By matching structural body shape models of several ant species to a macroscopic color image morphological features of the specimen are detected. This enables a proof of concept implementation for semantic content based image retrieval for the MCZ Type Specimen Database @ Harvard Entomology. alt text The code is available on GitHub with auto-generated documentation.

The hierarchical recognition model contains:

  • a compound deformable model where occurrence of structural components influences the distribution for search for further shapes (e.g. a neck should be near the head and vice versa),
  • a finite element model of deformable shape components, for which the involved physical parameters are learned from training data,
  • a multi-scale feature extraction including color edge and corner detection,
  • a parametric Gaussian color space model for ant skin classification.

All details are published in my thesis (bibtex) and a summary is provided in the ICIP04 paper (bibtex).