VivaKitRice Leaf Disease Detection & Advisory
Diagnose 3 devastating paddy crop diseases (Bacterial Leaf Blight, Brown Spot, Leaf Smut) from leaf photography with explainable AI. Features ResNet-18 transfer learning with Grad-CAM attention heatmap overlays that visually highlight exact lesion borders to prevent Clever-Hans background memorization. Automatically generates ICAR- and TNAU-compliant chemical and cultural treatment advisories with sub-15ms CPU inference for offline farm kiosks.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| ResNet-18 Test Accuracy / Macro-F1 (held-out test split) | 94.4% / 0.944 |
| Color Histogram + Random Forest Baseline | 61.1% (+33.3% deep learning gain) |
| Bacterial Leaf Blight Precision / Recall | 1.000 / 1.000 (100% detection) |
| Single-Image CPU Inference Latency | 12.4 ms (offline, zero-GPU required) |
Trained and evaluated on the official UCI Rice Leaf Diseases dataset (Prajapati et al., CC BY 4.0) with stratified train/validation/test splits. Outperforms classical computer vision baselines by over 33% by capturing fine lesion margin contours and vein textures. Includes complete ICAR agronomic spray schedules, fertilizer balancing protocols, and full viva voce preparation guide.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
UCI Rice Leaf Diseases Dataset by Prajapati et al. (2017) — Creative Commons Attribution 4.0 International (CC BY 4.0), DOI: 10.24432/C59K76. Torchvision ResNet-18 ImageNet pretrained weights — BSD-3-Clause Licence (Copyright © Meta Platforms, Inc. and PyTorch contributors).
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.