Comparison of different illumination systems for moisture prediction in cereal bars using hyperspectral imaging technology

The aim of this study is to develop a light-emitting diode- (LED-) based illumination system that can be used as an alternative light source forin vitrophotodynamic therapy (PDT). This illumination system includes a red LED array composed of 70 LEDs centered at 643 nm, an air-cooling unit, and a specific-designed case. The irradiance as a function of the irradiation distance between the LED array and the sample, the homogeneity and stability of irradiation, and the effect of long-time irradiation on culture medium temperature were characterized. Furthermore, the survival rate of the CNE1 cells that sensitized with 5-aminolevulinic acid after PDT treatment was evaluated to demonstrate the efficiency of the new LED-based illumination system. The obtained results show that the LED-based illumination system is a promising light source forin vitroPDT that performed in standard multiwell plate.

Mechanical bruise and fungi contamination are two typical defective features for strawberries, resulting in quick quality deterioration of the strawberries during transportation and storage. In this work, the approach of combined image processing with spectra analysis was successfully developed to identify defective strawberries (bruised and fungal infected) using hyperspectral reflectance imaging system. Hyperspectral image data was exploited by minimum noise fraction (MNF) transformation for strawberry defects distinguished by combining thresholding and morphology procedures, and defective regions were located and separated for spectra extracting. The linkages between quality parameters and spectra features were established based on the target defective regions of the fruit. After spectra normalization, three different spectral regions (400 to 600 nm, 650 to 720 nm, and 900 to 1010 nm) were identified for healthy, bruised, or infected strawberries, and eight optimal wavelengths were selected by the successive projection algorithms (SPA) from the whole range of wavelengths. Both linear and non-linear algorithms were developed to identify defective types in strawberries. The results indicated that based on full wavelengths, SVM model performed the highest overall identification accuracy, with the accuracy of 96.91% for calibration and 92.59% for prediction of the fruit. This work shows that hyperspectral reflectance imaging technology has the potential for identifying defective strawberries and provides theoretical basis for the development of online classification of different defected fruits.

Comparison of different illumination systems for moisture prediction in cereal bars using hyperspectral imaging technology

Mesenchymal stem cells derived from adult adipose tissue possess the ability to differentiate into adipocytes, osteocytes, and chondrocytes which in turn can be developed into adipose tissues, cartilages, and bones. This regenerative characteristics has fueled the need to define improved stem-cell analysis protocol for enabling investigation of the differentiation process efficiently, economically, and non-invasively by start-of-the art imaging modalities. Here, we have demonstrated hyperspectral microscopy-based label-free imaging approach to study ASCs at a single-cell level. ASCs has been stimulated to become osteocytes using the growth media containing β –glycerophosphate, L-ascorbic acid 2-phosphate sesquimagnesium salt hydrate, and dexamethasone. Further, ASCs were stimulated to form adipocytes using the growth media containing biotin, pantothenate, bovine insulin, IBMX, penicillin, rosiglitazone, and dexamethasone. In the present study, dark-field based hyperspectral Imaging (HSI) technique has been utilized to image single as well as multiple osteoblasts and adipocytes in salt media grown on the glass substrate. The spectral response of the cells at each pixel of the images were recorded in the visible-NIR range (400-900 nm). Response is stored in the three dimensional data-cube formed with two spatial dimensions and one spectral dimension. No special tagging or staining of the ASCs and derived osteoblasts, adipocytes has been done, as more likely required in traditional microscopy techniques. Incident light is diffracted at multiple angles and hence scattering response received after transmission is different even within the single cell due to sub-cellular heterogeneities present in the control and differentiating ASCs. Based on dark-field images of control and differentiated sample, we found significant structural and spectral distinctiveness at day 14 onwards for differentiated osteoblasts and at day 6 onwards for adipocytes. Fourier filtering of images provides good visual inspection of structural modifications. Spectral data from the cellular surface and intracellular markers, and secreted molecules is stored to build the spectral libraries. Matrix-assisted laser deposition/ionization (MALDI) spectrometry technique is performed on control and differentiated cells to obtain insight of sub-cellular single molecules, mineral deposits, fats, proteins, and other biological mono-constituents. In the hyperspectral images, the entire spectrum is stored within each pixel as a vector where the number of spectral bands (wavelength range) equals vector dimension and the corresponding intensity signifies the component of the individual vector. Spectral signatures from the identified lipids are then matched to the in vitro stem-cells via spectral angle mapping (SAM) algorithms. By computing angle between two pixels, remarkable spectral similarity and dissimilarity are identified between control and differentiated stem cells. Pseudo-colored differentiating maps are produced by calibrating ‘match’ threshold. Secondary validation to the HSI is provided by evaluating optical images with template-match and edge-detection algorithms as well as second-harmonic generation microscopy to investigate osteoblasts. Establishing this label-free protocol with minimum specimen preparation enables promising outcomes to overcome phototoxicity effect of traditional microscopy such as fluorescence/staining bleaching errors. The study would lead to high-throughput identification of patient specific derived cells for clinical use preventing mass rejection, and advance our understanding of the behavior of stem cellular clusters undergoing adipogenic and osteogenic differentiation.

