醋醋百科网

Good Luck To You!

高光谱成像技术应用于分类材料中的特殊目标

Determining Temperature-Dependent Optical Characteristics of Rmote Phosphor Plates by Transmission-Type Measurement System

透射式测量系统测定远程荧光粉板的温度相关光学特性


论文中所使用双利合谱产品:
显微高光谱系统

摘要:

We propose a transmission-type measurement system for determining temperature-dependent optical characteristics (TDOCs) for phosphors or remote phosphor plateswhich are applied in high-powerwhite light-emitting diodes, related to their stabilities and reliabilities. The proposed measurement system possesses remote-excitation characteristics and is able to separately control the temperature of tested phosphors or remote phosphor plates and that of excitation light sources (with the emission wavelength of 360–470 nm), to avoid the heat interference between them. This system is finally examined by fabricating two types of remote phosphor plates, i.e., yellow Y3Al5O12:Ce3+ and red CaAlSiN3:Eu2+ remote phosphor plates. A comparison between the proposed transmission-type system and the reflection-type system at various temperatures is also carried out. Results show that both the phosphor quantum efficiency and phosphor conversion efficiency of remote phosphor plates under various temperatures are possibly overestimated by the traditional reflection-type system. Employing the proposed method and carrying out experiments, we discover that the fraction of silicone in the silicone–phosphor mixture affects TDOCs of remote phosphor plates remarkably. Finally, via both the proposed system and the microhyperspectral imaging technology, thermal-quenching effects in the microcosmic level have also been investigated.

我们提出了一种透射式测量系统,用于测定大功率白光发光二极管中荧光粉或远程荧光粉板的温度相关光学特性 (TDOC),与它们的稳定性和可靠性有关。所提出的测量系统具有远程激发特性,能够分别控制测试荧光粉或远程荧光粉板的温度和激发光源(发射波长为 360-470 nm)的温度,以避免它们之间的热干扰。最后通过制造两种类型的远程荧光粉板(即黄色 Y3Al5O12:Ce3+ 和红色 CaAlSiN3:Eu2+ 远程荧光粉板)来检验该系统。还对所提出的透射式系统和反射式系统在不同温度下进行了比较。结果表明,传统反射式系统可能高估了不同温度下远程荧光粉板的荧光量子效率和荧光转换效率。采用所提出的方法并进行实验,我们发现硅-荧光粉混合物中硅的比例对远程荧光粉板的 TDOC有显著影响。最后,通过所提出的系统和微高光谱成像技术,还研究了微观层面的热猝灭效应。

DOI:10.1109/TED.2018.2890193

期刊:IEEE Transactions on Electron Devices

图注:设备采集图



A novel hyperspectral imaging and modeling method for the component identification of woven fabrics

一种用于机织物成分识别的新型高光谱成像与建模方法


论文中所使用双利合谱产品:
显微高光谱系统

摘要:

The component identification of textile materials is critical for quality control and measurement in the textile field. A novel hyperspectral imaging method and the related identification model are proposed to classify single-component textiles. Firstly, the hyperspectral data of the single-component fabrics were processed to conduct dimensionality reduction based on locally linear embedding (LLE), principal component analysis (PCA), and locally preserving projection (LPP) algorithms. Moreover, the original data of 288 wavelengths from 920nm to 2500nm were compressed to keep the typical wavelength regions. After that, these data were imported into two classifiers (decision tree classifier and K nearest neighbor (KNN) classifier) for training, and an identification model based on these training data was developed for the sample classification. The experimental results showed that all the samples could be identified correctly by the established identification model. The recognition rate and the stability of the classifier based on LPP model and KNN classification algorithm were proved to have the highest accuracy in our research.

纺织材料的成分识别对于纺织领域的质量控制和测量至关重要。提出了一种新的高光谱成像方法和相关的识别模型来对单组分纺织品进行分类。首先,基于局部线性嵌入(LLE)、主成分分析(PCA)和局部保留投影(LPP)算法对单组分织物的高光谱数据进行降维处理。此外,对920nm至2500nm的288个波长的原始数据进行压缩以保留典型波长区域。之后,将这些数据输入两个分类器(决策树分类器和K最近邻(KNN)分类器)进行训练,并基于这些训练数据开发了用于样品分类的识别模型。实验结果表明,建立的识别模型可以正确识别所有样品。本研究证明了基于LPP模型和KNN分类算法的分类器的识别率和稳定性具有最高的准确率

