Authors

Abstract

Maize eyespot and maize curvularia leaf spot are two diseases that often occur on maize leaves. Because of the similarity of the shape and structure, it is difficult to identify the two diseases just relying on the observation of the growers. For the harmfulness and prevention methods are different, it would cause great loss if the disease can't be identified accurately. To address this issue, this paper first employs a connected region feature recognition method to design an automated lesion cropping process after acquiring leaf images with several lesions. Subsequently, a lesion recognition model based on the AlexNet architecture is built and subjected to five-fold cross-validation experiments. The results indicate that the model achieves a comprehensive recognition accuracy exceeding 99%. To further comprehend model characteristics, an analysis of the recognition accuracy and its fluctuations is conducted, revealing that the fractal growth and biological characteristics of the lesions may influence the recognition results. Moreover, the distribution of model parameters could be a potential reason for fluctuations in recognition accuracy rates with increasing number of iterations. This paper could offer valuable reference and support for the intelligent identification and diagnosis of maize and other plant diseases.

Abstract in Chinese

玉米北方炭疽病和玉米弯孢菌叶斑病是常见于玉米叶片的两种疾病，由于病斑外形结构和形状特征相似，传统的神经网络和图像识别方法较难识别两者，而两者危害程度和防治方法不同，因此误识别会造成较大损失。为此，本文首先基于连通域特征识别实现了对带病叶片图像中病斑的自动裁切。之后，基于AlexNet架构构建了病斑识别模型，并采用五折交叉验证法进行试验。试验结果显示，模型的综合识别准确率超过了99%。为了进一步理解模型特性，本文还对模型的识别准确率及其波动性进行分析，分析结果显示，病斑的分形生长和生物学特性会影响识别结果，模型参数的分布可能是导致识别率随迭代次数增加而波动的潜在原因。本文研究可为玉米及其他植物病害的智能化识别诊断提供有效参考和支持。