Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches
Animal identification is essential for routine farm operations, residue traceback, insurance, and ownership management. Owing to their uniqueness, incorrigible nature, tamperproof over time, environment-friendly, and pain-free, visual biometrics- based animal identification has recently gained momen...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Akademia Baru Publishing
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/119993/ http://psasir.upm.edu.my/id/eprint/119993/1/119993.pdf |
| _version_ | 1848868093934174208 |
|---|---|
| author | Singh, Rana Ranjeet Khalid, Fatimah Ahlawat, Timur Rampalsingh Azman, Azreen Agrawal, Anuradha Ghorpade, Prerna Romle, Amirul Azuani |
| author_facet | Singh, Rana Ranjeet Khalid, Fatimah Ahlawat, Timur Rampalsingh Azman, Azreen Agrawal, Anuradha Ghorpade, Prerna Romle, Amirul Azuani |
| author_sort | Singh, Rana Ranjeet |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Animal identification is essential for routine farm operations, residue traceback, insurance, and ownership management. Owing to their uniqueness, incorrigible nature, tamperproof over time, environment-friendly, and pain-free, visual biometrics- based animal identification has recently gained momentum over traditional animal identification methods. Among visual biometrics-based cues, muzzle identification is a simple and relatively low-cost method. Therefore, to address the inherent significant limitations of conventional animal identification systems, we undertook this investigation to collect a database of digital images of muzzles that works as a benchmark, to apply deep learning frameworks to identify individual buffaloes from their muzzle images, and to compare their accuracy in terms of their identification capabilities. Muzzle images of 198 Surti buffaloes were subjected to transfer learning and fine-tuning processes in deep-learning neural networks. The performance was recorded for each pre-train model (ResNet50, InceptionV3, VGG16, AlexNet) with different hyperparameters of the epoch, batch size, and learning rate. A perusal of the data revealed that ResNet50 has the highest train accuracy (99.8%) and test accuracy (99.69%) among all four models used. AlexNet has the lowest train accuracy (90.8%) among the models. The findings concluded that all these four models could be applied to identify individual buffaloes; however, ResNet50 had the highest accuracy, and deep learning applications have great potential for individual buffalo identification and are promising tools for precision livestock farming |
| first_indexed | 2025-11-15T14:46:55Z |
| format | Article |
| id | upm-119993 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:46:55Z |
| publishDate | 2024 |
| publisher | Akademia Baru Publishing |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1199932025-10-28T05:34:43Z http://psasir.upm.edu.my/id/eprint/119993/ Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches Singh, Rana Ranjeet Khalid, Fatimah Ahlawat, Timur Rampalsingh Azman, Azreen Agrawal, Anuradha Ghorpade, Prerna Romle, Amirul Azuani Animal identification is essential for routine farm operations, residue traceback, insurance, and ownership management. Owing to their uniqueness, incorrigible nature, tamperproof over time, environment-friendly, and pain-free, visual biometrics- based animal identification has recently gained momentum over traditional animal identification methods. Among visual biometrics-based cues, muzzle identification is a simple and relatively low-cost method. Therefore, to address the inherent significant limitations of conventional animal identification systems, we undertook this investigation to collect a database of digital images of muzzles that works as a benchmark, to apply deep learning frameworks to identify individual buffaloes from their muzzle images, and to compare their accuracy in terms of their identification capabilities. Muzzle images of 198 Surti buffaloes were subjected to transfer learning and fine-tuning processes in deep-learning neural networks. The performance was recorded for each pre-train model (ResNet50, InceptionV3, VGG16, AlexNet) with different hyperparameters of the epoch, batch size, and learning rate. A perusal of the data revealed that ResNet50 has the highest train accuracy (99.8%) and test accuracy (99.69%) among all four models used. AlexNet has the lowest train accuracy (90.8%) among the models. The findings concluded that all these four models could be applied to identify individual buffaloes; however, ResNet50 had the highest accuracy, and deep learning applications have great potential for individual buffalo identification and are promising tools for precision livestock farming Akademia Baru Publishing 2024 Article PeerReviewed text en cc_by_nc_4 http://psasir.upm.edu.my/id/eprint/119993/1/119993.pdf Singh, Rana Ranjeet and Khalid, Fatimah and Ahlawat, Timur Rampalsingh and Azman, Azreen and Agrawal, Anuradha and Ghorpade, Prerna and Romle, Amirul Azuani (2024) Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches. Journal of Advanced Research in Applied Sciences and Engineering Technology, 59 (1). pp. 11-24. ISSN 2462-1943 https://semarakilmu.com.my/journals/index.php/applied_sciences_eng_tech/article/view/9884 10.37934/araset.59.2.178191 |
| spellingShingle | Singh, Rana Ranjeet Khalid, Fatimah Ahlawat, Timur Rampalsingh Azman, Azreen Agrawal, Anuradha Ghorpade, Prerna Romle, Amirul Azuani Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title | Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title_full | Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title_fullStr | Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title_full_unstemmed | Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title_short | Individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| title_sort | individual buffalo identification through muzzle dermatoglyphics images using deep learning approaches |
| url | http://psasir.upm.edu.my/id/eprint/119993/ http://psasir.upm.edu.my/id/eprint/119993/ http://psasir.upm.edu.my/id/eprint/119993/ http://psasir.upm.edu.my/id/eprint/119993/1/119993.pdf |