Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Community
Ask the community for help and clear up your study doubts
Discover the best universities in your country according to Docsity users
Free resources
Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors
The document is the project report of my final year project automated hydroponics with leaf disease detection
Typology: Cheat Sheet
1 / 42
This page cannot be seen from the preview
Don't miss anything!
submitted by
to the APJ Abdul Kalam Technological University in partial fulfillment of the requirement for the award of the Degree of Bachelor of Technology in Electronics and Communication Engineering
Amal Jyothi College of Engineering Kanjirappally-
We undersigned hereby declare that the project report “Automated Hydroponics with Leaf Disease Detection”, submitted for partial fulfillment of the requirements for the award of degree of Bachelor of Technology of the APJ Abdul Kalam Technological University, Kerala is a bonafide work done by us under supervision of Mrs. Deepa Joseph. This submission represents our ideas in our own words and where ideas or words of others have been included, we have adequately and accurately cited and referenced the original sources. We also declare that we have adhered to ethics of academic honesty and integrity and have not misrepresented or fabricated any data or idea or fact or source in our submission. We understand that any violation of the above will be a cause for disciplinary action by the institute and/or the University and can also evoke penal action from the sources which have thus not been properly cited or from whom proper permission has not been obtained. This report has not been previously formed the basis for the award of any degree, diploma or similar title of any other University.
Kanjirappally Date: BIbin V Babu Ashley Grace Thomas Aylikunnel Simon Sunny
First of all we sincerely thank the Almighty GOD who is most beneficent and merciful for giving us knowledge and courage to complete the Project successfully.
We derive immense pleasure in expressing our sincere thanks to our Manager, Fr. Dr. Mathew Paikatt and to our Principal, Dr. Lillykutty Jacob for the kind co-operation in all aspects of our Project.
We express our gratitude to Dr. Geevarghese Ttus, HOD, Department of Electronics and Communication Engineering for his kind co-operation in all aspects of our Project. We express our sincere thanks to our internal guide, Ms. Deepa Joseph, Assistant Professor and our Project Co-ordinators Ms. Deepa Joseph,Assistant Professor & Mr.Midhun Joy,Assistant Professor for their encouragement and motivation during the project.
We are indebted to our beloved teachers for their cooperation and suggestion throughout the project which helped us a lot. We also thank all our friends and classmates for their interest, dedication and encouragement shown towards the project. We convey hearty thanks to our parents for their moral support, suggestion and encouragement to make this venture a success.
i
Hydroponics is an alternative for soil which is used for plant cultivation, it includes grow- ing plants in nutrient-rich water solutions. Due to its many advantages over conventional soil-based farming, it is becoming more and more popular on a global scale. With hy- droponics, gardeners may precisely regulate factors that affect plant development, such as temperature, light, and fertilizer levels. Hydroponics is more water-efficient than con- ventional soil-based farming, using up to 90% less water, and it may be used in a number of contexts,from small-scale indoor systems to large-scale commercial operations. The proposed system incorporates to improve the development and productivity of tomato plants, automated hydroponics uses pH and electric conductivity sensors to regulate the nutrient delivery through water while simultaneously verifying the detection of leaf disease through real time using camera. Modern deep learning-based technology is used in the approach suggested in this study to automatically identify leaf diseases in tomato plants.
The system divides leaf photos into 10 distinct classes of leaf illnesses using the Mo- bileNetV2 architecture. The classifications we are detecting are spidermite, bacterial spot, early blight, leaf mold and yellow leaf curl virus.The proposed system gives the user a real-time prognosis of the disease along with a likelihood score after receiving input from a camera. With precise and reliable findings, even in the early stages of disease develop- ment, this method does away with the need for human inspection, enabling quick action to stop the spread of disease and reduce crop losses. Additionally, it is simple to use and doesn’t take a lot of skill to utilize, making it available to farmers and agricultural special- ists everywhere. The suggested method, which offers a precise, effective, and user-friendly tool for farmers and agricultural specialists, illustrates the promise of computer vision and deep learning for the automated diagnosis of leaf diseases in tomato plants. Manual ex- amination is a key component of traditional disease detection techniques, although it may be laborious and error-prone.
ii
4 Results and Discussion 29
5 Conclusion and Future work 32
REFERENCES 33
iv
Chapter 1. Introduction
Figure 1.1: Hydroponics plant
The production of tomato crops are increasing due to the high demand in markets. Diffi- cult for the farmers to manually identify the diseases accurately with their limited knowl- edge which leads to low quality tomatoes. Leaf disease detection is done using a camera in a real time manner so the farmers can easily identify the disease which is spread in leaf. Large area for cultivation will be difficult for the farmers in urban area. Hydroponics will be the best solution for this problem as we need less space and soil for the effective growth. We control the pH and EC of the solution and thereby give essential nutrition for the plant to grow. 3.5.
