Estrela, Vania},
biburl = {https://www.bibsonomy.org/bibtex/288d9ff88a5159c3173adb0098df634b3/vaniave},
doi = {10.1504/IJBM.2020.110813},
interhash = {c36acf03a07ba8036e008eb5bf178589},
intrahash = {88d9ff88a5159c3173adb0098df634b3},
journal = {International Journal of Biometrics},
keywords = {GPR Gaussian_process_recognition PSNR biomedical_engineering computer_vision ear_recognition healthcare image_analysis image_database image_processing image_retrieval imported myown peak_signal-to-noise_ratio super-resolution},
language = {English},
number = 4,
pages = {396--410},
publisher = {InternationVol. 12: , Issue. 4, : Pagehttps://doi.org/10.1504/IJBM.2020~…},
timestamp = {2021-05-16T19:19:48.000+0200},
title = {Super resolution and recognition of unconstrained ear image},
volume = 12,
year = 2020
}