A Dynamic Mode Decomposition Based Edge Detection Method for Art Images

Edge detection is a widely used feature extraction method in various fields, such as image processing, computer vision, machine vision, and so forth. However, it is still a challenging task to extract edges from art images, due to the false edge, shadow, and double lines of art images. In this paper...

Full description

Saved in:
Bibliographic Details
Main Authors: Chongke Bi, Ye Yuan, Ronghui Zhang, Yiqing Xiang, Yuehuan Wang, Jiawan Zhang
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8085124/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710568856879104
author Chongke Bi
Ye Yuan
Ronghui Zhang
Yiqing Xiang
Yuehuan Wang
Jiawan Zhang
author_facet Chongke Bi
Ye Yuan
Ronghui Zhang
Yiqing Xiang
Yuehuan Wang
Jiawan Zhang
author_sort Chongke Bi
collection DOAJ
description Edge detection is a widely used feature extraction method in various fields, such as image processing, computer vision, machine vision, and so forth. However, it is still a challenging task to extract edges from art images, due to the false edge, shadow, and double lines of art images. In this paper, we propose a dynamic mode decomposition algorithm (DMD) based method for edge detection of art images. This is achieved by proposing a new color space based denoise method to deal with the shadow issue. Then, the false edge and double lines can be resolved by employing DMD method, which can be used to extract sparse features from the denoised images. Here, the sparse features have been enhanced by a new designed eight direction gradient operator. Finally, the effectiveness of our method will be demonstrated through detecting the edges of three classical types of art images (Comic, Oil Painting, and Printmaking).
format Article
id doaj-art-e2ff440baf974b0e97eef362456d3391
institution DOAJ
issn 1943-0655
language English
publishDate 2017-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-e2ff440baf974b0e97eef362456d33912025-08-20T03:14:51ZengIEEEIEEE Photonics Journal1943-06552017-01-019611310.1109/JPHOT.2017.27668818085124A Dynamic Mode Decomposition Based Edge Detection Method for Art ImagesChongke Bi0https://orcid.org/0000-0002-4324-8028Ye Yuan1Ronghui Zhang2https://orcid.org/0000-0001-6107-4044Yiqing Xiang3Yuehuan Wang4Jiawan Zhang5https://orcid.org/0000-0002-0667-6744School of Computer Software, Tianjin University, Tianjin, ChinaSchool of Computer Software, Tianjin University, Tianjin, ChinaGuangdong Key Laboratory of Intelligent Transportation System, School of Engineering, Sun Yat-Sen University, Guangzhou, ChinaSchool of Computer Software, Tianjin University, Tianjin, ChinaSchool of Computer Software, Tianjin University, Tianjin, ChinaSchool of Computer Software, Tianjin University, Tianjin, ChinaEdge detection is a widely used feature extraction method in various fields, such as image processing, computer vision, machine vision, and so forth. However, it is still a challenging task to extract edges from art images, due to the false edge, shadow, and double lines of art images. In this paper, we propose a dynamic mode decomposition algorithm (DMD) based method for edge detection of art images. This is achieved by proposing a new color space based denoise method to deal with the shadow issue. Then, the false edge and double lines can be resolved by employing DMD method, which can be used to extract sparse features from the denoised images. Here, the sparse features have been enhanced by a new designed eight direction gradient operator. Finally, the effectiveness of our method will be demonstrated through detecting the edges of three classical types of art images (Comic, Oil Painting, and Printmaking).https://ieeexplore.ieee.org/document/8085124/Image processingimage edge detectionfilteringoptical filtersoptical engineering.
spellingShingle Chongke Bi
Ye Yuan
Ronghui Zhang
Yiqing Xiang
Yuehuan Wang
Jiawan Zhang
A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
IEEE Photonics Journal
Image processing
image edge detection
filtering
optical filters
optical engineering.
title A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
title_full A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
title_fullStr A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
title_full_unstemmed A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
title_short A Dynamic Mode Decomposition Based Edge Detection Method for Art Images
title_sort dynamic mode decomposition based edge detection method for art images
topic Image processing
image edge detection
filtering
optical filters
optical engineering.
url https://ieeexplore.ieee.org/document/8085124/
work_keys_str_mv AT chongkebi adynamicmodedecompositionbasededgedetectionmethodforartimages
AT yeyuan adynamicmodedecompositionbasededgedetectionmethodforartimages
AT ronghuizhang adynamicmodedecompositionbasededgedetectionmethodforartimages
AT yiqingxiang adynamicmodedecompositionbasededgedetectionmethodforartimages
AT yuehuanwang adynamicmodedecompositionbasededgedetectionmethodforartimages
AT jiawanzhang adynamicmodedecompositionbasededgedetectionmethodforartimages
AT chongkebi dynamicmodedecompositionbasededgedetectionmethodforartimages
AT yeyuan dynamicmodedecompositionbasededgedetectionmethodforartimages
AT ronghuizhang dynamicmodedecompositionbasededgedetectionmethodforartimages
AT yiqingxiang dynamicmodedecompositionbasededgedetectionmethodforartimages
AT yuehuanwang dynamicmodedecompositionbasededgedetectionmethodforartimages
AT jiawanzhang dynamicmodedecompositionbasededgedetectionmethodforartimages