Abstract
Identifying individual animals, especially in large mammals, is an important goal for wildlife biologists and managers. Bears, occupying diverse habitats, face and experience significant conflict. Among Asian bears, the sloth bear Melursus ursinus (Shaw, 1791; Vulnerable IUCN Red List) is reported vulnerable due to negative interactions with humans, requiring solutions like identifying bear individuals using morphological features. To do so, we used an image-comparison algorithm to evaluate the uniqueness of chest markings using structural similarity index (SSIM) and trained a deep learning model based on the EfficientNet architecture for predicting an individual bear classification. We collected 1567 images (of 144 bears) to examine individual-level differences in chestmark patterns. The comparison yielded 98% accuracy in differentiating chestmarks as a unique pattern for an individual. Subsequently, we trained a circular classification model based on EfficientNet framework using augmented 5628 images for training (80%; of 115 bears), which was validated over 95% for top one and 99% for five individual predictions on 1407 testing images (20%; of 115 bears). The final step involved passing 58 non-augmented images (of 29 out-of-train bears), and the top five predictions of closely similar patterns suggested by the model were then manually compared for similarities in shapes, which suggested whether the image belonged to a new individual. The high accuracy of comparison and classification models suggests the potential applicability of this technique for helping maintain the ex-situ bear database, identifying the conflict individual and estimating bear populations.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are not publicly available due to the sensitive nature and threatened status of the species, the data can be provided on reasonable request to the organization Wildlife SOS and the corresponding author.
References
Aiyadurai A, Verma S (2008) Evaluating status of forests and relative abundance of wildlife: a rapid survey from a remote and little explored tropical evergreen forest of North-east India. J Bombay Nat Hist Soc 105(2):139–147
Alibhai S, Jewell Z, Evans J (2017) The challenge of monitoring elusive large carnivores: An accurate and cost-effective tool to identify and sex pumas (Puma concolor) from footprints. PLoS ONE 12(3):e0172065. https://doi.org/10.1371/journal.pone.0172065
Anderson CJR, da Vitoria LN, Roth JD, Waterman JM (2010) Computer-aided photo-identification system with an application to polar bears based on whisker spot patterns. J Mammal 91(6):1350–1359. https://doi.org/10.1644/09-MAMM-A-425.1
Ardovini A, Cinque L, Sangineto E (2008) Identifying elephant photos by multi-curve matching. Pattern Recognit 41(6):1867–1877. https://doi.org/10.1016/j.patcog.2007.11.010
Bashir T, Bhattacharya T, Poudyal K, Sathyakumar S, Qureshi Q (2013) Estimating leopard cat Prionailurus bengalensis densities using photographic captures and recaptures. Wildl Biol 19(4):462–472. https://doi.org/10.2981/12-098
Blanc L, Marboutin E, Gatti S, Gimenez O (2013) Abundance of rare and elusive species: Empirical investigation of closed versus spatially explicit capture-recapture models with lynx as a case study. J Wildl Manange 77(2):372–378. https://doi.org/10.1002/jwmg.453
Brust CA, Burghardt T, Groenenberg M, Käding C, Kühl HS, Manguette ML, Denzler J (2017) Towards automated visual monitoring of individual gorillas in the wild. Proc IEEE Int Conf Conput vis Workshops 2017:2820–2830. https://doi.org/10.1109/ICCVW.2017.333
Chen Y, Garcia EK, Gupta MR, Rahimi A, Cazzanti L (2009) Similarity-based classification: concepts and algorithms. J Mach Learn Res 10:747–776
Clapham M, Miller E, Nguyen M, Darimont CT (2020) Automated facial recognition for wildlife that lack unique markings: a deep learning approach for brown bears. Ecol Evol 10(23):12883–12892. https://doi.org/10.1002/ece3.6840
Clapham M, Miller E, Nguyen M, van Horn RC (2022) Multispecies facial detection for individual identification of wildlife: a case study across ursids. Mamm Biol 102(3):921–933. https://doi.org/10.1007/s42991-021-00168-5
de Vries MFW (1995) Large herbivores and the design of large-scale nature reserves in western Europe. Conserv Biol 9(1):5–33. https://doi.org/10.1046/j.1523-1739.1995.09010025.x
Dharaiya N, Bargali HS, Sharp T (2020) Melursus ursinus (amended version of 2016 assessment) In the IUCN red list of threatened species 2020. https://doi.org/10.2305/IUCN.UK.2020-1.RLTS.T13143A166519315.en.
