Animal Bioscience

  • 제36권6호
  • /
  • Pages.980-989
  • /
  • 2023
  • /
  • 2765-0189(pISSN)
  • /
  • 2765-0235(eISSN)
아세아태평양축산학회 (Asian Australasian Association of Animal Production Societies)
권호 표지
DOI QR코드

DOI QR Code

Biometric identification of Black Bengal goat: unique iris pattern matching system vs deep learning approach

  • Menalsh Laishram (Department of Livestock Production Management, West Bengal University of Animal and Fishery Sciences) ;
  • Satyendra Nath Mandal (Department of Information Technology, Kalyani Government Engineering College) ;
  • Avijit Haldar (ICAR-Agricultural Technology Application Research Institute Kolkata, Indian Council of Agricultural Research) ;
  • Shubhajyoti Das (Department of Information Technology, Kalyani Government Engineering College) ;
  • Santanu Bera (Department of Livestock Production Management, West Bengal University of Animal and Fishery Sciences) ;
  • Rajarshi Samanta (Department of Livestock Production Management, West Bengal University of Animal and Fishery Sciences)
  • 투고 : 2022.04.18
  • 심사 : 2022.09.26
  • 발행 : 2023.06.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: Iris pattern recognition system is well developed and practiced in human, however, there is a scarcity of information on application of iris recognition system in animals at the field conditions where the major challenge is to capture a high-quality iris image from a constantly moving non-cooperative animal even when restrained properly. The aim of the study was to validate and identify Black Bengal goat biometrically to improve animal management in its traceability system. Methods: Forty-nine healthy, disease free, 3 months±6 days old female Black Bengal goats were randomly selected at the farmer's field. Eye images were captured from the left eye of an individual goat at 3, 6, 9, and 12 months of age using a specialized camera made for human iris scanning. iGoat software was used for matching the same individual goats at 3, 6, 9, and 12 months of ages. Resnet152V2 deep learning algorithm was further applied on same image sets to predict matching percentages using only captured eye images without extracting their iris features. Results: The matching threshold computed within and between goats was 55%. The accuracies of template matching of goats at 3, 6, 9, and 12 months of ages were recorded as 81.63%, 90.24%, 44.44%, and 16.66%, respectively. As the accuracies of matching the goats at 9 and 12 months of ages were low and below the minimum threshold matching percentage, this process of iris pattern matching was not acceptable. The validation accuracies of resnet152V2 deep learning model were found 82.49%, 92.68%, 77.17%, and 87.76% for identification of goat at 3, 6, 9, and 12 months of ages, respectively after training the model. Conclusion: This study strongly supported that deep learning method using eye images could be used as a signature for biometric identification of an individual goat.

키워드

과제정보

The authors would like to express their gratitude to Dr. A. Bandopadhyay, Senior Consultant, ITRA, Ag&Food, Government of India for perceiving the concept of the research work. The authors are thankful to Dr. Manoranjan Roy, Principal Investigator of All India Coordinated Research Project on Goat Improvement and Assistant Professor, Animal Genetics and Breeding, West Bengal University of Animal and Fishery Sciences, Kolkata- 700037, West Bengal, India for extending necessary supports to collect the data at Rangabelia, Gosaba Block, Sunderbans delta, West Bengal, India. The necessary help and cooperation extended by Mr. Kaushik Mukherjee, Mr. Sanket Dan, Mr. Kunal Roy, Mr. Subhranil Mustafi, Mr. Subhojit Roy and Mr. Pritam Ghosh, Department of Information Technology, Kalyani Government Engineering College, Kalyani, Nadia- 741235, West Bengal, India are duly acknowledged.

