基于改進(jìn)Swin-Transformer的果樹病葉分類模型

打開文本圖片集

中圖分類號：TP391.4 文獻(xiàn)標(biāo)志碼：A 文章編號：2096-9902（2025）14-0033-04

Abstract：Inrecentyears，climatechangeandchangesinagriculturalactivitieshaveincreasedthefrequencyandseverityof plantdiseases，havingamajorimpactonfoodproductionandqualitysafety.Therefore，toensurefoodsecurity，timelyand accuratedetectionanddiagnosisofplantdiseasesarecrucial.Thispaperdesignsatreediseaseleafclassficationmodelbased ontheimprovedSwin-Transformer，whichoptimizesfeaturesbyintegratingdual-pathatentionmechanisms.Atthefeature processinglevel，amulti-levelprocesingstructureicludinglayerandardzatiodaptivepolingndfullonecdasif isdesiged.ThiscompositearchitecturemaintainsteadvantagesofTransfomersglobalmodelingandsignificantlyimprovesthe eficiencyofcapturingfine-grainedpathologicalfeaturesthroughanatention-guidedfeatureenhancementmechanism.The proposed model achieves greater accuracy than previous convolution and visual transformer-based models.

Keywords：deeplearning;atentionmechanism;convolutional neural network；plantdiseaserecognition;smartagriculture

植物病害是導(dǎo)致糧食產(chǎn)量與質(zhì)量降低的重要因素。（剩余5333字）