Cargando…
Mask Attention-SRGAN for Mobile Sensing Networks
Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The higher resolution inside the crucial region reveals details of the physiological characteristics which p...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434631/ https://www.ncbi.nlm.nih.gov/pubmed/34502863 http://dx.doi.org/10.3390/s21175973 |
_version_ | 1783751645712089088 |
---|---|
author | Huang, Chi-En Chang, Ching-Chun Li, Yung-Hui |
author_facet | Huang, Chi-En Chang, Ching-Chun Li, Yung-Hui |
author_sort | Huang, Chi-En |
collection | PubMed |
description | Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The higher resolution inside the crucial region reveals details of the physiological characteristics which provides discriminative information to achieve extremely high recognition rate. Due to the growing needs for the IoT device in various applications, the image sensor is gradually integrated in the IoT device to decrease the cost, and low-cost image sensors may be preferable than high-cost ones. However, low-cost image sensors may not satisfy the minimum requirement of the resolution, which definitely leads to the decrease of the recognition accuracy. Therefore, how to maintain high accuracy for biometric systems without using expensive high-cost image sensors in mobile sensing networks becomes an interesting and important issue. In this paper, we proposed MA-SRGAN, a single image super-resolution (SISR) algorithm, based on the mask-attention mechanism used in Generative Adversarial Network (GAN). We modified the latest state-of-the-art (nESRGAN+) in the GAN-based SR model by adding an extra part of a discriminator with an additional loss term to force the GAN to pay more attention within the region of interest (ROI). The experiments were performed on the CASIA-Thousand-v4 dataset and the Celeb Attribute dataset. The experimental results show that the proposed method successfully learns the details of features inside the crucial region by enhancing the recognition accuracies after image super-resolution (SR). |
format | Online Article Text |
id | pubmed-8434631 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-84346312021-09-12 Mask Attention-SRGAN for Mobile Sensing Networks Huang, Chi-En Chang, Ching-Chun Li, Yung-Hui Sensors (Basel) Article Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The higher resolution inside the crucial region reveals details of the physiological characteristics which provides discriminative information to achieve extremely high recognition rate. Due to the growing needs for the IoT device in various applications, the image sensor is gradually integrated in the IoT device to decrease the cost, and low-cost image sensors may be preferable than high-cost ones. However, low-cost image sensors may not satisfy the minimum requirement of the resolution, which definitely leads to the decrease of the recognition accuracy. Therefore, how to maintain high accuracy for biometric systems without using expensive high-cost image sensors in mobile sensing networks becomes an interesting and important issue. In this paper, we proposed MA-SRGAN, a single image super-resolution (SISR) algorithm, based on the mask-attention mechanism used in Generative Adversarial Network (GAN). We modified the latest state-of-the-art (nESRGAN+) in the GAN-based SR model by adding an extra part of a discriminator with an additional loss term to force the GAN to pay more attention within the region of interest (ROI). The experiments were performed on the CASIA-Thousand-v4 dataset and the Celeb Attribute dataset. The experimental results show that the proposed method successfully learns the details of features inside the crucial region by enhancing the recognition accuracies after image super-resolution (SR). MDPI 2021-09-06 /pmc/articles/PMC8434631/ /pubmed/34502863 http://dx.doi.org/10.3390/s21175973 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Huang, Chi-En Chang, Ching-Chun Li, Yung-Hui Mask Attention-SRGAN for Mobile Sensing Networks |
title | Mask Attention-SRGAN for Mobile Sensing Networks |
title_full | Mask Attention-SRGAN for Mobile Sensing Networks |
title_fullStr | Mask Attention-SRGAN for Mobile Sensing Networks |
title_full_unstemmed | Mask Attention-SRGAN for Mobile Sensing Networks |
title_short | Mask Attention-SRGAN for Mobile Sensing Networks |
title_sort | mask attention-srgan for mobile sensing networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434631/ https://www.ncbi.nlm.nih.gov/pubmed/34502863 http://dx.doi.org/10.3390/s21175973 |
work_keys_str_mv | AT huangchien maskattentionsrganformobilesensingnetworks AT changchingchun maskattentionsrganformobilesensingnetworks AT liyunghui maskattentionsrganformobilesensingnetworks |