Canine age classification using Deep Learning as a step towards preventive medicine in animals

• Autorzy: Mazurek Szymon , Wielgosz Maciej , Caputa Jakub , Frączek Rafał , Karwatowski Michał , Grzeszczyk Jakub , Łukasik Daria , Śmiech Anna , Russek Paweł , Jamro Ernest , Dąbrowska-Boruch Agnieszka , Pietroń Marcin , Sebastian Koryciak , Wiatr Kazimierz

Identyfikatory

DOI

10.15439/2022F226

• Konferencja: Federated Conference on Computer Science and Information Systems (17 ; 04-07.09.2022 ; Sofia, Bulgaria)
• Języki publikacji: EN

Abstrakty

EN

The main goal of this work was to implement a reliable machine learning algorithm that can classify the age of a dog, given only a photograph of its face. The problem, which seems simple for humans, presents itself as very difficult for the machine learning algorithms due to differences of facial features among the dogs population. As convolutional neural networks (CNNs) performed poorly in this problem, authors took other approach of creating novel architecture consisting of combination of CNN and vision transformer (ViT) and examining the age of the dogs separately for every breed. Authors were able to achieve better results than those in initial works covering the problem.

Słowa kluczowe

EN

deep learning; machine learning algorithm; sociology; dog; transformer; convolutional neural network; reliability

PL

głębokie uczenie; algorytm uczenia maszynowego; socjologia; pies; transformator; konwolucyjna sieć neuronowa; niezawodność

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 30
• Strony: 169--172
• Opis fizyczny: Bibliogr. 11 poz., il., tab.

Twórcy

autor

Mazurek Szymon

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Wielgosz Maciej

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Caputa Jakub

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland

autor

Frączek Rafał

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Karwatowski Michał

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Grzeszczyk Jakub

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland

autor

Łukasik Daria

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland

autor

Śmiech Anna

• University of Life Sciences, al. Akademicka 13, 20-950 Lublin, Poland

autor

Russek Paweł

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Jamro Ernest

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Dąbrowska-Boruch Agnieszka

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Pietroń Marcin

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Sebastian Koryciak

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Wiatr Kazimierz

• ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland
• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

Bibliografia

• 1. Abood S. Estimating Age in Dogs and Cats Using Ocular Lens Examination. Compendium on Continuing Education for the Practising Veterinarian - North American Edition. (2000).
• 2. Roccaro, M. & Peli, A. A determination in dog puppies by teeth examination: legal, health and welfare implications, review of the literature and practical considerations. Veterinaria Italiana 56. pp. 149-162 (2020). http://dx.doi.org/10.12834/VetIt.1876.9968.2
• 3. Sutton, L., Byrd, J. & Brooks, J. Age Determination in Dogs and Cats. Veterinary Forensic Pathology, Volume 2. pp.151-163 (2018). https://doi.org/10.1007/978-3-319-67175-8
• 4. Petfinder.com, a website for pet adoption. https://www.petfinder.com/, date accessed 30.06.2021
• 5. Tech4Animals, DogAge Challenge, http://132.75.251.84:3000/~tech4animals/dogchallenge/, date accessed: 30.06.2021
• 6. Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition. (2016). DOI :10.1109/CVPR.2016.91
• 7. Tan, M. & Le, Q.V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019. pp. 6105-6114 (2019).
• 8. Loshchilov I. & Hutter F. Decoupled Weight Decay Regularization. International Conference on Learning Representations 2017. (2017).
• 9. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J. & Houlsby, N. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. (2020). https://doi.org/10.48550/arXiv.2010.11929
• 10. Zamansky, A., Sinitca, A., Kaplun, D., Dutra, L. & Young, R., Automatic Estimation of Dog Age: The DogAge Dataset and Challenge. Artificial Neural Networks And Machine Learning – ICANN 2019: Image Processing. pp. 421-426 (2019). http://dx.doi.org/10.1007/978-3-030-30508-6
• 11. Caputa, J., Łukasik, D., Wielgosz, M., Karwatowski, M., Frączek, R., Russek, P. & Wiatr, K. Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning. Applied Sciences. 11 (2021). https://doi.org/10.3390/app11167181

Uwagi

1. The code and datasets as well as additional results available: github.com/SzymonMazurekAGH/Age_recognition_Cyfrovet.

2. Short article

3. Track 1: 1st Workshop on Artificial Intelligence for Next-Generation Diagnostic Imaging

4. Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).