He Yun, Zhang Guangchuan, Gao Quan
School of Big Data, Yunnan Agricultural University, Kunming, China.
Key Laboratory for Crop Production and Intelligent Agriculture of Yunnan Province, Yunnan Agricultural University, Kunming, China.
Front Plant Sci. 2024 Jan 8;14:1280671. doi: 10.3389/fpls.2023.1280671. eCollection 2023.
Deep learning models have been widely applied in the field of crop disease recognition. There are various types of crops and diseases, each potentially possessing distinct and effective features. This brings a great challenge to the generalization performance of recognition models and makes it very difficult to build a unified model capable of achieving optimal recognition performance on all kinds of crops and diseases. In order to solve this problem, we have proposed a novel ensemble learning method for crop leaf disease recognition (named ELCDR). Unlike the traditional voting strategy of ensemble learning, ELCDR assigns different weights to the models based on their feature extraction performance during ensemble learning. In ELCDR, the models' feature extraction performance is measured by the distribution of the feature vectors of the training set. If a model could distinguish more feature differences between different categories, then it receives a higher weight during ensemble learning. We conducted experiments on the disease images of four kinds of crops. The experimental results show that in comparison to the optimal single model recognition method, ELCDR improves by as much as 1.5 (apple), 0.88 (corn), 2.25 (grape), and 1.5 (rice) percentage points in accuracy. Compared with the voting strategy of ensemble learning, ELCDR improves by as much as 1.75 (apple), 1.25 (corn), 0.75 (grape), and 7 (rice) percentage points in accuracy in each case. Additionally, ELCDR also has improvements on precision, recall, and F1 measure metrics. These experiments provide evidence of the effectiveness of ELCDR in the realm of crop leaf disease recognition.
深度学习模型已在作物病害识别领域得到广泛应用。作物和病害种类繁多，每种都可能具有独特且有效的特征。这给识别模型的泛化性能带来了巨大挑战，使得构建一个能在各类作物和病害上都实现最优识别性能的统一模型变得非常困难。为了解决这个问题，我们提出了一种用于作物叶片病害识别的新型集成学习方法（名为ELCDR）。与传统的集成学习投票策略不同，ELCDR在集成学习过程中根据模型的特征提取性能为其分配不同的权重。在ELCDR中，通过训练集特征向量的分布来衡量模型的特征提取性能。如果一个模型能够区分不同类别之间更多的特征差异，那么它在集成学习过程中会获得更高的权重。我们对四种作物的病害图像进行了实验。实验结果表明，与最优的单一模型识别方法相比，ELCDR在准确率上分别提高了1.5（苹果）、0.88（玉米）、2.25（葡萄）和1.5（水稻）个百分点。与集成学习的投票策略相比，ELCDR在每种情况下的准确率分别提高了1.75（苹果）、1.25（玉米）、0.75（葡萄）和7（水稻）个百分点。此外，ELCDR在精确率、召回率和F1值指标上也有提升。这些实验证明了ELCDR在作物叶片病害识别领域的有效性。
