A Self-attention Residual Convolutional Neural Network for Health Condition Classification of Cow Teat Images
Minghao Wang
TL;DR
The paper tackles automated assessment of teat health to support mastitis risk management by classifying teat-end hyperkeratosis from cow-teat images. It introduces CTSAR-CNN, a self-attention residual CNN designed to be robust to farm-environment variability and teat posture, configured for a four-class health grading. Empirical results show CTSAR-CNN achieving 62.63% test accuracy, modestly better than GoogLeNet, suggesting benefits from residual connections and self-attention though gains are constrained by data scarcity. The approach promises practical utility for dairy farms, with future work focusing on larger, more diverse datasets and enhanced augmentation to improve generalization across breeds and environments.
Abstract
Milk is a highly important consumer for Americans and the health of the cows' teats directly affects the quality of the milk. Traditionally, veterinarians manually assessed teat health by visually inspecting teat-end hyperkeratosis during the milking process which is limited in time, usually only tens of seconds, and weakens the accuracy of the health assessment of cows' teats. Convolutional neural networks (CNNs) have been used for cows' teat-end health assessment. However, there are challenges in using CNNs for cows' teat-end health assessment, such as complex environments, changing positions and postures of cows' teats, and difficulty in identifying cows' teats from images. To address these challenges, this paper proposes a cows' teats self-attention residual convolutional neural network (CTSAR-CNN) model that combines residual connectivity and self-attention mechanisms to assist commercial farms in the health assessment of cows' teats by classifying the magnitude of teat-end hyperkeratosis using digital images. The results showed that upon integrating residual connectivity and self-attention mechanisms, the accuracy of CTSAR-CNN has been improved. This research illustrates that CTSAR-CNN can be more adaptable and speedy to assist veterinarians in assessing the health of cows' teats and ultimately benefit the dairy industry.