A Visual Analytics Approach to Hypocotyl/Root Transition Detection in Arabidopsis Thaliana

Information

  • Publication Type: Bachelor Thesis
  • Workgroup(s)/Project(s):
  • Date: January 2018
  • Date (to): January 2018
  • Matrikelnummer: 01426125
  • First Supervisor: Viktor Vad

Abstract

Plant root phenotyping can be a tedious process if done manually, since it typically requires large data sets to be processed. The solution to this problem are automatic phenotyping pipelines, which allow significantly higher throughput than manual methods, by eliminating the need for human intervention. These pipelines rely on the robustness of automatic segmentation and detection methods for various plant characteristics. Due to numerous confounding factors, the detection of the hypocotyl/root transition point is still an unsolved task. In this thesis a novel approach to this problem, utilizing Statistical Break Point Analysis based on custom plant features, is presented. The approach has been developed using a visual analytics framework called PlateViewer, which was especially built for this task. The framework is able to analyze individual Arabidopsis Thaliana seedlings, taken from agar plate scan images, produced by an automatic phenotyping pipeline.

Additional Files and Images

Additional images and videos

Additional files

Weblinks

No further information available.

BibTeX

@bachelorsthesis{Strohmayer-2018-BT,
  title =      "A Visual Analytics Approach to Hypocotyl/Root Transition
               Detection in Arabidopsis Thaliana",
  author =     "Julian Strohmayer",
  year =       "2018",
  abstract =   "Plant root phenotyping can be a tedious process if done
               manually, since it typically requires large data sets to be
               processed. The solution to this problem are automatic
               phenotyping pipelines, which allow significantly higher
               throughput than manual methods, by eliminating the need for
               human intervention. These pipelines rely on the robustness
               of automatic segmentation and detection methods for various
               plant characteristics. Due to numerous confounding factors,
               the detection of the hypocotyl/root transition point is
               still an unsolved task. In this thesis a novel approach to
               this problem, utilizing Statistical Break Point Analysis
               based on custom plant features, is presented. The approach
               has been developed using a visual analytics framework called
               PlateViewer, which was especially built for this task. The
               framework is able to analyze individual Arabidopsis Thaliana
               seedlings, taken from agar plate scan images, produced by an
               automatic phenotyping pipeline. ",
  month =      jan,
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Institute of Computer Graphics and Algorithms, Vienna
               University of Technology ",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2018/Strohmayer-2018-BT/",
}