Lightweight error-tolerant edge detection using memristor-enabled stochastic computing

Abstract The demand for efficient edge computer vision has spurred the development of stochastic computing for image processing. Memristors, by introducing their inherent switching stochasticity into computation, readily enable stochastic image processing. Here, we present a lightweight, error-toler...

Full description

Saved in:
Bibliographic Details
Main Authors: Lekai Song, Pengyu Liu, Jingfang Pei, Yang Liu, Songwei Liu, Shengbo Wang, Leonard W. T. Ng, Tawfique Hasan, Kong-Pang Pun, Shuo Gao, Guohua Hu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-59872-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154530657796096
author Lekai Song
Pengyu Liu
Jingfang Pei
Yang Liu
Songwei Liu
Shengbo Wang
Leonard W. T. Ng
Tawfique Hasan
Kong-Pang Pun
Shuo Gao
Guohua Hu
author_facet Lekai Song
Pengyu Liu
Jingfang Pei
Yang Liu
Songwei Liu
Shengbo Wang
Leonard W. T. Ng
Tawfique Hasan
Kong-Pang Pun
Shuo Gao
Guohua Hu
author_sort Lekai Song
collection DOAJ
description Abstract The demand for efficient edge computer vision has spurred the development of stochastic computing for image processing. Memristors, by introducing their inherent switching stochasticity into computation, readily enable stochastic image processing. Here, we present a lightweight, error-tolerant edge detection approach based on memristor-enabled stochastic computing. By integrating memristors into compact logic circuits, we realise lightweight stochastic logics for stochastic number encoding and processing with well-regulated probabilities and correlations. This stochastic and probabilistic computational nature allows the stochastic logics to perform edge detection in edge visual scenarios characterised by high-level errors. As a demonstration, we implement a hardware edge detection operator using the stochastic logics, and prove its exceptional performance with 95% less energy consumption while withstanding 50% bit-flips. The results underscore the potential of our stochastic edge detection approach for developing efficient edge visual hardware for autonomous driving, virtual and augmented reality, medical imaging diagnosis, and beyond.
format Article
id doaj-art-4da4b00464674a9e9b2684248d00f032
institution OA Journals
issn 2041-1723
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-4da4b00464674a9e9b2684248d00f0322025-08-20T02:25:17ZengNature PortfolioNature Communications2041-17232025-05-011611910.1038/s41467-025-59872-2Lightweight error-tolerant edge detection using memristor-enabled stochastic computingLekai Song0Pengyu Liu1Jingfang Pei2Yang Liu3Songwei Liu4Shengbo Wang5Leonard W. T. Ng6Tawfique Hasan7Kong-Pang Pun8Shuo Gao9Guohua Hu10Department of Electronic Engineering, The Chinese University of Hong KongDepartment of Electronic Engineering, The Chinese University of Hong KongDepartment of Electronic Engineering, The Chinese University of Hong KongDepartment of Electronic Engineering, The Chinese University of Hong KongDepartment of Electronic Engineering, The Chinese University of Hong KongSchool of Instrumentation and Optoelectronic Engineering, Beihang UniversitySchool of Materials Science and Engineering, Nanyang Technological UniversityCambridge Graphene Centre, University of CambridgeDepartment of Electronic Engineering, The Chinese University of Hong KongSchool of Instrumentation and Optoelectronic Engineering, Beihang UniversityDepartment of Electronic Engineering, The Chinese University of Hong KongAbstract The demand for efficient edge computer vision has spurred the development of stochastic computing for image processing. Memristors, by introducing their inherent switching stochasticity into computation, readily enable stochastic image processing. Here, we present a lightweight, error-tolerant edge detection approach based on memristor-enabled stochastic computing. By integrating memristors into compact logic circuits, we realise lightweight stochastic logics for stochastic number encoding and processing with well-regulated probabilities and correlations. This stochastic and probabilistic computational nature allows the stochastic logics to perform edge detection in edge visual scenarios characterised by high-level errors. As a demonstration, we implement a hardware edge detection operator using the stochastic logics, and prove its exceptional performance with 95% less energy consumption while withstanding 50% bit-flips. The results underscore the potential of our stochastic edge detection approach for developing efficient edge visual hardware for autonomous driving, virtual and augmented reality, medical imaging diagnosis, and beyond.https://doi.org/10.1038/s41467-025-59872-2
spellingShingle Lekai Song
Pengyu Liu
Jingfang Pei
Yang Liu
Songwei Liu
Shengbo Wang
Leonard W. T. Ng
Tawfique Hasan
Kong-Pang Pun
Shuo Gao
Guohua Hu
Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
Nature Communications
title Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
title_full Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
title_fullStr Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
title_full_unstemmed Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
title_short Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
title_sort lightweight error tolerant edge detection using memristor enabled stochastic computing
url https://doi.org/10.1038/s41467-025-59872-2
work_keys_str_mv AT lekaisong lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT pengyuliu lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT jingfangpei lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT yangliu lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT songweiliu lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT shengbowang lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT leonardwtng lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT tawfiquehasan lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT kongpangpun lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT shuogao lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing
AT guohuahu lightweighterrortolerantedgedetectionusingmemristorenabledstochasticcomputing