A Weighted Ensemble of Convolutional Neural Networks for Anthracnose Detection in Avocado Fruit

Abstract

Global avocado production exceeds 10 million tons annually. Among the diseases affecting avocado fruit, anthracnose is one of the most significant, causing black lesions and fruit decay that can result in yield losses of 20–30%. To facilitate the early detection of anthracnose, this study proposes a computer vision-based approach. A dataset containing 2218 images of Fuerte avocados was first developed, comprising 1730 healthy samples and 488 anthracnose-infected samples after the labeling process. In the experimental phase, several convolutional neural network (CNN) models with varying depths (3, 4, 5, and 6 layers) were designed and evaluated. These models were subsequently integrated into different weighted ensemble configurations, where the best performance was achieved by the ensemble combining all four individual CNNs. The proposed weighted ensemble was compared against widely used state-of-the-art architectures, including VGG-16, ResNet-18, and MobileNetV2. Experimental results demonstrated the effectiveness of the proposed approach, achieving an F1-score of 0.9052, outperforming VGG-16 (0.8283), ResNet-18 (0.7328), and MobileNetV2 (0.7320).

Plant phenotyping relevance

アボカド果実の病徴（炭疽病病変）を画像から検出するコンピュータビジョン手法を開発・比較検証しており、植物状態の取得が研究の中心である。

Code and data availability

The paper's core asset is a newly developed dataset of 2218 Fuerte avocado images (healthy vs. anthracnose) used for CNN-based anthracnose detection, plus the authors' CNN/ensemble models. However, the Data Availability Statement says the data can only be requested from the corresponding author; no public repository,代码

No evidence-backed public reproduction asset is currently recorded.