Recent developments in hyperspectral imaging for assessment of food quality and safety

Optimal-Band Analysis for Chlorophyll Quantification in Rice Leaves Using a Custom Hyperspectral Imaging System

Hyperspectral imaging (HSI) is a promising tool in chlorophyll quantification, providing a non-invasive method to collect important information for effective crop management. HSI contributes to food security solutions by optimising crop yields. In this study, we presented a custom HSI system specifically designed to provide a quantitative analysis of leaf chlorophyll content (LCC). To ensure precise estimation, significant wavelengths were identified using optimal-band analysis. Our research was centred on two sets of 120 leaf samples sourced from Thailand's unique Chaew Khing rice variant. The samples were subjected to (i) an analytical LCC assessment and (ii) HSI imaging for spectral reflectance data capture. A linear regression comparison of these datasets revealed that the green (575 ± 2 nm) and near-infrared (788 ± 2 nm) bands were the most outstanding performers. Notably, the green normalised difference vegetation index (GNDVI) was the most reliable during cross-validation (R2=0.78 and RMSE = 2.4 µg∙cm-2), outperforming other examined vegetable indices (VIs), such as the simple ratio (RED/GREEN) and the chlorophyll index. The potential development of a streamlined sensor dependent only on these two wavelengths is a significant outcome of identifying these two optimal bands. This innovation can be seamlessly integrated into farming landscapes or attached to UAVs, allowing real-time monitoring and rapid, targeted N management interventions.

Application of Visible/Near-Infrared Spectroscopy and Hyperspectral Imaging with Machine Learning for High-Throughput Plant Heavy Metal Stress Phenotyping: A Review

Heavy metal pollution is becoming a prominent stress on plants. Plants contaminated with heavy metals undergo changes in external morphology and internal structure, and heavy metals can accumulate through the food chain, threatening human health. Detecting heavy metal stress on plants quickly, accurately, and nondestructively helps to achieve precise management of plant growth status and accelerate the breeding of heavy metal-resistant plant varieties. Traditional chemical reagent-based detection methods are laborious, destructive, time-consuming, and costly. The internal and external structures of plants can be altered by heavy metal contamination, which can lead to changes in plants' absorption and reflection of light. Visible/near-infrared (V/NIR) spectroscopy can obtain plant spectral information, and hyperspectral imaging (HSI) can obtain spectral and spatial information in simple, speedy, and nondestructive ways. These 2 technologies have been the most widely used high-throughput phenotyping technologies of plants. This review summarizes the application of V/NIR spectroscopy and HSI in plant heavy metal stress phenotype analysis as well as introduces the method of combining spectroscopy with machine learning approaches for high-throughput phenotyping of plant heavy metal stress, including unstressed and stressed identification, stress types identification, stress degrees identification, and heavy metal content estimation. The vegetation indexes, full-range spectra, and feature bands identified by different plant heavy metal stress phenotyping methods are reviewed. The advantages, limitations, challenges, and prospects of V/NIR spectroscopy and HSI for plant heavy metal stress phenotyping are discussed. Further studies are needed to promote the research and application of V/NIR spectroscopy and HSI for plant heavy metal stress phenotyping.

Rapid identification of counterfeited beef using deep learning-aided spectroscopy: Detecting colourant and curing agent adulteration

The adulteration of meat products using colourants and curing agents has heightened concerns over food safety, thereby necessitating the development of advanced detection methods. This study introduces a deep-learning-based spectroscopic method for swiftly identifying counterfeit beef altered to appear fresh. The experiment involved 60 beef samples, half of which were artificially adulterated using a colouring solution. Despite meticulous analysis of the beef's colour attributes, no significant differences were observed between the fresh and adulterated samples. However, our method, utilising a 344-1040 nm spectral range, achieved a classification accuracy of 98.84%. To enhance practicality, we employed gradient-weighted class activation mapping and identified the 580-600 nm range as particularly influential for classification. Remarkably, even when we narrowed the input to the model to this spectral range, a high level of classification accuracy was maintained. To further validate the model's robustness and generalisability, we allocated 70 beef samples to an external validation set. Comparative performance analysis revealed that our model outperformed traditional machine learning algorithms, such as SVM and logistic regression, by 9.3% and 28.4%, respectively. Overall, this study offers invaluable insights for detecting counterfeited beef, thereby contributing to the preservation of meat product quality and integrity within the food industry.

Hyperspectral imaging for estimating leaf, flower, and fruit macronutrient concentrations and predicting strawberry yields

Managing the nutritional status of strawberry plants is critical for optimizing yield. This study evaluated the potential of hyperspectral imaging (400-1,000 nm) to estimate nitrogen (N), phosphorus (P), potassium (K), and calcium (Ca) concentrations in strawberry leaves, flowers, unripe fruit, and ripe fruit and to predict plant yield. Partial least squares regression (PLSR) models were developed to estimate nutrient concentrations. The determination coefficient of prediction (R2P) and ratio of performance to deviation (RPD) were used to evaluate prediction accuracy, which often proved to be greater for leaves, flowers, and unripe fruit than for ripe fruit. The prediction accuracies for N concentration were R2P = 0.64, 0.60, 0.81, and 0.30, and RPD = 1.64, 1.59, 2.64, and 1.31, for leaves, flowers, unripe fruit, and ripe fruit, respectively. Prediction accuracies for Ca concentrations were R2P = 0.70, 0.62, 0.61, and 0.03, and RPD = 1.77, 1.63, 1.60, and 1.15, for the same respective plant parts. Yield and fruit mass only had significant linear relationships with the Difference Vegetation Index (R2 = 0.256 and 0.266, respectively) among the eleven vegetation indices tested. Hyperspectral imaging showed potential for estimating nutrient status in strawberry crops. This technology will assist growers to make rapid nutrient-management decisions, allowing for optimal yield and quality.

Detection and prevention of foreign material in food: A review

This review highlights the critical concern foreign material contamination poses across the food processing industry and provides information on methods and implementations to minimize the hazards caused by foreign materials. A foreign material is defined as any non-food, foreign bodies that may cause illness or injury to the consumer and are not typically part of the food. Foreign materials can enter the food processing plant as part of the raw materials such as fruit pits, bones, or contaminants like stones, insects, soil, grit, or pieces of harvesting equipment. Over the past 20 years, foreign materials have been responsible for about one out of ten recalls of foods, with plastic fragments being the most common complaint. The goal of this paper is to further the understanding of the risks foreign materials are to consumers and the tools that could be used to minimize the risk of foreign objects in foods.

