Performance Evaluation of Capsule Networks for Classification of Plant Leaf Diseases

Abstract

Deep Learning (DL) is a high capable machine learning algorithm which composed the advanced image processing as feature learning and supervised learning with detailed models with many hidden layers and neurons. DL demonstrated its efficiency and robustness in many big data problems, computer vision, and more. Whereas it has an increasing popularity day by day, it has still some deficiencies to construe the relationship between learned feature maps and spatial information. Capsule network (CapsNET) is proposed to overcome the shortcoming by excluding the pooling layer from the architecture and transferring spatial information between layers by capsule. In this paper, CapsNET architecture was proposed to evaluate the performance of the model on classification of plant leaf diseases using simple reduced capsules on leaf images. Plant leaf diseases are common and prevalent diseases that disrupt harvesting and yielding for agriculture. CapsNET has capability of detailed analysis for even small stains that may lead seed dressing time and duration. The proposed CapsNET model aimed at assessing the applicability of various feature learning models and enhancing the learning capacity of the DL models for bell pepper plants. The healthy and diseased leaf images were fed into the CapsNET. The proposed CapsNET model reached high classification performance rates of 95.76%, 96.37%, and 97.49% for accuracy, sensitivity, and specificity, respectively.

Plant phenotyping relevance

植物葉画像から病害状態を分類するCapsNETモデルを提案・評価しており、病徴の画像ベース推定が研究の中心である。

Code and data availability

The paper uses the public PlantVillage dataset (bell pepper subset) for CapsNet leaf disease classification, but PlantVillage is a cited third-party resource, not a paper-specific asset. No author code, trained models, or data availability statements appear in the supplied blocks, and no allowed URLs are provided.

No evidence-backed public reproduction asset is currently recorded.