Toggle Main Menu Toggle Search

Open Access padlockePrints

Multi-part segmentation for porcine offal inspection with auto-context and adaptive atlases

Lookup NU author(s): Dr Telmo Amaral, Dr Thomas Ploetz, Professor Ilias Kyriazakis

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

Extensions to auto-context segmentation are proposed and applied to segmentation of multiple organs in porcine offal as a component of an envisaged system for post-mortem inspection at abbatoir. In com- mon with multi-part segmentation of many biological objects, challenges include variations in configura- tion, orientation, shape, and appearance, as well as inter-part occlusion and missing parts. Auto-context uses context information about inferred class labels and can be effective in such settings. Whereas auto- context uses a fixed prior atlas, we describe an adaptive atlas method better suited to represent the multimodal distribution of segmentation maps. We also design integral context features to enhance con- text representation. These methods are evaluated on a dataset captured at abbatoir and compared to a method based on conditional random fields. Results demonstrate the appropriateness of auto-context and the beneficial effects of the proposed extensions for this application.


Publication metadata

Author(s): McKenna S, Amaral T, Ploetz T, Kyriazakis I

Publication type: Article

Publication status: Published

Journal: Pattern Recognition Letters

Year: 2018

Volume: 112

Pages: 290-296

Print publication date: 01/09/2018

Online publication date: 30/07/2018

Acceptance date: 29/07/2018

Date deposited: 22/08/2018

ISSN (print): 0167-8655

ISSN (electronic): 1872-7344

Publisher: Elsevier BV

URL: https://doi.org/10.1016/j.patrec.2018.07.031

DOI: 10.1016/j.patrec.2018.07.031


Altmetrics

Altmetrics provided by Altmetric


Funding

Funder referenceFunder name
BB/L017385/1Biotechnology and Biological Sciences Research Council (BBSRC)
BB/L017423/1

Share