%0 Journal Article
%T 基于深度学习的石榴缺陷检测<br>Pomegranate Defect Detection Based on Deep Learning
%A 于欢
%A 张圆圆
%A 林以星
%A 朱玉霞
%A 侯丽新
%J Hans Journal of Food and Nutrition Science
%P 318-326
%@ 2166-6121
%D 2024
%I Hans Publishing
%R 10.12677/hjfns.2024.133041
%X 由于石榴的缺陷严重影响了其品质&#65292;文章基于深度学习方法对石榴缺陷进行识别与检测。根据国家林业局发布的&#8220;LY/T2135&#8212;2013石榴质量等级&#8221;行业标准&#65292;将缺陷分为鸟啄、裂果、腐烂、锈斑和日灼五种类型。采用YOLOv5模型和Mask R-CNN模型进行缺陷识别&#65292;检测精度分别为93.6%和88%。<br>Because the defect of pomegranate seriously affects its quality, this paper uses deep learning method to identify and detect the defect of pomegranate. According to the industry standard &#8220;LY/T2135&#8212;2013 Pomegranate Quality Grade&#8221; issued by the State Forestry Administration, the defects are divided into five types: bird damage, fruit cracking, rot, rust and sunburn. YOLOv5 model and Mask R-CNN model were used for defect identification, and the detection accuracy was 93.6% and 88%, respectively.
%K 石榴&#65292
%K 缺陷&#65292
%K YOLOv5&#65292
%K Mask R-CNN<br>Pomegranate
%K Defects
%K YOLOv5
%K Mask R-CNN
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=93669