CITRUS DISEASE CLASSIFICATION WITH TRANSFER LEARNING AND CNN BASED MODELS

Halit Çetiner

doi:10.17780/ksujes.1170947

EN TR

CITRUS DISEASE CLASSIFICATION WITH TRANSFER LEARNING AND CNN BASED MODELS

Abstract

In recent years, image processing and deep learning have been widely used in the detection and classification of plant diseases. These uses offer great opportunities for the early detection of plant diseases in agriculture. Early detection of the disease is essential to prevent disease symptoms from spreading to intact leaves and to reduce crop damage. For the stated reasons, a deep learning model with three different approaches has been proposed and used for the classification of diseases that are most common in citrus leaves and affect citrus export to a great extent. Training and test data used in the proposed model are separated according to the K-fold 5 value. For this reason, the average of the performance values obtained according to the K-fold 5 value is presented in the study. As a result of the experimental studies, with the fine-tuned DenseNet201 model, which is the first model, an accuracy rate of 0.95 was achieved. In the second model, with the proposed 21-layer CNN model, an accuracy rate of 0.99 was achieved. The third model is defined to show the progress of the proposed DenseNet201 model over the basic DenseNet201 model. With the CNN method recommended for the classification of citrus grades, Blackspot (citrus black spot (CBS), canker (citrus bacterial cancer (CBC)), greening (huanglongbing (HLB)), and (healthy) Healthy) 100%, 100%, 98% and 100% rates have been reached.

Keywords

TRANSFER ÖĞRENME VE CNN TABANLI MODELLER İLE NARENCİYE HASTALIĞI SINIFLANDIRMASI

Öz

Son yıllarda görüntü işleme ve derin öğrenme bitki hastalıklarının tespiti ve sınıflandırılmasında yaygın olarak kullanılmaktadır. Bu kullanımlar, tarım alanında bitki hastalıklarının erken tespiti için büyük fırsatlar sunmaktadır. Hastalığın erken tespiti, hastalık belirtilerinin sağlam yapraklara yayılmasını engellemek ve mahsule zarar vermesini azaltabilmek için gereklidir. Belirtilen sebeplerden dolayı narenciye yapraklarında en sık görülen ve narenciye ihracatını büyük ölçüde etkileyen hastalıkların sınıflandırılması için üç farklı yaklaşımla derin öğrenme modeli önerilmiş ve kullanılmıştır. Önerilen modellerde kullanılan eğitim ve test verileri K-fold 5 değerine göre ayrılmıştır. Bu nedenle çalışmada K-fold 5 değerine göre elde edilen performans değerlerinin ortalaması sunulmuştur. Deneysel çalışmalar neticesinde birinci model olan ince ayarlı DenseNet201 modeli kullanarak 0.95 doğruluk oranına ulaşılmıştır. İkinci modelde ise önerilen 21 katmanlı CNN modeli ile 0.99 doğruluk oranına ulaşılmıştır. Üçüncü model ise önerilen DenseNet201 modelinin temel DenseNet201 modeline göre ilerlemesini göstermek için tanımlanmıştır. Önerilen CNN yöntemi ile Blackspot (citrius siyah nokta (CBS)), canker (citrius bakteriyel kanseri (CBC)), greening (huanglongbing (HLB)) ve (sağlıklı) Healthy adlı sınıflara sahip olan narenciye bitkisine ait görüntüler sırasıyla %100, %100, %98 ve %100 sınıflandırma oranlarına ulaşılmıştır.

