A Novel Method to Realize Optical Correlation Recognition Based on Neural Network

A neural network model is constructed according to 4F optical correlator. New optical filter is obtained by training the neural network. For recognition of distortion targets, the correlation peaks from correlator applying new filter are averagely increased up to 306.7% than applying the OTSDF filte...

Full description

Bibliographic Details
Main Authors: Ping Xu, Tuo Yang, Kai Liang, Xiongchao Li, Siwei Long, Haixuan Huang
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8418351/
_version_ 1818619025144414208
author Ping Xu
Tuo Yang
Kai Liang
Xiongchao Li
Siwei Long
Haixuan Huang
author_facet Ping Xu
Tuo Yang
Kai Liang
Xiongchao Li
Siwei Long
Haixuan Huang
author_sort Ping Xu
collection DOAJ
description A neural network model is constructed according to 4F optical correlator. New optical filter is obtained by training the neural network. For recognition of distortion targets, the correlation peaks from correlator applying new filter are averagely increased up to 306.7% than applying the OTSDF filter, and correlation peaks are higher, sharper and easier to be distinguished, which indicates optical correlator with new filter have better performance in distortion invariant recognition.
first_indexed 2024-12-16T17:30:55Z
format Article
id doaj.art-18e0fcd8f70a48618c10c5f6c1fc737b
institution Directory Open Access Journal
issn 1943-0655
language English
last_indexed 2024-12-16T17:30:55Z
publishDate 2018-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj.art-18e0fcd8f70a48618c10c5f6c1fc737b2022-12-21T22:22:55ZengIEEEIEEE Photonics Journal1943-06552018-01-0110411010.1109/JPHOT.2018.28585688418351A Novel Method to Realize Optical Correlation Recognition Based on Neural NetworkPing Xu0https://orcid.org/0000-0002-6878-4513Tuo Yang1https://orcid.org/0000-0002-5661-5157Kai Liang2Xiongchao Li3Siwei Long4Haixuan Huang5https://orcid.org/0000-0001-9166-3755Institute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaInstitute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaInstitute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaInstitute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaInstitute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaInstitute of Micro-Nano Photoelectronic Technology, College of Electronic Science and Technology, Shenzhen University, Shenzhen, ChinaA neural network model is constructed according to 4F optical correlator. New optical filter is obtained by training the neural network. For recognition of distortion targets, the correlation peaks from correlator applying new filter are averagely increased up to 306.7% than applying the OTSDF filter, and correlation peaks are higher, sharper and easier to be distinguished, which indicates optical correlator with new filter have better performance in distortion invariant recognition.https://ieeexplore.ieee.org/document/8418351/Optical correlatoroptical filterobject recognition.
spellingShingle Ping Xu
Tuo Yang
Kai Liang
Xiongchao Li
Siwei Long
Haixuan Huang
A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
IEEE Photonics Journal
Optical correlator
optical filter
object recognition.
title A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
title_full A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
title_fullStr A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
title_full_unstemmed A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
title_short A Novel Method to Realize Optical Correlation Recognition Based on Neural Network
title_sort novel method to realize optical correlation recognition based on neural network
topic Optical correlator
optical filter
object recognition.
url https://ieeexplore.ieee.org/document/8418351/
work_keys_str_mv AT pingxu anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT tuoyang anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT kailiang anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT xiongchaoli anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT siweilong anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT haixuanhuang anovelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT pingxu novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT tuoyang novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT kailiang novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT xiongchaoli novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT siweilong novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork
AT haixuanhuang novelmethodtorealizeopticalcorrelationrecognitionbasedonneuralnetwork