Recognition of mango fruit diseases based on image processing and deep transfer learning

ZHANG Dejun; ZHOU Xuecheng; YANG Xudong

doi:10.7671/j.issn.1001-411X.202011002

Journal of South China Agricultural University > 2021 > 42(4): 113-124. > DOI: 10.7671/j.issn.1001-411X.202011002

ZHANG Dejun, ZHOU Xuecheng, YANG Xudong. Recognition of mango fruit diseases based on image processing and deep transfer learning[J]. Journal of South China Agricultural University, 2021, 42(4): 113-124. DOI: 10.7671/j.issn.1001-411X.202011002

Citation:

PDF (12313 KB)

Recognition of mango fruit diseases based on image processing and deep transfer learning

1.
College of Engineering, South China Agricultural University, Guangzhou 510642, China
2.
Key Laboratory of Key Technology on Agricultural Machine and Equipment, Ministry of Education, South China Agricultural University, Guangzhou 510642, China

More Information

Received Date: November 03, 2020
Available Online: May 17, 2023

Graphical Abstract

Abstract

Abstract

Objective
To realize non-destructive detection of the internal quality of mangoes and disease identification and classification based on the CT sequence images of mangoes obtained by computed tomography (CT) equipment.

Method
We used piecewise function method and median filter combined with bilateral filter to achieve image enhancement, used local adaptive threshold method to achieve binarization processing, used seed filling method to perform area filling, and used the image difference method to accurately extract the damaged area in inner tissue of mango fruit. Based on the deep transfer learning model, training and testing were carried out on unprocessed and processed mango image data. Transfer learning was carried out through the AlexNet and GoogLeNet deep learning networks, and hyperparameters were adjusted to complete the network fine-tuning of the training process. Under different models, the classification results of unprocessed and processed mango test sets on the model were compared.

Result
Based on the unprocessed data set, the GoogLeNet model was trained at a learning rate of 0.0002, and the Accuracy and Macro-average were 98.79% and 98.41% respectively. Based on the processed data set, the GoogLeNet model was trained at a learning rate of 0.0002, and the Accuracy and Macro-average were 100% and 100% respectively. The deep transfer learning model had a greater improvement in the model classification index of the processed data set than the unprocessed data set. Based on the same data set and consistent hyperparameters, the classification effect of the GoogLeNet network was significantly better than that of the AlexNet network.

Conclusion
While learning rate is set to 0.0002, the Epoch value is 3, and the Mini Batch value is 64, deep transfer learning training is carried out based on the GoogLeNet network, and the resulting model is used as the final classification model.
- mango,
- disease recognition,
- CT imaging,
- damaged area extraction,
- deep transfer learning,
- image classification

FullText(HTML)

References (30)

