Plant disease detection using machine learning algorithm-1.pptx
- 1. Academic Project Phase-1 Presentation on “PLANT DISEASE DETECTION AND CLASSIFICATION USING MACHINE LEARNING ALGORITHM” Under the guidance of: Dr. Vijayashekhar S Sankannanavar Associate Professor Department of CS&E Presented by: Rumman Hajira (1AY16CS089) ACHARYA INSTITUTE OF TECHNOLOGY DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 1 (Affiliated to Visvesvarya Technological University, Belagavi, Approved by AICTE, New Delhi and Accredited by NBA & NAAC) Acharya Dr. Sarvepalli Radhakrishnan Road, Achithnagar Post, Soladevanahalli, BENGALURU-560107 Department of CS&E, Acharya Institute of Technology 21-Oct-22 1
- 2. AGENDA 2 • Agriculture is the boon to country’s Economy • Methods of detection • Machine learning Algorithms • Classification of various plant diseases • Suggest Pesticide Department of CS&E, Acharya Institute of Technology 22-Oct-22 2z
- 3. INTRODUCTION TO THE PROJECT
- 4. INTRODUCTION 22-Oct-22 Department of CS&E, Acharya Institute of Technology 4 1.PROBLEM DEFINITION: • Agriculture crops are threatened by wide variety of plant diseases. • These can damage the crop , lower the vegetable and fruits quality and wipe out the harvest. • About 42% of the world’s total agricultural crop is destroyed yearly by diseases.
- 5. 22-Oct-22 Department of CS&E, Acharya Institute of Technology 5 2. Overview Of Technical Area • Vision method • Laboratory methods – polymerase chain reaction ,thermography , etc. • Machine learning and Deep learning – accuracy and recognition • Algorithms – Random Forest , K-nearest neighbor • CNN
- 6. 22-Oct-22 Department of CS&E, Acharya Institute of Technology 6 3. Overview of Existing System • The most wanted crop, Paddy • Diseases- Brown spot , Paddy Blast , Bacterial blight affected leaf • Methods – Histograms, k-means clustering, Image Processing • Drawbacks – Accuracy
- 7. 22-Oct-22 Department of CS&E, Acharya Institute of Technology 7 4.Overview Of Proposed System • Innovation : Convolutional Neural Network • Benefit : Increase in accuracy rate • Classification of various plant diseases • Advancement : Pesticide suggestion
- 9. LITERATURE SURVEY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 9 S.N PAPER TITTLE & PUBLICATION DETAILS NAME OF THE AUTHORS TECHNICAL IDEAS / ALGORITHMS USED IN THE PAPER & ADVANTAGES SHORTFALLS/DISA D VANTAGES & SOLUTION PROVIDED BYTHE PROPOSED SYSTEM 1 F. Marzougui, M. Elleuch and M. Kherallah, "A Deep CNN Approach for Plant Disease Detection," 2020 21st International Arab Conference on Information Technology (ACIT), 2020, pp. 1-6, doi: 10.1109/ACIT50332.2020.930007 2. 1.Fatma Marzougui 2.Mohamed Elleuch 3.Monji kherallah Uses the ResNet and data argumentation on data , ResNet has more accuracy and less training time than CNN Without set background the accuracy is less
- 10. LITERATURE SURVEY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 10 S.N PAPER TITTLE & PUBLICATION DETAILS NAME OF THE AUTHORS TECHNICAL IDEAS / ALGORITHMS USED IN THE PAPER & ADVANTAGES SHORTFALLS/DISA D VANTAGES & SOLUTION PROVIDED BYTHE PROPOSED SYSTEM 2 A. KP and J. Anitha, "Plant disease classification using deep learning," 2021 3rd International Conference on Signal Processing and Communication (ICPSC), 2021, pp. 407-411, doi: 10.1109/ICSPC51351.2021.9451 696. 1.Akshai KP 2. J. Anitha The literature study reveals that pre-trained models using transfer learning are an efficient strategy for plant disease classification The ResNet model adds the output of one layer to the next layer that’s why the accuracy is less than the densenet.
- 11. LITERATURE SURVEY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 11 S.N PAPER TITTLE & PUBLICATION DETAILS NAME OF THE AUTHORS TECHNICAL IDEAS / ALGORITHMS USED IN THE PAPER & ADVANTAGES SHORTFALLS/DISA D VANTAGES & SOLUTION PROVIDED BYTHE PROPOSED SYSTEM 3 S. M. Hassan and A. K. Maji, "Plant Disease Identification Using a Novel Convolutional Neural Network," in IEEE Access, vol. 10, pp. 5390-5401, 2022, doi: 10.1109/ACCESS.2022.3141371. 1.SK Mahmudul 2. Hassan 3. Arnab Kumar Maji Novel CNN model based inception and residual connection. Number of parameters used are reduced. The imbalance cassava dataset is used ,so accuracy is less than balanced dataset accuracy.
- 12. LITERATURE SURVEY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 12 S.N PAPER TITTLE & PUBLICATION DETAILS NAME OF THE AUTHORS TECHNICAL IDEAS / ALGORITHMS USED IN THE PAPER & ADVANTAGES SHORTFALLS/DISA D VANTAGES & SOLUTION PROVIDED BYTHE PROPOSED SYSTEM 4 M. N and K. J. Gowda , "Image Processing System based Identification and Classification of Leaf Disease: A Case Study on Paddy Leaf," 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), 2020, pp. 451- 457, doi: 10.1109/ICESC48915.2020.91556 07. 1.Manohar N 2.Karuna J Gowda Image processing ,Ostu ,GLCM and KNN Longer training for the framework.
