This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Classifying Microfossils: Detecting Symmetry versus Neural Networks

S. Brechner and H.R. Thierstein
Fundamental Structural Properties in Image and Pattern Analysis (FSPIPA)


Two approaches are compared for the detection of microfossils. The first method detects the objects' outlines and uses the inherent symmetry for feature extraction and classification of elliptical and hammer-like objects. For the search for elliptical objects RANSAC is combined with a genetic algorithm. For the detection of hammer-like objects a hierarchical structural approach is employed which uses line-segments and symmetry axes for the shape description. In the second approach neural networks are directly applied to images after simple preprocessing to achieve invariance against translation, rotation, scaling and changes in contrast.

Download in postscript format
  author = {S. Brechner and H.R. Thierstein},
  title = {Classifying Microfossils: Detecting Symmetry versus Neural Networks},
  booktitle = {Fundamental Structural Properties in Image and Pattern Analysis (FSPIPA)},
  year = {1999},
  pages = {181--192},
  keywords = {classification,recognition,model based,natural objects,knowledge based}