Dosselmann R, Yang XD (2011) A comprehensive assessment of the structural similarity index. Signal Image Video Process 5(1):81–91. https://doi.org/10.1007/s11760-009-0144-1
East R (1981) Species-area curves and populations of large mammals in African savanna reserves. Biol Conserv 21(2):111–126. https://doi.org/10.1016/0006-3207(81)90074-4
Efford M, Fewster RM (2013) Estimating population size by spatially explicit capture-recapture. Oikos 122(6):918–928. https://doi.org/10.1111/j.1600-0706.2012.20440.x
Eisenberg JF (1980) The density and biomass of tropical mammals. In: Wilcox B, Soule M (eds) Conservation biology: an evolutionary-ecological perspective. Sinauer Associates, Sunderland, pp 35–55
Gros PM, Kelly MJ, Caro TM (1996) Estimating carnivore densities for conservation purposes: Indirect methods compared to baseline demographic data. Oikos 77(2):197–206. https://doi.org/10.2307/3546058
Gu K, Zhai G, Yang X, Zhang W (2012) An improved full-reference image quality metric based on structure compensation. Proceedings of the Asia Pacific Signal and Information Proc Assoc Annu Summit Conf IEEE 2012. ISBN 978–1–4673–4863–8. http://www.apsipa.org/proceedings_2012/papers/64.pdf.
Higashide D, Miura S, Miguchi H (2012) Are chest marks unique to Asiatic black bear individuals? J Zool 288(3):199–206. https://doi.org/10.1111/j.1469-7998.2012.00942.x
Howe EJ, Buckland ST, Després-Einspenner ML, Kühl HS (2017) Distance sampling with camera traps. Methods Ecol Evol 8(11):1558–1565. https://doi.org/10.1111/2041-210X.12790
IUCN (2023) IUCN SSC guidelines on human-wildlife conflict and coexistence. First edition. Gland, Switzerland: IUCN. https://portals.iucn.org/library/sites/library/files/documents/2023-009-En.pdf
Jeong JS, Kim YJ (2014) Structural similarity index for image assessment using pixel difference and saturation awareness. J KIISE 41(10):847–858
Jewell ZC, Alibhai S, Law PR, Uiseb K, Lee S (2020) Monitoring rhinoceroses in Namibia’s private custodianship properties. PeerJ 8:e9670. https://doi.org/10.7717/peerj.9670
Jewell ZC, Alibhai SK, Weise F, Munro S, van Vuuren M, van Vuuren R (2016) Spotting cheetahs: Identifying individuals by their footprints. J Vis Exp 2016(111). https://doi.org/10.3791/54034.
Jhala YV, Qureshi Q, Bhuva V, Sharma LN (1999) Population estimation of Asiatic lions. J Bombay Nat Hist Soc 96:3–15
Jhala YV, Qureshi Q, Yadav SP (2020) Status of leopards in India 2018. Technical Report TR/2020/16. National Tiger Conservation Authority, Government of India, New Delhi, and Wildlife Institute of India. Dehradun. https://wii.gov.in/tiger_reports.
Joshi AR, Garshelis DL, Smith JLD (1997) Seasonal and habitat-related diets of sloth bears in Nepal. J Mammal 78(2):587–597. https://doi.org/10.2307/1382910
Karanth KU (1995) Estimating tiger Panthera trigris populations from camera-trap data using capture-recapture models. Biol Conserv 71(3):333–338. https://doi.org/10.1016/0006-3207(94)00057-W
Kelly MJ, Noss AJ, di Bitetti MS, Maffei L, Arispe RL et al (2008) Estimating puma densities from camera trapping across three study sites: Bolivia, Argentina, and Belize. J Mammal 89(2):408–418. https://doi.org/10.1644/06-MAMM-A-424R.1
Kumara HN, Rathnakumar S, Sasi R, Singh M (2012) Conservation status of wild mammals in Biligiri Rangaswamy Temple Wildlife Sanctuary, the Western Ghats. India Curr Sci 103(8):933–940
Law PR, Jewell Z, Alibhai S (2013) Using shape and size to quantify variation in footprints for individual identification: Case study with white rhinoceros (Ceratotherium simum). Wildl Soc Bull 37(2):433–438. https://doi.org/10.1002/wsb.250
Lettink M, Armstrong DP (2003) An introduction to using mark-recapture analysis for monitoring threatened species. In Using mark-recapture analysis for monitoring threatened species: introduction and case study. Department of Conservation Technical Series 28A: 05–32. https://www.doc.govt.nz/Documents/science-and-technical/docts28a.pdf.
