A Novel Approach for Tomato Diseases Classification Based on Deep Convolutional Neural Networks
Download as PPT, PDF1 like1,095 views
This document summarizes Mohammad Shakirul Islam's research paper on classifying tomato plant diseases using deep convolutional neural networks. The paper includes sections on motivation, literature review, proposed methodology, results discussion, and future work. The proposed methodology uses a dataset of 3000 images across 6 tomato disease classes. A convolutional neural network model with 5 convolution layers, 5 max pooling layers, and 2 dense layers is trained on 80% of the data and tested on the remaining 20% for classification performance. Results show the model achieved high training and validation accuracy for identifying different tomato diseases.
![[1] Inge M. Hanssen, Moshe Lapidot, “Major Tomato Viruses in the Mediterranean Basin” ,Advances in Virus Research, Volume 84, 2012,
Pages 31-66.
[2] Mohammed Brahimi, Kamel Boukhalfa and Abdelouahab Moussaoui (2017) “Deep Learning for Tomato Diseases: Classification and
Symptoms Visualization”, Applied Artificial Intelligence, 31:4, 299-315, DOI: 10.1080/08839514.2017.1315516
[3] Y. Lu, Shujuan Yi, N. Zeng, Y. Liu, Yong Zhang, “Identification of rice diseases using deep convolutional neural
Networks.”,Neurocomputing Volume 267, 6 December 2017, Pages 378-384.
[4] Asma Akhtar, Aasia Khanum, Shoab A. Khan, Arslan Shaukat, 2013. “Automated Plant Disease Analysis (APDA): Performance
comparison of machine learning techniques.’ Proceedings of the 11th International Conference on Frontiers of Information Technology,
60–65.
[5] Hanssen, I. M., and M. Lapidot. 2012. “Major tomato viruses in the Mediterranean basin.” In Advances in virus research, volume 84
of advances in virus research, ed. G. Loebenstein and H. Lecoq, 31–66. Academic Press: San Diego, California, USA.
[6] Blancard, D. 2012. Tomato diseases. The Netherlands: Academic Press. Breitenreiter, A. H.Poppinga, T. U. Berlin, and F. N. Technik.
2015. Deep learning. Nature 521:2015.
[7] James H. Blake, Anthony P. Keinath, Marjan Kluepfel and Joey Williamson “Tomato Diseases & Disorders” by Clemson University
Home and Garden Information Center, Jun 28, 2018 [online]: https://hgic.clemson.edu/factsheet/tomato-diseases-disorders.
[8] J. Amara, B. Bouaziz, and A. Algergawy, “A Deep Learning-based Approach for Banana Leaf Diseases Classification”, B. Mitschang et
al. (Hrsg.): BTW 2017–Workshopband, Lecture Notes in Informatics (LNI), Gesellschaft für Informatik, Bonn 2017.
References (Cont.)](https://image.slidesharecdn.com/ijcci2018183-190530201016/85/A-Novel-Approach-for-Tomato-Diseases-Classification-Based-on-Deep-Convolutional-Neural-Networks-14-320.jpg)
![[9] R. Ghaffari, Fu Zhang, D. Iliescu, Evor L. Hines, M. S. Leeson, R. Napier, P. J. Clarkson, “Early detection of diseases in tomato crops: An
Electronic Nose and intelligent systems approach”, International Joint Conference on Neural Networks (IJCNN), 2010.
[10] Alex K., I. Sutskever, and G. E. Hinton. 2012. “Imagenet classification with deep convolutional neural networks.” In Neural Information
Processing Systems (NIPS),ed. F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Curran Associates Inc.: Lake Tahoe, Nevada, USA,
1097–105.
[11] Fuentes, A., Yoon, S., Kim, S.C., Park, D.S., 2017. “A robust deep-learning-based detector for real-time tomato plant diseases and pest
recognition.” Sensors 17, 2022. http://dx.doi.org/10.3390/s17092022.
[12] H Al-Hiary, S Bani-Ahmad, M Reyalat, M Braik and Z ALRahamneh. Article: Fast and Accurate Detection and Classification of Plant
Diseases. International Journal of Computer Applications 17(1):31-38, March 2011.
[13] T. Rumpf, A.K. Mahlein, U. Steiner, E. C. Oerke, H. W. Dehne, L. Plümer, “Early detection and classification of plant diseases with
Support Vector Machines based on hyperspectral reflectance”, October 2010Computers and Electronics in Agriculture 74(1):91-99, DOI:
10.1016/j.compag.2010.06.009
[14] Dandawate, Y., and R. Kokare. 2015. An automated approach for classification of plant diseases towards development of futuristic
decision support system in Indian perspective. Proceedings of the International Conference on Advances in Computing, Communications
and Informatics (ICACCI), Kochi, India, 794–99. IEEE.
[15] Koike, S. T., P. Gladders, and A. O. Paulus. 2007. Vegetable diseases: A color handbook. Ed Academic Press: San Diego, California, USA.
[16] Le, T.-L., N.-D. Duong, V. T. Nguyen, and H. Vu. 2015. Complex background leaf-based plant identification method based on interactive
segmentation and kernel descriptor. Proceedings of the 2nd International Workshop on Environmental Multimedia. In Conjunction with
ACM Conference on Multimedia Retrieval (ICMR), Shanghai, China, 3–8. ACM.
References](https://image.slidesharecdn.com/ijcci2018183-190530201016/85/A-Novel-Approach-for-Tomato-Diseases-Classification-Based-on-Deep-Convolutional-Neural-Networks-15-320.jpg)
A Novel Approach for Tomato Diseases Classification Based on Deep Convolutional Neural Networks
- 1. Mohammad Shakirul Islam Department of Computer Science and Engineering Daffodil International University, Dhaka, Bangladesh. A Novel Approach for Tomato Diseases Classification Based on Deep Convolutional Neural Networks International Joint Conference on Computational Intelligence (IJCCI 2018)
- 2. Motivation Literature Review Proposed Methodology Result discussion Future Work & Conclusion References Table of Contents
- 4. Literature Review Tomato: Septoria leaf spot Now a days scientists and researchers are working with early detection of crops and plant diseases. In 2012, M Hanssen et al. Published their work on major tomato viruses. In 2013 a Pakistani research group worked on automated plant diseases analysis (APDA). There are some works done on Rise, Potato, Cabbage etc.
- 5. Proposed Methodology: Tomato Diseases Classification
- 6. Dataset Fig: Sample data from Our Dataset
- 7. Data Processing 6 Class Total data: 3000 Train and Validation data: 80% (2400) Test Data: 20% (600) Resized Image size: 100 x 100 pixels. Converted to grayscale.
- 8. Our Proposed Model Fig: Our Proposed Model Our model have following number of layers: 5 convolution, 5 max pooling, 2 dropout, 1 flatten, 2 dense
- 9. Training the Model Our model was compiled by Adam Optimization Algorithm. Keras fit( ) function was used to train our model. Our model was trained for 40 epochs and batch size was 64. The loss type we have used is known as `Categorical cross entropy‘.
- 10. Performance Evaluation Fig. (a) Training and validation accuracy, (b) Training and validation loss.
- 12. Result Discussion Fig: Confusion Matrix
- 13. Future Work Enrich the dataset. Develop real life application (Android, IOS) Comparing with new approach for Better accuracy. Image from Google
- 14. [1] Inge M. Hanssen, Moshe Lapidot, “Major Tomato Viruses in the Mediterranean Basin” ,Advances in Virus Research, Volume 84, 2012, Pages 31-66. [2] Mohammed Brahimi, Kamel Boukhalfa and Abdelouahab Moussaoui (2017) “Deep Learning for Tomato Diseases: Classification and Symptoms Visualization”, Applied Artificial Intelligence, 31:4, 299-315, DOI: 10.1080/08839514.2017.1315516 [3] Y. Lu, Shujuan Yi, N. Zeng, Y. Liu, Yong Zhang, “Identification of rice diseases using deep convolutional neural Networks.”,Neurocomputing Volume 267, 6 December 2017, Pages 378-384. [4] Asma Akhtar, Aasia Khanum, Shoab A. Khan, Arslan Shaukat, 2013. “Automated Plant Disease Analysis (APDA): Performance comparison of machine learning techniques.’ Proceedings of the 11th International Conference on Frontiers of Information Technology, 60–65. [5] Hanssen, I. M., and M. Lapidot. 2012. “Major tomato viruses in the Mediterranean basin.” In Advances in virus research, volume 84 of advances in virus research, ed. G. Loebenstein and H. Lecoq, 31–66. Academic Press: San Diego, California, USA. [6] Blancard, D. 2012. Tomato diseases. The Netherlands: Academic Press. Breitenreiter, A. H.Poppinga, T. U. Berlin, and F. N. Technik. 2015. Deep learning. Nature 521:2015. [7] James H. Blake, Anthony P. Keinath, Marjan Kluepfel and Joey Williamson “Tomato Diseases & Disorders” by Clemson University Home and Garden Information Center, Jun 28, 2018 [online]: https://hgic.clemson.edu/factsheet/tomato-diseases-disorders. [8] J. Amara, B. Bouaziz, and A. Algergawy, “A Deep Learning-based Approach for Banana Leaf Diseases Classification”, B. Mitschang et al. (Hrsg.): BTW 2017–Workshopband, Lecture Notes in Informatics (LNI), Gesellschaft für Informatik, Bonn 2017. References (Cont.)
- 15. [9] R. Ghaffari, Fu Zhang, D. Iliescu, Evor L. Hines, M. S. Leeson, R. Napier, P. J. Clarkson, “Early detection of diseases in tomato crops: An Electronic Nose and intelligent systems approach”, International Joint Conference on Neural Networks (IJCNN), 2010. [10] Alex K., I. Sutskever, and G. E. Hinton. 2012. “Imagenet classification with deep convolutional neural networks.” In Neural Information Processing Systems (NIPS),ed. F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Curran Associates Inc.: Lake Tahoe, Nevada, USA, 1097–105. [11] Fuentes, A., Yoon, S., Kim, S.C., Park, D.S., 2017. “A robust deep-learning-based detector for real-time tomato plant diseases and pest recognition.” Sensors 17, 2022. http://dx.doi.org/10.3390/s17092022. [12] H Al-Hiary, S Bani-Ahmad, M Reyalat, M Braik and Z ALRahamneh. Article: Fast and Accurate Detection and Classification of Plant Diseases. International Journal of Computer Applications 17(1):31-38, March 2011. [13] T. Rumpf, A.K. Mahlein, U. Steiner, E. C. Oerke, H. W. Dehne, L. Plümer, “Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance”, October 2010Computers and Electronics in Agriculture 74(1):91-99, DOI: 10.1016/j.compag.2010.06.009 [14] Dandawate, Y., and R. Kokare. 2015. An automated approach for classification of plant diseases towards development of futuristic decision support system in Indian perspective. Proceedings of the International Conference on Advances in Computing, Communications and Informatics (ICACCI), Kochi, India, 794–99. IEEE. [15] Koike, S. T., P. Gladders, and A. O. Paulus. 2007. Vegetable diseases: A color handbook. Ed Academic Press: San Diego, California, USA. [16] Le, T.-L., N.-D. Duong, V. T. Nguyen, and H. Vu. 2015. Complex background leaf-based plant identification method based on interactive segmentation and kernel descriptor. Proceedings of the 2nd International Workshop on Environmental Multimedia. In Conjunction with ACM Conference on Multimedia Retrieval (ICMR), Shanghai, China, 3–8. ACM. References
- 16. Affiliation
- 17. Thank You!