Biometric identification of Black Bengal goat: unique iris pattern matching system vs deep learning approach
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (35)
- Bowling MB, "Identification and traceability of cattle in selected countries outside of North America", Pro Anim Sci, 24, pp.287~294 (2008)
- Edwards DS, "A comparison of commonly used ear tags on the ear damage of sheep", Anim Welf, 10, pp.141~151 (2001)[DOI]
- Gosalvez LF, "Traceability of extensively produced Iberian pigs using visual and electronic identification devices from farm to slaughter", J Anim Sci, 85, pp.2746~2752 (2007)[DOI]
- Regattieri A, "Traceability of food products : general framework and experimental evidence", J Food Eng, 81, pp.347~356 (2007)[DOI]
- Sahin E, "Performance evaluation of a traceability system", IEEE T Syst Man Cy B, 3, pp.210~218 (2002)
- Loftus R, "Traceability of biotech-derived animals : application of DNA technology", Rev Sci Tech Off Int Epiz, 24, pp.231~242 (2005)[DOI]
- Allen A, "Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland", Livest Sci, 116, pp.42~52 (2008)[DOI]
- Barry B, "Using muzzle pattern recognition as a biometric approach for cattle identification", Trans ASABE, 50, pp.1073~1080 (2007)[DOI]
- Corkery GP, "A preliminary investigation on face recognition as a biometric identifier of sheep", Trans ASABE, 50, pp.313~320 (2007)[DOI]
- Daugman J, "How iris recognition works", Proceedings of International Conference on Image Processing (2002)
- Musgrave C, "System andmethod of animal identification and animal transaction authorization using iris pattern" (2002), Technologies, Inc
- Daugman J, "New methods in iris recognition", IEEE T Syst Man Cy B, 37, pp.1167~1175 (2007)[DOI]
- Feng X, "Classifier combination and its application in iris recognition", ntern J Pattern Recognit Artif Intell, 22, pp.617~638 (2008)[DOI]
- Zhang M, "An iris localization algorithm based on geometrical features of cow eyes", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis (2009)
- Lu Y, "A new cow identification system based on iris analysis and recognition", Int J Biom, 6, pp.18~32 (2014)[DOI]
- De P, "Recognition of non circular iris pattern of the goat by structural, statistical and fourier descriptors", Procedia Comput Sci, 89, pp.845~849 (2016)[DOI]
- Roy S, "Black Bengal Goat Identification using Iris Images", Proceedings of International Conference on Frontiers in Computing and Systems. Advances in Intelligent Systems and Computing, 1255, pp.213~224 (2022)
- Sundararajan K, "Deep learning for biometrics : a survey", ACM Comput Surv(CSUR), 51, pp.1~34 (2019)[DOI]
- Minaee S, "Deepiris : Iris recognition using a deep learning approach", arXiv 2019;1907.09380, ~
- Nguyen K, "Iris recognition with off-the-shelf CNN features : A deep learning perspective", IEEE Access, 6, pp.18848~18855 (2017)[DOI]
- Nielsen MA, "Neural networks and deep learning. Vol 25" (2015), Determination Press
- Apostolidis K, "Performance evaluation of convolutional neural networks for gait recognition", 24th Pan-Hellenic Conference on Informatics, pp.61~63 (2020)
- Hwooi SKW, "Information science and applications", pp.249~257 (2020), Springer
- Masek L, "Recognition of human iris patterns for biometric identification", master, pp.2003
- Sant'Ana DA, "Computer vision system for superpixel classification and segmentation of sheep", Ecol Inform, 68, pp.101551~ (2022)[DOI]
- Pu J, "Research on Chengdu Ma goat recognition based on computer vison", Animals, 12, pp.1746~ (2022)[DOI]
- Wildes RP, "Iris recognition : an emerging biometric technology", Pro IEEE, 85, pp.1348~1363 (1997)[DOI]
- Prajwala NB, "Matching of iris pattern using image processing", Int J Recent Technol Eng, 8(2S11), pp.21~23 (2019)[DOI]
- Mandal SN, "InceptGI : a convnetbased classification model for identifying goat breeds in India", J Inst Eng India Ser B, 101, pp.573~584 (2020)[DOI]
- Bowyer KW, "Image understanding for iris biometrics : a survey", Comput Vis Image Underst, 110, pp.281~307 (2008)[DOI]
- Benalcazar DP, "A 3D iris scanner from a single image using convolutional neural networks", IEEE Access, 8, pp.98584~98599 (2020)[DOI]
- Vyas R, "Smartphone based iris recognition through optimized textural representation", Multimed Tools Appl, 79, pp.14127~14146 (2020)[DOI]
- Hamd MH, "Biometric system design for iris recognition using intelligent algorithms", Inter J Educ Mod Comp Sci, 10, pp.9~16 (2018)[DOI]
- Jayanthi J, "An effective deep learning features based integrated framework for iris detection and recognition", J Ambient Intell Humaniz Comput, 12, pp.3271~3281 (2020)[DOI]
- Daugman JG, "High confidence visual recognition of persons by a test of statistical independence", IEEE Trans Pattern Anal Mach Intell, 15, pp.1148~1161 (1993)[DOI]