首页|Investigators from China Agricultural University Zero in on Machine Learning (Research On Trimming Path for Forked Carrots Using Contour-based Machine Learning Methods)
Investigators from China Agricultural University Zero in on Machine Learning (Research On Trimming Path for Forked Carrots Using Contour-based Machine Learning Methods)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Wiley
Current study results on Machine Learning have been published. According to news reporting originating from Beijing, People’s Republic of China, by NewsRx correspondents, research stated, “Forked carrots are often used as animal feed or discarded directly, which affects the economic returns of growers and leads to resource waste and environmental pollution. After trimming, forked carrots become easier to peel and can be further processed.” Financial supporters for this research include the National Key Research and Development Program of China, National Key Research and Development Program of China. Our news editors obtained a quote from the research from China Agricultural University, “However, the lack of relevant studies and equipment hinders the full use of forked carrots, and the identification of fork points and determination of the trimming path are the main challenges in trimming forked carrots with unique and diverse shapes. Therefore, an automatic carrot-trimming path recognition solution based on contour analysis and machine learning was proposed in this study to address the above challenges. Specifically, a cascaded model and a parallel model consisting of Multilayer Perceptron (MLP) and Support Vector Machine (SVM) were constructed to identify fork points, and three trimming path determination methods based on fork points and carrot contours were proposed. The results demonstrated cascaded and parallel models achieved 100% and 92.7% recall rates, respectively, with accuracy rates of 90.4% and 100% and repetition rates of 97.1% and 96.4%. Among the trimming path determination methods, both the dynamic convex hull method and the static convex hull method achieved a convexity of 94.7%, surpassing 93.1% for the slope method. The static convex hull method exhibited the fastest speed in determining the trimming path, taking only 0.0032 s per carat. The parallel model and the static convex hull method could be effectively used for online determination of the trimming path for forked carrots.Practical applicationsTrimming forked carrots enhances usability, reduces resource wastage, and mitigates environmental pollution. Leveraging contour-based machine learning algorithms, we achieved precise fork point recognition with broad applicability. Using fork point and carrot contour data, we determined trimming paths that render carrots convex for mechanical peeling. This approach contributes to advancing sustainable agriculture by optimizing resource utilization. The study proposes an automatic carrot-trimming path recognition solution based on contour analysis and machine learning. First, using machine learning methods, the fork points of forked carrots are identified.”
BeijingPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningChina Agricultural University
NETL
NSTL
Wiley
