A hyperspectral imaging sensor for on-line quality control of extruded polymer composite products

Fusing spectral and spatial information with 2-D stationary wavelet transform (SWT 2-D) for a deeper exploration of spectroscopic images

Nowadays, it is clear that there is an increasing importance in spectroscopic imaging in all fields of science. Obviously, one bulk analysis can no longer be satisfactory, as the interest focuses more on the chemical nature and the location of the compounds present within a given complex matrix. This is, evidently, due to the fact that for a more comprehensive exploration of complex samples, one single acquired hyperspectral data cube can provide both spectral and spatial information simultaneously. Although many techniques were proposed by the chemometric community in explorations of these specific datasets, unfortunately, they are almost always focusing on spectral information, even if chemical images were ultimately observed. In other words, spatial information is not well exploited, and therefore lost during the actual chemometric calculation phase. The goal of this short communication is to present a very simple and fast spectral/spatial fusion approach based on 2-D stationary wavelet transform (SWT 2-D) which is able to improve the obtainable information, compared with a classical data analysis, in which the spatial domain would not be considered nor used.

A discrimination model in waste plastics sorting using NIR hyperspectral imaging system

Classification of plastics is important in the recycling industry. A plastic identification model in the near infrared spectroscopy wavelength range 1000-2500 nm is proposed for the characterization and sorting of waste plastics using acrylonitrile butadiene styrene (ABS), polystyrene (PS), polypropylene (PP), polyethylene (PE), polyethylene terephthalate (PET), and polyvinyl chloride (PVC). The model is built by the feature wavelengths of standard samples applying the principle component analysis (PCA), and the accuracy, property and cross-validation of the model were analyzed. The model just contains a simple equation, center of mass coordinates, and radial distance, with which it is easy to develop classification and sorting software. A hyperspectral imaging system (HIS) with the identification model verified its practical application by using the unknown plastics. Results showed that the identification accuracy of unknown samples is 100%. All results suggested that the discrimination model was potential to an on-line characterization and sorting platform of waste plastics based on HIS.

Segmentation and Quantitative Analysis of Apoptosis of Chinese Hamster Ovary Cells from Fluorescence Microscopy Images

Accurate and fast quantitative analysis of living cells from fluorescence microscopy images is useful for evaluating experimental outcomes and cell culture protocols. An algorithm is developed in this work to automatically segment and distinguish apoptotic cells from normal cells. The algorithm involves three steps consisting of two segmentation steps and a classification step. The segmentation steps are: (i) a coarse segmentation, combining a range filter with a marching square method, is used as a prefiltering step to provide the approximate positions of cells within a two-dimensional matrix used to store cells' images and the count of the number of cells for a given image; and (ii) a fine segmentation step using the Active Contours Without Edges method is applied to the boundaries of cells identified in the coarse segmentation step. Although this basic two-step approach provides accurate edges when the cells in a given image are sparsely distributed, the occurrence of clusters of cells in high cell density samples requires further processing. Hence, a novel algorithm for clusters is developed to identify the edges of cells within clusters and to approximate their morphological features. Based on the segmentation results, a support vector machine classifier that uses three morphological features: the mean value of pixel intensities in the cellular regions, the variance of pixel intensities in the vicinity of cell boundaries, and the lengths of the boundaries, is developed for distinguishing apoptotic cells from normal cells. The algorithm is shown to be efficient in terms of computational time, quantitative analysis, and differentiation accuracy, as compared with the use of the active contours method without the proposed preliminary coarse segmentation step.

Classification of oat and groat kernels using NIR hyperspectral imaging

An innovative procedure to classify oat and groat kernels based on coupling hyperspectral imaging (HSI) in the near infrared (NIR) range (1006-1650 nm) and chemometrics was designed, developed and validated. According to market requirements, the amount of groat, that is the hull-less oat kernels, is one of the most important quality characteristics of oats. Hyperspectral images of oat and groat samples have been acquired by using a NIR spectral camera (Specim, Finland) and the resulting data hypercubes were analyzed applying Principal Component Analysis (PCA) for exploratory purposes and Partial Least Squares-Discriminant Analysis (PLS-DA) to build the classification models to discriminate the two kernel typologies. Results showed that it is possible to accurately recognize oat and groat single kernels by HSI (prediction accuracy was almost 100%). The study demonstrated also that good classification results could be obtained using only three wavelengths (1132, 1195 and 1608 nm), selected by means of a bootstrap-VIP procedure, allowing to speed up the classification processing for industrial applications. The developed objective and non-destructive method based on HSI can be utilized for quality control purposes and/or for the definition of innovative sorting logics of oat grains.

Characterization of post-consumer polyolefin wastes by hyperspectral imaging for quality control in recycling processes

In this paper new analytical inspection strategies, based on hyperspectral imaging (HSI) in the VIS-NIR and NIR wavelength ranges (400-1000 and 1000-1700 nm, respectively), have been investigated and set up in order to define quality control logics that could be applied at industrial plant level for polyolefins recycling. The research was developed inside the European FP7 Project W2Plastics "Magnetic Sorting and Ultrasound Sensor Technologies for Production of High Purity Secondary Polyolefins from Waste". The main aim of the project is the separation of pure polyethylene and polypropylene adopting an innovative process, the magnetic density separation (MDS). Spectra of plastic particles and contaminants resulting from post-consumer complex wastes and of virgin polyolefins have been acquired by HSI and by Raman spectroscopy. The classification results obtained applying principal component analysis (PCA) on HSI data have been compared with those obtained by Raman spectroscopy, in order to validate the proposed innovative methodology. Results showed that HSI sensing techniques allow to identify both polyolefins and contaminants. Results also demonstrated that HSI has a great potentiality as a tool for quality control of feed (identification of contaminants in the plastic waste) and of the two different pure polypropylene and polyethylene flow streams resulting from the MDS-based recycling process.