Ensemble feature learning for material recognition with convolutional neural networks
Ensemble feature learning for material recognition with convolutional neural networks
复制标题
使用卷积神经网络进行材料识别的集成特征学习
DOI：
10.1186/s13640-018-0300-z
复制
发表时间：
2018-07-30
影响因子：
2.4
通讯作者：
Zhi, Ruicong
中科院分区：
文献类型：
--
作者：
Bian, Peng;Li, Wanwan;Zhi, Ruicong
材料识别是识别物体的组成材料的过程，是许多领域的关键步骤。因此，创建一个能够自动实现材料识别的系统是很有价值的。本文提出了一种基于卷积神经网络的材料识别集成学习方法。在该方法中，首先训练CNN模型提取图像特征；其次，学习基于知识的分类器，得到测试样本属于不同材料类别的概率；最后，我们提出了三种不同的方法来学习集成特征，从而达到更高的识别精度。与以往的工作有很大的不同之处在于我们将基于知识的分类器在概率水平上结合起来。实验结果表明，所提出的集成特征学习方法比现有的材料识别方法具有更好的识别性能，可以获得更高的识别精度。
Material recognition is the process of recognizing the constituent material of the object, and it is a crucial step in many fields. Therefore, it is valuable to create a system that could achieve material recognition automatically. This paper proposes a novel approach named ensemble learning for material recognition with convolutional neural networks (CNNs). In the proposed method, firstly, a CNN model is trained to extract the image features. Secondly, knowledge-based classifiers are learned to get the probabilities of the test sample that belongs to different material categories. Finally, we propose three different ways to learn the ensemble features, which achieves higher recognition accuracy. The great difference from the prior work is that we combine the knowledge-based classifiers on probability level. Experimental results show that the proposed ensemble feature learning method performs better than the state-of-the-art material recognition methods and can archive a much higher recognition accuracy.