基于深度学习的水果图像识别

doi:10.13733/j.jcam.issn.2095-5553.2025.01.030

摘要/Abstract

摘要： 为有效辨别水果种类，提高水果产业商业化的深加工和线下水果销售渠道的效率，针对大多数线下超市在水果售卖过程中主要采用人工识别，其成本高、效率低的问题，提出一种基于语义分割模型（U2-Net）和ResNet-50模型结合的水果图像识别方法，实现水果图像自动识别。使用U2-Net分割出水果的二值图像，然后结合OpenCV算法将二值图中的白色像素值改为水果真实的颜色值，最后通过ResNet-50进行水果图像识别。结果表明，Alexent、VGG16、GoogLeNet和本模型在训练集上的准确率分别为99.66%、99.65%、99.9%、99.8%，在验证集上的准确率分别为96.5%、99.9%、99.6%、100%。提出的水果图像识别方法能够有效提取水果的颜色、形状、纹理等特征，从而实现对不同种类水果图像的准确识别。

关键词: 水果, 深度学习, 语义分割, 图像识别, 二值图像

Abstract: In order to effectively identify the types of fruits and improve the efficiency of commercial deep processing of fruit industry and offline fruit sales channels, this paper proposes a fruit image recognition method based on the combination of semantic segmentation model （U2-Net） and ResNet-50 model to realize automatic fruit image recognition. U2-Net is used to segment the binary image of fruit, and then the white pixel value in the binary image is changed into the real color value of fruit by OpenCV algorithm. Finally, the fruit image is recognized by ResNet-50. The results show that the accuracy of Alexent, VGG16, GoogLeNet and this model on the training set is 99.66%, 99.65%, 99.9% and 99.8%, and the accuracy of the verification set is 96.5%, 99.9%, 99.6% and 100%, respectively. The result showed that the fruit image recognition method proposed in this paper can effectively extract the color, shape, texture and other features of fruits, thus realizing accurate recognition of different kinds of fruit images.

Key words: fruit, deep learning, semantic segmentation, image recognition, binary image

中图分类号:

TP391.41

李春雨, 郭肖琴, 杨晶晶, 李忠华. 基于深度学习的水果图像识别[J]. 中国农机化学报, 2025, 46(1): 198-203.

Li Chunyu, Guo Xiaoqin, Yang Jingjing, Li Zhonghua. Fruit image recognition based on deep learning[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 198-203.

参考文献

［1］　Miriti E. Classification of selected apple fruit varieties using Naive Bayes ［D］. Nairobi:University of Nairobi, 2016.
［2］　Ali M A H, Thai K W. Automated fruit grading system ［C］. 2017 IEEE 3rd International Symposium in Robotics and Manufacturing Automation （ROMA）. IEEE, 2017: 1-6.
［3］　Saranya N, Srinivasan K,et al. Fruit classification using traditional machine learning and deep learning approach ［C］. Computational Vision and BioInspired Computing: Springer International Publishing, 2020: 79-89.
［4］　Jia W, Tian Y, Luo R, et al. Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot ［J］. Computers and Electronics in Agriculture, 2020, 172: 105380.
［5］　Gill H S, Khehra B S. Fruit image classification using deep learning ［J］. Computers, Materials & Continua, 2022, 71(3).
［6］　向锐, 孙艺萌, 梁晨, 等. 葡萄PLATZ家族基因鉴定及其在种子发育过程中的表达分析［J］. 果树学报, 2023, 40（1）: 13-24.
Xiang Rui, Sun Yimeng, Liang Chen, et al. Genomewide identification of grape PLATZ family genes and expression analysis during seed development ［J］. Journal of Fruit Science, 2023, 40(1): 13-24.
［7］　韦晓霞, 梁党弟, 赖瑞联, 等. 优质早熟大果百香果新品种蜜语的选育［J］. 果树学报, 2023, 40(1): 187-190.
Wei Xiaoxia, Liang Dangdi, Lai Ruilian, et al. A new earlymaturing and highyielding passion fruit cultivar Miyu ［J］. Journal of Fruit Science, 2023, 40(1): 187-190.
［8］　Feng J, Zeng L, He L. Apple fruit recognition algorithm based on multispectral dynamic image analysis ［J］. Sensors, 2019, 19（4）: 949.
［9］　Wang Y, Chen Y. Fruit morphological measurement based on threedimensional reconstruction ［J］. Agronomy, 2020, 10（4）: 455.
［10］　林云森, 范文强, 姜佳良. 基于深度学习的水果识别技术研究［J］. 光电技术应用, 2019, 34（6）: 45-48, 58.

Lin Yunsen, Fan Wenqiang, Jiang Jialiang. Research on fruit recognition technology based on deep learning ［J］.ElectroOptic Technology Application, 2019, 34（6）: 45-48, 58.

