Disease Classification in Wheat from Images Using CNN
IEEE BASE PAPER TITLE:
Disease Classification in Wheat from Images Using CNN
(or)
OUR PROPOSED PROJECT TITLE:
Wheat Leaf Disease Detection using Deep Learning
IEEE BASE PAPER ABSTRACT:
Wheat is a staple crop for large sections of the global population. However, like all crops, a major impediment to its yield and expansion is the prevalence of diseases in wheat that cause significant losses to the crop each year. One of the methods that such losses can be prevented is by identifying and responding to the same appropriately and swiftly. Given that a majority of farmers in developing countries cannot afford specialist help for the same, and the fact that manual identification of disease in wheat is a challenging task to begin with, this problem may be aided by using computer vision methods to identify the diseases, after which the farmer needs to only refer to expert sources for solutions. This can greatly reduce the challenge and costs, as well as increase the availability of specialists to deal with the same. It can also be used as an early detection mechanism for the advent of plant epidemics. This review paper aims to perform a comparative analysis of some of the popular deep learning architectures-namely VGG16, MobileNet, ResNet50-for the problem of disease identification and classification in wheat.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
MobileNet Architecture.
OUR PROPOSED PROJECT ABSTRACT:
The rapid advancement of technology has paved the way for innovative solutions to pressing agricultural challenges. In this context, our project, “Wheat Leaf Disease Detection using Deep Learning,” emerges as a novel and impactful contribution to the field of agriculture. Leveraging the power of Python programming and the MobileNet architecture, our system demonstrates remarkable efficiency in automating the detection of various wheat leaf diseases.
Our project operates on a comprehensive dataset comprising 5,597 wheat leaf images, meticulously categorized into five distinct classes: Brown rust, Healthy, Loose Smut, Septoria, and Yellow rust. The dataset is a testament to our commitment to accuracy and diversity, ensuring that the model can accurately identify a wide range of wheat leaf conditions.
The MobileNet architecture, known for its efficiency and speed, serves as the cornerstone of our deep learning model. By harnessing the capabilities of MobileNet, we have optimized the computational resources required for disease detection without compromising on accuracy. This choice of architecture allows for real-time or near-real-time inference, making it a practical solution for on-field applications.
Our model has achieved a remarkable training accuracy of 96.00%, indicating its ability to learn and adapt to the intricate patterns and features present in the dataset. Furthermore, our validation accuracy of 91.00% underlines the robustness of our system in generalizing its knowledge to previously unseen data. This level of accuracy is crucial for early disease detection, enabling farmers to take timely corrective measures and minimize crop losses.
The significance of our project lies in its potential to revolutionize wheat crop management practices. By automating disease detection with a high degree of accuracy, we empower farmers to make informed decisions, reduce pesticide usage, and ensure food security. Furthermore, the scalability and adaptability of our system to other crops and diseases make it a versatile tool for agriculturalists worldwide.
In summary, “Wheat Leaf Disease Detection using Deep Learning” is a pioneering project that marries the power of Python, the efficiency of MobileNet architecture, and a robust dataset to address a critical agricultural challenge. With impressive training and validation accuracies, this project offers a promising solution for early disease detection in wheat crops, ushering in a new era of precision agriculture.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 / 11.
- Coding Language : Python 3.10.9.
- Web Framework : FLASK.
- Frontend : HTML, CSS, JavaScript.
REFERENCE:
Dhruv Suri; Shivie Saksenaa; Umang Sehgal; Rakesh Garg, “Disease Classification in Wheat from Images Using CNN”, 2023 13th International Conference on Cloud Computing, Data Science & Engineering (Confluence), IEEE Conference, 2023.