Projects / Computer Science / Computer Science project 3

Plant Leaf Disease Detection App Using a CNN

Approx. component budget: Rs. 0 - 2,000

Objective

Train a convolutional neural network with transfer learning on a public leaf dataset and test how well it works on photos taken with a phone.

What you will build

A web or mobile-friendly app where a farmer uploads a leaf photo and gets the likely disease name, a confidence value and a basic care tip.

Results you can expect

• Validation accuracy and per-class F1
• Confusion matrix
• A comparison of a small CNN vs MobileNet
• Accuracy on 50 real phone photos
• And inference time per image

What you will learn

Image augmentation, transfer learning, the gap between lab images and field images, and model size vs speed.

Tools and notes

Python, TensorFlow/Keras or PyTorch, PlantVillage dataset, free notebook GPU, Streamlit. Mention that results need expert confirmation before any treatment.

Resume points from this project

• Built and tested Plant Leaf Disease Detection App Using a CNN; objective: train a convolutional neural network with transfer learning on a public leaf dataset and test how well it works on photos taken with a phone.
• Measured and analysed validation accuracy and per-class F1 and confusion matrix; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects