Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features

Color, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility o...

Full description

Bibliographic Details
Main Authors: Liu Shuang, Chen Deyun, Chen Zhifeng, Pang Ming
Format: Article
Language:English
Published: Taylor & Francis Group 2019-10-01
Series:Computer Assisted Surgery
Subjects:
Online Access:http://dx.doi.org/10.1080/24699322.2018.1560087
id doaj-5353132efa644217b74b09da2d059e82
record_format Article
spelling doaj-5353132efa644217b74b09da2d059e822020-11-25T02:11:24ZengTaylor & Francis GroupComputer Assisted Surgery2469-93222019-10-01240728010.1080/24699322.2018.15600871560087Multi-feature fusion method for medical image retrieval using wavelet and bag-of-featuresLiu Shuang0Chen Deyun1Chen Zhifeng2Pang Ming3Harbin University of Science and TechnologyHarbin University of Science and TechnologyHarbin University of CommerceHarbin Engineering UniversityColor, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility of the retrieval process, many features can be combined to be used for medical image retrieval. Meanwhile, more features require more processing time, which will decrease the retrieval speed. In this paper, wavelet decomposition is adopted to generate different resolution images. Bag-of-feature, texture, and LBP feature are extracted from three different-level wavelet images. Finally, the similarity measure function is obtained by fusing these three types of features. Experimental results show that the proposed multi-feature fusion method can achieve a higher retrieval accuracy with an acceptable retrieval time.http://dx.doi.org/10.1080/24699322.2018.1560087Wordmedical image retrievalbag-of-featuretexture featureLBP feature
collection DOAJ
language English
format Article
sources DOAJ
author Liu Shuang
Chen Deyun
Chen Zhifeng
Pang Ming
spellingShingle Liu Shuang
Chen Deyun
Chen Zhifeng
Pang Ming
Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
Computer Assisted Surgery
Word
medical image retrieval
bag-of-feature
texture feature
LBP feature
author_facet Liu Shuang
Chen Deyun
Chen Zhifeng
Pang Ming
author_sort Liu Shuang
title Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
title_short Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
title_full Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
title_fullStr Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
title_full_unstemmed Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
title_sort multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
publisher Taylor & Francis Group
series Computer Assisted Surgery
issn 2469-9322
publishDate 2019-10-01
description Color, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility of the retrieval process, many features can be combined to be used for medical image retrieval. Meanwhile, more features require more processing time, which will decrease the retrieval speed. In this paper, wavelet decomposition is adopted to generate different resolution images. Bag-of-feature, texture, and LBP feature are extracted from three different-level wavelet images. Finally, the similarity measure function is obtained by fusing these three types of features. Experimental results show that the proposed multi-feature fusion method can achieve a higher retrieval accuracy with an acceptable retrieval time.
topic Word
medical image retrieval
bag-of-feature
texture feature
LBP feature
url http://dx.doi.org/10.1080/24699322.2018.1560087
work_keys_str_mv AT liushuang multifeaturefusionmethodformedicalimageretrievalusingwaveletandbagoffeatures
AT chendeyun multifeaturefusionmethodformedicalimageretrievalusingwaveletandbagoffeatures
AT chenzhifeng multifeaturefusionmethodformedicalimageretrievalusingwaveletandbagoffeatures
AT pangming multifeaturefusionmethodformedicalimageretrievalusingwaveletandbagoffeatures
_version_ 1724914367217008640