Plastic material identification with spectroscopic near infrared imaging and artificial neural networks
Plastic material identification with spectroscopic near infrared imaging and artificial neural networks
复制标题
DOI：
10.1016/s0003-2670(98)00012-9
复制
发表时间：
1998-03-31
影响因子：
6.2
通讯作者：
Buydens, LMC
中科院分区：
文献类型：
--
作者：
van den Broek, WHAM;Wienke, D;Buydens, LMC
一个遥感光谱近红外（NIR）系统已被安装在一个实验室设置实时塑料识别混合生活垃圾。废物的识别分两步进行。首先，实验测量设置用于获取光谱图像数据，其次，通过神经网络执行非线性变换，用于这些测量图像的监督分类。该神经元识别系统需要对其在线分类性能进行评估。然而，不仅材料分类正确的百分比是重要的，而且相应的精度和操作环境（鲁棒性），如温度和湿度的差异。此外。该定性识别系统结合了关于传感器响应的可变性的额外复杂性，例如伴随污染废物样本的可变废物样本位置和形状。为了验证这样的系统，考虑了分类系统的鲁棒性、重复性和再现性。最终的识别系统能够识别塑料，所需的成功率为80%，但改进是可以预期的，当一些实验参数可以稳定。(C)1998年Elsevier Science B.V.
A remote sensing spectroscopic near infrared (NIR) system has been installed in an experimental laboratory setup for realtime plastic identification in mixed household waste. The identification of waste objects is performed in two steps. First, the experimental measurement setup is used for the acquisition of the spectroscopic image data and second, a non-linear transformation is performed by a neural network for supervised classification of these measured images. This neu identification system needs an evaluation of its on-line classification performance. However, not only the percentage of correct material classification is of interest, but also the corresponding precision and the circumstances of operation (robustness) such as differences in temperature and humidity. Furthermore. this qualitative identification system incorporates additional complications with respect to the variability of the sensor response, such as variable waste sample positions and shapes accompanied with contaminated waste samples. In order to validate such a system, the robustness, repeatability and reproducibility of the classification system are considered. The final identification system is able to identify plastics with the required success rate of 80%, but improvement is to be expected when some experimental parameters can be stabilized. (C) 1998 Elsevier Science B.V.