Optimizing the automated recognition of individual animals to support population monitoring

Reliable estimates of population size and demographic rates are central to assessing the status of threatened species. However, obtaining individual-based demographic rates requires long-term data, which is often costly and difficult to collect. Photographic data offer an inexpensive, noninvasive method for individual-based monitoring of species with unique markings, and could therefore increase available demographic data for many species. However, selecting suitable images and identifying individuals from photographic catalogs is prohibitively time-consuming. Automated identification software can significantly speed up this process. Nevertheless, automated methods for selecting suitable images are lacking, as are studies comparing the performance of the most prominent identification software packages. In this study, we develop a framework that automatically selects images suitable for individual identification, and compare the performance of three commonly used identification software packages; Hotspotter, I3S-Pattern, and WildID. As a case study, we consider the African wild dog, Lycaon pictus, a species whose conservation is limited by a lack of cost-effective large-scale monitoring. To evaluate intraspecific variation in the performance of software packages, we compare identification accuracy between two populations (in Kenya and Zimbabwe) that have markedly different coat coloration patterns. The process of selecting suitable images was automated using convolutional neural networks that crop individuals from images, filter out unsuitable images, separate left and right flanks, and remove image backgrounds. Hotspotter had the highest image-matching accuracy for both populations. However, the accuracy was significantly lower for the Kenyan population (62%), compared to the Zimbabwean population (88%). Our automated image preprocessing has immediate application for expanding monitoring based on image matching. However, the difference in accuracy between populations highlights that population-specific detection rates are likely and may influence certainty in derived statistics. For species such as the African wild dog, where monitoring is both challenging and expensive, automated individual recognition could greatly expand and expedite conservation efforts.

Increasing numbers of harbour seals and grey seals in the Solent

Harbour seals (Phoca vitulina) and grey seals (Halichoerus grypus) both occur within the UK, but display regional contrasting population trends. While grey seals are typically increasing in number, harbour seals have shown varying trends in recent decades following repeated pandemics. There is a need for monitoring of regional and local populations to understand overall trends. This study utilized a 20-year dataset of seal counts from two neighboring harbours in the Solent region of south England. Generalized additive models showed a significant increase in the numbers of harbour (mean 5.3-30.5) and grey (mean 0-12.0) seals utilizing Chichester Harbour. Conversely, in Langstone Harbour there has been a slight decrease in the number of harbour seals (mean 5.3-4.0). Accompanying photographic data from 2016 to 18 supports the increase in seal numbers within Chichester Harbour, with a total of 68 harbour and 8 grey seals identified. These data also show evidence of site fidelity of harbour seals in this area, with almost a quarter of animals resighted within the past three years. Overall, this long-term study indicates an increasing number of both harbour and grey seals within the Solent. However, more research is required to identify the drivers of this trend.

Photo-identification comparison of four Indo-Pacific humpback dolphin populations off southeast China

Indo-Pacific humpback dolphins (Sousa chinensis) inhabit shallow coastal waters of the Indo-Pacific region including southeast China, with at least 6 putative populations identified to date in Chinese waters. However, the connectivity among these populations has not yet been fully investigated. In the present study, we compared and cross-matched photographic catalogs of individual dolphins collected to date in the Pearl River Delta region, Leizhou Bay, Sanniang Bay, and waters southwest of Hainan Island, a total of 3158 individuals, and found no re-sighting of individual dolphins among the 4 study areas. Furthermore, there was a notable difference in the pigmentation pattern displayed by individuals from these 4 regions. We suggest that this may be a phenotypical expression of fine-scale regional differentiation among humpback dolphin groups, possibly distinct populations. Given the considerable conservation management implications it may carry (e.g. definition of management units), further research is much needed.

Genotyping validates the efficacy of photographic identification in a capture-mark-recapture study based on the head scale patterns of the prairie lizard (Sceloporus consobrinus)

