Novel Deep Learning Framework For Bovine Iris Segmentation
This work addresses the problem of animal biometric identification for livestock management, but it is incremental as it applies existing methods to a specific domain.
The paper tackled bovine iris segmentation for livestock traceability by proposing a novel deep learning framework that achieved 99.50% accuracy and a 98.35% Dice coefficient score on the BovineAAEyes80 dataset.
Iris segmentation is the initial step to identify biometric of animals to establish a traceability system of livestock. In this study, we propose a novel deep learning framework for pixel-wise segmentation with minimum use of annotation labels using BovineAAEyes80 public dataset. In the experiment, U-Net with VGG16 backbone was selected as the best combination of encoder and decoder model, demonstrating a 99.50% accuracy and a 98.35% Dice coefficient score. Remarkably, the selected model accurately segmented corrupted images even without proper annotation data. This study contributes to the advancement of the iris segmentation and the development of a reliable DNNs training framework.