BP Neural Network Fuse with Morphology Edge Detection Method

In order to obtain better image edge information, an edge detection algorithm combining BP (Back Propagation) neural network and morphology is proposed. The Sigmoid function is commonly used as the excitation function in BP neural networks, but the traditional Sigmoid function is single in form an...

Full description

Saved in:
Bibliographic Details
Main Authors: YUE Xin-hua, DENG Cai-xia, ZHANG Zhao-ru
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2021-10-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710331983560704
author YUE Xin-hua
DENG Cai-xia
ZHANG Zhao-ru
author_facet YUE Xin-hua
DENG Cai-xia
ZHANG Zhao-ru
author_sort YUE Xin-hua
collection DOAJ
description In order to obtain better image edge information, an edge detection algorithm combining BP (Back Propagation) neural network and morphology is proposed. The Sigmoid function is commonly used as the excitation function in BP neural networks, but the traditional Sigmoid function is single in form and lacks flexibility. Therefore, it is very important to provide an adjustable Sigmoid function. First, a fully smooth Sigmoid function construction method is given, which is used as the excitation function in the BP neural network to detect the edge of the image effectively. Then, using the idea of multi-scale and multi-structure, an improved morphological edge detection algorithm is proposed, and the edge image with small noise and continuous is obtained by applying this algorithm. Finally, the wavelet analysis is used to fuse the BP neural network and the improved morphological algorithm, and then an edge detection fusion algorithm is obtained. The simulation results show that the evaluation index of the fusion algorithm is better than a single edge detection algorithm and the detected image edge lines are complete and clear.
format Article
id doaj-art-10fd5aa07fda43e1a899ff1333a21821
institution DOAJ
issn 1007-2683
language zho
publishDate 2021-10-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-10fd5aa07fda43e1a899ff1333a218212025-08-20T03:14:57ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832021-10-012605839010.15938/j.jhust.2021.05.011BP Neural Network Fuse with Morphology Edge Detection Method YUE Xin-hua0DENG Cai-xia1ZHANG Zhao-ru2School of Applied Sciences, Harbin Unjversily of Science and Technology, Harbin 150080, ChinaSchool of Applied Sciences, Harbin Unjversily of Science and Technology, Harbin 150080, ChinaSchool of Applied Sciences, Harbin Unjversily of Science and Technology, Harbin 150080, ChinaIn order to obtain better image edge information, an edge detection algorithm combining BP (Back Propagation) neural network and morphology is proposed. The Sigmoid function is commonly used as the excitation function in BP neural networks, but the traditional Sigmoid function is single in form and lacks flexibility. Therefore, it is very important to provide an adjustable Sigmoid function. First, a fully smooth Sigmoid function construction method is given, which is used as the excitation function in the BP neural network to detect the edge of the image effectively. Then, using the idea of multi-scale and multi-structure, an improved morphological edge detection algorithm is proposed, and the edge image with small noise and continuous is obtained by applying this algorithm. Finally, the wavelet analysis is used to fuse the BP neural network and the improved morphological algorithm, and then an edge detection fusion algorithm is obtained. The simulation results show that the evaluation index of the fusion algorithm is better than a single edge detection algorithm and the detected image edge lines are complete and clear.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2018back propagation neural networksigmoid functionmathematical morphologyedge detectionfusion algorithm
spellingShingle YUE Xin-hua
DENG Cai-xia
ZHANG Zhao-ru
BP Neural Network Fuse with Morphology Edge Detection Method
Journal of Harbin University of Science and Technology
back propagation neural network
sigmoid function
mathematical morphology
edge detection
fusion algorithm
title BP Neural Network Fuse with Morphology Edge Detection Method
title_full BP Neural Network Fuse with Morphology Edge Detection Method
title_fullStr BP Neural Network Fuse with Morphology Edge Detection Method
title_full_unstemmed BP Neural Network Fuse with Morphology Edge Detection Method
title_short BP Neural Network Fuse with Morphology Edge Detection Method
title_sort bp neural network fuse with morphology edge detection method
topic back propagation neural network
sigmoid function
mathematical morphology
edge detection
fusion algorithm
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2018
work_keys_str_mv AT yuexinhua bpneuralnetworkfusewithmorphologyedgedetectionmethod
AT dengcaixia bpneuralnetworkfusewithmorphologyedgedetectionmethod
AT zhangzhaoru bpneuralnetworkfusewithmorphologyedgedetectionmethod