Influence of Polymer Packaging Films on Hyperspectral Imaging Data in the Visible—Near-Infrared (450–950 nm) Wavelength Range

2010 ◽  
Vol 64 (3) ◽  
pp. 304-312 ◽  
Author(s):  
A. A. Gowen ◽  
C. P. O'Donnell ◽  
C. Esquerre ◽  
G. Downey
Keyword(s):  
Hyperspectral Imaging ◽  
Wavelength Range ◽  
Near Infrared ◽  
Imaging Data ◽  
Packaging Films

scholarly journals Comparison of spectral selection methods in the development of classification models from visible near infrared hyperspectral imaging data

2019 ◽  
Author(s):  
Aoife Gowen ◽  
Jun-Li Xu ◽  
Ana Herrero-Langreo
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Imaging Spectroscopy ◽  
Model Performance ◽  
Data Sampling ◽  
Classification Models ◽  
Imaging Data ◽  
Selection Of

Applications of hyperspectral imaging (HSI) to the quantitative and qualitative measurement of samples have grown widely in recent years, due mainly to the improved performance and lower cost of imaging spectroscopy instrumentation. Data sampling is a crucial yet often overlooked step in hyperspectral image analysis, which impacts the subsequent results and their interpretation. In the selection of pixel spectra for the calibration of classification models, the spatial information in HSI data can be exploited. In this paper, a variety of sampling strategies for selection of pixel spectra are presented, exemplified through five case studies. The strategies are compared in terms of the proportion of global variability captured, practicality and predictive model performance. The use of variographic analysis as a guide to the spatial segmentation prior to sampling leads to the selection of representative subsets while reducing the variation in model performance parameters over repeated random selection.

Quantification of protein in wheat using near infrared hyperspectral imaging: Performance comparison with conventional near infrared spectroscopy

2018 ◽  
Vol 26 (3) ◽  
pp. 186-195 ◽  
Author(s):  
Ana Morales-Sillero ◽  
Juan A. Fernández Pierna ◽  
George Sinnaeve ◽  
Pierre Dardenne ◽  
Vincent Baeten
Keyword(s):  
Infrared Spectroscopy ◽  
Least Squares ◽  
Partial Least Squares ◽  
Hyperspectral Imaging ◽  
Wavelength Range ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Performance Comparison ◽  
Imaging Instrument ◽  
Leave One Out

Hyperspectral imaging is a powerful technique that combines the advantages of near infrared spectroscopy and imaging technologies. Most hyperspectral imaging studies focus on qualitative analysis, but there is growing interest in using such technique for the quantitative analysis of agro-food products in order to use them as universal tools. The overall objective of this study was to compare the performance of a hyperspectral imaging instrument with a classical near infrared instrument for predicting chemical composition. The determination of the protein content of wheat flour was selected as example. Spectra acquisition was made in individual sealed cells using two classical near infrared instruments (NIR-DS and NIR-Perstop) and a near infrared hyperspectral line-scan camera (NIR-HSI). In the latter, they were also acquired in open cells in order to study the possibility of accelerating the measurement process. Calibration models were developed using partial least squares for the full wavelength range of each individual instrument and for the common range between instruments (1120–2424 nm). The partial least squares models were validated using the “leave-one-out” cross-validation procedure and an independent validation set. The results showed that the NIR-HSI system worked as well as the classical near infrared spectrometers when a common wavelength range was used, with an r2 of 0.99 for all instruments and Root Mean Square Error in Prediction (RMSEP) values of 0.15% for NIR-HSI and NIR-DS and 0.16% for NIR-Perstop. The high residual predictive deviation values obtained (8.08 for NIR-DS, 7.92 for NIR-HSI, and 7.56 for NIR-Perstop) demonstrate the precision of the models built. In addition, the prediction performance with open cells was almost identical to that obtained with sealed cells.

