发表机构
Efrei Research Lab, Paris Panthéon-Assas University; Institute of Applied Computer Science, Lodz University of Technology（巴黎先贤祠-阿萨斯大学埃弗雷研究所; 罗兹理工大学应用计算机科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对高光谱图像水果成熟度预测的挑战，提出Fruit-HSNet架构，经DeepHS Fruit数据集评估，其准确率达70.73%，较现有方法提升12%，性能最优。
AI 中文摘要
水果成熟度预测（FRP）是一项基于分类的农业计算机视觉任务，因其在农业领域的产前与产后管理中具有广泛优势而备受关注。基于机器学习/深度学习的高光谱图像分类技术可实现准确且及时的FRP，但存在标注数据有限、缺乏可推广至各类高光谱相机及水果类型的鲁棒方法等挑战，会影响基于高光谱图像的FRP的有效性。针对这些挑战，本文提出Fruit-HSNet，这是一种专为水果成熟度高光谱分类设计的机器学习架构，其包含基于傅里叶变换和中心像素光谱特征的空谱特征提取模块，后续接可学习特征融合模块及针对成熟度分类优化的分类器。该架构使用DeepHS Fruit数据集进行评估，该数据集是目前最大的公开可用标注真实世界高光谱水果成熟度预测数据集，包含鳄梨、猕猴桃、芒果、柿子、番木瓜5种不同水果，由3种不同高光谱相机在不同成熟阶段采集。实验结果表明，Fruit-HSNet显著优于从基线到最先进水平的现有深度学习方法，提升幅度达12%，取得了70.73%的整体准确率，达到新的最先进水平。
英文摘要
Fruit ripeness prediction (FRP) is a classification-based agricultural computer vision task that has attracted much attention, thanks to its wide-ranging advantages in agriculture field for both pre-harvest and post-harvest management. Accurate and timely FRP can be achieved using machine/deep learning-based hyperspectral image classification techniques. However, challenges including the limited availability of labeled data and the lack of robust methods generalizable to various hyperspectral cameras and fruit types can compromise the effectiveness of hyperspectral image-based FRP. Addressing these challenges, this paper introduces Fruit-HSNet, a machine learning architecture specifically designed for hyperspectral classification of fruit ripeness. Fruit-HSNet incorporates a spatio-spectral feature extraction module based on Fourier Transform and central pixel spectral signature followed by learnable feature fusion and a classifier optimized for ripeness classification. The proposed architecture was evaluated using the DeepHS Fruit dataset, the largest publicly available labeled real-world hyperspectral dataset for predicting fruit ripeness, which includes five different types of fruits-avocado, kiwi, mango, kaki, and papaya-captured with three distinct hyperspectral cameras at various stages of ripeness. Experimental results highlight that Fruit-HSNet substantially outperforms existing deep learning methods, from baseline to state-of-the-art models, with improvements of 12%, achieving a new state-of-the-art overall accuracy of 70.73%.
Journal refProceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025), Vol. 2, SciTePress, 2025, pp. 102-111
