Shortwave infrared hyperspectral reflectance imaging for cotton foreign matter classification

Zhang, Ruoyu; Li, Changying; Zhang, Mengyun; Rodgers, James

doi:10.1016/j.compag.2016.06.023

Cited by 27 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nearly all of the selected wavelengths were located near particular regions of the spectral range, which indicates some connection between seed reflectance and chemical information. For instance, many selected bands were located near the absorbance bands of plant pigments peaks: carotenoids (448, 471 nm), chlorophyll a (430, 662, and 680 nm), and chlorophyll b (448, 642 nm) [ 50 ]. In addition, bands near 970 nm may correspond to the O–H stretching (2nd overtone) and C–H stretching (3rd overtone) [ 33 , 50 ].…”

Section: Resultsmentioning

confidence: 99%

“…For instance, many selected bands were located near the absorbance bands of plant pigments peaks: carotenoids (448, 471 nm), chlorophyll a (430, 662, and 680 nm), and chlorophyll b (448, 642 nm) [ 50 ]. In addition, bands near 970 nm may correspond to the O–H stretching (2nd overtone) and C–H stretching (3rd overtone) [ 33 , 50 ]. Bands that exceed 760 nm were disproportionately represented in the selected wavelengths of the reverse side.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds

Zhang

Wei

Zhao

et al. 2018

Sensors

View full text Add to dashboard Cite

This study investigated the possibility of using visible and near-infrared (VIS/NIR) hyperspectral imaging techniques to discriminate viable and non-viable wheat seeds. Both sides of individual seeds were subjected to hyperspectral imaging (400–1000 nm) to acquire reflectance spectral data. Four spectral datasets, including the ventral groove side, reverse side, mean (the mean of two sides’ spectra of every seed), and mixture datasets (two sides’ spectra of every seed), were used to construct the models. Classification models, partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), coupled with some pre-processing methods and successive projections algorithm (SPA), were built for the identification of viable and non-viable seeds. Our results showed that the standard normal variate (SNV)-SPA-PLS-DA model had high classification accuracy for whole seeds (>85.2%) and for viable seeds (>89.5%), and that the prediction set was based on a mixed spectral dataset by only using 16 wavebands. After screening with this model, the final germination of the seed lot could be higher than 89.5%. Here, we develop a reliable methodology for predicting the viability of wheat seeds, showing that the VIS/NIR hyperspectral imaging is an accurate technique for the classification of viable and non-viable wheat seeds in a non-destructive manner.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds

Zhang

Wei

Zhao

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…The maximal detection accuracy of 99.58% well exceeds Yang et al’s detection accuracy of 92% [6,7], but does not top the 100% accuracy of Zhang et al using shortwave infrared hyperspectral imaging [13]. Although the results for bark are superior to those of Zhang et al, those for stems are not, and it should be noted that Zhang et al considered inner and outer bark and stem surfaces as separate categories, with most misclassification for these foreign matter types being the complementary category.…”

Section: Resultsmentioning

confidence: 99%

“…Guo et al achieved some success in this area, particularly for the detection of foreign fibers, which are a common contaminant in Chinese cotton fields [12]. Using mean NIR spectra collected from a set of 16 foreign matter types and cleaned cotton lint, Zhang et al achieved an accuracy of classification of 96.5% using linear discriminant analysis (LDA) classifiers, including 100% accuracy on the cotton lint [13]. …”

Section: Introductionmentioning

confidence: 99%

A Pulsed Thermographic Imaging System for Detection and Identification of Cotton Foreign Matter

Kuzy

2017

Sensors

Self Cite

View full text Add to dashboard Cite

Detection of foreign matter in cleaned cotton is instrumental to accurately grading cotton quality, which in turn impacts the marketability of the cotton. Current grading systems return estimates of the amount of foreign matter present, but provide no information about the identity of the contaminants. This paper explores the use of pulsed thermographic analysis to detect and identify cotton foreign matter. The design and implementation of a pulsed thermographic analysis system is described. A sample set of 240 foreign matter and cotton lint samples were collected. Hand-crafted waveform features and frequency-domain features were extracted and analyzed for statistical significance. Classification was performed on these features using linear discriminant analysis and support vector machines. Using waveform features and support vector machine classifiers, detection of cotton foreign matter was performed with 99.17% accuracy. Using frequency-domain features and linear discriminant analysis, identification was performed with 90.00% accuracy. These results demonstrate that pulsed thermographic imaging analysis produces data which is of significant utility for the detection and identification of cotton foreign matter.

show abstract

“…A new study classified cotton trash using shortwave infrared hyperspectral reflectance imaging [16]. This technique applied a liquid crystal tunable filter, as well as linear discriminant analysis for identification of cotton from cotton trash.…”

mentioning

confidence: 99%

Fourier-Transform Imaging of Cotton and Botanical and Field Trash Mixtures

Fortier

Cintrón

Rodgers

et al. 2017

Fibers

Self Cite

View full text Add to dashboard Cite

Botanical and field cotton trash comingled with Upland cotton lint can greatly reduce the marketability and quality of cotton. Trash found comingled with cotton lint during harvesting, ginning, and processing is of interest to the textile community. In the current study attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopic imaging was employed as an analytical technique to analyze cotton trash. Some benefits of this technique were its non-destructive nature and lack of required sample preparation. The technique used in this study, specifically ATR-FTIR spectroscopic chemical imaging, allows for three-dimensional spectral and spatial data to be obtained. In the current study, cotton in mixtures with botanical and field trash types have been identified spectrally and spatially using ATR-FTIR imaging. Botanical trash types (trash derived from the cotton plant) were evaluated and identified independently from cotton, even though both contained cellulose. The field trash types were easily identified from cotton due to their differences in chemical composition. This study can complement current cotton qualitative studies by adding spectral and spatial information to sample analysis.

show abstract

Shortwave infrared hyperspectral reflectance imaging for cotton foreign matter classification

Cited by 27 publications

References 23 publications

A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds

A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds

A Pulsed Thermographic Imaging System for Detection and Identification of Cotton Foreign Matter

Fourier-Transform Imaging of Cotton and Botanical and Field Trash Mixtures

Contact Info

Product

Resources

About