现代信息科技2025，Vol.9Issue(11)：64-69,6.DOI:10.19850/j.cnki.2096-4706.2025.11.013
基于深度学习的樱桃图像分类检测
Cherry Image Classification Detection Based on Deep Learning
摘要
Abstract
In order to detect cherry images in multiple types of fruit images and lay the foundation for the classification detection of subsequent cherry image high-quality fruits and defective fruits,this paper proposes model analysis,parameter optimization,training and testing of eight commonly used Deep Neural Networks,and evaluates the models by using objective evaluation criteria,and then uses the optimal model to train the image classification of cherry high-quality and defective fruits.Through detection experiments,it is verified that the T2T_ViT model achieves average accuracies of 99.40%and 99.12%for high-quality and defective fruits of cherry images,respectively.There are good classification detection results of cherry images with high-quality and defective fruits.关键词
深度学习/樱桃图像分类检测/T2T_ViT模型/客观评价Key words
Deep Learning/cherry image classification detection/T2T_ViT model/objective evaluation分类
信息技术与安全科学引用本文复制引用
刘勍,吴忠啸,张亚亚,何秉蔚,魏凯斌,赵利民,赵玉祥..基于深度学习的樱桃图像分类检测[J].现代信息科技,2025,9(11):64-69,6.基金项目
甘肃省科技计划项目(23JRRE0740,25JRRE004) （23JRRE0740,25JRRE004）
天水市秦州区科技计划项目(2023-SHFZG-6476) （2023-SHFZG-6476）
天水师范学院研究生创新引导项目(TYCX2330,TYCX2331) （TYCX2330,TYCX2331）
