基于高光谱成像的非控制农场环境下黑莓果实成熟度检测的卷积神经网络集成学习
Convolutional Neural Network Ensemble Learning for Hyperspectral Imaging-based Blackberry Fruit Ripeness Detection in Uncontrolled Farm Environment
AI总结：
本文提出一种基于VGG16的多输入CNN集成分类器，结合VIS-NIR光谱滤波图像，有效解决了黑莓成熟度难以通过肉眼识别的问题，在未见数据集和田间条件下分别达到95.1%和90.2%的准确率。
摘要：
几十年来，果实成熟度估计模型一直依赖于光谱指数特征或基于颜色的特征，如均值、标准差、偏度、颜色矩和/或直方图来学习果实成熟度特征。最近，少数研究探索了使用深度学习技术从具有可见成熟度线索的果实图像中提取特征。然而，黑莓果实成熟时并未表现出明显且可靠的可见成熟度特征，因此给果实采摘者带来了极大困难。在人眼看来，成熟的黑莓在成熟前、成熟中和成熟后都是黑色的。为了应对这一工程应用挑战，本文提出了一种新颖的多输入卷积神经网络（CNN）集成分类器，用于检测黑莓果实中细微的成熟度特征。该多输入CNN是基于在ImageNet数据集上训练的预训练视觉几何16层深度卷积网络（VGG16）模型创建的。全连接层针对学习成熟黑莓果实的成熟度特征进行了优化。由此产生的模型作为构建同质集成学习器的基础，这些学习器使用堆栈泛化集成（SGE）框架进行集成。网络的输入是使用立体传感器在700 nm和770 nm波长下利用可见光和近红外（VIS-NIR）光谱滤波器获取的图像。通过实验，所提出的模型在未见过的集合上达到了95.1%的准确率，在田间条件下达到了90.2%的准确率。进一步的实验表明，机器感官与人类感官在黑莓果实表皮纹理上具有高度正相关。
英文摘要：
Fruit ripeness estimation models have for decades depended on spectral index features or colour-based features, such as mean, standard deviation, skewness, colour moments, and/or histograms for learning traits of fruit ripeness. Recently, few studies have explored the use of deep learning techniques to extract features from images of fruits with visible ripeness cues. However, the blackberry (Rubus fruticosus) fruit does not show obvious and reliable visible traits of ripeness when mature and therefore poses great difficulty to fruit pickers. The mature blackberry, to the human eye, is black before, during, and post-ripening. To address this engineering application challenge, this paper proposes a novel multi-input convolutional neural network (CNN) ensemble classifier for detecting subtle traits of ripeness in blackberry fruits. The multi-input CNN was created from a pre-trained visual geometry group 16-layer deep convolutional network (VGG16) model trained on the ImageNet dataset. The fully connected layers were optimized for learning traits of ripeness of mature blackberry fruits. The resulting model served as the base for building homogeneous ensemble learners that were ensemble using the stack generalization ensemble (SGE) framework. The input to the network is images acquired with a stereo sensor using visible and near-infrared (VIS-NIR) spectral filters at wavelengths of 700 nm and 770 nm. Through experiments, the proposed model achieved 95.1% accuracy on unseen sets and 90.2% accuracy with in-field conditions. Further experiments reveal that machine sensory is highly and positively correlated to human sensory over blackberry fruit skin texture.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