An Effective Hyperspectral Image Classification Network Based on Multi-Head Self-Attention and Spectral-Coordinate Attention

In hyperspectral image (HSI) classification, convolutional neural networks (CNNs) have been widely employed and achieved promising performance. However, CNN-based methods face difficulties in achieving both accurate and efficient HSI classification due to their limited receptive fields and deep architectures. To alleviate these limitations, we propose an effective HSI classification network based on multi-head self-attention and spectral-coordinate attention (MSSCA). Specifically, we first reduce the redundant spectral information of HSI by using a point-wise convolution network (PCN) to enhance discriminability and robustness of the network. Then, we capture long-range dependencies among HSI pixels by introducing a modified multi-head self-attention (M-MHSA) model, which applies a down-sampling operation to alleviate the computing burden caused by the dot-product operation of MHSA. Furthermore, to enhance the performance of the proposed method, we introduce a lightweight spectral-coordinate attention fusion module. This module combines spectral attention (SA) and coordinate attention (CA) to enable the network to better weight the importance of useful bands and more accurately localize target objects. Importantly, our method achieves these improvements without increasing the complexity or computational cost of the network. To demonstrate the effectiveness of our proposed method, experiments were conducted on three classic HSI datasets: Indian Pines (IP), Pavia University (PU), and Salinas. The results show that our proposed method is highly competitive in terms of both efficiency and accuracy when compared to existing methods.

Flexible long-wave infrared snapshot multispectral imaging with a pixel-level spectral filter array

This paper proposes and demonstrates a flexible long-wave infrared snapshot multispectral imaging system consisting of a simple re-imaging system and a pixel-level spectral filter array. A six-band multispectral image in the spectral range of 8-12 µm with full width at half maximum of about 0.7 µm each band is acquired in the experiment. The pixel-level multispectral filter array is placed at the primary imaging plane of the re-imaging system instead of directly encapsulated on the detector chip, which diminishes the complexity of pixel-level chip packaging. Furthermore, the proposed method possesses the merit of flexible functions switching between multispectral imaging and intensity imaging by plugging and unplugging the pixel-level spectral filter array. Our approach could be viable for various practical long-wave infrared detection applications.

Colorimetric response in polydiacetylene at the single domain level using hyperspectral microscopy

The structural variance of polydiacetylene (PDA) at the nanoscale level, even under the same fabrication conditions, is one of the origins of its poor reproducibility in chemo/biosensing. In this work, we present a spatial map of such structural distributions within a single crystal by taking advantage of the recent development of hyperspectral microscopy at visible wavelengths. Hyperspectral microscopy provides the distribution of absorption spectra at the spatial resolution of standard optical microscopy. By tracking the blue-to-red transition via this technique, we found that heat or pH stimulation leaves a unique pattern in the transition pathways.

A comprehensive review on acquisition of phenotypic information of Prunoideae fruits: Image technology

Fruit phenotypic information reflects all the physical, physiological, biochemical characteristics and traits of fruit. Accurate access to phenotypic information is very necessary and meaningful for post-harvest storage, sales and deep processing. The methods of obtaining phenotypic information include traditional manual measurement and damage detection, which are inefficient and destructive. In the field of fruit phenotype research, image technology is increasingly mature, which greatly improves the efficiency of fruit phenotype information acquisition. This review paper mainly reviews the research on phenotypic information of Prunoideae fruit based on three imaging techniques (RGB imaging, hyperspectral imaging, multispectral imaging). Firstly, the classification was carried out according to the image type. On this basis, the review and summary of previous studies were completed from the perspectives of fruit maturity detection, fruit quality classification and fruit disease damage identification. Analysis of the advantages and disadvantages of various types of images in the study, and try to give the next research direction for improvement.

Human Hepatocellular Carcinoma Classification from H&E Stained Histopathology Images with 3D Convolutional Neural Networks and Focal Loss Function

This paper proposes a new Hepatocellular Carcinoma (HCC) classification method utilizing a hyperspectral imaging system (HSI) integrated with a light microscope. Using our custom imaging system, we have captured 270 bands of hyperspectral images of healthy and cancer tissue samples with HCC diagnosis from a liver microarray slide. Convolutional Neural Networks with 3D convolutions (3D-CNN) have been used to build an accurate classification model. With the help of 3D convolutions, spectral and spatial features within the hyperspectral cube are incorporated to train a strong classifier. Unlike 2D convolutions, 3D convolutions take the spectral dimension into account while automatically collecting distinctive features during the CNN training stage. As a result, we have avoided manual feature engineering on hyperspectral data and proposed a compact method for HSI medical applications. Moreover, the focal loss function, utilized as a CNN cost function, enables our model to tackle the class imbalance problem residing in the dataset effectively. The focal loss function emphasizes the hard examples to learn and prevents overfitting due to the lack of inter-class balancing. Our empirical results demonstrate the superiority of hyperspectral data over RGB data for liver cancer tissue classification. We have observed that increased spectral dimension results in higher classification accuracy. Both spectral and spatial features are essential in training an accurate learner for cancer tissue classification.

Non-Destructive Hyperspectral Imaging for Rapid Determination of Catalase Activity and Ageing Visualization of Wheat Stored for Different Durations

(1) In order to accurately judge the new maturity of wheat and better serve the collection, storage, processing and utilization of wheat, it is urgent to explore a fast, convenient and non-destructively technology. (2) Methods: Catalase activity (CAT) is an important index to evaluate the ageing of wheat. In this study, hyperspectral imaging technology (850-1700 nm) combined with a BP neural network (BPNN) and a support vector machine (SVM) were used to establish a quantitative prediction model for the CAT of wheat with the classification of the ageing of wheat based on different storage durations. (3) Results: The results showed that the model of 1ST-SVM based on the full-band spectral data had the best prediction performance (R² = 0.9689). The SPA extracted eleven characteristic bands as the optimal wavelengths, and the established model of MSC-SPA-SVM showed the best prediction result with R² = 0.9664. (4) Conclusions: The model of MSC-SPA-SVM was used to visualize the CAT distribution of wheat ageing. In conclusion, hyperspectral imaging technology can be used to determine the CAT content and evaluate wheat ageing, rapidly and non-destructively.

Imaging perfusion changes in oncological clinical applications by hyperspectral imaging: a literature review

BACKGROUND

Hyperspectral imaging (HSI) is a promising imaging modality that uses visible light to obtain information about blood flow. It has the distinct advantage of being noncontact, nonionizing, and noninvasive without the need for a contrast agent. Among the many applications of HSI in the medical field are the detection of various types of tumors and the evaluation of their blood flow, as well as the healing processes of grafts and wounds. Since tumor perfusion is one of the critical factors in oncology, we assessed the value of HSI in quantifying perfusion changes during interventions in clinical oncology through a systematic review of the literature.

MATERIALS AND METHODS

The PubMed and Web of Science electronic databases were searched using the terms "hyperspectral imaging perfusion cancer" and "hyperspectral imaging resection cancer". The inclusion criterion was the use of HSI in clinical oncology, meaning that all animal, phantom, ex vivo, experimental, research and development, and purely methodological studies were excluded.