Anahtar Kelimeler

Kaynakça

Aakif, Aimen, and Muhammad Faisal Khan. (2015). Automatic Classification of Plants Based on Their Leaves. Biosystems Engineering 139: 66–75. https://www.sciencedirect.com/science/article/pii/S1537511015001373.
Abbas, Amreen, Sweta Jain, Mahesh Gour, and Swetha Vankudothu. (2021). Tomato Plant Disease Detection Using Transfer Learning with C-GAN Synthetic Images. Computers and Electronics in Agriculture 187: 106279. https://www.sciencedirect.com/science/article/pii/S0168169921002969.
Agarwal, Mohit, Suneet Gupta, and K K Biswas. (2021). A New Conv2D Model with Modified ReLU Activation Function for Identification of Disease Type and Severity in Cucumber Plant. Sustainable Computing: Informatics and Systems 30: 100473. https://www.sciencedirect.com/science/article/pii/S2210537920301967.
de Carvalho, Sérgio Alves, de Carvalho Nunes, William Mário, Belasque, José, Machado, Marcos Antonio, Croce-Filho, José, Bock, Clive H, and Abdo, Zaid. (2014). Comparison of Resistance to Asiatic Citrus Canker Among Different Genotypes of Citrus in a Long-Term Canker-Resistance Field Screening Experiment in Brazil. Plant Disease 99(2): 207–18. https://doi.org/10.1094/PDIS-04-14-0384-RE.
Chen, Junde, Defu Zhang, Adnan Zeb, and Yaser A Nanehkaran. (2021). Identification of Rice Plant Diseases Using Lightweight Attention Networks. Expert Systems with Applications 169: 114514. https://www.sciencedirect.com/science/article/pii/S0957417420311581.
Chouhan, Vikash, Singh, Sanjay K, Khamparia, Aditya, Gupta, Deepak, Tiwari, Prayag, Moreira, Catarina, Damaševičius, Robertas, and de Albuquerque, Victor Hugo C. (2020). A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-Ray Images. Applied Sciences 10(2): 1-17. https://doi.org/10.3390/app10020559.
da Costa, Arthur Z, Hugo E H Figueroa, and Juliana A Fracarolli. (2020). Computer Vision Based Detection of External Defects on Tomatoes Using Deep Learning. Biosystems Engineering 190: 131–44. https://www.sciencedirect.com/science/article/pii/S1537511019309109.
Dogan, F, and I Türkoglu. (2018). Derin Ögrenme Algoritmalarının Yaprak Sınıflandırma Basarımlarının Karsılastırılması. Sakarya University Journal of Computer and Information Sciences 1(1): 10–21.

Dutt, Manjul, Choaa El Mohtar, and Nian Wang. (2020). Biotechnological Approaches for the Resistance to Citrus Diseases. Springer, Cham, 245–57. https://doi.org/10.1007/978-3-030-15308-3_14.
Ferentinos, Konstantinos P. (2018). Deep Learning Models for Plant Disease Detection and Diagnosis. Computers and Electronics in Agriculture 145: 311–18.
Garita-Cambronero, Jerson, Sena-Vélez, Marta, Ferragud, Elisa, Sabuquillo, Pilar, Redondo, Cristina, and Cubero, Jaime. (2019). Xanthomonas Citri Subsp. Citri and Xanthomonas Arboricola Pv. Pruni: Comparative Analysis of Two Pathogens Producing Similar Symptoms in Different Host Plants. PloS one 14(7): e0219797.
Guarnaccia, Vladimiro, Gehrmann, Thies, Silva-Junior, Geraldo J, Fourie, Paul H, Haridas, Sajeet, Vu, Duong, Spatafora, Joseph, Martin, Francis M, Robert, Vincent, Grigoriev, Igor V, Groenewald, Johannes Z, and Crous, Pedro W. (2019). Phyllosticta Citricarpa and Sister Species of Global Importance to Citrus. Molecular Plant Pathology 20(12): 1619–35. https://doi.org/10.1111/mpp.12861.
He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. (2016). Identity Mappings in Deep Residual Networks. In European Conference on Computer Vision, Springer, 630–45.
Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. (2017). Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, , 4700–4708.
Ioffe, Sergey, and Christian Szegedy. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning, PMLR, 448–56.
Kaggle. (2020). Citrus Leaves Prepared. https://www.kaggle.com/dtrilsbeek/citrus-leaves-prepared.
Khanramaki, Morteza, Ezzatollah Askari Asli-Ardeh, and Ehsan Kozegar. (2021). Citrus Pests Classification Using an Ensemble of Deep Learning Models. Computers and Electronics in Agriculture 186: 106192. https://www.sciencedirect.com/science/article/pii/S016816992100209X.
Kianat, Jaweria, Khan, Muhammad Attique, Sharif, Muhammad, Akram, Tallha, Rehman, Amjad, and Saba, Tanzila. (2021). A Joint Framework of Feature Reduction and Robust Feature Selection for Cucumber Leaf Diseases Recognition. Optik 240: 166566. https://www.sciencedirect.com/science/article/pii/S0030402621002904.
Kulkarn, A H, Dr H.M.Rai, Krishna Jahagirdar, and P.S.Upparamani. (2013). A Leaf Recognition Technique for Plant Classification Using RBPNN and Zernike Moments. Journal of Computer-Mediated Communication 2: 984–88.
Lee, Kuebum, and K.-S Hong. (2013). An Implementation of Leaf Recognition System Using Leaf Vein and Shape. International Journal of Bio-Science and Bio-Technology 5: 57–65.
Liu, Bin, Yun Zhang, DongJian He, and Yuxiang Li. (2018). Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks. Symmetry 10(1): 11. https://www.proquest.com/scholarly-journals/identification-apple-leaf-diseases-based-on-deep/docview/2002782281/se-2?accountid=204829.
Martínez-Minaya, Joaquín, David Conesa, Antonio López-Quílez, and Antonio Vicent. (2015). Climatic Distribution of Citrus Black Spot Caused by Phyllosticta Citricarpa. A Historical Analysis of Disease Spread in South Africa. European Journal of Plant Pathology 143(1): 69–83. https://doi.org/10.1007/s10658-015-0666-z.
Martins, Paula Maria Moreira, Maxuel de Oliveira Andrade, Celso Eduardo Benedetti, and Alessandra Alves de Souza. (2020). Xanthomonas Citri Subsp. Citri: Host Interaction and Control Strategies. Tropical Plant Pathology 45(3): 213–36. https://doi.org/10.1007/s40858-020-00376-3.
National Academies of Sciences and Medicine, Engineering. (2018). A Review of the Citrus Greening Research and Development Efforts Supported by the Citrus Research and Development Foundation. Washington, D.C.: National Academies Press. https://www.nap.edu/catalog/25026.
Shrivastava, V.~K., M.~K. Pradhan, S Minz, and M.~P. Thakur. (2019). Rice Plant Disease Classification Using Transfer Learning of Deep Convolution Neural Network. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 423: 631–35.
Sun, Hao, Zhai, Lihongi Tengi Feng, Li, Zhihong, and Zhang, Zuxin. (2021). QRgls1.06, a Major QTL Conferring Resistance to Gray Leaf Spot Disease in Maize. The Crop Journal 9(2): 342–50. https://www.sciencedirect.com/science/article/pii/S2214514120301215.
Sun, Shiliang, Zehui Cao, Han Zhu, and Jing Zhao. (2019). A Survey of Optimization Methods from a Machine Learning Perspective. IEEE transactions on cybernetics 50(8): 3668–81.
Syed-Ab-Rahman, Sharifah Farhana, Mohammad Hesam Hesamian, and Mukesh Prasad. (2021). Citrus Disease Detection and Classification Using End-to-End Anchor-Based Deep Learning Model. Applied Intelligence 52: 927-938. https://doi.org/10.1007/s10489-021-02452-w.
Szegedy, Christian, Vanhoucke, Vincent, Loffe, Sergey, Shlens, Jonathon, and Wojna, Zbignieew. (2016). Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2818-2826, https://doi.org/10.1109/CVPR.2016.308.
Szegedy, Christian, Sergey Ioffe, Vincent Vanhoucke, and Alexander A Alemi. (2016). Inception-v4, Inception-Resnet and the Impact of Residual Connections on Learning. In Thirty-First AAAI Conference on Artificial Intelligence 1-12. https://arxiv.org/abs/1602.07261.
Too, Edna Chebet, Li Yujian, Sam Njuki, and Liu Yingchun. (2019). A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification. Computers and Electronics in Agriculture 161: 272–79.
Tran, Nga T, Miles, Andrew K., Dietzgen, Ralf G., Dewdney, Megan M., Zhang, Ke, Rollins Jeffrey A., and Drenth, Andre. (2017). Sexual Reproduction in the Citrus Black Spot Pathogen, Phyllosticta Citricarpa. Phytopathology® 107(6): 732–39.
Turkoglu, Muammer, Davut Hanbay, and Abdulkadir Sengur. (2019). Multi-Model LSTM-Based Convolutional Neural Networks for Detection of Apple Diseases and Pests. Journal of Ambient Intelligence and Humanized Computing 13: 3335–3345. https://doi.org/10.1007/s12652-019-01591-w.
Wu, S G, Bao, Forrest Sheng, Xu, Eric You, Wang, Yu-Xuan, Chang, Yi-Fan, and Xiang, Qiao-Liang. (2007). A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network. In 2007 IEEE International Symposium on Signal Processing and Information Technology, 11–16.
Yu, Cui, Zhang Ai-hong, Ren Ai-jun, and Miao Hong-qin. (2014). Types of Maize Virus Diseases and Progress in Virus Identification Techniques in China. Journal of Northeast Agricultural University (English Edition) 21(1): 75–83. https://www.sciencedirect.com/science/article/pii/S100681041460026X.
Zhang, Shanwen, Zhang, Subing, Zhang, Chuanlei, Wang, Xianfeng, and Shi, Yun. (2019). Cucumber Leaf Disease Identification with Global Pooling Dilated Convolutional Neural Network. Computers and Electronics in Agriculture 162: 422–30. https://www.sciencedirect.com/science/article/pii/S0168169918317976.
Zhang, Shanwen, Wenzhun Huang, and Chuanlei Zhang. (2019). Three-Channel Convolutional Neural Networks for Vegetable Leaf Disease Recognition. Cognitive Systems Research 53: 31–41. https://www.sciencedirect.com/science/article/pii/S1389041717303236.
Zhang, Ziqiang, Hui Liu, Zhijun Meng, and Jingping Chen. (2019). Deep Learning-Based Automatic Recognition Network of Agricultural Machinery Images. Computers and Electronics in Agriculture 166: 104978. https://www.sciencedirect.com/science/article/pii/S0168169919308117.
Zhao, Zhong-Qiu, Ma, Lin Hai, Cheung, Yiu-ming, Wu, Xindong, Tang, Yuanyan, and Chen, Chun Lung Philip. (2015). ApLeaf: An Efficient Android-Based Plant Leaf Identification System. Neurocomputing 151: 1112–19. https://www.sciencedirect.com/science/article/pii/S0925231214013368.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Bilgisayar Yazılımı