Li BV, Alibhai S, Jewell Z, Li D, Zhang H (2018) Using footprints to identify and sex giant pandas. Biol Conserv 218:83–90. https://doi.org/10.1016/j.biocon.2017.11.029
McRae L, Freeman R, Geldmann J, Moss GB, Kjær-Hansen L, Burgess ND (2022) A global indicator of utilized wildlife populations: Regional trends and the impact of management. One Earth 5(4):422–433. https://doi.org/10.1016/j.oneear.2022.03.014
Miththapala S, Seidensticker J, Phillips LG, Fernando SBU, Smallwood JA (1989) Identification of individual leopards (Panthera pardus kotiya) using spot pattern variation. J Zool 218:527–536. https://doi.org/10.1111/j.1469-7998.1989.tb04996.x
Moreira DO, Alibhai SK, Jewell ZC, da Cunha CJ, Seibert JB, Gatti A (2018) Determining the numbers of a landscape architect species (Tapirus terrestris), using footprints. PeerJ 6:e4591. https://doi.org/10.7717/peerj.4591
Nanni L, Minchio G, Brahnam S, Maguolo G, Lumini A (2021) Experiments of image classification using dissimilarity spaces built with siamese networks. Sensors 21(5):1–17. https://doi.org/10.3390/s21051573
Ngoprasert D, Reed DH, Steinmetz R, Gale GA (2012) Density estimation of Asian bears using photographic capture-recapture sampling based on chest marks. Ursus 23(2):117–133. https://doi.org/10.2192/URSUS-D-11-00009.1
O’Brien TG, Kinnaird MF, Wibisono HT (2003) Crouching tigers, hidden prey: Sumatran tiger and prey populations in a tropical forest landscape. Anin Conserv 6(2):131–139. https://doi.org/10.1017/S1367943003003172
Penjor D, Dorji T (2020) Circumstances of human conflicts with bears and patterns of bear maul injuries in Bhutan: review of records 2015–2019. PLoS ONE 15(8):e0237812. https://doi.org/10.1371/journal.pone.0237812
Pennycuick CJ, Rudnai J (1970) A method of identifying individual lions Panthera leo with an analysis of the reliability of identification. J Zool 160(4):497–508. https://doi.org/10.1111/j.1469-7998.1970.tb03093.x.
Penteriani V, Melletti M (2020) Bears of the world: Ecology, conservation and management. Cambridge University Press. pp 388 + xxi. ISBN 9781108483520.
Puri M, Srivathsa A, Karanth KK, Kumar NS, Karanth KU (2015) Multiscale distribution models for conserving widespread species: the case of sloth bear Melursus ursinus in India. Divers Distrib 21(9):1087–1100. https://doi.org/10.1111/ddi.12335
R Core Team (2022). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
Rajput D, Wang WJ, Chen CC (2023) Evaluation of a decided sample size in machine learning applications. BMC Bioinform 24(1):48. https://doi.org/10.1186/s12859-023-05156-9
Ratnayeke S, van Manen FT, Pieris R, Pragash VSJ (2007) Landscape characteristics of sloth bear range in Sri Lanka. Ursus 18(2):189–202. https://doi.org/10.2192/1537-6176(2007)18[189:LCOSBR]2.0.CO;2
Reyes A, Rodríguez D, Reyes-Amaya N, Rodríguez-Castro D, Restrepo H, Urquijo M (2017) Comparative efficiency of photographs and videos for individual identification of the Andean bear (Tremarctos ornatus) in camera trapping. Therya 8(1):83–87. https://doi.org/10.12933/therya-17-453.
Roberge JM, Angelstam P (2004) Usefulness of the umbrella species concept as a conservation tool. Conserv Biol 18(1):76–85. https://doi.org/10.1111/j.1523-1739.2004.00450.x
Rowcliffe JM, Field J, Turvey ST, Carbone C (2008) Estimating animal density using camera traps without the need for individual recognition. J Appl Ecol 45(4):1228–1236. https://doi.org/10.1111/j.1365-2664.2008.01473.x
Sara U, Akter M, Uddin MS (2019) Image quality assessment through FSIM, SSIM, MSE and PSNR- a comparative study. J Comput Commun 7(3):8–18. https://doi.org/10.4236/jcc.2019.73002
Schofield D, Nagrani A, Zisserman A, Hayashi M, Matsuzawa T, Biro D, Carvalho S (2019) Chimpanzee face recognition from videos in the wild using deep learning. Sci Adv 5(9). https://doi.org/10.1126/sciadv.aaw0736.
