Meat Quality Evaluation by Hyperspectral Imaging Technique: An Overview

Learning to Recover Spectral Reflectance From RGB Images

This paper tackles spectral reflectance recovery (SRR) from RGB images. Since capturing ground-truth spectral reflectance and camera spectral sensitivity are challenging and costly, most existing approaches are trained on synthetic images and utilize the same parameters for all unseen testing images, which are suboptimal especially when the trained models are tested on real images because they never exploit the internal information of the testing images. To address this issue, we adopt a self-supervised meta-auxiliary learning (MAXL) strategy that fine-tunes the well-trained network parameters with each testing image to combine external with internal information. To the best of our knowledge, this is the first work that successfully adapts the MAXL strategy to this problem. Instead of relying on naive end-to-end training, we also propose a novel architecture that integrates the physical relationship between the spectral reflectance and the corresponding RGB images into the network based on our mathematical analysis. Besides, since the spectral reflectance of a scene is independent to its illumination while the corresponding RGB images are not, we recover the spectral reflectance of a scene from its RGB images captured under multiple illuminations to further reduce the unknown. Qualitative and quantitative evaluations demonstrate the effectiveness of our proposed network and of the MAXL. Our code and data are available at https://github.com/Dong-Huo/SRR-MAXL.

Recent advances in the color of aquatic products: Evaluation methods, discoloration mechanism, and protection technologies

Color plays a pivotal role in guiding and assessing the industrial production of aquatic products due to the swift sensory perception of information through vision. This review provides a comprehensive overview of the following four aspects: (a) mechanisms governing natural color formation in aquatic products, (b) factors and mechanisms contributing to the discoloration of aquatic products, (c) cutting-edge methods for color analysis and detection, and (d) current valuable techniques for preserving color quality. The natural color of aquatic products is derived from skin chromatophores, endogenous pigment proteins, and astaxanthin. Discoloration of aquatic products can occur due to lipid oxidation, as well as enzymatic and non-enzymatic browning. Furthermore, this review examines frontier color protective technologies, encompassing physical methods like ultra-high pressure, irradiation, and low-temperature plasma, as well as chemical methods involving natural preservatives. The findings of this study offer significant insights into the development of high-quality aquatic products.

Multispectral imaging: Review of current applications

Multispectral imaging (MSI) is a unique layer-by-layer imaging technique that allows the visualization of a wide array of retinal and choroidal pathologies including retinovascular disorders, retinal pigment epithelial changes, and choroidal lesions. Herein, we summarize the basic imaging principles and current applications of MSI together with recent technology advances in the field. MSI detects reflectance signal from both normal chorioretinal tissue and pathological lesions. Either hyperreflectance or hyporeflectance reveals the absorption activity of pigments such as hemoglobin and melanin and the reflection from interfaces such as the posterior hyaloid. Advances in MSI technique include creation of a retinal and choroidal oxy-deoxy map that could provide a better understanding of blood oxygen saturation within lesions as well as better interpretation of reflectance phenomenon of MSI images such as the different reflectance from the Sattler and Haller layers described in this review.

Systematic meta-analysis of computer-aided detection to detect early esophageal cancer using hyperspectral imaging

One of the leading causes of cancer deaths is esophageal cancer (EC) because identifying it in early stage is challenging. Computer-aided diagnosis (CAD) could detect the early stages of EC have been developed in recent years. Therefore, in this study, complete meta-analysis of selected studies that only uses hyperspectral imaging to detect EC is evaluated in terms of their diagnostic test accuracy (DTA). Eight studies are chosen based on the Quadas-2 tool results for systematic DTA analysis, and each of the methods developed in these studies is classified based on the nationality of the data, artificial intelligence, the type of image, the type of cancer detected, and the year of publishing. Deeks' funnel plot, forest plot, and accuracy charts were made. The methods studied in these articles show the automatic diagnosis of EC has a high accuracy, but external validation, which is a prerequisite for real-time clinical applications, is lacking.

Meat color and iridescence: Origin, analysis, and approaches to modulation

Meat color is an important aspect for the meat industry since it strongly determines the consumers' perception of product quality and thereby significantly influences the purchase decision. Emergence of new vegan meat analogs has renewed interest in the fundamental aspects of meat color in order to replicate it. The appearance of meat is based on a complex interplay between the pigment-based meat color from myoglobin and its chemical forms and light scattering from the muscle's microstructure. While myoglobin biochemistry and pigment-based meat color have been extensively studied, research on the physicochemical contribution of light scattering to meat color and the special case of structural colors causing meat iridescence has received only little attention. Former review articles focused mostly on the biochemical or physical mechanisms rather than the interplay between them, in particular the role that structural colors play. While from an economic point of view, meat iridescence might be considered negligible, an enhanced understanding of the underlying mechanisms and the interactions of light with meat microstructures can improve our overall understanding of meat color. Therefore, this review discusses both biochemical and physicochemical aspects of meat color including the origin of structural colors, highlights new color measurement methodologies suitable to investigate color phenomena such as meat iridescence, and finally presents approaches to modulate meat color in terms of base composition, additives, and processing.

