technical seminar [Pavan Y N] final.pptx

Coffee Bean

1. Technical Seminar Presentation on “RECOGNITION OF COFFEE LEAVES DISEASES” By PAVAN Y N(1JB20IS041) Under the Guidance of ABHILASH C N Professor, Dept of ISE || Jai Sri Gurudev || Sri Adichunchanagiri Shikshana Trust (R) SJB Institute of Technology An Autonomous Institute under Visvesvaraya Technological University, Belagavi , No. 67, BGS Health & Education City, Dr. Vishnuvardhan Road, Kengeri,Bengaluru-60 Department of Information Science & Engineering

2. OVERVIEW Introduction Literature Survey Problem Statement Methodology-1 Methodology-2 Results-1 Results-2 Conclusion reference

3. INTRODUCTION p rovides an overview of the problem of fine-grained categorization of plant leaf diseases using convolutional neural networks. Focuses on early detection and accurate identification of plant diseases to prevent crop losses and ensure food security. Discusses the importance of accurate classification in plant disease management and highlights the interest of researchers in automatic classification of diseases through images over the past few years. This work aims to provide insights into how deep learning techniques can be applied to solve real-world problems in agriculture and disease detection. Discusses the challenges associated with this task, including the difficulty in distinguishing between similar-looking diseases and the lack of annotated data for training models. Sample Footer Text 3

4. LITERATURE SURVEY Title of the paper​ Description​ Advantages​ Disadvantages​ Beans Leaf Disease Classification Using MobileNet Models - 2022 This paper proposes a method for Classifying beans leaf diseases using MobileNet Models   The proposed method provides an efficient way to classify bean leaf diseases into their classes with high accuracy. The accuracy of the classification may depend on the quality of the images used for training and testing. ​ Plant Leaf Diseases Fine-Grained Categorization Using Convolutional Neural Networks - 2022 This research paper presents the use of  Convolutional Neural Networks in the Categorization of fine grained plant leaf diseases. ​ The proposed method achieves higher classification accuracy,  demonstrating its effectiveness in fine-grained categorization of plant leaf diseases. There may be a risk of overfitting if the model is trained on a small dataset or with insufficient regularization. 4/21/2024 Sample Footer Text 4

5. PROBLEM STSTEMENT Sample Footer Text 5 recognition of unhealthy leaves in crops, which affects their production. And  develop an automated model capable of classifying and identifying disease types based on MobileNet models and  leaf images. The proposed method aims to build an accurate model that can easily classify bean leaf diseases into their classes. the fine-grained categorization of plant leaf diseases using convolutional neural networks.

6. METHODOLOGY-1 Figure 1:Major components of beans diseases classification using MobileNet V2.

7. METHODOLOGY-1 uses a deep learning approach to identify and classify beans leaf diseases based on images. use MobileNet architectures, which are efficient convolutional neural networks (CNNs) designed for mobile and embedded devices. The authors optimize the hyperparameters and optimization methods to define smaller and more efficient MobileNets models. hey also use transfer learning techniques to train the MobileNet models on the beans leaf images dataset, which involves using pre-trained models as a starting point for training new models on specific tasks. developing a classifier that can predict whether the bean leaf has been affected by a disease or not. The authors also compare their results with other state-of-the-art methods to evaluate the effectiveness of their proposed methodology.

8. methodology Figure 2:A glimpse of labeled dataset.

9. METHODOLOGY-2 Figure 2:Fine-grained disease categorization method based on attentional deep neural network.

10. METHODOLOGY-2 It is a fine-grained disease identification method based on attentional deep neural network for peach and tomato disease leaf identification. The proposed method consists of three parts: Identification Model, Discrimination Model, and Reconstruction & Generation Model. The Identification Model is responsible for extracting features from the input image using a ResNet-50 architecture. The Identification Model is responsible for extracting features from the input image using a ResNet-50 architecture. The Discrimination Model uses attention mechanisms to extract local features from the input image and generate a discriminative feature vector. The Reconstruction & Generation Model reconstructs the input image from the extracted features and generates new images with similar features.

11. methodology Figure 3:Examples of leaf diseases

12. RESULT-1 the deep learning approach using MobileNet architectures is effective in identifying and classifying beans leaf diseases based on images. They also use transfer learning techniques to train the MobileNet models on the beans leaf images dataset. it is mentioned that performance metrics were applied to the classification of crop disease (beans leaf image).  and various classification techniques were also applied on the test data in the prediction. The proposed method achieves high accuracy in classifying beans leaf diseases. The obtained results will be discussed in the result section.

13. RESULT-1 Figure 3:Comparison of accuracy and loss of two optimizer methods

14. RESULT-1 Table 1:Training and testing set accuracy and loss results of five optimizers.

15. RESULT-2 presents the results of experiments conducted to compare the performance of the proposed model with a classical convolutional neural network. The higher the classification accuracy, the better the performance of the model, and more outstanding is its generalization ability. The proposed model achieved better classification accuracy than a classical convolutional neural network in both peach and tomato leaf disease identification tasks, demonstrating its effectiveness in fine-grained categorization of plant leaf diseases. The classification accuracy of the testing-set was used as the main evaluation index of the experimental results. The comparison experiments were all completed under the same conditions.

16. RESULT-2 Table 2:Comparison of identification indexes of tomato leaf diseases in different networks.

17. RESULT-2 Table 3:Comparison of identification indexes of peach leaf diseases in different networks. In the experiment, the classification accuracy of the testing-set was used as the main evaluation index of the experimental results. lists the comparison of identification indexes of peach leaf diseases under different neural network models

18. CONCLUSION The research shows that the proposed method can accurately classify leaf diseases into their classes. The study also highlights the importance of accurate classification in plant disease management, which can help in saving crops and increasing productivity. The study provides a valuable contribution to the field of plant disease classification using deep learning techniques. Also highlights the challenges of this task, including the difficulty in distinguishing between similar-looking diseases and the lack of annotated data for training models. this work provides insights into how deep learning techniques can be applied to solve real-world problems in agriculture and disease detection.

19. REFERENCES Model Selection of Hybrid Feature Fusion for Coffee Leaf Disease Classification MUHAMAD FAISAL , JENQ-SHIOU LEU , (Senior Member, IEEE), AND JEREMIE T. DARMAWAN 2023. Coffee disease classification using Convolutional Neural Network based on feature concatenation Biniyam Mulugeta Abuhayi a, Abdela Ahmed Mossa 2023. An Intelligent System-Based Coffee Plant Leaf Disease Recognition Using Deep Learning Techniques on Rwandan Arabica Dataset Eric Hitimana , Omar Janvier Sinayobye , J. Chrisostome Ufitinema , Jane Mukamugema , Peter Rwibasira , Theoneste Murangira , Emmanuel Masabo , Lucy Cherono Chepkwony , Marie Cynthia Abijuru Kamikazi , Jeanne Aline Ukundiwabo Uwera , Simon Martin Mvuyekure , Gaurav Bajpai and Jackson Ngabonziza 2023. Plant Leaf Diseases Fine-Grained Categorization Using Convolutional Neural Networks - YANG WU, XIAN FENG1 , AND GUOJUN CHEN 2022. Beans Leaf Diseases Classification Using MobileNet Models ELHOUCINE ELFATIMI , RECEP ERYIGIT , AND LAHCEN ELFATIMI 2022. 19

20. Thank You PAVAN Y N 1JB20IS041 20