Visualization-Guided Classification of Carbonized Seeds from Early Human Civilizations | TU Wien

Information

Publication Type: Master Thesis
Workgroup(s)/Project(s):
- Visualization Group
Date: November 2020
Date (Start): 12. January 2020
Date (End): 25. November 2020
Second Supervisor: Manuela Waldner
Diploma Examination: 15. December 2020
Open Access: yes
First Supervisor: Eduard Gröller
Pages: 105
Keywords: Visualization-Guided Classification, Ancient Seeds

Abstract

Since the Neolithic Revolution approximately 10.000 years ago, crop plants are an important part of our food. Researchers of archeobotany try to ﬁnd and determine the species that humankind used already in the past. Most of the gathered samples are preserved due to carbonization, but the shape and inner structures are deformed because of this process. The amount of distortion is given by the temperature and the time they are heated. Normally, an expert is consulted to classify them. Since there are only a few experts in this ﬁeld, an automatic approach is requested. The result of this work is a software, which can load the Computed Tomography (CT) scans, segment and separate the seeds within the samples, calculate diﬀerent shape features as descriptors, and train a classiﬁer. To have an overview of how the seeds look like, diﬀerent volume visualizations are available to show selected samples or median seeds of each class. To validate the probabilities of the learner, additional visualizations are available, which show the inﬂuence of the extracted features on the classiﬁcation. A cross validation method with 1043 known samples results in a classiﬁcation accuracy of 85 %. The incorrectly classiﬁed samples of the ground truth are visualized to display the expert user where they are located regard to the extracted features and which results are especially inaccurate. It turned out, that the opportunity to export the features into a tabular ﬁletype and the visualization of the output probabilities of the classiﬁer for each species were particularly helpful for the domain experts.

Additional Files and Images

Additional images and videos

Image

Additional files

Master Thesis

Poster

Weblinks

BibTeX

@mastersthesis{Gogel2020,
  title =      "Visualization-Guided  Classification of Carbonized  Seeds
               from Early Human  Civilizations",
  author =     "Andreas Gogel",
  year =       "2020",
  abstract =   "Since the Neolithic Revolution approximately 10.000 years
               ago, crop plants are an important part of our food.
               Researchers of archeobotany try to ﬁnd and determine the
               species that humankind used already in the past. Most of the
               gathered samples are preserved due to carbonization, but the
               shape and inner structures are deformed because of this
               process. The amount of distortion is given by the
               temperature and the time they are heated. Normally, an
               expert is consulted to classify them. Since there are only a
               few experts in this ﬁeld, an automatic approach is
               requested. The result of this work is a software, which can
               load the Computed Tomography (CT) scans, segment and
               separate the seeds within the samples, calculate diﬀerent
               shape features as descriptors, and train a classiﬁer. To
               have an overview of how the seeds look like, diﬀerent
               volume visualizations are available to show selected samples
               or median seeds of each class. To validate the probabilities
               of the learner, additional visualizations are available,
               which show the inﬂuence of the extracted features on the
               classiﬁcation. A cross validation method with 1043 known
               samples results in a classiﬁcation accuracy of 85 %. The
               incorrectly classiﬁed samples of the ground truth are
               visualized to display the expert user where they are located
               regard to the extracted features and which results are
               especially inaccurate. It turned out, that the opportunity
               to export the features into a tabular ﬁletype and the
               visualization of the output probabilities of the classiﬁer
               for each species were particularly helpful for the domain
               experts.",
  month =      nov,
  pages =      "105",
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien",
  keywords =   "Visualization-Guided Classification, Ancient Seeds",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2020/Gogel2020/",
}