Examining the viability of dorsal fin pigmentation for individual identification of poorly-marked delphinids

Abstract

Dolphin photo-identification has traditionally relied only on distinctive markings on the dorsal fin—this is problematic for delphinids whose populations exhibit a low mark ratio. We used common dolphins (genus Delphinus) as a model species to assess the viability of using pigmentation for photo-identification. Using a photo-identification catalogue of 169 adult individuals collected between 2002 and 2013, we extracted features that quantified pigmentation in a manner that was robust to lighting artefacts and dorsal fin orientation. We determined the proportion of individuals which exhibited pigmentation and examined temporal stability by (i) visually examining individuals and (ii) testing for seriation. We found 88–91% of images could be manually matched to the correct individual in the catalogue based on pigmentation patterns alone. A linear discriminant analysis classifier correctly identified the correct individual 77% of the time. We found 95% common dolphins exhibited distinctive pigmentation—all of which were temporarily stable. Our work challenges the current thinking that pigmentation is an unreliable feature for delphinid photo-identification and suggests that this feature could be applied to common dolphins and other poorly-marked delphinids.

The conservation of the endangered Mediterranean common dolphin (Delphinus delphis): Current knowledge and research priorities

“…This species is reported to have the second lowest mark ratio of any delphinid (Hupman, 2016; Neumann, Leitenberger, & Orams, 2002; Stockin & Vella, 2005) that is found in highly mobile, large pelagic aggregations. These difficulties may explain the limited number of studies dealing with photo‐identification that have been published on this species worldwide (Pawley, Hupman, Stockin, & Gilman, 2018; Stockin & Vella, 2005). In fact, only 16 peer‐reviewed works have been found including those by Neumann et al (2002); Bearzi et al (2005, 2008); Bearzi, Bonizzoni, Agazzi, Gonzalvo, and Currey (2011); Bearzi, Bonizzoni, Santostasi, Eddy, and Gimenez (2016); Genov, Bearzi, Bonizzoni, and Tempesta (2012); Bamford and Robinson (2015); Hupman (2016); Mason, Salgado Kent, Donnelly, Weir, and Bilgmann (2016); Santostasi, Bonizzoni, Bearzi, Eddy, and Gimenez (2016); Inch et al (2018); Pawley et al (2018); Santostasi, Bonizzoni, Gimenez, Eddy, and Bearzi (2021); Bouma, Pawley, Hupman, and Gilman (2018); Mussi et al (2021); and Genov et al (2021).…”

“…As part of the long‐term research effort for the species in the Central Mediterranean (Mannocci et al, 2018; Vella, 1998, 2005, 2014, 2015; Vella & Vella, 2016), unpublished photo‐identification work is also in progress. For the identification of short‐beaked common dolphin individuals, other researchers have used a combination of white patch patterns and long‐term natural markings on the dorsal fins, but it was recently demonstrated that the majority of images could be manually matched to the correct individual based on distinctive pigmentation patterns alone (Pawley et al, 2018). The unique position and shape of the dorsal edge marking and white patches of these dolphins highlighted low to medium distinctiveness of the classified dorsal fins in Italian waters, with indented mark types in the upper part of the dorsal fin and diffuse/basal white patches being the most prevalent patterns.…”

Comparisons of image-matching software when identifying pool frog (Pelophylax lessonae) individuals from a reintroduced population

“…Unlike other studies, we applied minimal operator effort (considering only the first potential matches presented as correct or not and only selecting the minimum requirement of 12 feature points when using I3S-Spot) to achieve our findings whereas others used greater levels of user effort (Sannolo et al, 2016;Treilibs et al, 2016;Matthé et al, 2017). Whilst not compared directly in this work, it is recognised that automated image processing can achieve successful match rates at least equal to manual observation, with potential for an increase in accuracy in several cases (Bendick et al, 2013;Treilibs et al, 2016;Matthé et al, 2017;Pawley et al, 2018). When comparing processing Table 1.…”

Recognition software successfully aids the identification of individual small‐spotted catsharks Scyliorhinus canicula during their first year of life

“…Animal biometrics offers a non‐invasive and economical alternative to invasive identification methods. Natural markings, scars and contours that are unique to individuals and that are maintained throughout their lives have been used for individual recognition across a variety of marine taxa including pinnipeds, cetaceans, sirenians and elasmobranchs (Gubili et al ., ; MacLeod, ; Pawley et al ., ; Wells, ). Such databases can grow large and performing the identifications manually can become time‐inefficient.…”