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 common with multi-part segmentation of many biological objects, challenges include variations in configuration, 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 context 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.
Original language | English |
---|---|
Pages (from-to) | 290-296 |
Number of pages | 7 |
Journal | Pattern Recognition Letters |
Volume | 112 |
Early online date | 30 Jul 2018 |
DOIs | |
Publication status | Published - 01 Sept 2018 |
Externally published | Yes |
Bibliographical note
Funding Information:We are grateful to Sheralyn Smith, Gareth Woodward and Lazar Valkov for annotating images, to Katharine Yuill and Jake Waddilove for expert advice, and to colleagues at Tulip Ltd and Hellenic Systems Ltd for support throughout this research. Tulip Ltd provided access to their abattoir facility. This work was supported by the BBSRC (grants BB/L017385/1 and BB/L017423/1 ) and Innovate UK. The project also received funding from Tulip Ltd. and Hellenic Systems Ltd.
Publisher Copyright:
© 2018 The Authors
Keywords
- Atlas-based segmentation
- Auto-context
- Automated inspection
- Multi-class segmentation
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence