Affiliation:
1. University of Wisconsin-Madison
2. UW-Madison
3. Genus PLC
Abstract
Abstract
The measurement of carcass traits in live pigs, such as muscle depth (MD) and backfat thickness (BF), is a topic of great interest for breeding companies and production farms. Breeding companies currently measure MD and BF using medical imaging technologies such as ultrasound (US). However, US is costly, requires trained personnel, and involves direct interaction with the animals, which is an added stressor. An interesting alternative in this regard is to use computer vision techniques. Farmers would also take advantage of such an application as they would be able to better adjust feed composition and delivery. Therefore, the objectives of this study were: (1) to develop a computer vision system for prediction of MD and BF from 3D images of finishing pigs; (2) to compare the predictive ability of statistical (multiple linear regression, partial least squares) and machine learning (elastic networks and artificial neural networks) approaches using features extracted from the images against a deep learning (DL) approach that uses the raw image as input. A dataset containing 3D images and ultrasound measurements of 618 pigs with average body weight of 120 kg, MD of 65 mm, and BF of 6 mm was used in this study. To assess the predictive performance of the different strategies, a 5-fold cross-validation approach was used. The DL achieved the best predictive performance for both traits, with predictive mean absolute scaled error (MASE) of 5.10% and 13.62%, root-mean-square error (RMSE) of 4.35mm and 1.10mm, and R2 of 0.51 and 0.45, for MD and BF respectively. In conclusion, it was demonstrated that it is possible to satisfactorily predict MD and BF using 3D images that were autonomously collected in farm conditions. Also, the best predictive quality was achieved by a DL approach, simplifying the data workflow as it uses raw 3D images as inputs.
Publisher
Oxford University Press (OUP)
Subject
Genetics,Animal Science and Zoology,General Medicine,Food Science
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献