Disease Detection In Chilli Plants By Using Deep Learning
M.Sreenandan Reddy, Jinkala Pranathi, Dudekula Ruksana Begum, Venkannagari Haritha, Singanamal Sohail Khan, Y.Sree Sai Govardhan Yadav
To detect diseases in chili plants using deep learning, we first need a large set of images that include
both healthy plants and those affected by various diseases, such as Anthracnose or Bacterial Wilt. These
images must be carefully labelled so the model can learn to differentiate between healthy and diseased
plants. Once we have the images, we need to prepare them for training the deep learning model. This
preparation includes resizing the images to a standard size, normalizing the pixel values for consistency,
and augmenting the data by applying transformations like rotating or flipping the images. These steps
help the model recognize plants in various conditions and increase the amount of data available for
training. The core of the system relies on Convolutional Neural Networks (CNNs), which are specialized
for analyzing images. To improve performance, we can use a technique called transfer learning, where
we take a model that has already been trained on large datasets (like those used for general image
recognition) and fine-tune it with our specific chili plant data. This approach allows the model to learn
to detect plant diseases more effectively, even if the dataset is small. After training, the model can
automatically classify images of chili plants as healthy or diseased, providing farmers with a fast and
accurate tool for early disease detection.
