Efficient chemometric strategies for PET–PLA discrimination in recycling plants using hyperspectral imaging

Ulrici, Alessandro; Serranti, Silvia; Ferrari, Carina; Cesare, Daniela; Foca, Giorgia; Bonifazi, Giuseppe

doi:10.1016/j.chemolab.2013.01.001

Cited by 91 publications

(53 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in order to reduce the variability among images over time, an additional internal calibration was performed [48], based on the average reflectance values of the reflectance standard, of the two ceramic tiles and of the black silicon carbide sandpaper.…”

Section: Image Acquisitionmentioning

confidence: 99%

Practical comparison of sparse methods for classification of Arabica and Robusta coffee species using near infrared hyperspectral imaging

Calvini

Ulrici

Amigo

2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

In the present work sparse-based methods are applied to the analysis of hyperspectral images with the aim at studying their capability of being adequate methods for variable selection in a classification framework. The key aspect of sparse methods is the possibility of performing variable selection by forcing the model coefficients related to irrelevant variables to zero. In particular, two different sparse classification approaches, i.e. sPCA+kNN and sPLS-DA, were compared with the corresponding classical methods (PCA + kNN and PLS-DA) to classify Arabica and Robusta coffee species. Green coffee samples were analyzed using near infrared hyperspectral imaging and the average spectra from each hyperspectral image were used to build training and test sets; furthermore a test image was used to evaluate the performances of the considered methods at pixel-level. In our case, sparse methods led to similar results as classical methods, with the advantage of obtaining more interpretable and parsimonious models. An important result to highlight is that variable selection performed with two different sparse classification approaches converged to the selection of same spectral regions, which implies the chemical relevance of those regions in the discrimination of Arabica and Robusta coffee species

show abstract

Section: Image Acquisitionmentioning

confidence: 99%

Practical comparison of sparse methods for classification of Arabica and Robusta coffee species using near infrared hyperspectral imaging

Calvini

Ulrici

Amigo

2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

show abstract

“…By using near-infrared spectroscopy as a spectroscopic method, measurements of samples can be performed accurately, non-destructively and rapidly. Hyperspectral imaging has been applied to prediction of protein and fat content in cheeses (Burger and Geladi, 2006), estimation of fruit yield in citrus (Ye et al, 2006), mapping piroxicam polymorphs (Rocha et al, 2011), assessment of regional leaf area index (Canisius and Fernandes, 2012), food authentication (Ottavian et al, 2012), discrimination between polylactic acid and polyethylene terephthalate (Ulrici et al, 2013) and monitoring of polymorphic transformation (Terra and Poppi, 2014). Pre-treatment (Esquerre et al, 2012) and spatial resolution (Offroy et al, 2012) have been discussed as well.…”

Section: Introductionmentioning

confidence: 98%

Classification of drug tablets using hyperspectral imaging and wavelength selection with a GAWLS method modified for classification

Kaneko

Funatsu

2015

International Journal of Pharmaceutics

View full text Add to dashboard Cite

Right drug tablets must be brought to the right places. We apply hyperspectral imaging, which can measure infrared spectra at many points on a two-dimensional plane, to classify tablets correctly. The k-nearest neighbor algorithm (kNN) is employed to classify tablets using a database including their spectra and true classes. Although classification accuracy is not 100%, we can correctly classify tablets overall, since spectra at many points are measured with spectroscopy and misclassification at some points does not have much influence on the final tablet classification result. In addition, we propose a wavelength selection method for classification. Genetic algorithm-based wavelength selection is applied to classification and combined with kNN, and thus, not wavelengths but wavelength-regions can be selected in classification problems. Through a case study, we confirmed that the proposed method could classify three kinds of tablets correctly and select appropriate wavelength-regions.

show abstract

“…This explains why there is a strong interest to investigate biopolymer properties and develop their production as an alternative to synthetic polymers. For example, a high number of research projects have been devoted to enhance polylactic acid (PLA) properties as a promising bioplastic in food packaging because it is recyclable and biodegradable in addition of its good mechanical properties, availability and transparency [8], [9].…”

Section: Packaging Materialsmentioning

confidence: 99%

“…NIR hyperspectral imaging coupled with the Multivariate Image Analysis (MIA) technique was effectively used by Ghasemzadeh-Barvarz et al to classify multilayer polymer films according to the absence or presence of functional layers [67]. Partial Least SquaresDiscriminant Analysis (PLS-DA) was also applied to NIR images to discriminate between PLA and polyethylene terephthalate (PET) [9] in recycling (sorting) applications. However, most of the work in this area focused on the qualitative analysis of plastic films [19,22] or are limited to quantify the concentration of specific constituents or contaminants in the films [18,23] which is not enough to meet the quality control objectives.…”

Section: Introductionmentioning

confidence: 99%

Characterization of PLA-talc films using NIR chemical imaging and Multivariate Image Analysis techniques

2018

View full text Add to dashboard Cite

Maîtrise en génie chimiqueToutefois, puisque la structure de ces films est plus complexe, le contrôle de qualité de ces derniers est plus difficile. Dans l'industrie, des méthodes hors-ligne sont très souvent utilisées pour effectuer le contrôle de qualité des films produits. Le contrôle est nécessaire puisque la variabilité de la matière première ainsi que le changement des conditions opératoires amènent des modifications qui changent considérablement les propriétés du film. Par conséquent, une inspection en temps réel ainsi qu'un contrôle des films de polymère est nécessaire sur la ligne de production afin d'obtenir un contrôle de qualité s'approchant de l'analyse en temps réel.Un système d'imagerie proche infrarouge (NIR) rapide et non-destructif est proposé pour caractériser les films biodégradables d'acide polylactique contenant du talc produits par extrusion-soufflage et utilisés pour l'emballage. Le but ultime est d'utiliser le système pour faire un contrôle de qualité sur la ligne d'extrusion ainsi qu'après le post-traitement thermique, soit le recuit. Un ensemble d'échantillon de film de PLA contenant différentes concentrations en talc ont été fabriqués. Ces derniers ont ensuite été soumis à différentes conditions de recuit. Des images NIR ont été collectées avant la caractérisation des propriétés physiques et mécaniques ainsi que l'étanchéité aux gaz. Des techniques d'imagerie multivariées ont été appliquées aux images hyperspectrales. Celles-ci ont montré que la quantité de talc peut être déterminée et que l'information du spectre NIR permet de prédire les propriétés du film. Dans tous les cas, la méthode proposée permet de déterminer les variations dans les propriétés du film avec une bonne précision. iv AbstractFood packaging plays a great role in the food industry to maintain food products quality as long as possible. Polymer films are widely used in food packaging and also attract attention because of their outstanding advantages. Since petroleum-based polymers are known to cause environmental concerns, biodegradable polymers like PLA were studied more intensively in recent years due to their environmentally friendly properties. The application of reinforced films exceeds simple ones in achieving specific functions and enhancing their properties such as barrier properties. Since the films structures are more complex, quality control is more challenging. In industry, off-line methods are vastly used for quality control of the produced films while variability in raw materials and processing conditions substantially change the film specifications. Consequently, real-time inspection and monitoring of polymer films is needed on the production line to achieve a real-time quality control of the films.A fast and non-invasive near-infrared (NIR) imaging system is proposed to characterize biodegradable polylactic acid (PLA) films containing talc, and produced by extrusion film-blowing for packaging applications. The ultimate goal is to use the system for quality control on the extrusion line, and after a po...

show abstract

Efficient chemometric strategies for PET–PLA discrimination in recycling plants using hyperspectral imaging

Cited by 91 publications

References 29 publications

Practical comparison of sparse methods for classification of Arabica and Robusta coffee species using near infrared hyperspectral imaging

Practical comparison of sparse methods for classification of Arabica and Robusta coffee species using near infrared hyperspectral imaging

Classification of drug tablets using hyperspectral imaging and wavelength selection with a GAWLS method modified for classification

Characterization of PLA-talc films using NIR chemical imaging and Multivariate Image Analysis techniques

Contact Info

Product

Resources

About