Advanced search
1 file | 483.64 KB

Bipolar comparison of 3D ear models

Author
Organization
Abstract
Comparing ear photographs is considered to be an important aspect of victim identification. In this paper we study how automated ear comparison can be improved with soft computing techniques. More specifically we describe and illustrate how bipolar data modelling techniques can be used for handling data imperfections more adequately. In order to minimise rescaling and reorientation problems, we start with 3D ear models that are obtained from 2D ear photographs. To compare two 3D models, we compute and aggregate the similarities between corresponding points. Hereby, a novel bipolar similarity measure is proposed. This measure is based on Euclidian distance, but explicitly deals with hesitation caused by bad data quality. Comparison results are expressed using bipolar satisfaction degrees which, compared to traditional approaches, provide a semantically richer description of the extent to which two ear photographs match.
Keywords
IMAGES, RECOGNITION, Ear comparison, data quality, bipolarity, similarity

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 483.64 KB

Citation

Please use this url to cite or link to this publication:

Chicago
De Tré, Guy, Dirk Vandermeulen, Jeroen Hermans, Peter Claeys, Joachim Nielandt, and Antoon Bronselaer. 2014. “Bipolar Comparison of 3D Ear Models.” In Communications in Computer and Information Science, ed. Anne Laurent, Oliver Strauss, Bernadette Bouchon-Meunier, and Ronald R Yager, 444:160–169. Heidelberg, Germany: Springer.
APA
De Tré, G., Vandermeulen, D., Hermans, J., Claeys, P., Nielandt, J., & Bronselaer, A. (2014). Bipolar comparison of 3D ear models. In A. Laurent, O. Strauss, B. Bouchon-Meunier, & R. R. Yager (Eds.), Communications in Computer and Information Science (Vol. 444, pp. 160–169). Presented at the 15th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2014), Heidelberg, Germany: Springer.
Vancouver
1.
De Tré G, Vandermeulen D, Hermans J, Claeys P, Nielandt J, Bronselaer A. Bipolar comparison of 3D ear models. In: Laurent A, Strauss O, Bouchon-Meunier B, Yager RR, editors. Communications in Computer and Information Science. Heidelberg, Germany: Springer; 2014. p. 160–9.
MLA
De Tré, Guy, Dirk Vandermeulen, Jeroen Hermans, et al. “Bipolar Comparison of 3D Ear Models.” Communications in Computer and Information Science. Ed. Anne Laurent et al. Vol. 444. Heidelberg, Germany: Springer, 2014. 160–169. Print.
@inproceedings{5663298,
  abstract     = {Comparing ear photographs is considered to be an important aspect of victim identification. In this paper we study how automated ear comparison can be improved with soft computing techniques. More specifically we describe and illustrate how bipolar data modelling techniques can be used for handling data imperfections more adequately. In order to minimise rescaling and reorientation problems, we start with 3D ear models that are obtained from 2D ear photographs. To compare two 3D models, we compute and aggregate the similarities between corresponding points. Hereby, a novel bipolar similarity measure is proposed. This measure is based on Euclidian distance, but explicitly deals with hesitation caused by bad data quality. Comparison results are expressed using bipolar satisfaction degrees which, compared to traditional approaches, provide a semantically richer description of the extent to which two ear photographs match.},
  author       = {De Tr{\'e}, Guy and Vandermeulen, Dirk and Hermans, Jeroen and Claeys, Peter and Nielandt, Joachim and Bronselaer, Antoon},
  booktitle    = {Communications in Computer and Information Science},
  editor       = {Laurent, Anne and Strauss, Oliver and Bouchon-Meunier, Bernadette and Yager, Ronald R},
  isbn         = {9783319088518},
  issn         = {1865-0929},
  language     = {eng},
  location     = {Montpellier, France},
  pages        = {160--169},
  publisher    = {Springer},
  title        = {Bipolar comparison of 3D ear models},
  url          = {http://dx.doi.org/10.1007/978-3-319-08852-5\_17},
  volume       = {444},
  year         = {2014},
}

Altmetric
View in Altmetric
Web of Science
Times cited: