Markov random field segmentation for industrial computed tomography with metal artefacts

被引：4

作者：

Jaiswal, Avinash ^{[1
]}

Williams, Mark A. ^{[2
]}

Bhalerao, Abhir ^{[3
]}

Tiwari, Manoj K. ^{[1
]}

Warnett, Jason M. ^{[2
]}

机构：

[1] IIT Kharagpur, Dept Ind & Syst Engn, Kharagpur 721302, W Bengal, India

[2] Univ Warwick, WMG, Coventry, W Midlands, England

[3] Univ Warwick, Dept Comp Sci, Coventry, W Midlands, England

来源：

JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY | 2018年 / 26卷 / 04期

关键词：

Computed tomography; Markov Random Fields; segmentation; metal artefacts; STATISTICAL-ANALYSIS; CT; REDUCTION; ALGORITHM; IMAGES; RECONSTRUCTION; HIDDEN; MODEL;

D O I：

10.3233/XST-17322

中图分类号：

TH7 [仪器、仪表];

学科分类号：

0804 ; 080401 ; 081102 ;

摘要：

X-ray Computed Tomography (XCT) has become an important tool for industrial measurement and quality control through its ability to measure internal structures and volumetric defects. Segmentation of constituent materials in the volume acquired through XCT is one of the most critical factors that influence its robustness and repeatability. Highly attenuating materials such as steel can introduce artefacts in CT images that adversely affect the segmentation process, and results in large errors during quantification. This paper presents a Markov Random Field (MRF) segmentation method as a suitable approach for industrial samples with metal artefacts. The advantages of employing the MRF segmentation method are shown in comparison with Otsu thresholding on CT data from two industrial objects.

引用

页码：573 / 591

页数：19

共 50 条

[21] Unsupervised Segmentation of Markov Random Fields Corrupted by Nonstationary Noise
Habbouchi, Ahmed
Boudaren, Mohamed El Yazid
Aissani, Amar
Pieczynski, Wojciech
IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (11) : 1607 - 1611
[22] Skin Cancer Segmentation Using a Unified Markov Random Field
Salih, Omran
Viriri, Serestina
ADVANCES IN VISUAL COMPUTING, ISVC 2018, 2018, 11241 : 25 - 33
[23] Multiscale Markov Random Field Method for SAR Image Segmentation
Zhang, Jian-Guang
Wen, Xian-Bin
Jiao, Xu
Wang, Lei
PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9, 2009, : 1846 - 1850
[24] Kidney Tumor Segmentation and Detection on Computed Tomography Data
Skalski, Andrzej
Jakubowski, Jacek
Drewniak, Tomasz
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS AND TECHNIQUES (IST), 2016, : 238 - 242
[25] UNSUPERVISED TEXTURE SEGMENTATION USING MARKOV RANDOM FIELD MODELS
MANJUNATH, BS
CHELLAPPA, R
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (05) : 478 - 482
[26] Image segmentation using a unified Markov random field model
Chen, Xiaohui
Zheng, Chen
Yao, Hongtai
Wang, Bingxue
IET IMAGE PROCESSING, 2017, 11 (10) : 860 - 869
[27] Segmentation of SAR images based on Markov random field model
Lankoande, O
Hayat, MM
Santhanam, B
INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOL 1-4, PROCEEDINGS, 2005, : 2956 - 2961
[28] Oriented Markov Random Field Based Dendritic Spine Segmentation for Fluorescence Microscopy Images
Cheng, Jie
Zhou, Xiaobo
Miller, Eric L.
Alvarez, Veronica A.
Sabatini, Bernardo L.
Wong, Stephen T. C.
NEUROINFORMATICS, 2010, 8 (03) : 157 - 170
[29] Segmentation of Brain Regions by Integrating Meta Heuristic Multilevel Threshold with Markov Random Field
Krishnan, Palani T.
Balasubramanian, Parvathavarthini
Krishnan, Chitra
CURRENT MEDICAL IMAGING, 2016, 12 (01) : 4 - 12
[30] Reduction of metal artifacts for industrial computed tomography using multipositional data fusion
Herl, Gabriel
Hiller, Jochen
Und, Stefan Kasperl
Maier, Andreas
TM-TECHNISCHES MESSEN, 2020, 87 (02) : 101 - 110

← 1 2 3 4 5 →