RESULTS

Twenty articles met the inclusion criteria. The anatomic locations of the neoplasms in the selected articles were as follows: kidneys (1 article), breasts (2 articles), eye (1 article), brain (4 articles), entire gastrointestinal (GI) tract (1 article), upper GI tract (5 articles), and lower GI tract (6 articles).

CONCLUSIONS

HSI is a potentially attractive imaging modality for clinical application in oncology, with assessment of mastectomy skin flap perfusion after reconstructive breast surgery and anastomotic perfusion during reconstruction of gastrointenstinal conduit as the most promising at present.

Intelligent detection for fresh-cut fruit and vegetable processing: Imaging technology

Fresh-cut fruits and vegetables are healthy and convenient ready-to-eat foods, and the final quality is related to the raw materials and each step of the cutting unit. It is necessary to integrate suitable intelligent detection technologies into the production chain so as to inspect each operation to ensure high product quality. In this paper, several imaging technologies that can be applied online to the processing of fresh-cut products are reviewed, including: multispectral/hyperspectral imaging (M/HSI), fluorescence imaging (FI), X-ray imaging (XRI), ultrasonic imaging, thermal imaging (TI), magnetic resonance imaging (MRI), terahertz imaging, and microwave imaging (MWI). The principles, advantages, and limitations of these imaging technologies are critically summarized. The potential applications of these technologies in online quality control and detection during the fresh-cut processing are comprehensively discussed, including quality of raw materials, contamination of cutting equipment, foreign bodies mixed in the processing, browning and microorganisms of the cutting surface, quality/shelf-life evaluation, and so on. Finally, the challenges and future application prospects of imaging technology in industrialization are presented.

Spectroscopic techniques for authentication of animal origin foods

Milk and milk products, meat, fish and poultry as well as other animal derived foods occupy a pronounced position in human nutrition. Unfortunately, fraud in the food industry is common, resulting in negative economic consequences for customers as well as significant threats to human health and the external environment. As a result, it is critical to develop analytical tools that can quickly detect fraud and validate the authenticity of such products. Authentication of a food product is the process of ensuring that the product matches the assertions on the label and complies with rules. Conventionally, various comprehensive and targeted approaches like molecular, chemical, protein based, and chromatographic techniques are being utilized for identifying the species, origin, peculiar ingredients and the kind of processing method used to produce the particular product. Despite being very accurate and unimpeachable, these techniques ruin the structure of food, are labor intensive, complicated, and can be employed on laboratory scale. Hence the need of hour is to identify alternative, modern instrumentation techniques which can help in overcoming the majority of the limitations offered by traditional methods. Spectroscopy is a quick, low cost, rapid, non-destructive, and emerging approach for verifying authenticity of animal origin foods. In this review authors will envisage the latest spectroscopic techniques being used for detection of fraud or adulteration in meat, fish, poultry, egg, and dairy products. Latest literature pertaining to emerging techniques including their advantages and limitations in comparison to different other commonly used analytical tools will be comprehensively reviewed. Challenges and future prospects of evolving advanced spectroscopic techniques will also be descanted.

Recent advances in muscle food safety evaluation: Hyperspectral imaging analyses and applications

As there is growing interest in process control for quality and safety in the meat industry, by integrating spectroscopy and imaging technologies into one system, hyperspectral imaging, or chemical or spectroscopic imaging has become an alternative analytical technique that can provide the spatial distribution of spectrum for fast and nondestructive detection of meat safety. This review addresses the configuration of the hyperspectral imaging system and safety indicators of muscle foods involving biological, chemical, and physical attributes and other associated hazards or poisons, which could cause safety problems. The emphasis focuses on applications of hyperspectral imaging techniques in the safety evaluation of muscle foods, including pork, beef, lamb, chicken, fish and other meat products. Although HSI can provide the spatial distribution of spectrum, characterized by overtones and combinations of the C-H, N-H, and O-H groups using different combinations of a light source, imaging spectrograph and camera, there still needs improvement to overcome the disadvantages of HSI technology for further applications at the industrial level.

Design and Validation of a Custom-Made Laboratory Hyperspectral Imaging System for Biomedical Applications Using a Broadband LED Light Source

Hyperspectral imaging (HSI) is a promising optical modality that is already being used in numerous applications. Further expansion of the capabilities of HSI depends on the modularity and versatility of the systems, which would, inter alia, incorporate profilometry, fluorescence imaging, and Raman spectroscopy while following a rigorous calibration and verification protocols, thus offering new insights into the studied samples as well as verifiable, quantitative measurement results applicable to the development of quantitative metrics. Considering these objectives, we developed a custom-made laboratory HSI system geared toward biomedical applications. In this report, we describe the design, along with calibration, characterization, and verification protocols needed to establish such systems, with the overall goal of standardization. As an additional novelty, our HSI system uses a custom-built broadband LED-based light source for reflectance imaging, which is particularly important for biomedical applications due to the elimination of sample heating. Three examples illustrating the utility and advantages of the integrated system in biomedical applications are shown. Our attempt presents both the development of a custom-based laboratory HSI system with novel LED light source as well as a framework which may improve technological standards in HSI system design.

Experimental data manipulations to assess performance of hyperspectral classification models of crop seeds and other objects

BACKGROUND

Optical sensing solutions are being developed and adopted to classify a wide range of biological objects, including crop seeds. Performance assessment of optical classification models remains both a priority and a challenge.

METHODS

As training data, we acquired hyperspectral imaging data from 3646 individual tomato seeds (germination yes/no) from two tomato varieties. We performed three experimental data manipulations: (1) Object assignment error: effect of individual object in the training data being assigned to the wrong class. (2) Spectral repeatability: effect of introducing known ranges (0-10%) of stochastic noise to individual reflectance values. (3) Size of training data set: effect of reducing numbers of observations in training data. Effects of each of these experimental data manipulations were characterized and quantified based on classifications with two functions [linear discriminant analysis (LDA) and support vector machine (SVM)].

RESULTS

For both classification functions, accuracy decreased linearly in response to introduction of object assignment error and to experimental reduction of spectral repeatability. We also demonstrated that experimental reduction of training data by 20% had negligible effect on classification accuracy. LDA and SVM classification algorithms were applied to independent validation seed samples. LDA-based classifications predicted seed germination with RMSE = 10.56 (variety 1) and 26.15 (variety 2), and SVM-based classifications predicted seed germination with RMSE = 10.44 (variety 1) and 12.58 (variety 2).

CONCLUSION

We believe this study represents the first, in which optical seed classification included both a thorough performance evaluation of two separate classification functions based on experimental data manipulations, and application of classification models to validation seed samples not included in training data. Proposed experimental data manipulations are discussed in broader contexts and general relevance, and they are suggested as methods for in-depth performance assessments of optical classification models.

