An innovative technique for faecal score classification based on RGB images and Artificial Intelligence algorithms
Author(s)
Date Issued
2023
Type
article
Volume
161
Issue
2
Start Page
291
End Page
296
Abstract
The milk production is strongly influenced by the dairy cow welfare related to a good nutrition and the analysis of the digestibility of feeds allows to evaluate the health status of the animals. Through faeces visual examination it is possible to estimate the quality of diet fed in terms of lacking in fibre or too high in non-structural carbohydrates. The study was carried out in 2021, on 4 dairy farms in Central Italy. The purpose of this work is the classification and evaluation of dairy cow faeces using RGB image analysis through an artificial intelligence (CNN) algorithm. The main features to analyse are pH, colour and consistency. For the latter two RGB imaging was used combined with deep learning and Artificial Intelligence (AI) to reach objectivity in samples evaluation. The images have been captured with several smartphones and cameras, in various light conditions, collecting a dataset of 441 images. Image acquired by RGB cameras are then analysed through Convolutional Neural Networks (CNNs) technology that extract features and data previously standardized by a faecal score index (FCI) assigned after a visual analysis and based on 5 classes. The results achieved with different training strategy show a training accuracy of 90% and a validation accuracy of 78% of the model which allow to identify problems in bovine digestion and to intervene promptly in feed variation. The method used in this study eliminates subjectivity in field analysis and allows future improvement increasing the data set to strengthen the model.
File(s)![Thumbnail Image]()
Name
2023_Ortenzi et al_FecalScore_Pubb.pdf
Description
Manoscritto
Size
577.32 KB
Format
Adobe PDF
Checksum (MD5)
3fdca0979786f80fb8dab6c35db7c393
Project(s)
MiPAAF - Progetto INNOVALAT, D.M. n. 27443, 25/09/2018