&lt;title&gt;Query by sketch in DARWIN: digital analysis to recognize whale images on a network&lt;/title&gt;

Wilkin, Daniel J.; Debure, Kelly R.; Roberts, Zach

doi:10.1117/12.333870

Cited by 6 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The availability of large data sets has rendered manual photo‐identification unfeasible, motivating the development of computer‐aided techniques for scanning photographic catalogues accurately and efficiently. Recent computer‐aided efforts for marine mammals have focused on the characteristic shapes and colouring of fins and flukes; these include EUROPHLUKES (Evans 2003), DARWIN (Wilkin, Debure & Roberts 1998), The Dolphin Project (Lapolla 2005) and the Mid‐Atlantic Bottlenose Dolphin Catalogue (Urian 2005). The last two use the Finscan software (Hillman et al .…”

Section: Introductionmentioning

confidence: 99%

An astronomical pattern‐matching algorithm for computer‐aided identification of whale sharks Rhincodon typus

Arzoumanian

Holmberg²,

Norman

2005

Journal of Applied Ecology

266

278

View full text Add to dashboard Cite

Summary1. The formulation of conservation policy relies heavily on demographic, biological and ecological knowledge that is often elusive for threatened species. Essential estimates of abundance, survival and life-history parameters are accessible through mark and recapture studies given a sufficiently large sample. Photographic identification of individuals is an established mark and recapture technique, but its full potential has rarely been exploited because of the unmanageable task of making visual identifications in large data sets. 2. We describe a novel technique for identifying individual whale sharks Rhincodon typus through numerical pattern matching of their natural surface 'spot' colourations. Together with scarring and other markers, spot patterns captured in photographs of whale shark flanks have been used, in the past, to make identifications by eye. We have automated this process by adapting a computer algorithm originally developed in astronomy for the comparison of star patterns in images of the night sky. 3. In tests using a set of previously identified shark images, our method correctly matched pairs exhibiting the same pattern in more than 90% of cases. From a larger library of previously unidentified images, it has to date produced more than 100 new matches. Our technique is robust in that the incidence of false positives is low, while failure to match images of the same shark is predominantly attributable to foreshortening in photographs obtained at oblique angles of more than 30 ° . 4. We describe our implementation of the pattern-matching algorithm, estimates of its efficacy, its incorporation into the new ECOCEAN Whale Shark Photo-identification Library, and prospects for its further refinement. We also comment on the biological and conservation implications of the capability of identifying individual sharks across wide geographical and temporal spans. 5. Synthesis and applications. An automated photo-identification technique has been developed that allows for efficient 'virtual tagging' of spotted animals. The pattern-matching software has been implemented within a Web-based library created for the management of generic encounter photographs and derived data. The combined capabilities have demonstrated the reliability of whale shark spot patterns for long-term identifications, and promise new ecological insights. Extension of the technique to other species is anticipated, with attendant benefits to management and conservation through improved understanding of life histories, population trends and migration routes, as well as ecological factors such as exploitation impact and the effectiveness of wildlife reserves.

show abstract

Section: Introductionmentioning

confidence: 99%

An astronomical pattern‐matching algorithm for computer‐aided identification of whale sharks Rhincodon typus

Arzoumanian

Holmberg²,

Norman

2005

Journal of Applied Ecology

266

278

View full text Add to dashboard Cite

show abstract

“…These libraries can be examined manually to develop a suite of individual matches [19]; however, as the number of photos in a library increases beyond a person's capacity to process the suite of candidate matches manually, the development of faster, automated techniques to compare new photographs to those previously obtained is required [20,21]. Several automated matching algorithms have been trialled with some success [e.g., [20,22-26]], but these are generally highly technical, specialized and target a particular taxon or unique morphological feature of the species in question (e.g., dorsal fin shape and markings in cetaceans). Furthermore, uncertainty in the matching algorithms themselves have never been contextualized within a multi-model inferential framework [27], and so subjective manual matching is still required to assess reliability [28].…”

Section: Introductionmentioning

confidence: 99%

Spot the match – wildlife photo-identification using information theory

2007

View full text Add to dashboard Cite

Background: Effective approaches for the management and conservation of wildlife populations require a sound knowledge of population demographics, and this is often only possible through mark-recapture studies. We applied an automated spot-recognition program (I 3 S) for matching natural markings of wildlife that is based on a novel information-theoretic approach to incorporate matching uncertainty. Using a photo-identification database of whale sharks (Rhincodon typus) as an example case, the information criterion (IC) algorithm we developed resulted in a parsimonious ranking of potential matches of individuals in an image library. Automated matches were compared to manual-matching results to test the performance of the software and algorithm.

show abstract

“…Early computer vision applications to assist in dorsal fin matching included the development of programs such as Darwin (Wilkin et al, 1998) and Finscan (Hillman et al, 2002), which rely on characterizing features such as unique nicks, notches, and scars along the trailing edge of a dorsal fin. While these programs automatically rank fins based on similar identifying features, they require significant time to prepare and import images.…”

Section: Introductionmentioning

confidence: 99%

Rise of the Machines: Best Practices and Experimental Evaluation of Computer-Assisted Dorsal Fin Image Matching Systems for Bottlenose Dolphins

et al. 2022

View full text Add to dashboard Cite

Photographic-identification (photo-ID) of bottlenose dolphins using individually distinctive features on the dorsal fin is a well-established and useful tool for tracking individuals; however, this method can be labor-intensive, especially when dealing with large catalogs and/or infrequently surveyed populations. Computer vision algorithms have been developed that can find a fin in an image, characterize the features of the fin, and compare the fin to a catalog of known individuals to generate a ranking of potential matches based on dorsal fin similarity. We examined if and how researchers use computer vision systems in their photo-ID process and developed an experiment to evaluate the performance of the most commonly used, recently developed, systems to date using a long-term photo-ID database of known individuals curated by the Chicago Zoological Society’s Sarasota Dolphin Research Program. Survey results obtained for the “Rise of the machines – Application of automated systems for matching dolphin dorsal fins: current status and future directions” workshop held at the 2019 World Marine Mammal Conference indicated that most researchers still rely on manual methods for comparing unknown dorsal fin images to reference catalogs of known individuals. Experimental evaluation of the finFindR R application, as well as the CurvRank, CurvRank v2, and finFindR implementations in Flukebook suggest that high match rates can be achieved with these systems, with the highest match rates found when only good to excellent quality images of fins with average to high distinctiveness are included in the matching process: for the finFindR R application and the CurvRank and CurvRank v2 algorithms within Flukebook more than 98.92% of correct matches were in the top 50-ranked positions, and more than 91.94% of correct matches were returned in the first ranked position. Our results offer the first comprehensive examination into the performance and accuracy of computer vision algorithms designed to assist with the photo-ID process of bottlenose dolphins and can be used to build trust by researchers hesitant to use these systems. Based on our findings and discussions from the “Rise of the Machines” workshop we provide recommendations for best practices for using computer vision systems for dorsal fin photo-ID.

show abstract

<title>Query by sketch in DARWIN: digital analysis to recognize whale images on a network</title>

Cited by 6 publications

References 0 publications

An astronomical pattern‐matching algorithm for computer‐aided identification of whale sharks Rhincodon typus

An astronomical pattern‐matching algorithm for computer‐aided identification of whale sharks Rhincodon typus

Spot the match – wildlife photo-identification using information theory

Rise of the Machines: Best Practices and Experimental Evaluation of Computer-Assisted Dorsal Fin Image Matching Systems for Bottlenose Dolphins

Contact Info

Product

Resources

About