ABSTRACT
Agriculture plays an important role in the economic growth of every country and so it is necessary to ensure its development. The spread of various diseases in paddy plants has increased in recent years. There is a variety of plant pathogens such as viral, bacterial, fungal and these can damage different plant parts above and below the ground. However, some abiotic factors such as water, light, radiation, temperature, humidity, atmosphere, acidity, and soil also affect the growth of the plant. Crop diseases are creating problems for farmers due to low output and economic losses and industrial agriculture. So, it is need of the hour to detect such diseases as earliest as possible. A large number of crops are grown in India which often serve as hosts to different kinds of insect pests and pathogens. Most of the Indian regions being subtropical to tropical, the agro-climate is more conducive for the development of insect pests than disease causing pathogens. Prevention and early diagnosis are critical to limiting damage by plant pathogens. The producers need to monitor their crops and detect the first symptoms in order to prevent the spread of a plant disease, with low cost and save the major part of the production. Detection of leaf diseases falls important for these reasons. Identifying diseases through naked eye is often prone to high error rates and faulty classification. This project proposes a method that solves this issue and helps in identifying and classifying the leaf diseases by applying various image processing and convolutional neural network algorithms. Due to this complexity, even the experienced agronomists and plant pathologists are often unsuccessful to diagnose the plant diseases accurately. The use of an automated system which can detect and diagnose the plant diseases can exponentially help the agronomists keep an eye on the plants and ensure good health of the plants. This project is developed in matlab.
PROJECT OUTPUT
PROJECT DEMO VIDEO
.png)
