Pattern recognition for animal identification

Abstract

Image recognition techniques can be used to identify animals based on patterns occuring on the animal (such as the stripe pattern on zebra). Currently we investigate image pattern recognition techniques that can be used to identify animal species through the classication of their hair patterns. This investigation should result in a system that provides sufficiently accurate information which can be used by a researcher to corroborate findings from a manual hair identication process. The system will be pilot-tested in a real-life pattern recognition application of identifying the hair of prey found in predator scat.

Participants

Journal Articles

[1] Greg Foster, Hans Krijger, and Shaun Bangay. Zebra fingerprints: towards a computer-aided identification system for individual zebra. African Journal of Ecology, 45(2):225-227, June 2007. [PDF] [BibTeX]

Conference Papers (peer reviewed)

[1] Thamsanqa Moyo, Shaun Bangay, and Greg Foster. The identification of mammalian species through the classification of hair patterns using image pattern recognition. In Afrigraph '06: Proceedings of the 4th international conference on Computer graphics, virtual reality, visualisation and interaction in Africa, pages 177-181, Cape Town, South Africa, January 2006. ACM Press, New York, NY, USA. [PDF] [BibTeX]

Technical Reports

[1] Thamsanqa Moyo. A literature review of techniques applicable to mammalian hair identification. Technical Report Literature Review, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, June 2005. [PDF] [BibTeX]

[2] Thamsanqa Moyo. The identification of mammalian species through the classification of hair patterns using image pattern recognition. Technical Report Honours Project Report, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, November 2005. [PDF] [BibTeX]

[3] Thamsanqa Moyo. Hair pattern recognition. Technical Report Poster, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, August 2005. [PDF] [PNG] [BibTeX]

[4] Hans Krijger, Greg Foster, and Shaun Bangay. Designing a framework for animal identification. Technical report, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, November 2002. [PDF] [BibTeX]

[5] Hans Krijger. Individual zebra identification; an investigation into image pre-processing, stripe extraction and pattern matching techniques. Technical Report Honours Project Report, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, November 2002. [PDF] [BibTeX]

Images