Abstract
［Objective］ Improving the accuracy and efficiency of rotting strawberry classification using modern computer vision techniques and deep learning methods.［Methods］ A classification method for rotten strawberries based on EfficientNet V 2 fusion with Graph Convolutional Network (GCN ) and Channel -Attention Transformer (CA-Transformer ) has been proposed.Firstly,a graph convolution branch was added to the baseline model,which updated feature representations by aggregating the surrounding information of nodes,better capturing the contextual information of nodes in the graph structure.Secondly,this study integrated the Transformer structure with attention into the backbone of the baseline model,replacing some convolution operations with this structure to achieve the fusion of global and local features,thereby better identifying the rottenness of strawberries.Finally,learning parameters were introduced on the basis of the traditional residual structure to achieve dynamic feature fusion.［Results］］ The GC -EfficientNet V 2 model improved the accuracy by 1.86% and the recall by 1.49% compared to the baseline model.Compared with Inception V 3,ResNet 50,VGGNet,Vision Transformer,and EfficientNet V2-m,the recognition accuracy of the model was improved by 0.93%,2.08%,2.79%,3.26%,and 0.47%,respectively.［Conclusion］ This model can accurately classify rotten strawberries,providing some theoretical support for automatic strawberry sorting.
Publication Date
2-18-2025
First Page
81
Last Page
88
DOI
10.13652/j.spjx.1003.5788.2024.80468
Recommended Citation
Wei, WANG; Shizhong, YANG; Yucheng, GONG; Sheng, GAO; and Zhaopeng, DENG
(2025)
"Rotten strawberry classification based on EfficientNet V 2 algorithm fused with GCN and CA-Transformer,"
Food and Machinery: Vol. 40:
Iss.
12, Article 11.
DOI: 10.13652/j.spjx.1003.5788.2024.80468
Available at:
https://www.ifoodmm.cn/journal/vol40/iss12/11
References
[1] 刘小刚,范诚,李加念,等.基于卷积神经网络的草莓识别方法[J].农业机械学报,2020,51(2):237-244.LIU X G,FAN C,LI J N,et al.Identification method of strawberry based on convolutional neural network [J].Transactions of the Chinese Society for Agricultural Machinery,2020,51(2):237-244.
[2] 黄家才,赵雪迪,高芳征,等.基于改进 YOLOv 5s的草莓多阶段识别检测轻量化算法 [J].农业工程学报,2023,39(21):181-187.HUANG J C,ZHAO X D,GAO F Z,et al.Recognizing and detecting the strawberry at multi-stages using improved lightweight YOLOv 5s[J].Transactions of the Chinese Society of Agricultural Engineering,2023,39(21):181-187.
[3] WU F,GUAN Z F,WHITAKER V.Optimizing yield distribution under biological and economic constraints:florida strawberries as a model for perishable commodities [J].Agricultural Systems,2015,141:113-120.
[4] CHEN Y,HUANG Y Q,ZHANG Z Z,et al.Plant image recognition with deep learning:a review [J].Computers and Electronics in Agriculture,2023,212:108072.
[5] 焦方圆,申金媛,郝同盟.一种基于卷积神经网络的烟叶等级识别方法 [J].食品与机械,2022,38(2):222-227.JIAO F Y,SHEN J Y,HAO T M.A method of tobacco leaf grade recognition based on convolutional neural network [J].Food & Machinery,2022,38(2):222-227.
[6] 周胜安,黄耿生,张译匀,等.基于深度学习的水果缺陷实时检测方法 [J].食品与机械,2021,37(11):123-129.ZHOU S A,HUANG G S,ZHANG Y J,et al.Real time detection method of fruit defects based on deep learning [J].Food & Machinery,2021,37(11):123-129.
[7] LAMB N,CHUAH M C.A strawberry detection system using convolutional neural networks [C]// 2018 IEEE International Conference on Big Data (Big Data ).Seattle,WA:IEEE,2018:2 515-2 520.
[8] 曾平平,李林升.基于卷积神经网络的水果图像分类识别研究[J].机械设计与研究,2019,35(1):23-26,34.ZENG P P,LI L S.Classification and recognition of common fruit images based on convolutional neural network [J].Machine Design & Research,2019,35(1):23-26,34.
