Plant disease detection using AI
Plant diseases cause great damage in agriculture, resulting in significant yield losses. The recent expansion of deep learning methods has found its application in plant disease detection, offering a robust tool with highly accurate results. Convolutional neural network models were developed to perf
2025-06-28 16:28:47 - Adil Khan
Plant disease detection using AI
Project Area of Specialization Artificial IntelligenceProject SummaryPlant diseases cause great damage in agriculture, resulting in significant yield losses. The recent expansion of deep learning methods has found its application in plant disease detection, offering a robust tool with highly accurate results. Convolutional neural network models were developed to perform plant disease detection and diagnosis using simple leaf images of healthy and diseased plants, through deep learning methodologies. Training of the models was performed with the use of an open database, containing 5 different plants in a set of 24 distinct classes of plant disease combinations, including healthy plants. Two approaches were used to augment the number of images in the dataset: traditional augmentation methods and state-of-the-art style generative adversarial networks. Several model architectures were trained, with the best performance reaching a 95.34% success rate in identifying the corresponding plant disease combination (or healthy plant). The significantly high success rate makes the model a very useful advisory or early warning tool, and an approach that could be further expanded to support an integrated plant disease identification system to operate in real cultivation conditions. Fast and accurate models for plant disease identification are desired so that accurate measures can be applied early. Thus, alleviating the problem of food security.
In the former case in particular, except for the fact that a farmer at a remote location could have an incipient warning about a possible threat to his/her cultivation, and an agronomist could have a valuable advisory tool at his/her disposal, a future possibility could be the development of an automated pesticide prescription system that would require a confirmation by the automated disease diagnosis system to allow the purchase of appropriate pesticides by the farmers. That would drastically limit the uncontrolled acquisition of pesticides that leads to their overuse and misuse, with the consequent catastrophic effects on the environment.
The main benefit of this app is that with very less computational efforts the optimum results were obtained, which also shows the efficiency of the proposed algorithm in the recognition and classification of the leaf diseases. Another benefit of using this method is that the plant diseases can be identified properly at the early stage or the initial stage.
Project Objectives- To reduce the economic and aesthetic damage caused by plant diseases.
- To capture an image of a plant in real-time or to use the mobile storage in which the images are stored that should processed to analyses.
- To identify the plant and analysis the disease.
- To determine the health status of the plant.
- To recommend the precautions and pesticides for the disease.
A recent boom in deep learning (DL) methods has also expanded in the agriculture area. Progression in computer vision and artificial intelligence can lead to new solutions. These methods provide more accurate predictions than traditional methods, which enable better decision-making. Owing to advances in hardware technology, DL methods are now used for solving complex problems in a reasonably short amount of time. The results of the research in this field are not trivial. DL is already a state-of-the-art technique for land cover classification tasks, and could also prove useful for many other tasks. Various types of deep neural networks (DNNs) have achieved remarkable results in the hyperspectral analysis [1]. Convolutional neural networks (CNNs) have performed well in plant disease detection and diagnosis tasks. AlexNet and GoogLeNet architectures have shown state-of-the-art performance in these experiments[3].
Deep learning is currently a very active research field in computer vision and image classification. A typical Deep CNN consists of an input and an output or classification layer, as well as multiple hidden layers. The hidden layers of a CNN typically consist of convolutional layers, pooling layers, fully connected layers, and in some cases Softmax layer. Most CNN architectures follow the design pattern of LeCun et al., Lenet-5 architecture (LeCun et al., 1998).[5] The architectures evaluated include VGG 19 and ResNet 152 layers. Fast and accurate models for plant disease identification are desired so that accurate measures can be applied early.
VGG19:One of our approaches is that by using the Tensorflow and Keras API, we can use VGG-19 architecture. The model attained a 7.5% top-5 error rate on the validation set which is an outcome that secured them a second place in the competition. Typically, the model is symbolized by its modesty as depicted in Simonyan and Zisserman (2015), with only 3×3 convolutional layers stacked on top of each other in increasing depth. Max pooling handles reduce the size of the volume (downsampling). Additionally, two fully-connected layers each with 4096 nodes and a softmax classifier.[5] The VGG models are no longer state-of-the-art by only a few percentage points. Nevertheless, they are very powerful models and useful both as image classifiers and as the basis for new models that use image inputs. The VGG model can be loaded and used in the Keras deep learning library. Keras provides an application interface for loading and using pre-trained models. Using this interface, we can create a VGG model using the pre-trained model and use it as a starting point in your own model, or use it as a model directly for classifying images.
Benefits of the Project- To reduce the economic and aesthetic damage caused by plant diseases.
- To design a user-friendly app that captures an image of a plant in real-time or to use the mobile storage in which the images are stored that should process for analyses.
- To identify the plant name and diagnose the disease.
- To determine the health status of the plant.
- To recommend the precautions and pesticides in case of any disease.
To design a user-friendly web app that uses an image of a plant in real-time or to use the mobile storage in which the images are stored that should process for analyses and classify the disease and also give that disease precaution to farmers.
Final Deliverable of the Project Software SystemCore Industry AgricultureOther Industries Medical , Food , Health Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for People, Industry, Innovation and Infrastructure, Climate ActionRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 12796 | |||
| web hosting | Equipment | 1 | 5000 | 5000 |
| cloud GPU | Equipment | 1 | 3000 | 3000 |
| mid report printing | Miscellaneous | 1 | 899 | 899 |
| mid log file printing | Miscellaneous | 3 | 299 | 897 |
| final report printing | Miscellaneous | 1 | 1000 | 1000 |
| final log file printing | Miscellaneous | 1 | 1000 | 1000 |
| Some stationary | Miscellaneous | 1 | 1000 | 1000 |