Leveraging Pre-trained CNNs for Efficient Feature Extraction in Rice Leaf Disease Classification

TL;DR

This study demonstrates that integrating Histogram of Oriented Gradients (HOG) feature extraction with pre-trained CNNs, especially EfficientNet-B7, significantly improves rice leaf disease classification accuracy to 97%, enhancing focus on disease-specific features.

Contribution

The paper introduces the effective combination of HOG feature extraction with pre-trained CNNs, notably EfficientNet-B7, to substantially boost disease classification accuracy in rice leaves.

Findings

HOG integration increased EfficientNet-B7 accuracy from 92% to 97%.

Grad-CAM visualizations showed improved focus on disease regions.

Baseline models achieved over 91% accuracy without feature extraction.

Abstract

Rice disease classification is a critical task in agricultural research, and in this study, we rigorously evaluate the impact of integrating feature extraction methodologies within pre-trained convolutional neural networks (CNNs). Initial investigations into baseline models, devoid of feature extraction, revealed commendable performance with ResNet-50 and ResNet-101 achieving accuracies of 91% and 92%, respectively. Subsequent integration of Histogram of Oriented Gradients (HOG) yielded substantial improvements across architectures, notably propelling the accuracy of EfficientNet-B7 from 92\% to an impressive 97%. Conversely, the application of Local Binary Patterns (LBP) demonstrated more conservative performance enhancements. Moreover, employing Gradient-weighted Class Activation Mapping (Grad-CAM) unveiled that HOG integration resulted in heightened attention to disease-specific features, corroborating the performance enhancements observed. Visual representations further validated HOG's notable influence, showcasing a discernible surge in accuracy across epochs due to focused attention on disease-affected regions. These results underscore the pivotal role of feature extraction, particularly HOG, in refining representations and bolstering classification accuracy. The study's significant highlight was the achievement of 97% accuracy with EfficientNet-B7 employing HOG and Grad-CAM, a noteworthy advancement in optimizing pre-trained CNN-based rice disease identification systems. The findings advocate for the strategic integration of advanced feature extraction techniques with cutting-edge pre-trained CNN architectures, presenting a promising avenue for substantially augmenting the precision and effectiveness of image-based disease classification systems in agricultural contexts.