Rice Leaf Disease Classification (CNN)
CNN image classification of rice leaf diseases with a custom model plus AlexNet, VGG19, and DenseNet — deployed on Flask.
Architecture
Image classification pipeline: from a small Kaggle dataset through CNN training and model comparison to a Flask web app.
Frameworks
Overview
An image classification project that identifies three rice leaf diseases — leaf smut, brown spot, and bacterial leaf blight — from a Kaggle dataset of 40 images per class.
I trained a custom CNN and compared it against pretrained AlexNet, VGG19, and DenseNet architectures, then deployed the best model with a Flask web app.
Highlights
- Custom CNN vs. pretrained AlexNet, VGG19, DenseNet
- 3-class disease classification from a small dataset
- Deployed as a Flask web app
Context
College project
Tech stack
More projects
View all →JKII Stock Price Prediction
Jakarta Islamic Index price forecasting with LSTM, XGBoost, SVR and more — evaluated on 5 metrics, deployed on Streamlit.
SMILE Platform (UNDP for Kemenkes)
National immunization logistics system in production across all of Indonesia — streaming CDC + batch analytics platform.
LidValid — Unified Data Validation Platform
Full-stack data validation platform with Tiered Validation — cheap aggregate checks across every table, then precise row-level checks only where they fail.