[论文解读] SWP-Leaf NET: a novel multistage approach for plant leaf identification based on deep learning.

Ali Beikmohammadi, Karim Faez+1 more|arXiv (Cornell University)|Sep 10, 2020

Smart Agriculture and AI参考文献 38被引用 7

一句话总结

该论文提出SWP-Leaf NET，一种新颖的多阶段深度学习框架，用于植物叶片识别，通过三种专用模型模拟植物学家的行为，其中两个为定制设计，一个为微调的MobileNetV2，无需手工特征提取，在Flavia和MalayaKew数据集上分别实现了99.67%和99.81%的准确率，且在速度和可分发性方面有所提升。

ABSTRACT

Modern scientific and technological advances are allowing botanists to use computer vision-based approaches for plant identification tasks. These approaches have their own challenges. Leaf classification is a computer-vision task performed for the automated identification of plant species, a serious challenge due to variations in leaf morphology, including its size, texture, shape, and venation. Researchers have recently become more inclined toward deep learning-based methods rather than conventional feature-based methods due to the popularity and successful implementation of deep learning methods in image analysis, object recognition, and speech recognition. In this paper, a botanist's behavior was modeled in leaf identification by proposing a highly-efficient method of maximum behavioral resemblance developed through three deep learning-based models. Different layers of the three models were visualized to ensure that the botanist's behavior was modeled accurately. The first and second models were designed from scratch.Regarding the third model, the pre-trained architecture MobileNetV2 was employed along with the transfer-learning technique. The proposed method was evaluated on two well-known datasets: Flavia and MalayaKew. According to a comparative analysis, the suggested approach was more accurate than hand-crafted feature extraction methods and other deep learning techniques in terms of 99.67% and 99.81% accuracy. Unlike conventional techniques that have their own specific complexities and depend on datasets, the proposed method required no hand-crafted feature extraction, and also increased accuracy and distributability as compared with other deep learning techniques. It was further considerably faster than other methods because it used shallower networks with fewer parameters and did not use all three models recurrently.

研究动机与目标

• 为解决植物物种间叶片形态的高变异性（如大小、形状、纹理和叶脉）带来的挑战。
• 开发一种方法，利用深度学习模拟植物学家在叶片识别中的决策过程。
• 消除对手工、手工设计特征提取的依赖，后者耗时且依赖数据集。
• 与传统及现有深度学习方法相比，提升准确率、速度和模型可分发性。

提出的方法

• 从零开始设计两个定制深度学习模型，以捕捉分层的叶片特征，模拟植物学家逐步分析的过程。
• 在第三个模型中采用预训练的MobileNetV2架构进行迁移学习，以减少训练复杂度，提升特征表示能力。
• 通过可视化所有三个模型不同层的特征图，验证模型在叶片分类中实现了类人视觉推理。
• 将三个模型集成到多阶段流水线中，每个阶段逐步优化分类结果，通过避免重复使用全部模型来提升效率。
• 通过使用参数更少的浅层网络优化架构，提升推理速度，增强实时应用能力。
• 在两个基准数据集（Flavia和MalayaKew）上训练并评估该框架，确保模型的鲁棒性和泛化能力。

实验结果

研究问题

• RQ1 多阶段深度学习框架能否有效模拟植物学家在植物叶片识别中的决策行为？
• RQ2 与手工特征提取及其他深度学习技术相比，该方法在准确率和效率方面表现如何？
• RQ3 使用MobileNetV2进行迁移学习在降低模型复杂度的同时，能在多大程度上提升性能？
• RQ4 一种无需手工特征的框架能否在多样化的数据集上实现更高的准确率和更好的可分发性？

主要发现

• 所提出的SWP-Leaf NET在Flavia数据集上达到99.67%的准确率，优于传统及基于深度学习的方法。
• 在MalayaKew数据集上，该方法达到99.81%的准确率，展示了在复杂叶片分类任务中的卓越性能。
• 该框架消除了对手工特征提取的依赖，降低了对数据集特定预处理的依赖，提升了泛化能力。
• 通过使用浅层网络和选择性模型使用策略，该方法相比其他深度学习方法实现了显著更快的推理速度。
• 视觉特征图分析表明，模型在不同层次上学习到了分层的、类植物学家的表征。
• 迁移学习与MobileNetV2的结合显著提升了性能，同时减少了参数数量和计算成本。