Application-Oriented Retinal Image Models for Computer Vision

Silva, Ewerton; da S. Torres, Ricardo; Pinto, Allan; Tzy Li, Lin; S. Vianna, José Eduardo; Azevedo, Rodolfo; Goldenstein, Siome

doi:10.3390/s20133746

Open AccessLetter

Application-Oriented Retinal Image Models for Computer Vision

by

Ewerton Silva

¹,

Ricardo da S. Torres

^2,*

,

Allan Pinto

¹

,

Lin Tzy Li

¹,

José Eduardo S. Vianna

¹,

Rodolfo Azevedo

¹ and

Siome Goldenstein

¹

Institute of Computing, University of Campinas, Campinas 13083-852, Brazil

²

Department of ICT and Natural Sciences, Norwegian University of Science and Technology, Ålesund, 2 6009 Larsgårdsvegen, Norway

^*

Author to whom correspondence should be addressed.

Sensors 2020, 20(13), 3746; https://doi.org/10.3390/s20133746

Submission received: 8 June 2020 / Revised: 27 June 2020 / Accepted: 30 June 2020 / Published: 4 July 2020

(This article belongs to the Special Issue Information Fusion and Machine Learning for Sensors)

Download

Browse Figures

Versions Notes

Abstract

Energy and storage restrictions are relevant variables that software applications should be concerned about when running in low-power environments. In particular, computer vision (CV) applications exemplify well that concern, since conventional uniform image sensors typically capture large amounts of data to be further handled by the appropriate CV algorithms. Moreover, much of the acquired data are often redundant and outside of the application’s interest, which leads to unnecessary processing and energy spending. In the literature, techniques for sensing and re-sampling images in non-uniform fashions have emerged to cope with these problems. In this study, we propose Application-Oriented Retinal Image Models that define a space-variant configuration of uniform images and contemplate requirements of energy consumption and storage footprints for CV applications. We hypothesize that our models might decrease energy consumption in CV tasks. Moreover, we show how to create the models and validate their use in a face detection/recognition application, evidencing the compromise between storage, energy, and accuracy.

Keywords: retinal image model; space-variant computer vision; foveation; low-power; energy consumption

Graphical Abstract

Share and Cite

MDPI and ACS Style

Silva, E.; da S. Torres, R.; Pinto, A.; Tzy Li, L.; S. Vianna, J.E.; Azevedo, R.; Goldenstein, S. Application-Oriented Retinal Image Models for Computer Vision. Sensors 2020, 20, 3746. https://doi.org/10.3390/s20133746

AMA Style

Silva E, da S. Torres R, Pinto A, Tzy Li L, S. Vianna JE, Azevedo R, Goldenstein S. Application-Oriented Retinal Image Models for Computer Vision. Sensors. 2020; 20(13):3746. https://doi.org/10.3390/s20133746

Chicago/Turabian Style

Silva, Ewerton, Ricardo da S. Torres, Allan Pinto, Lin Tzy Li, José Eduardo S. Vianna, Rodolfo Azevedo, and Siome Goldenstein. 2020. "Application-Oriented Retinal Image Models for Computer Vision" Sensors 20, no. 13: 3746. https://doi.org/10.3390/s20133746

APA Style

Silva, E., da S. Torres, R., Pinto, A., Tzy Li, L., S. Vianna, J. E., Azevedo, R., & Goldenstein, S. (2020). Application-Oriented Retinal Image Models for Computer Vision. Sensors, 20(13), 3746. https://doi.org/10.3390/s20133746

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Application-Oriented Retinal Image Models for Computer Vision

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI