# Validation of Biometric Identification of Dairy Cows based on Udder NIR Images

arXiv: https://arxiv.org/abs/1811.09918 · HTML: https://mlsanity.com/paper/1811.09918/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [A Systematic Review of Machine Learning Techniques for Cattle Identification: Datasets, Methods and Future Directions](https://mlsanity.com/paper/2210.09215/) (2022)
- [Advanced Machine Learning and Deep Learning Techniques for Enhanced Cattle Identification and Detection: A Comprehensive Review](https://mlsanity.com/paper/2606.15655/) (2026)

## Abstract (arXiv)

Identifying dairy cows with infections such as mastitis or cows on medications is an extremely important task and legally required by the FDA's Pasteurized Milk Ordinance. The milk produced by these dairy cows cannot be allowed to mix with the milk from healthy cows or it risks contaminating the entire bulk tank or milk truck. Ear tags, ankle bands, RFID tags and even iris patterns are some of the identification methods currently used in the dairy farms. In this work we propose the use of NIR images of cow's mammary glands as a novel biometric identification modality. Two datasets, containing 302 samples from 151 cows has been collected and various machine learning techniques applied to demonstrate the viability of the proposed biometric modality. The results suggest promising identification accuracy for samples collected over consecutive days