Differentiation of Livestock Internal Organs Using Visible and Short-Wave Infrared Hyperspectral Imaging Sensors

Automatic identification and sorting of livestock organs in the meat processing industry could reduce costs and improve efficiency. Two hyperspectral sensors encompassing the visible (400-900 nm) and short-wave infrared (900-1700 nm) spectra were used to identify the organs by type. A total of 104 parenchymatous organs of cattle and sheep (heart, kidney, liver, and lung) were scanned in a multi-sensory system that encompassed both sensors along a conveyor belt. Spectral data were obtained and averaged following manual markup of three to eight regions of interest of each organ. Two methods were evaluated to classify organs: partial least squares discriminant analysis (PLS-DA) and random forest (RF). In addition, classification models were obtained with the smoothed reflectance and absorbance and the first and second derivatives of the spectra to assess if one was superior to the rest. The in-sample accuracy for the visible, short-wave infrared, and combination of both sensors was higher for PLS-DA compared to RF. The accuracy of the classification models was not significantly different between data pre-processing methods or between visible and short-wave infrared sensors. Hyperspectral sensors, particularly those in the visible spectrum, seem promising to identify organs from slaughtered animals which could be useful for the automation of quality and process control in the food supply chain, such as in abattoirs.

Detection of food fraud of meat products from the different brands by application of histological methods

In Sohag City, 400 samples were collected from different food markets of different meat products from two companies with high and low prices (e.g., minced meat, kofta sausage, beef burger, and luncheon meat) for determining food fraud. Light, fluorescence, and scanning electron microscopy (SEM) were used to examine the samples. "Special histochemical stains" permit the microscopic examination of different cell types, structures, and/or microorganisms. Histological examination revealed variant tissue types, besides skeletal muscles. Nuchal ligaments, bones, hyaline cartilages, white fibrocartilages, large and medium arteries, cardiac muscles, tendons, and collagenous connective tissues comprised the capsule of a parenchymatous organ. Additionally, a crystal of food additives was recognized using light microscopy and SEM. SEM allows the visualization of bacterial contamination. Using different microscopic anatomy techniques is an efficient methodology for qualitative evaluations of various meat products. No difference in quality was observed between low- and high-priced meat products.

Optical imaging spectroscopy for rapid, primary screening of SARS-CoV-2: a proof of concept

Effective testing is essential to control the coronavirus disease 2019 (COVID-19) transmission. Here we report a-proof-of-concept study on hyperspectral image analysis in the visible and near-infrared range for primary screening at the point-of-care of SARS-CoV-2. We apply spectral feature descriptors, partial least square-discriminant analysis, and artificial intelligence to extract information from optical diffuse reflectance measurements from 5 µL fluid samples at pixel, droplet, and patient levels. We discern preparations of engineered lentiviral particles pseudotyped with the spike protein of the SARS-CoV-2 from those with the G protein of the vesicular stomatitis virus in saline solution and artificial saliva. We report a quantitative analysis of 72 samples of nasopharyngeal exudate in a range of SARS-CoV-2 viral loads, and a descriptive study of another 32 fresh human saliva samples. Sensitivity for classification of exudates was 100% with peak specificity of 87.5% for discernment from PCR-negative but symptomatic cases. Proposed technology is reagent-free, fast, and scalable, and could substantially reduce the number of molecular tests currently required for COVID-19 mass screening strategies even in resource-limited settings.

Application of hyperspectral imaging technology in the rapid identification of microplastics in farmland soil

Microplastics (MPs) are emerging environmental pollutants and their accumulation in the soil can adversely affect the soil biota. This study aims to employ hyperspectral imaging technology for the rapid screening and classification of MPs in farmland soil. In this study, a total of 600 hyperspectral data are collected from 180 sets of farmland soil samples with a hyperspectral imager in the wavelength range of 369- 988 nm. To begin, the hyperspectral data are preprocessed by the Savitzky-Golay (S-G) smoothing filter and mean normalization. Second, principal component analysis (PCA) is used to minimize the dimensions of the hyperspectral data and hence the amount of data, making the subsequent model easier to construct. The cumulative contribution rate of the first three principal components is reached 98.37%, including the main information of the original spectral data. Finally, three models including decision tree (DT), support vector machine (SVM), and convolutional neural network (CNN) are established, all of which can achieve well classification effects on three MP polymers including polyethylene (PE), polypropylene (PP), and polyvinyl chloride (PVC) in farmland soil. By comparing the recognition accuracy of the three models, the classification accuracy of DT and SVM is 87.9% and 85.6%, respectively. The CNN model based on the S-G smoothing filter obtains the best prediction effect, the classification accuracy reaches 92.6%, exhibiting obvious advantages in classification effect. Altogether, these results show that the proposed hyperspectral imaging technique identifies the soil MPs rapidly and nondestructively, and provides an effective automated method for the detection of polymers, requiring only rapid and simple sample preparation.

A novel proposal to investigate the interplay between the spatial and spectral domains in near-infrared spectral imaging data by means of Image Decomposition, Encoding and Localization (IDEL)

The emergence of new spectral imaging applications in many science fields and in industry has not come to be a surprise, considering the immense potential this technique has to map spectral information. In the case of near-infrared spectral imaging, a rapid evolution of the technology has made it more and more appealing in non-destructive analysis of food and materials as well as in process monitoring applications. However, despite its great diffusion, some challenges remain open from the data analysis point of view, with the aim to fully uncover patterns and unveil the interplay between both the spatial and spectral domains. Here we propose a new approach, called Image Decomposition, Encoding and Localization (IDEL), where a spatial perspective is taken for the analysis of spectral images, while maintaining the significant information within the spectral domain. The methodology benefits from wavelet transform to exploit spatial features, encoding the outcoming images into a set of descriptors and utilizing multivariate analysis to isolate and extract the significant spatial-spectral information. A forensic case study of near-infrared images of biological stains on cotton fabrics is used as a benchmark. The stain and fabric have hardly distinguishable spectral signatures due to strong scattering effects that originate from the rough surface of the fabric and the high spectral absorbance of cotton in the near-infrared range. There is no selective information that can isolate signals related to these two components in the spectral images under study, and the complex spatial structure is highly interconnected to the spectral signatures. IDEL was capable of isolating the stains, (spatial) scattering effects, and a possible drying effect from the stains. It was possible to recover, at the same time, specific spectral regions that mostly highlight these isolated spatial structures, which was previously unobtainable.