Population studies often incorporate capture-mark-recapture (CMR) techniques to gather information on long-term biological and demographic characteristics. A fundamental requirement for CMR studies is that an individual must be uniquely and permanently marked to ensure reliable reidentification throughout its lifespan. Photographic identification involving automated photographic identification software has become a popular and efficient noninvasive method for identifying individuals based on natural markings. However, few studies have (a) robustly assessed the performance of automated programs by using a double-marking system or (b) determined their efficacy for long-term studies by incorporating multi-year data. Here, we evaluated the performance of the program Interactive Individual Identification System (I3S) by cross-validating photographic identifications based on the head scale pattern of the prairie lizard (Sceloporus consobrinus) with individual microsatellite genotyping (N = 863). Further, we assessed the efficacy of the program to identify individuals over time by comparing error rates between within-year and between-year recaptures. Recaptured lizards were correctly identified by I3S in 94.1% of cases. We estimated a false rejection rate (FRR) of 5.9% and a false acceptance rate (FAR) of 0%. By using I3S, we correctly identified 97.8% of within-year recaptures (FRR = 2.2%; FAR = 0%) and 91.1% of between-year recaptures (FRR = 8.9%; FAR = 0%). Misidentifications were primarily due to poor photograph quality (N = 4). However, two misidentifications were caused by indistinct scale configuration due to scale damage (N = 1) and ontogenetic changes in head scalation between capture events (N = 1). We conclude that automated photographic identification based on head scale patterns is a reliable and accurate method for identifying individuals over time. Because many lizard or reptilian species possess variable head squamation, this method has potential for successful application in many species.

Killer whale abundance and predicted narwhal consumption in the Canadian Arctic

Range expansions and increases in the frequency of killer whale (Orcinus orca) sightings have been documented in the eastern Canadian Arctic, presumably the result of climate change-related sea-ice declines. However, the effects of increased predator occurrence on this marine ecosystem remain largely unknown. We explore the consequences of climate change-related range expansions by a top predator by estimating killer whale abundance and their possible consumptive effects on narwhal (Monodon monoceros) in the Canadian Arctic. Individual killer whales can be identified using characteristics such as acquired scars and variation in the shape and size of their dorsal fins. Capture-mark-recapture analysis of 63 individually identifiable killer whales photographed between 2009 and 2018 suggests a population size of 163 ± 27. This number of killer whales could consume >1,000 narwhal during their seasonal residency in Arctic waters. The effects of such mortality at the ecosystem level are uncertain, but trophic cascades caused by top predators, including killer whales, have been documented elsewhere. These findings illustrate the magnitude of ecosystem-level modifications that can occur with climate change-related shifts in predator distributions.

Unfamiliar Face Matching With Driving Licence and Passport Photographs

Matching two different images of an unfamiliar face is difficult, although we rely on this process every day when proving our identity. Although previous work with laboratory photosets has shown that performance is error-prone, few studies have focussed on how accurately people carry out this matching task using photographs taken from official forms of identification. In Experiment 1, participants matched high-resolution, colour face photos with current UK driving licence photos of the same group of people in a sorting task. Averaging 19 mistaken pairings out of 30, our results showed that this task was both difficult and error-prone. In Experiment 2, high-resolution photographs were paired with either driving licence or passport photographs in a typical pairwise matching paradigm. We found no difference in performance levels for the two types of ID image, with both producing unacceptable levels of accuracy (around 75%-79% correct). The current work benefits from increased ecological validity and provides a clear demonstration that these forms of official identification are ineffective and alternatives should be considered.

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

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.

Manta Matcher: automated photographic identification of manta rays using keypoint features

For species which bear unique markings, such as natural spot patterning, field work has become increasingly more reliant on visual identification to recognize and catalog particular specimens or to monitor individuals within populations. While many species of interest exhibit characteristic markings that in principle allow individuals to be identified from photographs, scientists are often faced with the task of matching observations against databases of hundreds or thousands of images. We present a novel technique for automated identification of manta rays (Manta alfredi and Manta birostris) by means of a pattern-matching algorithm applied to images of their ventral surface area. Automated visual identification has recently been developed for several species. However, such methods are typically limited to animals that can be photographed above water, or whose markings exhibit high contrast and appear in regular constellations. While manta rays bear natural patterning across their ventral surface, these patterns vary greatly in their size, shape, contrast, and spatial distribution. Our method is the first to have proven successful at achieving high matching accuracies on a large corpus of manta ray images taken under challenging underwater conditions. Our method is based on automated extraction and matching of keypoint features using the Scale-Invariant Feature Transform (SIFT) algorithm. In order to cope with the considerable variation in quality of underwater photographs, we also incorporate preprocessing and image enhancement steps. Furthermore, we use a novel pattern-matching approach that results in better accuracy than the standard SIFT approach and other alternative methods. We present quantitative evaluation results on a data set of 720 images of manta rays taken under widely different conditions. We describe a novel automated pattern representation and matching method that can be used to identify individual manta rays from photographs. The method has been incorporated into a website (mantamatcher.org) which will serve as a global resource for ecological and conservation research. It will allow researchers to manage and track sightings data to establish important life-history parameters as well as determine other ecological data such as abundance, range, movement patterns, and structure of manta ray populations across the world.