Bioinspired robotic vision with online learning capability and rotation-invariant properties

Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational tran...

Full description

Saved in:
Bibliographic Details
Main Authors: Berco, Dan, Ang, Diing Shenp
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/159291
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-159291
record_format dspace
spelling sg-ntu-dr.10356-1592912022-06-10T06:14:23Z Bioinspired robotic vision with online learning capability and rotation-invariant properties Berco, Dan Ang, Diing Shenp School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Bioinspired Machine Vision Cognitive Artificial Retinas Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational transformations. There are software-based approaches used to address this issue, such as artificial rotation of training data or preliminary image processing. However, these workarounds require a large computational effort and are mostly done offline. This work presents a bioinspired, robotic vision system with inherent rotation-invariant properties that may be taught either offline or in real time by feeding back error indications. It is successfully trained to counter the move of a human player in a game of Paper Scissors Stone. The architecture and operation principles are first discussed alongside the experimental setup. This is followed by performance analysis of pattern recognition under misaligned and rotated conditions. Finally, the process of online, supervised learning is demonstrated and analyzed. Ministry of Education (MOE) Published version The authors acknowledge the partial funding support by Singapore Ministry of Education under grants MOE2016-T2-1-102 and MOE2016-T2-2-102. 2022-06-10T06:14:23Z 2022-06-10T06:14:23Z 2021 Journal Article Berco, D. & Ang, D. S. (2021). Bioinspired robotic vision with online learning capability and rotation-invariant properties. Advanced Intelligent Systems, 3(8), 2100025-. https://dx.doi.org/10.1002/aisy.202100025 2640-4567 https://hdl.handle.net/10356/159291 10.1002/aisy.202100025 8 3 2100025 en MOE2016-T2-1-102 MOE2016-T2-2-102 Advanced Intelligent Systems © 2021 The Authors. Advanced Intelligent Systems published by Wiley- VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Bioinspired Machine Vision
Cognitive Artificial Retinas
spellingShingle Engineering::Electrical and electronic engineering
Bioinspired Machine Vision
Cognitive Artificial Retinas
Berco, Dan
Ang, Diing Shenp
Bioinspired robotic vision with online learning capability and rotation-invariant properties
description Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational transformations. There are software-based approaches used to address this issue, such as artificial rotation of training data or preliminary image processing. However, these workarounds require a large computational effort and are mostly done offline. This work presents a bioinspired, robotic vision system with inherent rotation-invariant properties that may be taught either offline or in real time by feeding back error indications. It is successfully trained to counter the move of a human player in a game of Paper Scissors Stone. The architecture and operation principles are first discussed alongside the experimental setup. This is followed by performance analysis of pattern recognition under misaligned and rotated conditions. Finally, the process of online, supervised learning is demonstrated and analyzed.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Berco, Dan
Ang, Diing Shenp
format Article
author Berco, Dan
Ang, Diing Shenp
author_sort Berco, Dan
title Bioinspired robotic vision with online learning capability and rotation-invariant properties
title_short Bioinspired robotic vision with online learning capability and rotation-invariant properties
title_full Bioinspired robotic vision with online learning capability and rotation-invariant properties
title_fullStr Bioinspired robotic vision with online learning capability and rotation-invariant properties
title_full_unstemmed Bioinspired robotic vision with online learning capability and rotation-invariant properties
title_sort bioinspired robotic vision with online learning capability and rotation-invariant properties
publishDate 2022
url https://hdl.handle.net/10356/159291
_version_ 1735491258291322880