Nutritional composition changes in bell pepper as affected by the ripening stage of fruits at harvest or postharvest storage and assessed non-destructively

BACKGROUND

Nutritional quality in bell pepper is related to the ripening stage of the fruit at harvest and postharvest storage. Its determination requires time-consuming, tissue-destructive, analytical laboratory techniques. The objective of this study was to investigate the effect of ripening stage and of postharvest storage period on fruit nutritional quality, and whether it is feasible to develop reliable models for assessing the nutritional components in peppers using non-destructive methods. The dry matter, soluble solids, ascorbic acid, phenolics, chlorophylls, carotenoids and the total antioxidant capacity were determined in bell pepper fruits at six ripening stages, from green to full red, during storage at 10 °C for 8 days. Color, chlorophyll fluorescence, visible/near infrared (Vis/NIR) spectroscopy, red-green-blue (R-G-B) and red-green-near infrared (R-G-NIR) digital imaging were tested for assessing the nutritional quality of peppers.

RESULTS

The nutritional composition was mainly affected by the ripening stage of bell pepper fruits at harvest and only to a small degree by the storage period. Indeed, the more advanced ripening stage of fruit at harvest resulted in superior nutritional quality. Most of the non-destructive techniques reliably predicted the internal quality of the fruit. The genetic algorithm (GA), the variable importance in projection (VIP) scores, and the variable inflation factor (VIF) tests identified nine distinct regions and four specific wavelengths on the whole visible/NIR electromagnetic spectrum that exhibited the most significant effect in the assessment of the nutritional components.

CONCLUSION

It is possible to predict individual nutritional components in bell pepper fruit reliably and non-destructively, and irrespective of the ripening stage of fruits at harvest. © 2021 Society of Chemical Industry.

Early pregnancy diagnosis of rabbits: A non-invasive approach using Vis-NIR spatially resolved spectroscopy

Pregnancy diagnosis is essential for rabbit's reproductive management. The early identification of non-pregnant rabbits allows for earlier re-insemination, increases the service rate, and reduces the laboring interval in commercial operations. The objective of this study was to establish the feasibility of using a Vis-NIR spatially resolved spectroscopy for diagnosing pregnancy in female rabbits. A total of 141 female rabbits, including 67 pregnant female rabbits (PRs) and 74 non-pregnant female rabbits (NPRs), were measured spectrally between 350 and 1000 nm with different source-detector distances (SDD). Different preprocessing methods were used to transform and enhance the spectral signal. A partial least squares-discriminant analysis (PLS-DA) classification model of the original and preprocessed spectra was established. The highest accuracy of the calibration set and prediction set was 91.75% and 86.05%, respectively. Competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA) were used to select characteristic wavelengths from the variables of VIP > 1 (Variable importance in projection),and four classification models were established based on selected wavelengths, including PLS-DA, support vector machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes. SPA-SVM was the optimal classification model, the sensitivity, specificity, and accuracy of the validation set and prediction set were 93.18%, 94.44%, 93.88%, 86.96%, 90.00%, 90.69% respectively. The results showed that Vis-NIR spatially resolved spectroscopy combined with classification models could discriminate the PRs and NPRs.

Leveraging high-throughput hyperspectral imaging technology to detect cadmium stress in two leafy green crops and accelerate soil remediation efforts

Cadmium (Cd) is a toxic metal that can accumulate in soils and negatively impact crop as well as human health. Amendments like biochar have potential to address these challenges by reducing Cd bioavailability in soil, though reliance on post-harvest wet chemical methods to quantify Cd uptake have slowed efforts to identify the most effective amendments. Hyperspectral imaging (HSI) is a novel technology that could overcome this limitation by quantifying symptoms of Cd stress while plants are still growing. The goals of this study were to: 1) determine whether HSI can detect Cd stress in two distinct leafy green crops, 2) quantify whether a locally sourced biochar derived from hardwoods can reduce Cd stress and uptake in these crops, and 3) identify vegetative indices (VIs) that best quantify changes in plant stress responses. Experiments were conducted in a tightly controlled automated phenotyping facility that allowed all environmental factors to be kept constant except Cd concentration (0, 5 10 and 15 mg kg^-1). Symptoms of Cd stress were stronger in basil (Ocimum basilicum) than kale (Brassica oleracea), and were easier to detect using HSI. Several VIs detected Cd stress in basil, but only the anthocyanin reflectance index (ARI) detected all levels of Cd stress in both crop species. The biochar amendment did reduce Cd uptake, especially at low Cd concentrations in kale which took up more Cd than basil. Again, the ARI index was the most effective in quantifying changes in plant stress mediated by the biochar. These results indicate that the biochar evaluated in this study has potential to reduce Cd bioavailability in soil, and HSI could be further developed to identify rates that can best achieve this benefit. The technology also may be helping in elucidating mechanisms mediating how biochar can influence plant growth and stress responses.

Reflectance based non-destructive determination of colour and ripeness of tomato fruits

The preference and quality of tomato fruit are primarily determined by its apparent colour and appearance. Non-destructive and rapid methods for assessment of tomato colour and ripeness are therefore of immense significance. This study was conducted to identify reflectance-based indices and to develop models for the non-destructive determination of colour and ripeness (maturity) of tomato fruits. Tomato fruits of two varieties and two hybrids, representing different ripening stages were investigated. Fruits were either harvested directly from the plants or they were picked up from the lots stored at 25 °C. Reflectance from individual fruit was recorded in a spectrum ranging from 350 to 2500 nm. These fruits at different ripening stages were ranked on a relative ripening score (0.0-8.5). Obtained data (reflectance and ripening score) were subjected to chemometric analysis. In total, six models were developed. The first-best model was based on the index R₅₂₁ (reflectance at wavelength 521 nm) i.e., y (colour/ripeness) =  - 2.456 ln (x) - 1.093 where x is R₅₂₁. This model had a root mean standard error of prediction (RMSEP) ≥ 0.86 and biasness =  - 0.09. The second-best model y = 2.582 ln (x) - 0.805 was based on the index R₅₄₆ (x) and had RMSEP ≥ 0.89 and biasness = 0.10. Models could bifurcate tomatoes into basic ripening stages and also red and beyond red tomato fruits from other stages across the varieties/hybrids and ripening conditions [for plant harvested (fresh) and stored (aged) fruits]. Findings will prove useful in developing simple and thereby cost-effective tools for rapid screening/sorting of tomato fruits based on their colour or ripeness not only for basic research (phenotyping) but also for the purpose of processing, value-addition, and pharmaceutical usages.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s12298-022-01126-2.

