Biometric animal databases from field photographs: Identification of individual zebra in the wild

Mayank Lahiri, Chayant Tantipathananandh, Rosemary Warungu, Daniel Ian Rubenstein, Tanya Y. Berger-Wolf

Research output: Contribution to conferencePaper

51 Scopus citations

Abstract

We describe an algorithmic and experimental approach to a fundamental problem in field ecology: computer-assisted individual animal identification. We use a database of noisy photographs taken in the wild to build a biometric database of individual animals differentiated by their coat markings. A new image of an unknown animal can then be queried by its coat markings against the database to determine if the animal has been observed and identified before. Our algorithm, called StripeCodes, efficiently extracts simple image features and uses a dynamic programming algorithm to compare images. We test its accuracy against two different classes of methods: Eigenface, which is based on algebraic techniques, and matching multi-scale histograms of differential image features, an approach from signal processing. StripeCodes performs better than all competing methods for our dataset, and scales well with database size.

Original languageEnglish (US)
DOIs
StatePublished - Jul 4 2011
Event1st ACM International Conference on Multimedia Retrieval, ICMR'11 - Trento, Italy
Duration: Apr 18 2011Apr 20 2011

Other

Other1st ACM International Conference on Multimedia Retrieval, ICMR'11
CountryItaly
CityTrento
Period4/18/114/20/11

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Keywords

  • biometrics
  • ecology
  • edit distance
  • image databases

Fingerprint Dive into the research topics of 'Biometric animal databases from field photographs: Identification of individual zebra in the wild'. Together they form a unique fingerprint.

  • Cite this

    Lahiri, M., Tantipathananandh, C., Warungu, R., Rubenstein, D. I., & Berger-Wolf, T. Y. (2011). Biometric animal databases from field photographs: Identification of individual zebra in the wild. Paper presented at 1st ACM International Conference on Multimedia Retrieval, ICMR'11, Trento, Italy. https://doi.org/10.1145/1991996.1992002