DOI:10.1177/0040517518821907

期刊:Textile Research Journal

关键词:高光谱成像、光谱分析、成分识别、降维、分类算法

图注:设备采集图



Active hyperspectral imaging with a supercontinuum laser source in the dark

黑暗环境下利用超连续谱激光源进行主动高光谱成像


论文中所使用双利合谱产品:
便携式成像光谱系统

摘要:

An active hyperspectral imaging (HSI) system was built with a supercontinuum (SC) laser illuminator and a visible/near-infrared hyperspectral camera, which was used for object spectrum detection in the dark. It was demonstrated that the Gaussian-like distribution of the SC illuminator can still be used for accurate reflectance spectrum measurement once the illuminator was characterized in advance. The validity of active HSI results was demonstrated by comparison with passive results. Then, the active HSI system was used to acquire reflectance spectra of different objects in just one push broom measurement successfully. With algorithms of principal component analysis clustering and unsupervised K-means spectral classification, this active HSI system with high spectral and spatial resolutions was demonstrated to be efficient and applicable for specific spectrum detections.

利用超连续谱 (SC) 激光照明器和可见/近红外高光谱相机构建了主动高光谱成像 (HSI) 系统,用于黑暗环境下的物体光谱检测。结果表明,一旦提前对照明器进行特性分析,SC 照明器的高斯分布仍可用于精确的反射光谱测量。通过与被动结果的比较证明了主动 HSI 结果的有效性。然后,利用主动 HSI 系统在一次推扫式测量中成功获取了不同物体的反射光谱。通过主成分分析聚类和无监督 K 均值光谱分类算法,证明了这种具有高光谱和空间分辨率的主动 HSI 系统对于特定光谱检测是高效且适用的。

DOI:10.1088/1674-1056/28/3/034206

关键词:激光光谱、主动高光谱成像、超连续谱激光



FGRC-Net: A high-information interactive convolutional neural network for identifying ink spectral information

FGRC-Net:一种用于识别墨水光谱信息的高信息量交互式卷积神经网络


论文中所使用双利合谱产品:

显微高光谱系统

摘要:

Modifying some keywords or numbers on documents to change the original intention is illegal. In some litigation cases, especially economic cases, there is often a need to examine the type of ink on documents. This paper proposes a nondestructive and accurate detection method for ink inspection. In this work, a high-information interactive, full group residual convolution network (FGRC-Net) is proposed and combined with spectral information to classify the inks of six different brands of pens. First, FGRC-Net realizes the information interaction among channels to effectively improve the feature extraction ability through multigroup convolution and multipath cascade. Meanwhile, to avoid feature degradation, the residual connection is introduced. Second, the ink spectral information of six pens based on the hyperspectral system is obtained. Finally, in comparing FGRCNet and other deep learning methods, FGRC-Net shows the best classiffcation performance with 98.38% accuracy, 98.53% precision, and 98.40% recall. The results show that combining FGRC-Net with a hyperspectral system is an effective detection method for handwritten ink classiffcation. It also provides an effective detection method for handwritten document ink inspection. At the same time, the universality and validity of FGRC-Net in processing spectral information are veriffed by the comparison of multiple datasets.

篡改文件中的关键词或数字以改变原意是一种违法行为。在某些诉讼案件,尤其是经济案件中,常常需要对文件上的墨水类型进行鉴定。本文提出了一种无损且精确的墨水检测方法。本研究提出了一种高信息交互的全群残差卷积网络(FGRC-Net),并结合光谱信息对六种不同品牌钢笔的墨水进行分类。首先,FGRC-Net通过多组卷积和多路径级联实现了通道间的信息交互,有效提升了特征提取能力。同时,为避免特征退化,引入了残差连接。其次,基于高光谱系统获取了六种钢笔的墨水光谱信息。最后,通过对比FGRC-Net与其他深度学习方法,FGRC-Net表现出最佳的分类性能,准确率达到98.38%,精确度为98.53%,召回率为98.40%。结果表明,将FGRC-Net与高光谱系统相结合是一种有效的手写墨水分类检测方法,同时也为手写文件墨水鉴定提供了一种有效的检测手段。此外,通过多个数据集的对比,验证了FGRC-Net在处理光谱信息方面的普适性和有效性。

DOI:https://DOI.org/10.1063/1.5048795

期刊:Expert Systems With Applications

关键词:墨水分类、光谱信息、卷积神经网络、信息交互

控制面板
您好,欢迎到访网站!
  查看权限
网站分类
最新留言