Non-destructive prediction of colour and water-related properties of frozen/thawed beef meat by Raman spectroscopy coupled multivariate calibration

Freeze-thaw accelerated the colour deterioration of beef with the increase of colour b* and the decrease of colour a* values (P < 0.05). The maximum exudate loss reached 22 % after the seventh freeze-thaw. A strong correlation between the transversal relaxation time T₂₁ and thawing loss may mean that T₂₁ water contributed to the exudate loss during freeze-thaw. Afterwards, competitive adaptive reweighted sampling-partial least square (CARS-PLS) has the best prediction in thawing loss of frozen/thawed beef with correlation coefficients of prediction (R_p) of 0.971, and root mean square error of prediction (RMSEP) of 1.436. Besides, Uninformative variable elimination-partial least squares (UVE-PLS) showed good prediction effects on colour values (R_p = 0.932 - 0.994) and water content (R_p = 0.928, RMSEP = 0.582) of frozen/thawed beef. Therefore, this work demonstrated that Raman spectroscopy coupled with multivariate calibration has a good ability for non-destructive prediction in colour and water-related properties of frozen/thawed beef.

Hyperspectral Imaging of Adaxial and Abaxial Leaf Surfaces as a Predictor of Macadamia Crop Nutrition

Tree crop yield is highly dependent on fertiliser inputs, which are often guided by the assessment of foliar nutrient levels. Traditional methods for nutrient analysis are time-consuming but hyperspectral imaging has potential for rapid nutrient assessment. Hyperspectral imaging has generally been performed using the adaxial surface of leaves although the predictive performance of spectral data has rarely been compared between adaxial and abaxial surfaces of tree leaves. We aimed to evaluate the capacity of laboratory-based hyperspectral imaging (400-1000 nm wavelengths) to predict the nutrient concentrations in macadamia leaves. We also aimed to compare the prediction accuracy from adaxial and abaxial leaf surfaces. We sampled leaves from 30 macadamia trees at 0, 6, 10 and 26 weeks after flowering and captured hyperspectral images of their adaxial and abaxial surfaces. Partial least squares regression (PLSR) models were developed to predict foliar nutrient concentrations. Coefficients of determination (R²_P) and ratios of prediction to deviation (RPDs) were used to evaluate prediction accuracy. The models reliably predicted foliar nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), copper (Cu), manganese (Mn), sulphur (S) and zinc (Zn) concentrations. The best-fit models generally predicted nutrient concentrations from spectral data of the adaxial surface (e.g., N: R²_P = 0.55, RPD = 1.52; P: R²_P = 0.77, RPD = 2.11; K: R²_P = 0.77, RPD = 2.12; Ca: R²_P = 0.75, RPD = 2.04). Hyperspectral imaging showed great potential for predicting nutrient status. Rapid nutrient assessment through hyperspectral imaging could aid growers to increase orchard productivity by managing fertiliser inputs in a more-timely fashion.

Development of a Portable Near-Infrared Spectroscopy Tool for Detecting Freshness of Commercial Packaged Pork

Real-time monitoring of meat quality requires fast, accurate, low-cost, and non-destructive analytical methods that can be used throughout the entire production chain, including the packaged product. The aim of this work was to evaluate the potential of a portable near-infrared (NIR) spectroscopy tool for the on-site detection of freshness of pork loin fillets in modified atmosphere packaging (MAP) stored on display counters. Pork loin slices were sealed in MAP trays under two proportions of O2/CO2/N2: High-Ox-MAP (30/40/30) and Low-Ox-MAP (5/20/75). Changes in pH, color, thiobarbituric acid reactive substances (TBARS), Warner−Bratzler shear force (WBSF), and microbiology (total viable counts, Enteriobacteriaceae, and lactic acid bacteria) were monitored over 15 days post-mortem at 4 °C. VIS-NIR spectra were collected from pork fillets before (through the film cover) and after opening the trays (directly on the meat surface) with a portable LABSPEC 5000 NIR system in diffuse reflectance mode (350−2500 nm). Quantitative NIR models by partial least squares regression (PLSR) showed a promising prediction ability for meat color (L*, a*, C*, and h*) and microbiological variables (R2VAL > 0.72 and RPDVAL > 2). In addition, qualitative models using PLS discriminant analysis obtained good accuracy (over 90%) for classifying pork samples as fresh (acceptable for consumption) or spoiled (not acceptable) based on their microbiological counts. VIS-NIR spectroscopy allows rapid evaluation of product quality and shelf life and could be used for on-site control of pork quality.

