基于深度学习的樱桃图像分类检测

打开文本图片集

中图分类号：TP391.4 文献标识码：A文章编号：2096-4706（2025）11-0064-06

Cherry Image Classification Detection Based on Deep Learning

LIU Qing, WU Zhongxiao, ZHANG Yaya, HE Bingwei, WEI Kaibin, ZHAO Limin, ZHAO Yuxiang (SchoolofElectronic InformationandElectricalEngineering,TianshuiNormal University,Tianshui741o,China)

Abstract:Inorderto detect cherry images in multiple types of fruit images and laythe foundation for theclasification detectionofsubsequentcherryimage high-qualityfruitsanddefective fruits,this paperproposesmodelanalysis,parameter optimization,trainingandtestingofeightcommonlyusedDepNeuralNetworks,andevaluatesthemodels byusingobjective evaluationcriteriaandthenusestheoptimalmodeltotraitheimageclassificationofcherryhighqualityanddefectivefruits. Through detection experiments,it is verified that the T2T_ViTmodel achieves average accuracies of 99.40% and 99.12% for high-qualityand defective fruitsofcherry images,espectively.There are good clasificationdetectionresultsofcherry images withhigh-qualityand defective fruits.

Keywords:DeepLearning;cherry image classification detection;T2T_ViTmodel; objectiveevaluation

0 引言

在农业智能化领域，果实检测是一个重要研究热点。（剩余10361字）