Figure 1.2: Hdroponics Setup
Department of Electronics and Communication Engineering,AJCE 2
Chapter 1. Introduction
The main objective of hydroponics with leaf disease detection in tomato plants is to combine the advantages of hydroponic cultivation with advanced technologies to achieve early and accurate detection of diseases, enable timely interventions, improve overall crop management, and promote sustainable agricultural practices.
This section gives the organization of the report work. Overall, this report work gives a clear and thorough study about the existing study of the proposed system and gives a description about the implementation details. The second chapter gives a detailed description about the literature survey. Third chapter gives a brief idea about the imple- mentation details including hardware and software requirements, outline of the proposed methodology. Fourth chapter depicts the Results and Discussions and fifth Chapter gives the Conclusion and Future Work
Department of Electronics and Communication Engineering,AJCE 3
Chapter 2. Literature Survey
fabrication materials than earlier approaches.
Proposed System In their review, Ghosal et al. propose a system for automatic de- tection of leaf diseases in plants using machine learning techniques. The system involves Image Acquisition which is the system begins with the acquisition of high-quality leaf images. Various imaging techniques, such as digital cameras or sensors, can be em- ployed to capture leaf images under controlled conditions. Preprocessing acquired leaf images undergo preprocessing to enhance image quality and remove any noise or arti- facts. Techniques such as image resizing, noise reduction, and contrast enhancement may be applied to ensure accurate disease detection. Feature Extraction, it is a ma- chine learning techniques rely on extracting meaningful features from the input data. In the proposed system, relevant features are extracted from the preprocessed leaf images. These features may include color histograms, texture descriptors, shape characteristics, or spatial frequency information. Machine Learning Algorithms the extracted features are then used as inputs for various machine learning algorithms. Ghosal et al. discuss the application of several popular machine learning techniques such as Support Vector Machines (SVM), Random Forests (RF), Artificial Neural Networks (ANN), and Convo- lutional Neural Networks (CNN). These algorithms are trained using a labeled dataset of diseased and healthy leaf images to learn the patterns associated with different diseases. Disease Classification which is once the machine learning models are trained, they can be used for disease classification. The proposed system applies the trained models to unseen leaf images, predicting the presence and type of disease based on the learned patterns and features. ??.
The proposed system in accurately detecting leaf diseases in plants. They discuss the potential benefits of using machine learning techniques, including increased accuracy, scalability, and the ability to handle large datasets. Moreover, they emphasize the impor- tance of continuous model refinement and validation to ensure reliable disease detection performance. By proposing a comprehensive system that integrates image acquisition, preprocessing, feature extraction, and machine learning algorithms, the authors provide a valuable framework for the automatic detection of leaf diseases in plants. The pro-
Department of Electronics and Communication Engineering,AJCE 5
Chapter 2. Literature Survey
posed system has the potential to revolutionize disease diagnosis and contribute to the improvement of crop management practices in agriculture.
Conclusion The paper provides a comprehensive review of machine learning techniques for automatic detection of leaf diseases in plants. It highlights the potential benefits and challenges associated with these techniques and emphasizes the need for further research and development. Moreover, machine learning models can be trained to detect diseases at an early stage, enabling proactive disease management and preventing severe crop losses. The authors also acknowledge the potential of machine learning techniques to reduce labor-intensive tasks associated with manual disease detection and improve overall productivity in agriculture. The findings of this review contribute to the advancement of disease detection methodologies, paving the way for improved crop management practices and enhanced plant health in agriculture.
Advantages
Disadvantages
Authors: Jiang, Y., and Li, C
Department of Electronics and Communication Engineering,AJCE 6
Chapter 2. Literature Survey
They delve into the importance of data preprocessing steps such as image augmenta- tion, normalization, and segmentation to enhance the quality and diversity of the training data. Moreover, the authors elaborate on different CNN architectures utilized in plant disease detection, such as AlexNet, VGGNet, Inception, and ResNet. They highlight the advantages and limitations of each architecture and provide insights into their applica- bility in different scenarios. Additionally, the paper discusses the training procedures involved in the proposed system, including data partitioning, optimization algorithms, and hyperparameter tuning. The authors emphasize the significance of proper training to ensure model convergence and avoid issues like overfitting or underfitting
The evaluation metrics used to assess the performance of the proposed system are also discussed, including accuracy, precision, recall, and F1-score. The authors explain the importance of selecting appropriate evaluation metrics based on the specific requirements of plant disease detection applications. Overall, the proposed system in the paper aims to harness the capabilities of deep learning, particularly CNNs, to accurately and efficiently detect and diagnose plant diseases. The authors provide a comprehensive discussion on the various components of the system, highlighting their significance and potential impact in the field of plant disease detection and diagnosis.
