Alpha-tree segmentation of human anatomical photographic imagery

Wilbert Tabone, Michael H.F. Wilkinson, Anne E.J.V. Gaalen, Janniko Georgiadis, George Azzopardi

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Segmentation of anatomical imagery is important in several areas, such as forensics, medical analysis and educational material. The manual segmentation of such images and the subsequent labelling of regions is a very laborious task. We propose an interactive segmentation scheme which we evaluate on a new data set of anatomical imagery. We use a morphological tree-based segmentation method, known as the alpha-tree, together with a Hu-moment thresholding mechanism in order to extract segments from a number of structures. Both qualitative and quantitative results in anatomical imagery of embalmed head, arm and leg specimens indicate that the proposed method can produce meaningful segmentation outputs, which could facilitate further refined labelling.

Original languageEnglish
Title of host publicationProceedings of APPIS 2019 - 2nd International Conference on Applications of Intelligent Systems
EditorsNicolai Petkov, Nicola Strisciuglio, Carlos M. Travieso
PublisherAssociation for Computing Machinery (ACM)
ISBN (Electronic)9781450360852
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event2nd International Conference on Applications of Intelligent Systems, APPIS 2019 - Las Palmas de Gran Canaria, Spain
Duration: 7 Jan 20199 Jan 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Applications of Intelligent Systems, APPIS 2019
Country/TerritorySpain
CityLas Palmas de Gran Canaria
Period7/01/199/01/19

Keywords

  • Alpha tree
  • Anatomy
  • Hu moments
  • Mathematical morphology
  • Segmentation

Fingerprint

Dive into the research topics of 'Alpha-tree segmentation of human anatomical photographic imagery'. Together they form a unique fingerprint.

Cite this