Radiofrequency Ablation for Liver: Comparison between Expert Eye and Hyperspectral Imaging Assessment

Liver/hepatic cancer (HC) is a disease that roughly afflicts 10% of cancer patients worldwide. HC is in charge of the death of 0.8 million patients on the earth. Multiple approaches, including thermal ablation, target the treatment of HC. In this study, we investigated radiofrequency (RF) ablation. Expert clinicians' visual assessment (VA) dominantly evaluated the outcome of ablation. Inattentively, the disfavors of VA are being subjective and eye-acuity dependent. In support, we propose hyperspectral imaging (HSI) for objective assessment of liver ablation. To verify our proposal, we computed the ablated liver area using VA and HSI. Unfortunately, HSI is a time-intensive technique. To make it less intensive, we present a way of reducing data analysis time. Saving time permits medical decisions, likewise continue or stop RF ablation, to be taken safer and faster. The way to reduce the time for HSI data analysis depends on narrowing the spectral bands of interest to only the most relevant ones to liver chromophores. Liver chromophores change in concentration because of thermal ablation. VA hardly senses these changes, however, HSI does it. Ultimately, the spectral band centered at 630 nm is optimal for objectively support RF ablation decision-makers.

Intelligent Sensors for Sustainable Food and Drink Manufacturing

Food and drink is the largest manufacturing sector worldwide and has significant environmental impact in terms of resource use, emissions, and waste. However, food and drink manufacturers are restricted in addressing these issues due to the tight profit margins they operate within. The advances of two industrial digital technologies, sensors and machine learning, present manufacturers with affordable methods to collect and analyse manufacturing data and enable enhanced, evidence-based decision making. These technologies will enable manufacturers to reduce their environmental impact by making processes more flexible and efficient in terms of how they manage their resources. In this article, a methodology is proposed that combines online sensors and machine learning to provide a unified framework for the development of intelligent sensors that work to improve food and drink manufacturers' resource efficiency problems. The methodology is then applied to four food and drink manufacturing case studies to demonstrate its capabilities for a diverse range of applications within the sector. The case studies included the monitoring of mixing, cleaning and fermentation processes in addition to predicting key quality parameter of crops. For all case studies, the methodology was successfully applied and predictive models with accuracies ranging from 95 to 100% were achieved. The case studies also highlight challenges and considerations which still remain when applying the methodology, including efficient data acquisition and labelling, feature engineering, and model selection. This paper concludes by discussing the future work necessary around the topics of new online sensors, infrastructure, data acquisition and trust to enable the widespread adoption of intelligent sensors within the food and drink sector.

Determination of Sugar, pH, and Anthocyanin Contents in Port Wine Grape Berries through Hyperspectral Imaging: An Extensive Comparison of Linear and Non-Linear Predictive Methods

This paper presents an extended comparison study between 16 different linear and non-linear regression methods to predict the sugar, pH, and anthocyanin contents of grapes through hyperspectral imaging (HIS). Despite the numerous studies on this subject that can be found in the literature, they often rely on the application of one or a very limited set of predictive methods. The literature on multivariate regression methods is quite extensive, so the analytical domain explored is too narrow to guarantee that the best solution has been found. Therefore, we developed an integrated linear and non-linear predictive analytics comparison framework (L&NL-PAC), fully integrated with five preprocessing techniques and five different classes of regression methods, for an effective and robust comparison of all alternatives through a robust Monte Carlo double cross-validation stratified data splitting scheme. L&NLPAC allowed for the identification of the most promising preprocessing approaches, best regression methods, and wavelengths most contributing to explaining the variability of each enological parameter for the target dataset, providing important insights for the development of precision viticulture technology, based on the HSI of grape. Overall, the results suggest that the combination of the Savitzky−Golay first derivative and ridge regression can be a good choice for the prediction of the three enological parameters.

Review on Active and Passive Remote Sensing Techniques for Road Extraction

Digital maps of road networks are a vital part of digital cities and intelligent transportation. In this paper, we provide a comprehensive review on road extraction based on various remote sensing data sources, including high-resolution images, hyperspectral images, synthetic aperture radar images, and light detection and ranging. This review is divided into three parts. Part 1 provides an overview of the existing data acquisition techniques for road extraction, including data acquisition methods, typical sensors, application status, and prospects. Part 2 underlines the main road extraction methods based on four data sources. In this section, road extraction methods based on different data sources are described and analysed in detail. Part 3 presents the combined application of multisource data for road extraction. Evidently, different data acquisition techniques have unique advantages, and the combination of multiple sources can improve the accuracy of road extraction. The main aim of this review is to provide a comprehensive reference for research on existing road extraction technologies.

Hyperspectral Imaging as a Potential Online Detection Method of Microplastics

Microplastic pollution in aquatic environment has raised concern and as a result a number of studies have recently been published to find solutions for its rapid increase. Different methods have been proposed for microplastic identification. Spectral imaging shows a lot of promise for polymer identification; however, the identification time needs to be improved. Hyperspectral imaging (HSI) combined with chemometric analysis can reduce the identification times. In this study, we provide a review of recent studies related to polymer identification using HSI with a focus on the adopted classification algorithm and its factors for the online implementation of HSI. Furthermore, we review the limit of detection by HSI and the effect of particle size on classification accuracy. Additionally, performance of this method for various types of samples is also discussed. We conclude that HSI is possible to be a fast alternative for online microplastic detection.

Food Tray Sealing Fault Detection in Multi-Spectral Images Using Data Fusion and Deep Learning Techniques

A correct food tray sealing is required to preserve food properties and safety for consumers. Traditional food packaging inspections are made by human operators to detect seal defects. Recent advances in the field of food inspection have been related to the use of hyperspectral imaging technology and automated vision-based inspection systems. A deep learning-based approach for food tray sealing fault detection using hyperspectral images is described. Several pixel-based image fusion methods are proposed to obtain 2D images from the 3D hyperspectral image datacube, which feeds the deep learning (DL) algorithms. Instead of considering all spectral bands in region of interest around a contaminated or faulty seal area, only relevant bands are selected using data fusion. These techniques greatly improve the computation time while maintaining a high classification ratio, showing that the fused image contains enough information for checking a food tray sealing state (faulty or normal), avoiding feeding a large image datacube to the DL algorithms. Additionally, the proposed DL algorithms do not require any prior handcraft approach, i.e., no manual tuning of the parameters in the algorithms are required since the training process adjusts the algorithm. The experimental results, validated using an industrial dataset for food trays, along with different deep learning methods, demonstrate the effectiveness of the proposed approach. In the studied dataset, an accuracy of 88.7%, 88.3%, 89.3%, and 90.1% was achieved for Deep Belief Network (DBN), Extreme Learning Machine (ELM), Stacked Auto Encoder (SAE), and Convolutional Neural Network (CNN), respectively.