References

[1]	曹霞, 周学成, 范品良. 基于近红外漫反射光谱技术的芒果糖度无损检测方法研究[J]. 农机化研究, 2013(1): 177-180.
[2]	郭辉. 基于机器视觉的蜜柚品质检测方法研究[D]. 北京: 中国农业大学, 2015.
[3]	黄滔滔, 孙腾, 张京平. 基于CT图像的苹果内部品质无损检测[J]. 浙江大学学报(农业与生命科学版), 2013, 39(1): 92-97.
[4]	曹霞. 核桃果实内部品质的无损检测技术研究[D]. 广州: 华南农业大学, 2013.
[5]	孙腾. CT技术及图像变换对苹果内部品质的无损检测模型研究[D]. 杭州: 浙江大学, 2013.
[6]	郭文川, 孔繁荣, 王转卫, 等. 梨生长发育后期介电特性、生理特性和内部品质的关系[J]. 现代食品科技, 2015, 31(11): 56-61.
[7]	吴迪, 杨万能, 牛智有, 等. 小麦分蘖形态学特征X射线−CT无损检测[J]. 农业工程学报, 2017, 33(14): 196-201.
[8]	王转卫, 赵春江, 商亮, 等. 基于介电频谱技术的甜瓜品种无损检测[J]. 农业工程学报, 2017, 33(9): 290-295.
[9]	张京平, 彭争, 汪剑. 苹果水分与CT值相关性的研究[J]. 农业工程学报, 2003, 19(3): 180-182.
[10]	余心杰. 农产品无损检测中的模式识别问题研究[D]. 杭州: 浙江大学, 2018.
[11]	NASIRI A, TAHERI-GARAVAND A , ZHANG Y D. Image-based deep learning automated sorting of date fruit[J]. Postharvest Biology and Technology, 2019, 153: 133-141. doi: 10.1016/j.postharvbio.2019.04.003
[12]	WAN S H, GOUDOS S. Faster R-CNN for multi-class fruit detection using a robotic vision system[J]. Computer Networks, 2020(168): 107036. doi: 10.1016/j.comnet.2019.107036.
[13]	OSAKO Y, YAMANE H, LIN S Y, et al. Cultivar discrimination of litchi fruit images using deep learning[J]. Scientia Horticulturae, 2020, 269: 109360. doi: 10.1016/j.scienta.2020.109360.
[14]	OQUAB M, BOTTOU L, LAPTEV I, et al. Learning and transferring mid-level image representations using convolutional neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition, Columbus: IEEE, 2014: 1122-1129.
[15]	GE W, YU Y. Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning[C]//IEEE Conference on Computer Vision and Pattern Recognition, Hawaii: IEEE, 2017: 2102-2113.
[16]	PAN S, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359. doi: 10.1109/TKDE.2009.191
[17]	SUN C, SHRIVASTAVA A, SINGH S, et al. Revisiting unreasonable effectiveness of data in deep learning era[C]//IEEE. IEEE International Conference on Computer Vision, Venice: IEEE, 2017: 843-852.
[18]	ROJAS-CARULLA M, SCHOLKOPF B, TURNER R, et al. Invariant models for causal transfer learning[J]. Journal of Machine Learning Research, 2018, 19(36): 1-34.
[19]	CORTES C, MOHRI M, MEDINA A M. Adaptation based on generalized discrepancy[J]. Journal of Machine Learning Research, 2019, 20(1): 1-30.
[20]	MOHRI M, ROSTAMIZADEH A, TALWALKAR A. Foundations of Machine Learning[M]. Cambridge: MIT Press, 2012.
[21]	刘慧力, 贾洪雷, 王刚, 等. 基于深度学习与图像处理的玉米茎秆识别方法与试验[J]. 农业机械学报, 2020, 51(4): 207-215.
[22]	马金林, 魏萌, 马自萍. 基于深度迁移学习的肺结节分割方法[J]. 计算机应用, 2020(7): 2117-2125.
[23]	罗琪. 基于深度学习的水果图像识别系统[J]. 农业工程, 2018, 8(10): 31-34.
[24]	岑冠军, 华俊达, 高燕. 基于深度学习芒果图像在线识别与计数方法研究[J]. 热带作物学报, 2020, 41(3): 425-432.
[25]	廉小亲, 成开元, 安飒, 等. 基于深度学习和迁移学习的水果图像分类[J]. 测控技术, 2019, 38(6): 15-18.
[26]	SMIRNOV E A, TIMOSHENKO D M, ANDRIANOV S N. Comparison of regularization methods for ImageNet classification with deep convolutional neural networks[J]. AASRI Procedia, 2014, 6: 89-94. doi: 10.1016/j.aasri.2014.05.013
[27]	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 1: 1097-1105.
[28]	WAN L, ZEILER M, ZHANG S, et al. Regularization of neural networks using DropConnect[C]//ICML. Proceedings of The 30th International Conference on Machine Learning, Atlanta: ICML, 2013.
[29]	李一海. 植物根系三维矢量模型的构建与分析方法[D]. 广州: 华南农业大学, 2016.
[30]	陈郁淦, 周学成, 乐凯. 根系CT序列图像区域生长分割的新方法[J]. 计算机工程与应用, 2011, 47(28): 158-161.

Cited By

Cited by

Periodical cited type(6)

1.	柯愉. 基于迁移学习的正温度系数热敏电阻表面损伤分类算法研究. 计算机与数字工程. 2024(06): 1703-1707 .
2.	刘小刚，李荣梅，范诚，杨启良，赵璐. 基于语义分割的芒果表皮缺陷识别. 华南农业大学学报. 2023(01): 134-141 . 本站查看
3.	罗旭斌，刘波. 结合集成学习与迁移学习的标签比例学习方法. 计算机应用研究. 2023(05): 1422-1427 .
4.	叶永雪，马鸿雁. 基于人体关键点与迁移学习的口罩佩戴检测研究. 计算机仿真. 2023(06): 234-239 .
5.	周泽聿，王昊，张小琴，范涛，任秋彤. 基于Xception-TD的中华传统刺绣分类模型构建. 数据分析与知识发现. 2022(Z1): 338-347 .
6.	王建冲，高军伟，张炳星，刘佳浩. 基于机器视觉的SOP芯片引脚缺陷检测系统. 工业仪表与自动化装置. 2022(05): 32-37 .

Other cited types(10)

Get Citation

PDF

XML

Article views (748) PDF downloads (885) Cited by(16)

Turn off MathJax

Article Contents

Abstract

References

Recognition of mango fruit diseases based on image processing and deep transfer learning

Abstract

References

Cited by

Periodical cited type(6)

Other cited types(10)

Catalog

Export File

Citation

Format

Content