Comparison of hyperspectral imaging with conventional RGB imaging for quality evaluation of Agaricus bisporus mushrooms

The objective of this study was to assess the beef-marbling grade using hyperspectral imaging technology. A hyperspectral scanning imaging system was developed to collect hyperspectral images in the spectral region of 400-1100 nm. Original turned line-scanning hyperspectral images were transformed into three-dimensional spectral data with a computer program developed by authors. The maximal ratio of gray value of fat and lean in each band was used to select characteristic bands. As a result, the images at 530nm were used to differentiate beef-marbling. Three characteristic parameters were extracted, and used to establish prediction model by multiple linear regression (MLR) methods. The MLR model gave a good result with R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.92, SE <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CV</sub> = 0.45. The research demonstrated that hyperspectral imaging technology is useful for nondestructive determination of beef marbling level.

Rapid identification of cod authenticity based on hyperspectral imaging technology

Early detection of bruising is one of the major challenges in postharvest quality sorting processes for pears. In this study, visible/near infrared (VIS/NIR) hyperspectral imaging (400–1000 nm) was utilized for early detection of pear bruise type and timing (1, 12, and 24 h post-bruise). Spectral images of nonbruised and mechanically bruised pears (collision and compression) were captured at these intervals for modeling. Spectral data was processed using principal component analysis (PCA) and uninformative variable elimination (UVE) to select optimum wavelengths. Classification models were then built using an extreme learning machine (ELM) and support vector machine (SVM), and compared with a model combining genetic algorithm, sooty tern optimization algorithm, and SVM (STOA-GA-SVM). For PCA-ELM, UVE-ELM, PCA-SVM, and UVE-SVM models, the calibration set accuracies were 98.99%, 98.98%, 96.94%, and 99.23% respectively. And the validation set accuracies were 89.29%, 87.97%, 88.78%, and 88.78% respectively. The STOA-GA-SVM model shows the best performance, and the accuracy of the calibration set and validation set is determined to be 97.19% and 92.86%, respectively. This study shows that the use of the VIS/NIR hyperspectral imaging technique combined with the STOA-GA-SVM algorithm is feasible for the rapid and nondestructive identification of the bruise type and time for pears.

The necessity for precise determination of fruit storage durations is paramount in both industrial and domestic spheres, with hyperspectral imaging (HSI) technology emerging as a pivotal tool for prognosticating the physicochemical attributes indicative of mature fruit quality. This investigation employed hyperspectral imaging to conduct a noninvasive analysis of variations in soluble solids content (SSC), hardness, and moisture content (MC) in jujube fruit over the course of storage at divergent temperatures. Throughout the storage intervals (0, 7, 14, and 21 days) at varying temperatures (4 and 20°C), both physicochemical and spectral data were amassed. The raw spectral information underwent preprocessing through multiple scattering correction (MSC), standard normal variation (SNV), and Savitzky–Golay (SG) algorithms to refine the methodologies for SSC, hardness, and moisture content. Subsequently, the competitive adaptive reweighted sampling (CARS) algorithm facilitated the discernment and elimination of extraneous variables, thereby enhancing feature wavelength extraction. This process underpinned the development of partial least squares regression (PLSR), back propagation (BP), and genetic algorithm‐back propagation (GA‐BP) models predicated on CARS‐derived features, culminating in the selection of an optimal model. The findings underscore the capability of hyperspectral imaging technology to swiftly and nondestructively ascertain the SSC, hardness, and MC of jujube throughout the storage phase, thereby enabling the assessment of quality attributes over varying storage durations and facilitating the surveillance of jujube quality maintenance during storage.Practical ApplicationsThe winter jujube garners appreciation from consumers owing to its exquisite flavor, yet its quality diminishes over time in storage due to various factors, thereby impacting its market value. Consequently, it is imperative to surveil the quality alterations of jujube throughout its storage to mitigate the degradation of its quality. Hyperspectral imaging technology offers a sophisticated means to forecast the physicochemical index changes indicative of the fruit's quality at maturity. This research delineates the development of predictive models for the soluble solids, hardness, and moisture content of jujube at divergent temperatures throughout the storage interval, selecting the paramount model through a holistic assessment, thereby fully harnessing the capabilities of hyperspectral imaging technology in monitoring jujube quality during storage. Moreover, the methodology employed herein is adaptable to other fruits in storage, harboring the potential for future application in the real‐time quality monitoring of fruits as they exit the storage facilities.

