Semi-automated software for dorsal fin photographic identification of marine species: application to Carcharodon carcharias

Andreotti, Sara; Holtzhausen, Pieter; Rutzen, Michael; Meÿer, Michael A.; Walt, Stéfan van der; Herbst, B. M.; Matthee, Conrad A.

doi:10.1007/s12526-017-0634-2

Cited by 8 publications

(25 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Differences in dorsal fin shape are used broadly to distinguish and identify specimens at different taxonomic levels (Andreotti et al, 2018;Yahn et al, 2019) confirming the reliability of this approach for the purposes of our study. In this perspective, the creation of a public database of shark fins, along with the implementation of the landmarks-based techniques, could promote the development of reliable and easy-touse tools for a quick identification in the field (http:// www.fao.org/ipoa-sharks/tools/software/isharkfin/en/).…”

Section: Morphometric Assessmentsupporting

confidence: 68%

Call me by my name: unravelling the taxonomy of the gulper shark genus Centrophorus in the Mediterranean Sea through an integrated taxonomic approach

Bellodi

Benvenuto

Melis

et al. 2022

Zoological Journal of the Linnean Society

View full text Add to dashboard Cite

The current shift of fishery efforts towards the deep sea is raising concern about the vulnerability of deep-water sharks, which are often poorly studied and characterized by problematic taxonomy. For instance, in the Mediterranean Sea the taxonomy of genus Centrophorus has not been clearly unravelled yet. Since proper identification of the species is fundamental for their correct assessment and management, this study aims at clarifying the taxonomy of this genus in the Mediterranean Basin through an integrated taxonomic approach. We analysed a total of 281 gulper sharks (Centrophorus spp.) collected from various Mediterranean, Atlantic and Indian Ocean waters. Molecular data obtained from cytochrome c oxidase subunit I (COI), 16S ribosomal RNA (16S), NADH dehydrogenase subunit 2 (ND2) and a portion of a nuclear 28S ribosomal DNA gene region (28S) have highlighted the presence of a unique mitochondrial clade in the Mediterranean Sea. The morphometric results confirmed these findings, supporting the presence of a unique and distinct morphological group comprising all Mediterranean individuals. The data strongly indicate the occurrence of a single Centrophorus species in the Mediterranean, ascribable to C. cf. uyato, and suggest the need for a revision of the systematics of the genus in the area.

show abstract

Section: Morphometric Assessmentsupporting

confidence: 68%

Call me by my name: unravelling the taxonomy of the gulper shark genus Centrophorus in the Mediterranean Sea through an integrated taxonomic approach

Bellodi

Benvenuto

Melis

et al. 2022

Zoological Journal of the Linnean Society

View full text Add to dashboard Cite

show abstract

“…Survey respondents that reported using computer vision systems in their photo-ID process were most likely to use the finFindR R application (Thompson et al, 2021; N = 15), followed by Flukebook (Blount et al, 2020;Blount et al, 2022a; N = 5), Darwin (Wilkin et al, 1998; N = 4), and Finscan (Hillman et al, 2002; N = 2). FinBase (Adams et al, 2006), ACDSee ( © ACD Systems International Inc., 2018), a Google Application (Mann, 2018), Identifin Software (Andreotti et al, 2018), and Photo-ID Ninja (available online at https://photoid.ninja/) were also each listed once by users (Figure 3B).…”

mentioning

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

“…Leafsnap, using leaf images to identify tree species; Kumar et al, ). And, going beyond fully automated species identification, programs similar to facial recognition software could be used within EM systems to identify individual organisms that are recaptured in a fishery (including endangered, threatened and protected [ETP] species) (Andreotti et al, ; Moya et al, ), to augment the understanding of post‐release survival and population sizes, similar to mark and recapture studies.…”

Section: Results: Methods To Expand Data Fields and Improve The Accurmentioning

confidence: 99%

Increasing the functionalities and accuracy of fisheries electronic monitoring systems

Gilman

Legorburu

Fedoruk³

et al. 2019

Aquatic Conservation

View full text Add to dashboard Cite

1. Fisheries-dependent data underpin essential scientific and management applications. Electronic monitoring (EM) systems are increasingly being used to supplement human observer programmes and provide coverage where none previously existed.2. Candidate methods were identified to expand EM functionalities to collect data fields of human observer programmes that contemporary EM systems either cannot collect or require improved accuracy. Options were also identified to enable EM systems to collect new data fields that human observers cannot collect, prioritized by scientists, managers and the catch sector. 3. Many EM limitations could be resolved through simple changes of repositioning existing or adding new cameras with suitable fields of view and resolution, integrating additional sensors, and making minor modifications to fishers' practices. Research, development and trials, however, are required for possible EM integration of some existing and emerging technologies. 4. Whether an EM improvement method should be pursued requires consideration of: the relative importance for meeting monitoring objectives; the accuracy and cost of alternative monitoring methods, such as data collection by fishers with EM auditing, and by dockside inspections; impacts on fishing operations and crew safety; and net costs.5. Active support from fishers is necessary for EM collection of some data fields, where EM enables auditing fisher compliance with required procedures. Having EM systems supply data desired by the seafood industry could augment their support for EM and incentivize fisher cooperation.6. EM systems have the capacity to collect most data fields collected by human observer programmes with high precision and in some cases improved accuracy, to supply information of interest to seafood companies, and to meet expanding data requirements as fisheries management frameworks continue to transition to implementing elements of ecosystem-based fisheries management.

show abstract

Semi-automated software for dorsal fin photographic identification of marine species: application to Carcharodon carcharias

Cited by 8 publications

References 31 publications

Call me by my name: unravelling the taxonomy of the gulper shark genus Centrophorus in the Mediterranean Sea through an integrated taxonomic approach

Call me by my name: unravelling the taxonomy of the gulper shark genus Centrophorus in the Mediterranean Sea through an integrated taxonomic approach

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

Increasing the functionalities and accuracy of fisheries electronic monitoring systems

Contact Info

Product

Resources

About