Sharp TR, Smith TS, Swaminathan S, Arun AS (2022) Sloth bear attacks: regional differences and safety messaging. Sci Rep 12(1):3943. https://doi.org/10.1038/s41598-022-07974-y
Shi C, Jing XU, Roberts NJ, Liu D, Jiang G (2023) Individual automatic detection and identification of big cats with the combination of different body parts. Integr Zool 18(1):157–168. https://doi.org/10.1111/1749-4877.12641
Singh P, Macdonald DW (2017) Populations and activity patterns of clouded leopard and marbled cats in Dampa Tiger Reserve, India. J Mammal 98(5):1453–1462. https://doi.org/10.1093/jmammal/gyx104
Singh P, Gopalaswamy AM, Karanth KU (2010) Factors influencing densities of striped hyenas (Hyaena hyaena) in arid regions of India. J Mammal 91(5):1152–1159. https://doi.org/10.1644/09-MAMM-A-159.1
Smelyakov K, Honchar Y, Bohomolov O, Chupryna A (2022) Machine learning models efficiency analysis for image classification problem. 6th International Conference on Computational Linguistics and Intelligent Systems. Gliwice, Poland. https://ceur-ws.org/Vol-3171/paper68.pdf.
Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. Proc 36th Int Conf Mach Learn, Long Beach, California. pp 6105–6114. arXiv:1905.11946v5. https://doi.org/10.48550/arXiv.1905.11946.
Thompson WL, White GC, Gowan C (1998) Monitoring vertebrate populations. Academic Press. Elsevier. pp 365 + xv. https://doi.org/10.1016/B978-0-12-688960-4.X5000-X.
van Horn RC, Zug B, Lacombe C, Velez-Liendo X, Paisley S (2014) Human visual identification of individual Andean bears Tremarctos ornatus. Wildl Biol 20(5):291–299. https://doi.org/10.2981/wlb.00023
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
Wang Z, Bovik AC, Sheikh HR (2017) Structural similarity based image quality assessment. In: Digital Video image quality and perceptual coding. CRC Press, pp 225–242
Wei T, Simko V (2021) R package ‘corrplot’: Visualization of a correlation matrix (version 0.92). https://github.com/taiyun/corrplot.
Yoganand K, Rice CG, Johnsingh AJT (2005) Evaluating Panna National Park with special reference to ecology of sloth bear (Melursus ursinus). Report. Wildlife Institute of India, Dehradun, India. pp 08. https://www.bearbiology.org/fileadmin/tpl/Downloads/Grants/Final_Reports/YOGANAND_Sloth_Bear_Panna_Report_Summary.pdf.
Zhang H, Yuan B, Dong B, Jiang Z (2018) No-reference blurred image quality assessment by structural similarity index. Appl Sci 8(10):2003. https://doi.org/10.3390/app8102003
Acknowledgements
First, we thank Wildlife SOS for providing all the facilities from bear to finance for conducting the study; also, warm thanks to Lenu Kannan and Manoj Chaurasiya for helping during the photograph collection. Dr Ilayaraja and Dr Rajat hold a significant vote of thanks. Also, we acknowledge Karnataka Forest Department, Madhya Pradesh Forest Department and Uttar Pradesh Forest Department for providing the required research permits to conduct the study. We thank the researchers who provided their valuable time for the blind test. AKJ thanks Sree, Dev, Shimontika, Mohit P, Jason DG, Mohit M, Varun, Pushkar, Abhishek and Avinash (Ballu) for their input in enhancing the quality of research.
Funding
No external funding was received for conducting the study.
Author information
Authors and Affiliations
Contributions
Conceptualization: AKJ, AAS; methodology: AKJ; formal analysis and investigation: AKJ, ST, NC; writing—original draft preparation: AKJ; writing—review and editing: AKJ, AAS, ST, NC, BMV, TS, KS, GS; funding acquisition: AKJ, AAS, KS, GS; resources: AKJ; Supervision: AAS.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Ethical statement
No animal was physically harmed by the authors during the field exercises.
Additional information
Handling editor: Heiko Georg Rödel.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jangid, A.K., Sha, A.A., Thakkar, S. et al. Bear biometrics: developing an individual recognition technique for sloth bears. Mamm Biol 104, 165–173 (2024). https://doi.org/10.1007/s42991-023-00396-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42991-023-00396-x