［11］　黄玉富, 朴燕, 张汉辉. 基于多尺度特征融合的水果图像识别算法研究［J］. 长春理工大学学报（自然科学版）, 2021, 44（1）: 87-94.
Huang Yufu, Pu Yan,Zhang Hanhui. Research on fruit image recognition algorithm based on multiscale feature fusion ［J］. Journal of Changchun University of Science and Technology, 2021, 44（1）: 87-94.
［12］　陈雪鑫, 卜庆凯. 基于改进的最大类间方差法的水果图像识别研究［J］.青岛大学学报（工程技版）, 2019, 34（2）:33-38, 62.
Chen Xuexin, Bu Qingkai. Fuzzy backstepping position control for flexible joint robots ［J］.Journal of Qingdao University （Engineering & Technology Edition）, 2019, 34（2）: 33-38, 62.
［13］　Hussain D, Hussain I, Ismail M, et al. A simple and efficient deep learningbased framework for automatic fruit recognition ［J］. Computational Intelligence and Neuroscience, 2022(1): 6538117.
［14］　Zhang Y D, Dong Z, Chen X, et al.Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation ［J］. Multimedia Tools and Applications, 2019, 78: 3613-3632.
［15］　Xiang Q, Wang X, Li R, et al.Fruit image classification based on Mobilenetv2 with transfer learning technique ［C］. Proceedings of the 3rd International Conference on Computer Science and Application Engineering. 2019: 1-7.
［16］　Nikhitha M, Sri S R, Maheswari B U. Fruit recognition and grade of disease detection using inception v3 model ［C］. 2019 3rd International conference on Electronics, Communication and Aerospace Technology （ICECA）. IEEE, 2019: 1040-1043.
［17］　Duong L T, Nguyen P T,Di Sipio C,et al. Automated fruit recognition using EfficientNet and MixNet ［J］. Computers and Electronics in Agriculture, 2020, 171: 105326.
［18］　He K, Zhang X,Ren S,et al.Deep residual learning for image recognition ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
［19］　Grandini M, Bagli E, Visani G. Metrics for multiclass classification: An overview ［J］. arXiv preprint arXiv: 200805756, 2020.

[1]	夏子林, 张新洲, 王文波, 夏先飞, 陈兰, 顾寄南. 基于机器视觉的蚕豆荚高精度检测方法研究[J]. 中国农机化学报, 2025, 46(1): 157-163.
[2]	牛潘婷, 张宝林, 潘丽杰, 郭建鹏(. 基于改进GoogLeNet的玉米叶片病害识别及其可解释性研究[J]. 中国农机化学报, 2025, 46(1): 204-212.
[3]	彭勇, 乔印虎, 张春燕, 姚杰, 包殿令. 改进YOLOv5模型的草莓检测方法研究[J]. 中国农机化学报, 2025, 46(1): 213-219.
[4]	韩鹏飞, 宋其江, 贾梦实. 基于改进轻量化 EfficientNet-V2模型的小麦种子分类[J]. 中国农机化学报, 2024, 45(9): 111-117.
[5]	李志臣, 凌秀军, 李鸿秋. 基于声音深度学习的发动机失火故障诊断[J]. 中国农机化学报, 2024, 45(9): 134-140.
[6]	桑一男 , 徐增莱 , 汪琼 , 葛海涛 , 王殿广 . 一种轮式采花机器人设计——以黄蜀葵为例[J]. 中国农机化学报, 2024, 45(9): 202-208.
[7]	李邦国, 王辉, 宋杨, 任志伟, 刘跃华, 徐乐程. 基于无人驾驶小麦收割机立体视觉感知系统[J]. 中国农机化学报, 2024, 45(9): 244-249.
[8]	许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222.
[9]	刘星, 顾寄南, 黄则栋, 张文浩, 张伟. 基于深度学习的苹果点云语义分割方法研究[J]. 中国农机化学报, 2024, 45(8): 223-227.
[10]	胡国玉, 刘广, 周星光, 董娅兰, 周建平, . 基于Swin-TDL算法的果园环境下葡萄病害检测方法[J]. 中国农机化学报, 2024, 45(8): 234-239.
[11]	黄亦其, 鹿林飞, 沈豪, 王福宽, 乔曦, . 基于卷积神经网络的入侵昆虫识别研究[J]. 中国农机化学报, 2024, 45(7): 222-227.
[12]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.
[13]	张继成, 黄向党. 基于改进YOLOv3的玉米病害识别方法[J]. 中国农机化学报, 2024, 45(7): 269-275.
[14]	雷浩, 苑迎春, 何振学. 基于多尺度卷积和注意力机制的枣品种识别[J]. 中国农机化学报, 2024, 45(6): 135-141.
[15]	李龙杰, 史勇, , 刘彦岑, , 郭俊先, . 基于RGB图像处理预测哈密瓜叶片叶绿素研究[J]. 中国农机化学报, 2024, 45(6): 149-155.