- 13. LITERATURE SURVEY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 13 S.N PAPER TITTLE & PUBLICATION DETAILS NAME OF THE AUTHORS TECHNICAL IDEAS / ALGORITHMS USED IN THE PAPER & ADVANTAGES SHORTFALLS/DISA D VANTAGES & SOLUTION PROVIDED BYTHE PROPOSED SYSTEM 5 P. A. H. Vardhini, S. Asritha and Y. S. Devi, "Efficient Disease Detection of Paddy Crop using CNN," 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), 2020, pp. 116-119, doi: 10.1109/ICSTCEE49637.2020.927 6775. 1. P. A Harsha 2. Vardini 3. S. Asritha 4. Y. Sumitha Devi Disease prediction , raspberry pi, CNN ,Artificial Intelligence . Cost and User friendly. Applicable on Paddy crop plant.
- 15. FUNCTIONAL REQUIREMENTS 15 • The Functional requirements define the internal workings of the software • The technical details, data manipulation and processing and other specific functionality that show how the use cases are to be satisfied. • They are supported by non-functional requirements, which impose constraints on the design or implementation. Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 16. NON-FUNCTIONAL REQUIREMENTS 16 • Dependability • Availability • Reliability • Safety • Security Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 17. SOFTWARE REQUIREMENTS • Operating System : Windows 10 • IDE : python 3.7, MATLab , TensorFlow • Language : Python As of now, we are vigorously focusing on only software algorithms. We are using python tool for developing algorithms. In future, we will be using TensorFlow and Python IDE for transforming this algorithm into a complete product. 17 Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 18. HARDWARE REQUIREMENTS • Processor : Intel i7 • Hard Disk :120 GB • RAM : 16 GB 18 Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 20. PROPOSED METHODOLOGY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 20 The main steps in the proposed work is summarized below: • This work proposes a training image generation technology based on image processing techniques, which can enhance the robustness and prevent overfitting of the CNN-based model in the training process. • A convolutional neural network is first employed to diagnose leaf diseases; the end-to -end learning model can automatically discover the discriminative features of the leaf images and identify the common types of leaf diseases with high accuracy.
- 21. PROPOSED METHODOLOGY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 20 • Convolutional Neural Network (CNN) A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other.
- 22. PROPOSED METHODOLOGY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 20 • By analyzing the characteristics of leaf diseases, a novel deep convolutional neural network model based on ResNet shall be proposed; the convolution kernel size is adjusted, fully-connected layers are replaced by a convolutional layer, and GoogLeNet’s Inception is applied to improve the feature extraction ability. • Residual network (ResNet) is a CNN architecture whose core building element is a residual block.
- 23. PROPOSED METHODOLOGY 22-Oct-22 Department of CS&E, Acharya Institute of Technology 20 • The strength of ResNet34 to solve the degradation problem to give higher accuracies and the advantages of this pre-trained model is the motivation of using it as the classification technique in our proposed work. • Proposed work is planning to use a dataset of various images of many crops diseased leaves as shown below. Fig. 1 Image samples of leaf disease
- 24. CONCLUSION AND FUTURE ENHANCEMENT
- 25. CONCLUSION 25 ⚫This project shall propose a novel deep convolutional neural network model to accurately identify and classify leaf diseases, which can automatically discover the discriminative features of leaf diseases and enable an end-to-end learning pipeline with high accuracy. ⚫ A novel structure of a deep convolutional neural network based on the ResNet model shall be designed by removing partial full connected layers, adding pooling layers, introducing the GoogLeNet Inception structure into the proposed network model. Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 26. FUTURE ENHANCEMENT 26 ⚫The future work can also be dedicated to the automatic estimation of the severity of these diseases. ⚫Usage of real-time images to identify the diseases which would increase time efficiency of the project and it can be carried out to identify diseases on other crops such as wheat, sugarcaneand others. ⚫The instant solutions can be made available to the farmers by designing mobile based applications. ⚫Online solutions related to plant diseases can be provided by using web portals Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 27. 1 F. Marzougui, M. Elleuch and M. Kherallah, "A Deep CNN Approach for Plant Disease Detection," 2020 21st International Arab Conference on Information Technology (ACIT), 2020, pp. 1-6, doi: 10.1109/ACIT50332.2020.9300072. 2 A. KP and J. Anitha, "Plant disease classification using deep learning," 2021 3rd International Conference on Signal Processing and Communication (ICPSC), 2021, pp. 407-411, doi: 10.1109/ICSPC51351.2021.9451696. 3 S. M. Hassan and A. K. Maji, "Plant Disease Identification Using a Novel Convolutional Neural Network," in IEEE Access, vol. 10, pp. 5390-5401, 2022, doi: 10.1109/ACCESS.2022.3141371. 4 M. N and K. J. Gowda, "Image Processing System based Identification and Classification of Leaf Disease: A Case Study on Paddy Leaf," 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), 2020, pp. 451-457, doi: 10.1109/ICESC48915.2020.9155607. 5 P. A. H. Vardhini, S. Asritha and Y. S. Devi, "Efficient Disease Detection of Paddy Crop using CNN," 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), 2020, pp. 116-119, doi: 10.1109/ICSTCEE49637.2020.9276775. REFERENCES 27 Department of CS&E, Acharya Institute of Technology 22-Oct-22
- 28. THANK YOU 28 Department of CS&E, Acharya Institute of Technology 22-Oct-22