Facial Region Analysis for Individual Identification of Cows and Feeding Time Estimation

Abstract

With the increasing number of cows per farmer in Japan, an automatic cow monitoring system is being introduced. One important aspect of such a system is the ability to identify individual cows and estimate their feeding time. In this study, we propose a method for achieving this goal through facial region analysis. We used a YOLO detector to extract the cow head region from video images captured during feeding with the head region cropped as a face region image. The face region image was used for cow identification and transfer learning was employed for identification. In the context of cow identification, transfer learning can be used to train a pre-existing deep neural network to recognize individual cows based on their unique physical characteristics, such as their head shape, markings, or ear tags. To estimate the time of feeding, we divided the feeding area into vertical strips for each cow and established a horizontal line just above the feeding materials to determine whether a cow was feeding or not by using Hough transform techniques. We tested our method using real-life data from a large farm, and the experimental results showed promise in achieving our objectives. This approach has the potential to diagnose diseases and movement disorders in cows and could provide valuable insights for farmers.

Research on Automatic Recognition of Dairy Cow Daily Behaviors Based on Deep Learning

“…Individual cow recognition will also be an important part of future research. In both [19,35], they conducted cow identity studies based on cow face patterns and back patterns, respectively, through the improved YOLO model. In future studies, we will explore the performance of the Res-DenseYOLO model on cow identity.…”

“…Wang et al [18] optimized anchor box sizes and boundary box loss functions based on the YOLOv3 model to quickly identify estrus behaviors in dairy cows. Kawagoe et al [19] used a YOLO detector to capture cow heads eating from videos and applied transfer learning for detection of cow feeding time. Guo et al [20] used a YOLOv3-tiny model for cow individual identification and used eye temperature recognition technology to measure cow body temperature, realizing non-invasive identification of cow temperature and individuals.…”

Integrating Artificial Intelligence in Dairy Farm Management - Biometric Facial Recognition for Cows

“…Research on Behavioral Prediction: Kawagoe et al, [50] explored the use of facial recognition technology not just for identification but also for predicting behavioral patterns and health conditions in cows. The research indicated that certain facial features and expressions could be linked to health status, stress levels, and even reproductive cycles [51].…”