[9] HOSSAIN M S,AL-HAMMADI M,MUHAMMAD G.Automatic fruit classification using deep learning for industrial applications [J].IEEE Transactions on Industrial Informatics,2019,15(2):1 027-1 034.
[10] MOMENY M,JAHANBAKHSHI A,JAFARNEZHAD K,et al.Accurate classification of cherry fruit using deep CNN based on hybrid pooling approach [J].Postharvest Biology and Technology,2020,166:111204.
[11] GAO Z M,SHAO Y Y,XUAN G T,et al.Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning [J].Artificial Intelligence in Agriculture,2020,4:31-38.
[12] NI J G,GAO J Y,LI J,et al.E-AlexNet:quality evaluation of strawberry based on machine learning [J].Journal of Food Measurement and Characterization,2021,15(5):4 530-4 541.
[13] YUAN Y,CHEN X L.Vegetable and fruit freshness detection based on deep features and principal component analysis [J].Current Research in Food Science,2024,8:100656.
[14] FOONG C C,MENG G K,TZE L L.Convolutional Neural Network based Rotten Fruit Detection using ResNet 50[C]// 2021 IEEE 12th Control and System Graduate Research Colloquium (ICSGRC ).Shah Alam,Malaysia:IEEE,2021:75-80.
[15] WANG Q Y,WU D H,SUN Z Z,et al.Design,integration,and evaluation of a robotic peach packaging system based on deep learning [J].Computers and Electronics in Agriculture,2023,211:108013.
[16] 孙杰,杨静,丁书杰,等.基于多注意力机制与编译图神经网络的高光谱图像分类 [J].农业机械学报,2024,55(3):183-192,212.SUN J,YANG J,DING S J,et al.Hyperspectral image classification based on multi-attention mechanism and compiled graph neural networks [J].Transactions of the Chinese Society for Agricultural Machinery,2024,55(3):183-192,212.
[17] YU Y D,CHU T Z,TONG S B,et al.Emergence of segmentation with minimalistic white-box transformers [J/OL ].arXiv.(2023 -08-30) [2024 -08-13].https://arxiv.org/abs/ 2308.16271.
[18] 沈宇麒,崔衍.基于双层路由注意力及特征融合的细粒度图像分类 [J].计算机技术与发展,2024,34(6):23-28.SHEN Y Q,CUI Y.Fine-grained image classification based on bi-level routing attention and feature fusion [J].Computer Technology and Development,2024,34(6):23-28.
[19] 陈辉,张甜,陈润斌.基于残差卷积与多头自注意力的 CXR图像分类 [J].工程科学与技术,2024,56(3):219-227.CHEN H,ZHANG T,CHEN R B.CXR image classification based on residual convolution and multi-headed self-attentions[J].Advanced Engineering Sciences,2024,56(3):219-227.
[20] 刘玉良,白玉洁.基于 CSNet网络的肺炎图像分类研究 [J].天津科技大学学报,2024,39(3):49-55.LIU Y L,BAI Y J.Research on pneumonia image classification based on CSNet network [J].Journal of Tianjin University of Science & Technology,2024,39(3):49-55.
[21] 逯登科,罗亦泳,张紫怡,等.基于 ResNet 50与通道注意力的遥感图像场景分类 [J].江西科学,2024,42(2):396-404.LU D K,LUO Y Y,ZHANG Z Y,et al.Remote sensing image scene classification based on ResNet 50 and channel attention[J].Jiangxi Science,2024,42(2):396-404.
[22] 郑世杰,王高才.基于 ConvNeXt 热图定位和对比学习的细粒度图像分类研究 [J].计算机科学,2023,50(10):119-125.ZHENG S J,WANG G C.Study on fine-grained image classification based on ConvNeXt heatmap localization and contrastive learning [J].Computer Science,2023,50(10):119-125.
[23] QIAN C Y,SUN S G,DONG C H,et al.A study on phenotypic micro-variation of stored melon based on weight loss rate [J].Postharvest Biology and Technology,2023,204:112464.
[24] SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Las Vegas,NV:IEEE,2016:2 818-2 826.
[25] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Las Vegas,NV:IEEE,2016:770-778.