Bölüm

Araştırma Makalesi

Yazarlar

Halit Çetiner ^*
0000-0001-7794-2555
Türkiye

Yayımlanma Tarihi

15 Mart 2023

Gönderilme Tarihi

5 Eylül 2022

Kabul Tarihi

4 Ekim 2022

Yayımlandığı Sayı

Yıl 2023 Cilt: 26 Sayı: 1

DOI

https://doi.org/10.17780/ksujes.1170947

IZ

https://izlik.org/JA52EH25DU

Kaynak Göster

RIS / Bibtex

APA

Çetiner, H. (2023). CITRUS DISEASE CLASSIFICATION WITH TRANSFER LEARNING AND CNN BASED MODELS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(1), 43-56. https://doi.org/10.17780/ksujes.1170947

CITRUS DISEASE CLASSIFICATION WITH TRANSFER LEARNING AND CNN BASED MODELS

CITRUS DISEASE CLASSIFICATION WITH TRANSFER LEARNING AND CNN BASED MODELS

Abstract

Keywords

TRANSFER ÖĞRENME VE CNN TABANLI MODELLER İLE NARENCİYE HASTALIĞI SINIFLANDIRMASI

Öz

Anahtar Kelimeler

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster

Cited By

Exploring Deep Learning Approaches for Citrus Diseases Detection and Classification: A Review

Artificial Intelligence in enhancing sustainable practices for infectious municipal waste classification

Citrus diseases detection and classification based on efficientnet-B5