A comparison of point and imaging visible-near infrared spectroscopy for determining soil organic carbon

2018 ◽  
Vol 26 (2) ◽  
pp. 133-146 ◽  
Author(s):  
Mohammad Sadegh Askari ◽  
Sharon M O'Rourke ◽  
Nicholas M Holden
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Soil Sample ◽  
Hyperspectral Imaging ◽  
Wavelength Range ◽  
Spectral Resolution ◽  
Near Infrared ◽  
Predictive Ability ◽  
Imaging Systems ◽  
Sample Representation

This study evaluated whether the accuracy of soil organic carbon measurement by laboratory hyperspectral imaging can match that of standard point spectroscopy operating in the visible–near infrared. Hyperspectral imaging allows a greater amount of spectral information to be collected from the soil sample compared to standard spectroscopy, accounting for greater sample representation. A total of 375 representative Irish soils were scanned by two-point spectrometers (a Foss NIR Systems 6500 labelled S-1 and a Varian FT-IR 3100 labelled S-2) and two laboratory hyperspectral imaging systems (two push broom line-scanning hyperspectral imaging systems manufactured by DV optics and Spectral Imaging Ltd, respectively, labelled S-3 and S-4). The objectives were (a) to compare the predictive ability of spectral datasets for soil organic carbon prediction for each instrument evaluated and (b) to assess the impact of imposing a common wavelength range and spectral resolution on soil organic carbon model accuracy. These objectives examined the predictive ability of spectral datasets for soil organic carbon prediction based on optimal settings of each instrument in (a) and introduced a constraint in wavelength range and spectral resolution to achieve common settings for instruments in (b). Based on optimal settings for each instrument, the deviation (root-mean square error of prediction) from the best fit line between laboratory measured and predicted soil organic carbon, ranked the instruments as S-1 (26.3 g kg−1) < S-2 (29.4 g kg−1) < S-3 (34.3 g kg−1) < S-4 (41.1 g kg−1). The S-1 model outperformed in all partial least squares regression performance indicators, and across all spectral ranges, and produced the most favourable outcomes in means testing, variance testing and identification of significant variables. It is assumed that a larger wavelength range produced more accurate soil organic carbon predictions for S-1 and S-2. Under common instrument settings, the prediction accuracy for S-3 that was almost equal to S-1. It is concluded that under standard operating procedures, greater soil sample representation captured by hyperspectral imaging can equal the quality of the spectra from point spectroscopy. This result is important for the development of laboratory hyperspectral imaging for soil image analysis.

Pork Tissue Recognition Using Visible and Near Infrared Hyperspectral Imaging

2020 ◽  
Author(s):  
Chih-Cheng Pai ◽  
Yang-Chu Chen ◽  
Keng-Hao Liu ◽  
Yuan-Hsun Tsai ◽  
Po-Chi Hu ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared

scholarly journals Estimating Agricultural Soil Moisture Content through UAV-Based Hyperspectral Images in the Arid Region

2021 ◽  
Vol 13 (8) ◽  
pp. 1562
Author(s):  
Xiangyu Ge ◽  
Jianli Ding ◽  
Xiuliang Jin ◽  
Jingzhe Wang ◽  
Xiangyue Chen ◽  
...  
Keyword(s):  
Data Mining ◽  
Soil Moisture ◽  
Moisture Content ◽  
Hyperspectral Imaging ◽  
Fractional Order ◽  
Arid Regions ◽  
Soil Moisture Content ◽  
Order Derivative ◽  
Imaging Data ◽  
Strategy I

Unmanned aerial vehicle (UAV)-based hyperspectral remote sensing is an important monitoring technology for the soil moisture content (SMC) of agroecological systems in arid regions. This technology develops precision farming and agricultural informatization. However, hyperspectral data are generally used in data mining. In this study, UAV-based hyperspectral imaging data with a resolution o 4 cm and totaling 70 soil samples (0–10 cm) were collected from farmland (2.5 × 104 m2) near Fukang City, Xinjiang Uygur Autonomous Region, China. Four estimation strategies were tested: the original image (strategy I), first- and second-order derivative methods (strategy II), the fractional-order derivative (FOD) technique (strategy III), and the optimal fractional order combined with the optimal multiband indices (strategy IV). These strategies were based on the eXtreme Gradient Boost (XGBoost) algorithm, with the aim of building the best estimation model for agricultural SMC in arid regions. The results demonstrated that FOD technology could effectively mine information (with an absolute maximum correlation coefficient of 0.768). By comparison, strategy IV yielded the best estimates out of the methods tested (R2val = 0.921, RMSEP = 1.943, and RPD = 2.736) for the SMC. The model derived from the order of 0.4 within strategy IV worked relatively well among the different derivative methods (strategy I, II, and III). In conclusion, the combination of FOD technology and the optimal multiband indices generated a highly accurate model within the XGBoost algorithm for SMC estimation. This research provided a promising data mining approach for UAV-based hyperspectral imaging data.

Sign in / Sign up

Export Citation Format

Share Document