Triple coding empowered FDMA-CDMA mode high-security CAOS camera

For the first time, to the best of our knowledge, the hybrid triple coding empowered frequency division multiple access (FDMA)-code division multiple access (CDMA) mode of the coded access optical sensor (CAOS) camera is demonstrated. Compared to the independent FDMA and CDMA modes, the FDMA-CDMA mode has a novel high-security space-time-frequency triple signal encoding design for robust, faster, linear irradiance extraction at a moderately high dynamic range (HDR). Specifically, this hybrid mode simultaneously combines the linear HDR strength of the FDMA-mode fast Fourier transform (FFT) digital signal processing (DSP)-based spectrum analysis with the high signal-to-noise ratio (SNR) provided by the many simultaneous CAOS pixels' photodetection of the CDMA mode. In particular, the demonstrated FDMA-CDMA mode with P FDMA channels provides a P times faster camera operation versus the equivalent linear HDR frequency modulation (FM)-CDMA mode. Visible band imaging experiments using a digital-micromirror-device-based CAOS camera operating in its passive light mode demonstrates a P=4 channels FDMA-CDMA mode, illustrating high-quality image recovery of a calibrated 64 dB six-patch HDR target versus the CDMA and FM-CDMA CAOS modes, which limit dynamic range and speed, respectively. For the first time to our knowledge, we demonstrate the simultaneous dual image capture capability of the FDMA-CDMA mode using silicon (Si) and germanium (Ge) large-area point photodetectors, allowing the capture of the ultraviolet-near-infrared 350-1,800 nm full spectrum. The active FDMA-CDMA mode CAOS camera operation is also demonstrated using P=3 LED light sources, each with its unique optical spectral content driven by its independent FDMA frequency. This illuminated target spectral signature matched active CAOS mode allows simultaneous capture of P images without the use of P time-multiplexed slot operation tunable optical filters. Applications for such a FDMA-CDMA camera includes controlled light illumination food inspection to bright light exposure security systems.

Hyperspectral image processing for the identification and quantification of lentiviral particles in fluid samples

Optical spectroscopic techniques have been commonly used to detect the presence of biofilm-forming pathogens (bacteria and fungi) in the agro-food industry. Recently, near-infrared (NIR) spectroscopy revealed that it is also possible to detect the presence of viruses in animal and vegetal tissues. Here we report a platform based on visible and NIR (VNIR) hyperspectral imaging for non-contact, reagent free detection and quantification of laboratory-engineered viral particles in fluid samples (liquid droplets and dry residue) using both partial least square-discriminant analysis and artificial feed-forward neural networks. The detection was successfully achieved in preparations of phosphate buffered solution and artificial saliva, with an equivalent pixel volume of 4 nL and lowest concentration of 800 TU·\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\upmu$$\end{document}μL⁻¹. This method constitutes an innovative approach that could be potentially used at point of care for rapid mass screening of viral infectious diseases and monitoring of the SARS-CoV-2 pandemic.

Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts

Cereal grains and nuts are represented as the economic backbone of many developed and developing countries. Kernels of cereal grains and nuts are prone to mold infection under high relative humidity and suitable temperature conditions in the field as well as storage conditions. Health risks caused by molds and their molecular metabolite mycotoxins are, therefore, important topics to investigate. Strict regulations have been developed by international trade regulatory bodies for the detection of mold growth and mycotoxin contamination across the food chain starting from the harvest to storage and consumption. Molds and aflatoxins are not evenly distributed over the bulk of grains, thus appropriate sampling for detection and quantification is crucial. Existing reference methods for mold and mycotoxin detection are destructive in nature as well as involve skilled labor and hazardous chemicals. Also, these methods cannot be used for inline sorting of the infected kernels. Thus, analytical methods have been extensively researched to develop the one that is more practical to be used in commercial detection and sorting processes. Among various analytical techniques, optical imaging and spectroscopic techniques are attracting growers' attention for their potential of nondestructive and rapid inline identification and quantification of molds and mycotoxins in various food products. This review summarizes the recent application of rapid and nondestructive optical imaging and spectroscopic techniques, including digital color imaging, X-ray imaging, near-infrared spectroscopy, fluorescent, multispectral, and hyperspectral imaging. Advance chemometric techniques to identify very low-level mold growth and mycotoxin contamination are also discussed. Benefits, limitations, and challenges of deploying these techniques in practice are also presented in this paper.

High Precision Monitoring of Radiofrequency Ablation for Liver Using Hyperspectral Imaging

Minimally invasive procedures are achieving better satisfaction for treating liver cancers. Energy-based techniques were studied as prospective alternatives to the gold standard of liver transplantation. Among these techniques, radiofrequency (RF) was investigated for the selective ablation of liver tissue. In addition to optimizing the RF settings for the purpose of overcoming tissue perforation or inadequate ablation, an instrument collecting quantitative data regarding the intraoperative tissue status can aid the treatment procedure. This study demonstrates an innovative noninvasive technique using hyperspectral imaging (HSI) for monitoring RF ablative therapy in ex-vivo liver tissue. The cubic data generated by HSI provides spectral as well as spatial properties of the liver tissue included in each pixel of the field of view. In our study, the applied statistical analysis saves the computational burdens of multivariate analysis techniques. For this purpose, spectral angle mapper, logistic regression algorithm, and principal component analysis were applied. Of all spectral bands captured by the HSI camera, bands centered at 760 and 960 nm were identified for predicting the ablated area. Based on statistical analysis, the threshold for predicting the ablated area of the liver samples was determined, provided that the specificity is kept at 90%.

Hyperspectral autofluorescence characterization of drusen and sub-RPE deposits in age-related macular degeneration

Background:

Soft drusen and basal linear deposit (BLinD) are two forms of the same extracellular lipid rich material that together make up an Oil Spill on Bruch’s membrane (BrM). Drusen are focal and can be recognized clinically. In contrast BLinD is thin and diffusely distributed, and invisible clinically, even on highest resolution OCT, but has been detected on en face hyperspectral autofluorescence (AF) imaging ex vivo. We sought to optimize histologic hyperspectral AF imaging and image analysis for recognition of drusen and sub-RPE deposits (including BLinD and basal laminar deposit), for potential clinical application.

Methods:

Twenty locations specifically with drusen and 12 additional locations specifically from fovea, perifovea and mid-periphery from RPE/BrM flatmounts from 4 AMD donors underwent hyperspectral AF imaging with 4 excitation wavelengths (λ_ex 436, 450, 480 and 505 nm), and the resulting image cubes were simultaneously decomposed with our published non-negative matrix factorization (NMF). Rank 4 recovery of 4 emission spectra was chosen for each excitation wavelength.

Results:

A composite emission spectrum, sensitive and specific for drusen and presumed sub-RPE deposits (the SDr spectrum) was recovered with peak at 510–520 nm in all tissues with drusen, with greatest amplitudes at excitations λ_ex 436, 450 and 480 nm. The RPE spectra of combined sources Lipofuscin (LF)/Melanolipofuscin (MLF) were of comparable amplitude and consistently recapitulated the spectra S1, S2 and S3 previously reported from all tissues: tissues with drusen, foveal and extra-foveal locations.

