Segmentation of organs in pig offal using auto-context

Telmo  Amaral; Ilias  Kyriazakis; Stephen McKenna; Thomas  Plotz

doi:10.1109/ISBI.2016.7493511

Segmentation of organs in pig offal using auto-context

Telmo Amaral, Ilias Kyriazakis, Stephen McKenna, Thomas Plotz

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

429 Downloads (Pure)

Abstract

The segmentation of 2D images of 3D non-rigid objects into their constituent parts can pose challenging problems, such as missing and occluded parts, weak constraints over the spatial arrangement of parts, and variance in form and appearance. These problems have been addressed via segmentation methods that incorporate spatial context information, such as the auto-context technique. In this paper, we address for the ﬁrst time the problem of segmenting multiple organs in images of pig offal, a challenging image analysis task that constitutes an essential step towards automated screening at abattoir for signs of sub-clinical diseases. We applied auto-context segmentation to a large data set of images and explored the effect of complementing conventional context features with integral features suited to our application.

Original language	English
Title of host publication	2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
Subtitle of host publication	From Nano to Macro, ISBI 2016 - Proceedings
Publisher	IEEE
Pages	1324-1328
Number of pages	5
Volume	June-2016
ISBN (Electronic)	9781479923496
ISBN (Print)	9781479923502
DOIs	https://doi.org/10.1109/ISBI.2016.7493511
Publication status	Published - 16 Jun 2016
Event	2016 IEEE 13th International Symposium on Biomedical Imaging - Clarion Congress Hotel, Prague, Czech Republic Duration: 13 Apr 2016 → 16 Apr 2016 http://biomedicalimaging.org/2016/ (Link to Conference website)

Conference

Conference	2016 IEEE 13th International Symposium on Biomedical Imaging
Abbreviated title	ISBI 2016
Country/Territory	Czech Republic
City	Prague
Period	13/04/16 → 16/04/16
Internet address	http://biomedicalimaging.org/2016/ (Link to Conference website)

Keywords

Context
Feature extraction
Training
Image segmentation
Heart
Lungs
Image color analysis

Access to Document

10.1109/ISBI.2016.7493511

Author Accepted ManuscriptAccepted author manuscript, 1.16 MB

Automated Screening for Pathologies at Abattoir Through Computer Vision-Based Inspection of Pig Carcases (Joint with Tulip Limited, Hellenic Systems, University of Newcastle and BPEX)
McKenna, S. (Investigator)
Biotechnology and Biological Sciences Research Council
31/01/14 → 31/10/17
Project: Research

Cite this

@inproceedings{cf8eb9e8c8ec4090850a32eefcab1939,

title = "Segmentation of organs in pig offal using auto-context",

abstract = "The segmentation of 2D images of 3D non-rigid objects into their constituent parts can pose challenging problems, such as missing and occluded parts, weak constraints over the spatial arrangement of parts, and variance in form and appearance. These problems have been addressed via segmentation methods that incorporate spatial context information, such as the auto-context technique. In this paper, we address for the ﬁrst time the problem of segmenting multiple organs in images of pig offal, a challenging image analysis task that constitutes an essential step towards automated screening at abattoir for signs of sub-clinical diseases. We applied auto-context segmentation to a large data set of images and explored the effect of complementing conventional context features with integral features suited to our application.",

keywords = "Context, Feature extraction, Training, Image segmentation, Heart, Lungs, Image color analysis",

author = "Telmo Amaral and Ilias Kyriazakis and Stephen McKenna and Thomas Plotz",

year = "2016",

month = jun,

day = "16",

doi = "10.1109/ISBI.2016.7493511",

language = "English",

isbn = "9781479923502",

volume = "June-2016",

pages = "1324--1328",

booktitle = "2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)",

publisher = "IEEE",

note = "2016 IEEE 13th International Symposium on Biomedical Imaging, ISBI 2016 ; Conference date: 13-04-2016 Through 16-04-2016",

url = "http://biomedicalimaging.org/2016/",

}

Amaral, T, Kyriazakis, I, McKenna, S & Plotz, T 2016, Segmentation of organs in pig offal using auto-context. in 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI): From Nano to Macro, ISBI 2016 - Proceedings. vol. June-2016, IEEE, pp. 1324-1328, 2016 IEEE 13th International Symposium on Biomedical Imaging, Prague, Czech Republic, 13/04/16. https://doi.org/10.1109/ISBI.2016.7493511

TY - GEN

T1 - Segmentation of organs in pig offal using auto-context

AU - Amaral, Telmo

AU - Kyriazakis, Ilias

AU - McKenna, Stephen

AU - Plotz, Thomas

PY - 2016/6/16

Y1 - 2016/6/16

N2 - The segmentation of 2D images of 3D non-rigid objects into their constituent parts can pose challenging problems, such as missing and occluded parts, weak constraints over the spatial arrangement of parts, and variance in form and appearance. These problems have been addressed via segmentation methods that incorporate spatial context information, such as the auto-context technique. In this paper, we address for the ﬁrst time the problem of segmenting multiple organs in images of pig offal, a challenging image analysis task that constitutes an essential step towards automated screening at abattoir for signs of sub-clinical diseases. We applied auto-context segmentation to a large data set of images and explored the effect of complementing conventional context features with integral features suited to our application.

AB - The segmentation of 2D images of 3D non-rigid objects into their constituent parts can pose challenging problems, such as missing and occluded parts, weak constraints over the spatial arrangement of parts, and variance in form and appearance. These problems have been addressed via segmentation methods that incorporate spatial context information, such as the auto-context technique. In this paper, we address for the ﬁrst time the problem of segmenting multiple organs in images of pig offal, a challenging image analysis task that constitutes an essential step towards automated screening at abattoir for signs of sub-clinical diseases. We applied auto-context segmentation to a large data set of images and explored the effect of complementing conventional context features with integral features suited to our application.

KW - Context

KW - Feature extraction

KW - Training

KW - Image segmentation

KW - Heart

KW - Lungs

KW - Image color analysis

U2 - 10.1109/ISBI.2016.7493511

DO - 10.1109/ISBI.2016.7493511

M3 - Conference contribution

SN - 9781479923502

VL - June-2016

SP - 1324

EP - 1328

BT - 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)

PB - IEEE

T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging

Y2 - 13 April 2016 through 16 April 2016

ER -

Segmentation of organs in pig offal using auto-context

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

Automated Screening for Pathologies at Abattoir Through Computer Vision-Based Inspection of Pig Carcases (Joint with Tulip Limited, Hellenic Systems, University of Newcastle and BPEX)

Cite this