Merge c501cabe34 into 08b771c863

Projects/3-Advanced/Leaf-disease-detection

@@ -0,0 +1,3 @@
+Our project aims to detect whether a given plant leaf image is healthy or diseased. This is a binary classification task, where the output is either 0 (healthy) or 1 (diseased). A Convolutional Neural Network (CNN) model is used to classify the images. The system is written in Python and uses deep learning capabilities for image classification tasks. The dataset used for this project consists of images of plant leaves. The Dataset is collected from the open-source site “Plant Village” and it consists of around 61,486 images of healthy and unhealthy plants divided into 39 different classes. With the help of a Python code, we have converted 39 classes into 2 classes which consist of all healthy and unhealthy plant leaf images. Then the dataset is pre-processed by resizing the images to a uniform size (256x256) and normalizing the pixel values between 0 and 1. Images used for a whole range of training and testing were done using the ratio of 90-10(90% of the whole dataset used for the training and 10% for the testing).Our proposed system is an effective solution for detecting leaf diseases in crops using deep learning. The model developed in this project can be used as a foundation for future research and development in the field of leaf disease detection. Model Architecture: The CNN model used for this project consists of several layers. The first layer is a 2D convolutional layer with 32 filters and a kernel size of (3,3). This is followed by a max pooling layer with a pool size of (2,2) and a dropout layer with a rate of 0.25. The same sequence of convolutional, max pooling and dropout layers is repeated twice, with the number of filters increasing to 64 and 128 in the second and third convolutional layers respectively. The output from the convolutional layers is flattened and passed through two dense layers with 512 and 256 neurons respectively. Each dense layer is followed by a dropout layer with a rate of 0.5. The final layer is a dense layer with a single neuron and a sigmoid activation function, which gives the binary classification output.
+
+Sample Project link: https://github.com/nandaydas/Leaf-Disease-Detection-using-CNN-Model-with-Binary-Classification