Conclusions:

A clinical hyperspectral AF camera, with properly chosen excitation wavelengths in the blue range and a hyperspectral AF detector, should be capable of detecting and quantifying drusen and sub-RPE deposits, the earliest known lesions of AMD, before any other currently available imaging modality.

Investigating the Effect of Different Drying Strategies on the Quality Parameters of Daucus carota L. Using Dynamic Process Control and Measurement Techniques

The present work aims to improve the understanding of the effect of different drying strategies at varying temperatures on the dynamic drying behaviour and quality of organic products such as carrots using non-invasive measurement techniques. For this purpose, carrot slices of 3 mm thickness were dried under three different strategies namely air temperature controlled (A), product temperature controlled (P) and stepwise temperature controlled (S) at different temperatures (50 °C, 60 °C and 70 °C) to measure and analyse the changes in moisture content, colour, total carotenoid retention, water activity, rehydration ratio and specific energy consumption. From the investigation performed, it was incurred that the application of different drying strategies influences rather significantly both the product quality as well as the overall process efficiency. Modelling the drying curves deemed Page model to be a good fit for all the strategies with R2adj = 0.99 and RMSE = 0.01. The results also show that implementing strategy P not only led to shorter drying times but also led to higher total carotenoid retention within the samples (TCR = 0.59–0.73). Colour changes, however, were observed to be maximum with strategy P as compared to strategy A and strategy S. Furthermore, the use of a non-invasive measurement technique such as infrared camera proved to be reliable in order to detect the phase transition of the product during the drying process.

Hyperspectral imaging assessment for radiotherapy induced skin-erythema: Pilot study

Skin cancer (SC) is a widely spread disease in the USA, Canada, and Australia. Skin cancer patients may be treated by many different techniques including radiation therapy. However, radiation therapy has side effects, which may range from skin erythema to skin necrosis. As erythema is the early evidence of exposure to radiation, monitoring erythema is important to prevent more severe reactions. Visual assessment (VA) is the gold standard for evaluating erythema. Nevertheless, VA is not ideal, since it depends on the observer's experience and skills. Digital photography and hyperspectral imaging (HSI) are optical techniques that provide an opportunity for objective assessment of erythema. Erythema indices were computed from the spectral data using Dawson's technique. The Dawson relative erythema index proved to be highly correlated (97.1 %) with clinical visual assessment scores. In addition, on the 7th session of radiation therapy, the relative erythema index differentiates with 99 % significance between irradiated and non-radiated skin regions. In this study, HSI is compared to digital photography for skin erythema statistical classification.

Nondestructive Detection of Authenticity of Thai Jasmine Rice Using Multispectral Imaging

The detection of authenticity is essential to the development and management of Thai jasmine rice industry. In this study, the multispectral imaging system (405–970 nm) was used for the detection of adulteration in Thai jasmine rice combined with chemometric methods including principal component analysis (PCA), partial least squares (PLS), least squares-support vector machines (LS-SVM), and backpropagation neural network (BPNN). Three varieties of rice that were similar to Thai jasmine rice in appearance were selected to perform the classification and quantitative prediction experiments by multispectral images. For the classification experiment, four varieties of rice samples could be easily classified with accuracy achieved to 92% by the BPNN model. For the quantitative prediction of adulteration proportion experiments, the results showed that, among the different chemometric methods, LS-SVM achieved the best prediction performance comparing the results of coefficient of determination, root-mean-square error (RMSEP), bias, and residual predictive deviation (RPD). It can be concluded that multispectral imaging technology with chemometric methods can be applied in the rapid and nondestructive detection of authenticity of Thai jasmine rice.

Determining Sonication Effect on E. coli in Liquid Egg, Egg Yolk and Albumen and Inspecting Structural Property Changes by Near-Infrared Spectra

In this study, liquid egg, albumen, and egg yolk were artificially inoculated with E. coli. Ultrasound equipment (20/40 kHz, 180/300 W; 30/45/60 min) with a circulation cooling system was used to lower the colony forming units (CFU) of E. coli samples. Frequency, absorbed power, energy dose, and duration of sonication showed a significant impact on E. coli with 0.5 log CFU/mL in albumen, 0.7 log CFU/mL in yolk and 0.5 log CFU/mL decrease at 40 kHz and 6.9 W absorbed power level. Significant linear correlation (p < 0.001) was observed between the energy dose of sonication and the decrease of E. coli. The results showed that sonication can be a useful tool as a supplementary method to reduce the number of microorganism in egg products. With near-infrared (NIR) spectra analysis we were able to detect the structural changes of the egg samples, due to ultrasonic treatment. Principal component analysis (PCA) showed that sonication can alter C-H, C-N, -OH and N-H bonds in egg. The aquagrams showed that sonication can alter the properties of H₂O structure in egg products. The observed data showed that the absorbance of free water (1412 nm), water molecules with one (1440 nm), two (1462 nm), three (1472 nm) and four (1488 nm) hydrogen bonds, water solvation shell (1452 nm) and strongly bonded water (1512 nm) of the egg samples have been changed during ultrasonic treatment.

GhoMR: Multi-Receptive Lightweight Residual Modules for Hyperspectral Classification

In recent years, hyperspectral images (HSIs) have attained considerable attention in computer vision (CV) due to their wide utility in remote sensing. Unlike images with three or lesser channels, HSIs have a large number of spectral bands. Recent works demonstrate the use of modern deep learning based CV techniques like convolutional neural networks (CNNs) for analyzing HSI. CNNs have receptive fields (RFs) fueled by learnable weights, which are trained to extract useful features from images. In this work, a novel multi-receptive CNN module called GhoMR is proposed for HSI classification. GhoMR utilizes blocks containing several RFs, extracting features in a residual fashion. Each RF extracts features which are used by other RFs to extract more complex features in a hierarchical manner. However, the higher the number of RFs, the greater the associated weights, thus heavier is the network. Most complex architectures suffer from this shortcoming. To tackle this, the recently found Ghost module is used as the basic building unit. Ghost modules address the feature redundancy in CNNs by extracting only limited features and performing cheap transformations on them, thus reducing the overall parameters in the network. To test the discriminative potential of GhoMR, a simple network called GhoMR-Net is constructed using GhoMR modules, and experiments are performed on three public HSI data sets—Indian Pines, University of Pavia, and Salinas Scene. The classification performance is measured using three metrics—overall accuracy (OA), Kappa coefficient (Kappa), and average accuracy (AA). Comparisons with ten state-of-the-art architectures are shown to demonstrate the effectiveness of the method further. Although lightweight, the proposed GhoMR-Net provides comparable or better performance than other networks. The PyTorch code for this study is made available at the iamarijit/GhoMR GitHub repository.