AgriMind: An Ensemble Deep Learning Framework for Multi-Class Plant Disease Classification
For agricultural extension in Bangladesh, this provides a high-accuracy automated disease detection method, though it is an incremental application of existing ensemble techniques to a standard dataset.
AgriMind, an ensemble of ResNet50, EfficientNet-B0, and DenseNet121, achieves 99.23% accuracy on PlantVillage plant disease classification, reducing error rate by two-thirds compared to individual models (96-97%).
Plant disease detection is still largely manual in Bangladesh, where extension workers eyeball leaf samples across millions of smallholdings. We built AgriMind to automate this: an ensemble of ResNet50, EfficientNet-B0, and DenseNet121 trained on 20,638 PlantVillage images across 15 pepper, potato, and tomato disease classes. Transfer learning with frozen ImageNet backbones and 10 epochs of head-only training keeps the pipeline lightweight. Individual models hit 96--97% on the held-out test set, but averaging their softmax outputs pushes the ensemble to 99.23% -- a two-thirds cut in error rate. We tried biasing the average toward the best validation model; it backfired. Dropping any single model also hurt. Pepper and potato classify perfectly; tomato, with ten visually similar classes, still reaches 99.01%. On an NVIDIA T4 GPU the full ensemble runs at 53 FPS. Whether that translates to real-time mobile use depends on TensorFlow Lite optimization -- work we have not yet completed.