This paper presents a simulation method of hyper-spectral dynamic scene and image sequence for hyper-spectral equipment evaluation and target detection algorithm. Because of high spectral resolution, strong band continuity, anti-interference and other advantages, in recent years, hyper-spectral imaging technology has been rapidly developed and is widely used in many areas such as optoelectronic target detection, military defense and remote sensing systems. Digital imaging simulation, as a crucial part of hardware in loop simulation, can be applied to testing and evaluation hyper-spectral imaging equipment with lower development cost and shorter development period. Meanwhile, visual simulation can produce a lot of original image data under various conditions for hyper-spectral image feature extraction and classification algorithm. Based on radiation physic model and material characteristic parameters this paper proposes a generation method of digital scene. By building multiple sensor models under different bands and different bandwidths, hyper-spectral scenes in visible, MWIR, LWIR band, with spectral resolution 0.01μm, 0.05μm and 0.1μm have been simulated in this paper. The final dynamic scenes have high real-time and realistic, with frequency up to 100 HZ. By means of saving all the scene gray data in the same viewpoint image sequence is obtained. The analysis results show whether in the infrared band or the visible band, the grayscale variations of simulated hyper-spectral images are consistent with the theoretical analysis results.

This paper presents a simulation method of hyper-spectral dynamic scene and image sequence for hyper-spectral equipment evaluation and target detection algorithm. Because of high spectral resolution, strong band continuity, anti-interference and other advantages, in recent years, hyper-spectral imaging technology has been rapidly developed and is widely used in many areas such as optoelectronic target detection, military defense and remote sensing systems. Digital imaging simulation, as a crucial part of hardware in loop simulation, can be applied to testing and evaluation hyper-spectral imaging equipment with lower development cost and shorter development period. Meanwhile, visual simulation can produce a lot of original image data under various conditions for hyper-spectral image feature extraction and classification algorithm. Based on radiation physic model and material characteristic parameters this paper proposes a generation method of digital scene. By building multiple sensor models under different bands and different bandwidths, hyper-spectral scenes in visible, MWIR, LWIR band, with spectral resolution 0.01μm, 0.05μm and 0.1μm have been simulated in this paper. The final dynamic scenes have high real-time and realistic, with frequency up to 100 HZ. By means of saving all the scene gray data in the same viewpoint image sequence is obtained. The analysis results show whether in the infrared band or the visible band, the grayscale variations of simulated hyper-spectral images are consistent with the theoretical analysis results.

SummaryTo realise accurate and nondestructive detection on moisture content of maize seed based on visible/near‐infrared (Vis/NIR) and near‐infrared (NIR) hyperspectral imaging technology, the hyperspectral images on two sides (embryo and endosperm sides) of each maize seed of four varieties were collected. The effects of average spectra extraction regions, that is centroid region and whole seed region, and different spectral preprocessing methods, were investigated. Uninformative variable elimination (UVE) was used to extract the feature wavelengths, and the partial least squares regression (PLSR) prediction models were established. The results showed that extracting the average spectra from the centroid region did better than from the whole seed region, and S‐G smoothing was prior to other preprocessing methods. The PLSR models established with NIR spectra had better performance than that with Vis/NIR spectra. The model developed for a single variety was superior to that for all varieties together.

Rapid identification of moxa wool storage period based on hyperspectral imaging technology and machine learning

Hyperspectral Imaging (HSI) is gaining increasing interest in the field of analytical chemistry, since this fast and non-destructive technique allows one to easily acquire a large amount of spectral and spatial information on a wide number of samples in very short times. However, the large size of hyperspectral image data often limits the possible uses of this technique, due to the difficulty of evaluating many samples altogether, for example when one needs to consider a representative number of samples for the implementation of on-line applications. In order to solve this problem, we propose a novel chemometric strategy aimed to significantly reduce the dataset size, which allows to analyze in a completely automated way from tens up to hundreds of hyperspectral images altogether, without losing neither spectral nor spatial information. The approach essentially consists in compressing each hyperspectral image into a signal, named hyperspectrogram, which is created by combining several quantities obtained by applying PCA to each single hyperspectral image. Hyperspectrograms can then be used as a compact set of descriptors and subjected to blind analysis techniques. Moreover, a further improvement of both data compression and calibration/classification performances can be achieved by applying proper variable selection methods to the hyperspectrograms. A visual evaluation of the correctness of the choices made by the algorithm can be obtained by representing the selected features back into the original image domain. Likewise, the interpretation of the chemical information underlying the selected regions of the hyperspectrograms related to the loadings is enabled by projecting them in the original spectral domain. Examples of applications of the hyperspectrogram-based approach to hyperspectral images of food samples in the NIR range (1000–1700nm) and in the vis–NIR range (400–1000nm), facing a calibration and a defect detection issue respectively, demonstrate the effectiveness of the proposed approach.

Nondestructive detection of Clonorchis sinensis infection of raw Pseudorasbora parva fish by near-infrared hyperspectral imaging