HiT-LIDIA: A Framework for Rice Leaf Disease Classification using Ensemble and Hierarchical Transfer Learning

Abstract

Rice is one of the global most critical harvests, and a great many people eat it as a staple eating routine. Different rice plant diseases harm, spread, and drastically reduce crop yields. In extreme situations, they may result in no grain harvest at all, posing a severe threat to food security. In this paper, to amplify the recognition ability for rice leaf disease (RLD) classification, we proposed hierarchical transfer learning (HTL) methods incorporating ensemble models containing two-step. In the first step, an ensemble combining MobileNet and DenseNet was addressed to tackle the diseased leaf problem. Consequently, DenseNet and XceptionNet were fused to identify three RLDs. Here, we compare our models with state-of-the-art deep learning models such as ResNet, DenseNet, InceptionNet, Xception, MobileNet, and EfficientNet. Our framework at top-notch with 89 % and 91 % for accuracy. In future works, RLD segmentation is suggested to pinpoint the illness and quantify the afflicted region.

Comparative Analysis of Transfer Learning, LeafNet, and Modified LeafNet Models for Accurate Rice Leaf Diseases Classification

“…The authors of [32] used the WS-DAN algorithm and reported a testing accuracy of 87.60% for all classes. The authors of [33] used the HTL algorithm and reported a validation accuracy of 91% for three classes: brown spot, hispa, and leaf blast. The authors of [34] used a Lightweight CNN model and reported a testing accuracy of 73.02% for all classes.…”

“…They utilized a weakly supervised data augmentation network (WS-DAN) and obtained a testing accuracy of 87.60%. Putra et al [33] proposed a novel methodology known as Hierarchical Transfer Learning (HTL), wherein they utilized pretrained models such as DenseNet, XceptionNet, and MobileNet for feature extraction. Subsequently, the models were assembled and fused.…”

Transfer Learning untuk Klasifikasi Penyakit dan Hama Padi Menggunakan MobileNetV2

“…Jamur, bakteri, virus dan hama adalah organisme yang dapat mengakibatkan penyakit pada tanaman padi [5]. Penyakit dan hama pada tanaman padi dapat mengganggu pertumbuhan tanaman padi, karna penyakit dan hama tersebut dapat mengganggu proses fotosintesis pada tanaman dan menimbulkan perubahan pada bentuk dan warna [6] pada tanaman padi yang diserang. Secara tradisional deteksi penyakit padi dilakukan dengan memberikan sampel tanaman yang terkena penyakit kepada tenaga ahli, dari sampel tersebut tenaga ahli akan mengidentifikasi penyakit tersebut, hal ini tentu akan memakan banyak waktu jika terimplementasikan pada pertanian besar [7].…”