Crop diseases are a major threat to food security, but their rapid identification remains difficult in many parts of the world due to the lack of the necessary infrastructure. The combination of increasing global smartphone penetration and recent advances in computer vision and deep learning has paved the way for smartphone-assisted disease diagnosis. The trained model which we are developing here works on a test set using a public dataset of various images of diseased and healthy plant leaves collected under controlled conditions, demonstrating the feasibility of this approach.
Deep neural networks have recently been successfully applied in many diverse domains as examples of end to end learning. Neural networks provide a mapping between an input—such as an image of a diseased plant—to an output—such as a crop~disease pair. The nodes in a neural network are mathematical functions that take numerical inputs from the incoming edges, and provide a numerical output as an outgoing edge. Deep neural networks are simply mapping the input layer to the output layer over a series of stacked layers of nodes.
A Sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.
We decided to use a deep learning model with neural networks to train the AI with thousands of images from a dataset. There are 4 main steps involved in this process:
- Image augmentation
- Image acquisition
- Image pre-processing
- Classification
- Python
- TensorFlow
- Streamlit
- Numpy
- Keras
(https://www.kaggle.com/competitions/plant-pathology-2020-fgvc7/overview)
(https://docs.google.com/presentation/d/1ha0oWEk9F32dldHa0lDRyvztk8VweeoYAEsh1s7hB60/edit?usp=sharing)