A Resource-Efficient Hybrid CNN-LSTM network for image-based bean leaf disease classification

arXiv cs.CV / 4/16/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces a lightweight hybrid CNN–LSTM architecture for bean leaf disease image classification aimed at improving diagnostic accuracy while reducing memory requirements for deployment on portable devices.
It reports 94.38% classification accuracy with a very small model footprint of 1.86 MB, representing about a 70% size reduction versus conventional CNN-based systems.
The authors evaluate image augmentation strategies and find that tailored augmentation transformations better preserve diagnostic patterns than generic augmentation combinations.
Experiments on the iBean dataset show state-of-the-art performance, including an F1 score of 99.22% with an EfficientNet-B7+LSTM variant, supporting real-time agricultural decision support in resource-constrained settings.
The study provides publicly available code and augmented datasets via a GitHub repository to facilitate reuse and further research.

Abstract

Accurate and resource-efficient automated diagnosis is a cornerstone of modern agricultural expert systems. While Convolutional Neural Networks (CNNs) have established benchmarks in plant pathology, their ability to capture long-range spatial dependencies is often limited by standard pooling layers, and their high memory footprint hinders deployment on portable devices. This paper proposes a lightweight hybrid CNN-LSTM system for bean leaf disease classification. By integrating an LSTM layer to model the spatial-sequential relationships within feature maps, our hybrid architecture achieves a 94.38% accuracy while maintaining an exceptionally small footprint of 1.86 MB; a 70% reduction in size compared to traditional CNN-based systems. Furthermore, we provide a systematic evaluation of image augmentation strategies, demonstrating that tailored transformations are superior to generic combinations for maintaining the integrity of diagnostic patterns. Results on the

\textit{ibean}

dataset confirm that the proposed system achieves state-of-the-art F1 scores of 99.22% with EfficientNet-B7+LSTM, providing a robust and scalable framework for real-time agricultural decision support in resource-constrained environments. The code and augmented datasets used in this study are publicly available on this