Classification and Feature Extraction Using Supervised and Unsupervised Machine Learning Approach for Broiler Woody Breast Myopathy Detection

Bioelectrical impedance analysis (BIA) was established to quantify diverse cellular characteristics. This technique has been widely used in various species, such as fish, poultry, and humans for compositional analysis. This technology was limited to offline quality assurance/detection of woody breast (WB); however, inline technology that can be retrofitted on the conveyor belt would be more helpful to processors. Freshly deboned (n = 80) chicken breast fillets were collected from a local processor and analyzed by hand-palpation for different WB severity levels. Data collected from both BIA setups were subjected to supervised and unsupervised learning algorithms. The modified BIA showed better detection ability for regular fillets than the probe BIA setup. In the plate BIA setup, fillets were 80.00% for normal, 66.67% for moderate (data for mild and moderate merged), and 85.00% for severe WB. However, hand-held BIA showed 77.78, 85.71, and 88.89% for normal, moderate, and severe WB, respectively. Plate BIA setup is more effective in detecting WB myopathies and could be installed without slowing the processing line. Breast fillet detection on the processing line can be significantly improved using a modified automated plate BIA.

A Comparative Study on Microbiological and Chemical Characteristics of Small Ruminant Carcasses from Abattoirs in Greece

Meat quality dictates consumer preferences with hygiene forming a key component, especially in meat types with declining popularity, such as sheep and goat meat. Aiming to increase the marketability of sheep and goat meat, we examined 370 sheep and goat carcasses from two abattoirs in Greece. Tests included enumeration of the total mesophilic viable count, total psychrophilic viable count and coliform count, and detection of Salmonella spp., Listeria monocytogenes and presumptive ESBL Escherichia coli. Moreover, designated samples of meat were used to measure pH, moisture, total fat and protein content. Goat carcasses had significantly higher microbial counts compared to sheep carcasses. Lamb and kid carcasses had larger TMVC, TPVC and coliform counts compared to carcasses from adult animals. One strain of L. monocytogenes (0.8%), typed as serovar 1/2a (3a), was isolated from one adult sheep carcass. Twelve strains of ESBL Escherichia coli (25%) were isolated; there were not any strains of Salmonella spp. The average values of pH, moisture, total fat and total protein were 5.83%, 67.76%, 7.21% and 21.31%, respectively, for sheep carcasses and 5.70%, 68.2%, 5.69% and 24.10%, respectively, for goat carcasses. The results showed a small deviation in assessed parameters, implying the uniformity of the conditions concerning rearing and slaughtering.

CRISPR-Cas-based detection for food safety problems: Current status, challenges, and opportunities

Food safety is one of the biggest public issues occurring around the world. Microbiological, chemical, and physical hazards can lead to food safety issues, which may occur at all stages of the supply chain. In order to tackle food safety issues and safeguard consumer health, rapid, accurate, specific, and field-deployable detection methods meeting diverse requirements are one of the imperative measures for food safety assurance. CRISPR-Cas system, a newly emerging technology, has been successfully repurposed in biosensing and has demonstrated huge potential to establish conceptually novel detection methods with high sensitivity and specificity. This review focuses on CRISPR-Cas-based detection and its current status and huge potential specifically for food safety inspection. We firstly illustrate the pending problems in food safety and summarize the popular detection methods. We then describe the potential applications of CRISPR-Cas-based detection in food safety inspection. Finally, the challenges and futuristic opportunities are proposed and discussed. Generally speaking, the current food safety detection methods are still unsatisfactory in some ways such as being time-consuming, displaying unmet sensitivity and specificity standards, and there is a comparative paucity of multiplexed testing and POCT. Recent studies have shown that CRISPR-Cas-based biosensing is an innovative and fast-expanding technology, which could make up for the shortcomings of the existing methods or even replace them. To sum up, the implementation of CRISPR-Cas and the integration of CRISPR-Cas with other techniques is promising and desirable, which is expected to provide "customized" and "smart" detection methods for food safety inspection in the coming future.

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.