참고문헌

  1. Bowling MB, Pendell DL, Morris DL, et al. Identification and traceability of cattle in selected countries outside of North America. Pro Anim Sci 2008;24:287-94. https://doi.org/10.15232/S1080-7446(15)30858-5
  2. Edwards DS, Johnston AM, Pfeiffer DU. A comparison of commonly used ear tags on the ear damage of sheep. Anim Welf 2001;10:141-51. https://doi.org/10.1017/S0962728600023812
  3. Gosalvez LF, Santamarina C, Averos X, Hernandez-Jover M, Caja G, Babot D. Traceability of extensively produced Iberian pigs using visual and electronic identification devices from farm to slaughter. J Anim Sci 2007;85:2746-52. https://doi.org/10.2527/jas.2007-0173
  4. Regattieri A, Gamber M, Manzini R. Traceability of food products: general framework and experimental evidence. J Food Eng 2007;81:347-56. https://doi.org/10.1016/j.jfoodeng.2006.10.032
  5. Sahin E, Dallery Y, Gershwin S. Performance evaluation of a traceability system. IEEE T Syst Man Cy B 2002;3:210-8.
  6. Loftus R. Traceability of biotech-derived animals: application of DNA technology. Rev Sci Tech Off Int Epiz 2005;24:231-42. https://doi.org/10.20506/rst.24.1.1563 
  7. Allen A, Golden B, Taylor M, Patterson D, Henriksen D, Skuce R. Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland. Livest Sci 2008;116:42-52. https://doi.org/10.1016/j.livsci.2007.08.018
  8. Barry B, Gonzales-Barron UA, Mcdonnell K, Butler F, Ward S. Using muzzle pattern recognition as a biometric approach for cattle identification. Trans ASABE 2007;50:1073-80. https://doi.org/10.13031/2013.23121
  9. Corkery GP, Gonzales-Barron UA, Butler F, McDennell K, Ward S. A preliminary investigation on face recognition as a biometric identifier of sheep. Trans ASABE 2007;50:313-20. https://doi.org/10.13031/2013.22395
  10. Daugman J. How iris recognition works. In: Proceedings of International Conference on Image Processing 1; 2002, Sept 22-5; Rochester, NY, USA.
  11. Musgrave C, Cambier JL. System andmethod of animal identification and animal transaction authorization using iris pattern. Moorestown, NJ, USA: Iridian Technologies, Inc.; 2002. US Patent 6424727.
  12. Daugman J. New methods in iris recognition. IEEE T Syst Man Cy B 2007;37:1167-75. https://doi.org/10.1109/TSMCB.2007.903540
  13. Feng X, Ding X, Wu Y, Wang PSP. Classifier combination and its application in iris recognition. ntern J Pattern Recognit Artif Intell 2008;22:617-38. https://doi.org/10.1142/S0218001408006314
  14. Zhang M, Zhao L,. An iris localization algorithm based on geometrical features of cow eyes. Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749517 (30 October 2009). https://doi.org/10.1117/12.832494
  15. Lu Y, He X, Wen Y, Wang PSP. A new cow identification system based on iris analysis and recognition. Int J Biom 2014;6:18-32. https://doi.org/10.1504/IJBM.2014.059639
  16. De P, Ghoshal D. Recognition of non circular iris pattern of the goat by structural, statistical and fourier descriptors. Procedia Comput Sci 2016;89:845-9. https://doi.org/10.1016/j.procs.2016.06.070
  17. Roy S, Dan S, Mukherjee K, et al. Black Bengal Goat Identification using Iris Images. Pro Int Con Front Com Sys 2020: 213-24. In: Bhattacharjee D, Kole DK, Dey N, Basu S, Plewczynski D, editors. Proceedings of International Conference on Frontiers in Computing and Systems. Advances in Intelligent Systems and Computing; 2022. vol 1255. Springer, Singapore. https://doi.org/10.1007/978-981-15-7834-2_20
  18. Sundararajan K, Woodard DL. Deep learning for biometrics: a survey. ACM Comput Surv (CSUR) 2019;51:1-34. https://doi.org/10.1145/3190618
  19. Minaee S, Abdolrashidi A. Deepiris: Iris recognition using a deep learning approach. arXiv 2019;1907.09380. https://doi.org/10.48550/arXiv.1907.09380
  20. Nguyen K, Fookes C, Ross A, Sridharan S. Iris recognition with off-the-shelf CNN features: A deep learning perspective. IEEE Access 2017;6:18848-55. https://doi.org/10.1109/ACCESS.2017.2784352
  21. Nielsen MA. Neural networks and deep learning. Vol 25, San Francisco, CA, USA: Determination Press; 2015.
  22. Apostolidis K, Amanatidis P, Papakostas G. Performance evaluation of convolutional neural networks for gait recognition. In 24th Pan-Hellenic Conference on Informatics; 2020. pp. 61-3.
  23. Hwooi SKW, Loo CK, Sabri AQM. Emotion differentiation based on arousal intensity estimation from facial expressions. In: Information science and applications; Singapore, Springer; 2020. pp. 249-57.
  24. Masek L. Recognition of human iris patterns for biometric identification [master's thesis]. Crawley, WA, Australia: School of Computer Science and Software Engineering, the University of Western Australia; 2003.
  25. Sant'Ana DA, Pache MCB, Martins J, et al. Computer vision system for superpixel classification and segmentation of sheep. Ecol Inform 2022;68:101551. https://doi.org/10.1016/j.ecoinf.2021.101551
  26. Pu J, Yu C, Chen X, Zhang Y, Yang X, Li J. Research on Chengdu Ma goat recognition based on computer vison. Animals 2022; 12:1746. https://doi.org/10.3390/ani12141746
  27. Wildes RP. Iris recognition: an emerging biometric technology. Pro IEEE 1997;85:1348-63. https://doi.org/10.1109/5.628669
  28. Prajwala NB, Pushpa NB. Matching of iris pattern using image processing. Int J Recent Technol Eng 2019;8(2S11):21-3. https://doi.org/10.35940/ijrte.B1004.0982S1119
  29. Mandal SN, Ghosh P, Mukherjee K, et al. InceptGI: a convnet-based classification model for identifying goat breeds in India. J Inst Eng India Ser B 2020;101:573-84. https://doi.org/10.1007/s40031-020-00471-8
  30. Bowyer KW, Hollingsworth K, Flynn PJ. Image understanding for iris biometrics: a survey. Comput Vis Image Underst 2008; 110:281-307. https://doi.org/10.1016/j.cviu.2007.08.005
  31. Benalcazar DP, Zambrano JE, Bastias D, Perez CA, Bowyer KW. A 3D iris scanner from a single image using convolutional neural networks. IEEE Access 2020;8:98584-99. https://doi.org/10.1109/ACCESS.2020.2996563
  32. Vyas R, Kanumuri T, Sheoran G, Dubey P. Smartphone based iris recognition through optimized textural representation. Multimed Tools Appl 2020;79:14127-46. https://doi.org/10.1007/s11042-019-08598-7
  33. Hamd MH, Ahmed SK. Biometric system design for iris recognition using intelligent algorithms. Inter J Educ Mod Comp Sci 2018;10:9-16. https://doi.org/10.5815/ijmecs.2018.03.02
  34. Jayanthi J, Lydia EL, Krishnaraj N, Jayasankar T, Babu RL, Suji RA. An effective deep learning features based integrated framework for iris detection and recognition. J Ambient Intell Humaniz Comput 2020;12:3271-81. https://doi.org/10.1007/s12652-020-02172-y
  35. Daugman JG. High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 1993;15:1148-61. https://doi.org/10.1109/34.244676