Advanced search

Comparison of photo-matching algorithms commonly used for photographic capture-recapture studies

(2017) ECOLOGY AND EVOLUTION. 7(15). p.5861-5872
Author
Organization
Abstract
Photographic capture-recapture is a valuable tool for obtaining demographic information on wildlife populations due to its noninvasive nature and cost-effectiveness. Recently, several computer-aided photo-matching algorithms have been developed to more efficiently match images of unique individuals in databases with thousands of images. However, the identification accuracy of these algorithms can severely bias estimates of vital rates and population size. Therefore, it is important to understand the performance and limitations of state-of-the-art photo-matching algorithms prior to implementation in capture-recapture studies involving possibly thousands of images. Here, we compared the performance of four photo-matching algorithms; Wild-ID, I3S Pattern+, APHIS, and AmphIdent using multiple amphibian databases of varying image quality. We measured the performance of each algorithm and evaluated the performance in relation to database size and the number of matching images in the database. We found that algorithm performance differed greatly by algorithm and image database, with recognition rates ranging from 100% to 22.6% when limiting the review to the 10 highest ranking images. We found that recognition rate degraded marginally with increased database size and could be improved considerably with a higher number of matching images in the database. In our study, the pixel-based algorithm of AmphIdent exhibited superior recognition rates compared to the other approaches. We recommend carefully evaluating algorithm performance prior to using it to match a complete database. By choosing a suitable matching algorithm, databases of sizes that are unfeasible to match by eye can be easily translated to accurate individual capture histories necessary for robust demographic estimates.
Keywords
AmphIdent, APHIS, capture-recapture, I3S, photographic identification, Wild-ID, MARK-RECAPTURE, INDIVIDUAL IDENTIFICATION, PATTERN, PHOTOIDENTIFICATION, SURVIVAL, MISIDENTIFICATION, RECOGNITION, FEATURES, ANIMALS, ERRORS

Citation

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

Chicago
Matthé, Maximilian, Marco Sannolo, Kristopher Winiarski, Adriana Marieke van der Sluijs, Daniel Goedbloed, Sebastian Steinfartz, and Ulrich Stachow. 2017. “Comparison of Photo-matching Algorithms Commonly Used for Photographic Capture-recapture Studies.” Ecology and Evolution 7 (15): 5861–5872.
APA
Matthé, M., Sannolo, M., Winiarski, K., van der Sluijs, A. M., Goedbloed, D., Steinfartz, S., & Stachow, U. (2017). Comparison of photo-matching algorithms commonly used for photographic capture-recapture studies. ECOLOGY AND EVOLUTION, 7(15), 5861–5872.
Vancouver
1.
Matthé M, Sannolo M, Winiarski K, van der Sluijs AM, Goedbloed D, Steinfartz S, et al. Comparison of photo-matching algorithms commonly used for photographic capture-recapture studies. ECOLOGY AND EVOLUTION. 2017;7(15):5861–72.
MLA
Matthé, Maximilian, Marco Sannolo, Kristopher Winiarski, et al. “Comparison of Photo-matching Algorithms Commonly Used for Photographic Capture-recapture Studies.” ECOLOGY AND EVOLUTION 7.15 (2017): 5861–5872. Print.
@article{8549438,
  abstract     = {Photographic capture-recapture is a valuable tool for obtaining demographic information on wildlife populations due to its noninvasive nature and cost-effectiveness. Recently, several computer-aided photo-matching algorithms have been developed to more efficiently match images of unique individuals in databases with thousands of images. However, the identification accuracy of these algorithms can severely bias estimates of vital rates and population size. Therefore, it is important to understand the performance and limitations of state-of-the-art photo-matching algorithms prior to implementation in capture-recapture studies involving possibly thousands of images. Here, we compared the performance of four photo-matching algorithms; Wild-ID, I3S Pattern+, APHIS, and AmphIdent using multiple amphibian databases of varying image quality. We measured the performance of each algorithm and evaluated the performance in relation to database size and the number of matching images in the database. We found that algorithm performance differed greatly by algorithm and image database, with recognition rates ranging from 100% to 22.6% when limiting the review to the 10 highest ranking images. We found that recognition rate degraded marginally with increased database size and could be improved considerably with a higher number of matching images in the database. In our study, the pixel-based algorithm of AmphIdent exhibited superior recognition rates compared to the other approaches. We recommend carefully evaluating algorithm performance prior to using it to match a complete database. By choosing a suitable matching algorithm, databases of sizes that are unfeasible to match by eye can be easily translated to accurate individual capture histories necessary for robust demographic estimates.},
  author       = {Matthé, Maximilian and Sannolo, Marco and Winiarski, Kristopher and van der Sluijs, Adriana Marieke and Goedbloed, Daniel and Steinfartz, Sebastian and Stachow, Ulrich},
  issn         = {2045-7758},
  journal      = {ECOLOGY AND EVOLUTION},
  keywords     = {AmphIdent,APHIS,capture-recapture,I3S,photographic identification,Wild-ID,MARK-RECAPTURE,INDIVIDUAL IDENTIFICATION,PATTERN,PHOTOIDENTIFICATION,SURVIVAL,MISIDENTIFICATION,RECOGNITION,FEATURES,ANIMALS,ERRORS},
  language     = {eng},
  number       = {15},
  pages        = {5861--5872},
  title        = {Comparison of photo-matching algorithms commonly used for photographic capture-recapture studies},
  url          = {http://dx.doi.org/10.1002/ece3.3140},
  volume       = {7},
  year         = {2017},
}

Altmetric
View in Altmetric
Web of Science
Times cited: