Scientists with the University of Saskatchewan are harnessing artificial intelligence to identify lesions on swine carcasses at slaughter to assess and document on-farm animal welfare.
The Western College of Veterinary Medicine and the University of Saskatchewan's Department of Computer Engineering, in partnership with 14 industry partners with support from the Natural Sciences and Engineering Research Council, are using artificial intelligence to develop new tools to document and analyze animal-based indicators of on-farm welfare, such as skin or tail lesions detected on swine carcasses at slaughter.
Dr. Martyna Lagoda, a Post-doctoral Fellow Swine Behavior and Welfare with the Western College of Veterinary Medicine, says the computer engineering team now has a fully working computer model that can identify body regions that are important for animal welfare and the model is now being trained to detect lesions on carcasses.
Quote-Dr. Martyna Lagoda-Western College of Veterinary Medicine:
This research will definitely help to improve the robustness and reliability of the Canadian swine industry's animal care program and provide a mechanism for feedback for continual improvement to animal welfare in the country.The improvements to pig welfare made by producers upon the receipt of feedback from abattoirs will help to increase their economic return for their products through fewer condemnations and cut-outs to the carcass.
The objective and reliable nature of the automated assessment system also means the data should be easily collectable and therefore there is potential for the development of a premium scheme for producers meeting specific targets for welfare both within the Canadian quality assurance program, but also to provide information for international standards when, for example, communicating for trade agreements.
Dr. Lagoda says the successful develop of the computer vision technology to automate the detection and scanning of pig carcasses for welfare indictors is a very important step and suggests success in this area confirms, we can scale up this technology for commercial adoption.
Source : Farmscape.ca