期刊
INFRARED PHYSICS & TECHNOLOGY
卷 96, 期 -, 页码 303-310出版社
ELSEVIER
DOI: 10.1016/j.infrared.2018.11.036
关键词
Algorithms; Broilers; Image processing; Machine learning
资金
- National Council for Scientific and Technological Development (CNPq)/Brazil
Wooden Breast (WB) anomaly on poultry meat causes changes in appearance, reduction of technological and nutritional quality, and consumer acceptance. The objective of this study was to identify and classify chicken with WB using a Computer Vision System (CVS) and spectral information from the Near Infrared (NIR) region by linear and nonlinear algorithms. Moreover, it was characterized the physicochemical and technological parameters, which supported a decision tree modeling. Pectoralis major muscle (n = 80) were collected from a poultry slaughterhouse, spectral information was obtained by NIR and CVS, and WB of chicken was characterized. Combining image analyses with a Support Vector Machine (SVM) classification model, 91.8% of chicken breasts were correctly classified as WB or Normal (N). NIR spectral information showed 97.5% of accuracy. WB showed significant increases in moisture and lipid contents and value of a*, decreases of protein and ash contents, and water holding capacity. The shear force of raw WB was 49.51% hardness, and after cooking was 31.79% softer than N breast. CVS and NIR spectroscopy can be applied as rapid and non-destructive methods for identifying and classifying WB in slaughterhouses.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据