Conclusion The conclusion of the paper summarizes the key findings and insights ob- tained from the review of deep learning approaches for plant disease detection and di- agnosis. The authors highlight the advancements made in deep learning techniques and their potential in improving the accuracy and efficiency of disease detection compared to traditional methods. They discuss the challenges and limitations faced in the field, such as the need for large-scale and diverse datasets, interpretability of deep learning mod- els, and the integration of sensor-based technologies for data collection. The conclusion also provides recommendations for future research directions, such as the development of transfer learning and ensemble learning techniques, the integration of multi-modal data sources, and the deployment of deep learning models in practical agricultural settings. Overall, the conclusion offers a synthesis of the reviewed literature, identifies the gaps and opportunities, and suggests avenues for further advancements in the field of deep
Department of Electronics and Communication Engineering,AJCE 8
Chapter 2. Literature Survey
learning for plant disease detection and diagnosis.
Advantages
Disadvantages
Authors: Singh, D., Khanna, R., and Singh, P
Introduction The paper focuses on the development of an automated system for the identification of disease spots on plant leaves using image processing techniques. The introduction section of the paper provides an overview of the importance of early disease detection in plants and the challenges associated with manual identification methods. The authors highlight that plant diseases can have a significant impact on agricultural productivity and food security. Early detection of disease spots on plant leaves plays a crucial role in implementing timely intervention strategies to minimize crop losses. However, traditional manual methods of disease identification are often subjective, time- consuming, and labor-intensive.
Department of Electronics and Communication Engineering,AJCE 9
Chapter 2. Literature Survey
undergo preprocessing, which involves techniques like noise removal, image enhancement, and segmentation. These steps aim to improve the quality of the images, remove unwanted artifacts, and isolate the disease spots from the background.Feature extraction is another key component of the proposed system. The authors discuss various feature extraction methods, such as texture analysis and color-based features, which capture the distinctive characteristics of disease spots on plant leaves. These features serve as input for the subsequent classification step.
In the classification stage, the authors employ machine learning algorithms to classify the extracted features into disease or non-disease categories. They mention the use of algorithms like support vector machines (SVM) or decision trees, which are trained on labeled data to accurately identify disease spots. Overall, the proposed system aims to automate the process of disease spot identification on plant leaves by utilizing image processing techniques and machine learning algorithms. It streamlines the identification process, improves accuracy, and enables timely intervention for effective plant disease management.
Conclusion It highlights the effectiveness and potential of the proposed automated image processing approach for disease spot identification on plant leaves. It concludes that the automated approach offers significant advantages over traditional manual methods for disease spot identification. It provides higher accuracy, objective analysis, and time efficiency. By utilizing computer vision techniques and machine learning algorithms, the system can analyze digital images of plant leaves and accurately classify disease spots. The automated approach enables early detection of disease spots, which is crucial for effective disease management. By promptly identifying and categorizing the spots, farmers or researchers can implement timely interventions to prevent the spread of diseases and minimize crop losses. Also discuss the scalability of the proposed system.
It can be easily integrated into existing agricultural systems or deployed as a standalone solution, making it adaptable to different agricultural settings. This scalability enhances its practicality and potential for widespread adoption. However, the authors acknowledge certain limitations of the approach. They highlight the dependency on image quality and
Department of Electronics and Communication Engineering,AJCE 11
Chapter 2. Literature Survey
the need for properly acquired and processed images to ensure accurate identification. The system’s effectiveness may also be limited to specific diseases for which it has been trained, requiring additional training data for broader disease coverage. The automated image processing approach presented in the paper shows great promise for disease spot identification on plant leaves. It offers advantages in terms of accuracy, objectivity, time efficiency, and scalability. While there are limitations to consider, the approach represents a significant advancement in automated disease detection in plants and holds potential for improving agricultural practices and crop management.
The conclusion of the paper ”An Automated Image Processing Approach for Disease Spot Identification on Plant Leaves” by Singh, Khanna, and Singh summarizes the key findings and outcomes of their research. It highlights the effectiveness and potential of the proposed automated image processing approach for disease spot identification on plant leaves. Additionally, here are five advantages and five disadvantages associated with the approach discussed in the paper
Advantages
Disadvantages
Department of Electronics and Communication Engineering,AJCE 12
