Sloop: A pattern retrieval engine for individual animal identification. Issue 4 (April 2015)

• Record Type: Journal Article
• Authors: Duyck, James; Finn, Chelsea; Hutcheon, Andy; Vera, Pablo; Salas, Joaquin; Ravela, Sai
• Is Part Of: Pattern recognition. Volume 48:Issue 4(2015:Apr.)
• Page Start: 1059
• Page End: 1073
• Publication Date: 2015-04
• Subjects: Photo-identification -- Animal biometrics -- Individual identification -- Relevance feedback -- Crowdsourcing -- Conservation -- Scale-cascaded alignment -- Local features -- Hybrid shape contexts -- Gecko -- Skink -- Whale shark -- Salamander; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2014.07.017
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Identifying individuals in photographs of animals collected over time is a non-invasive approach for ecological monitoring and conservation. This paper describes the design and use of Sloop, the first image retrieval system for individual animal identification incorporating crowd-sourced relevance feedback. Sloop׳s iterative retrieval strategy using hierarchical and aggregated matching and relevance feedback consistently improves deformation and correspondence-based approaches for individual identification across several species. Its crowdsourcing strategy is successful in utilizing relevance feedback on a large scale. Sloop is in operational use. The user experience and results are presented here to facilitate the creation of a community-based individual identification system for conservation planning. Abstract : Highlights: First individual animal identification system based on relevance feedback. State-of-the-art results for five species with operational use in two of them. A framework to create scalable and extensible systems with multiple methods. An iterative strategy for integration of vision, biology, crowds and citizen science.