Live-cell fluorescence spectral imaging as a data science challenge

Live-cell fluorescence spectral imaging is an evolving modality of microscopy that uses specific properties of fluorophores, such as excitation or emission spectra, to detect multiple molecules and structures in intact cells. The main challenge of analyzing live-cell fluorescence spectral imaging data is the precise quantification of fluorescent molecules despite the weak signals and high noise found when imaging living cells under non-phototoxic conditions. Beyond the optimization of fluorophores and microscopy setups, quantifying multiple fluorophores requires algorithms that separate or unmix the contributions of the numerous fluorescent signals recorded at the single pixel level. This review aims to provide both the experimental scientist and the data analyst with a straightforward description of the evolution of spectral unmixing algorithms for fluorescence live-cell imaging. We show how the initial systems of linear equations used to determine the concentration of fluorophores in a pixel progressively evolved into matrix factorization, clustering, and deep learning approaches. We outline potential future trends on combining fluorescence spectral imaging with label-free detection methods, fluorescence lifetime imaging, and deep learning image analysis.

Developing an affordable hyperspectral imaging system for rapid identification of Escherichia coli O157:H7 and Listeria monocytogenes in dairy products

The objective of this foundational study was to develop and evaluate the efficacy of an affordable hyperspectral imaging (HSI) system to identify single and mixed strains of foodborne pathogens in dairy products. This study was designed as a completely randomized design with three replications. Three strains each of Escherichia coli O157:H7 and Listeria monocytogenes were evaluated either as single or mixed strains with the HSI system in growth media and selected dairy products (whole milk, and cottage and cheddar cheeses). Test samples from freshly prepared single or mixed strains of pathogens in growth media or inoculated dairy products were streaked onto selective media (PALCAM and/or Sorbitol MacConkey agar) for isolation. An isolated colony was selected and mixed with 1 ml of HPLC grade water, vortexed for 1 min, and spread over a microscope slide. Images were captured at 2000× magnification on the built HSI system at wavelengths ranging from 400 nm to 1100 nm with 5‐nm band intervals. For each image, three cells were selected as regions of interest (ROIs) to obtain hyperspectral signatures of respective bacteria. Reference pathogen libraries were created using growth media, and then test pathogenic cells were classified by their hyperspectral signatures as either L. monocytogenes or E. coli O157:H7 using k‐nearest neighbor (kNN) and cross‐validation technique in R‐software. With the implementation of kNN (k = 3), overall classification accuracies of 58.97% and 61.53% were obtained for E. coli O157:H7 and L. monocytogenes, respectively.

Effect of Breed and Finishing Diet on Chemical Composition and Quality Parameters of Meat from Burguete and Jaca Navarra Foals

The purpose of this study was to investigate the influence of breed, Jaca Navarra (JN) vs. Burguete (BU), and finishing diet, conventional concentrate and straw, diet 1 (D1), vs. silage and organic feed, diet 2 (D2), on chemical composition and quality parameters of the longissimus thoracis et lumborum muscle from forty-six foals. Animals were reared under a semi-extensive system and slaughtered at a mean age of 21 months. The results reported that both studied effects had a significant (p < 0.05) impact on meat quality; however, it was the breed to strongly influence the majority of the parameters evaluated. In particular, BU foals reported the highest amounts of intramuscular fat, positively affecting the meat properties of marbling and texture traits. Moreover, this group presented higher values for L* and b* and the lowest cholesterol contents. As regards the diet, D1 increased the fat content in foals supplemented with this diet, improving the organoleptic properties of this group. On the other hand, the combination of silage and organic feed (D2) had an opposite trend. Thus, both BU and D1 groups presented enhanced quality attributes, such as marbling, juiciness and reduced hardness, which are some of the most demanded by meat consumers.

Effects of Polyunsaturated Fatty Acids Supplementation on the Meat Quality of Pigs: A Meta-Analysis

Polyunsaturated fatty acids (PUFAs) supplementation has been widely discussed as a strategy for improving meat quality in pig production, but the effects are inconsistent. This meta-analysis was performed to comprehensively evaluate its effects on the meat quality and growth performance of pigs. We searched the PubMed and the Web of Science databases (articles published from January 1, 2000 to October 16, 2020) and compared PUFAs-supplemented diets with control diets. We identified 1,670 studies, of which 14 (with data for 752 pigs) were included in our meta-analysis. The subgroup analysis was classified as PUFA source [conjugated linoleic acid (CLA) or linseed], concentration (high or low concentration), and initial stage (growing or finishing pigs). Our analysis found that PUFA supplementation increased the intramuscular fat (IMF) content (WMD = 0.467%, 95% CI: 0.312–0.621, p < 0.001), decreased the meat color L^* (WMD = −0.636, 95% CI: −1.225 to −0.047, p = 0.034), and pH 24 h (WMD = −0.021, 95% CI: −0.032 to −0.009, p < 0.001) but had no influence on drip loss, meat color a^* and b^*, pH 45 min, and growth performance. CLA supplementation improved IMF content (WMD = 0.542%, 95% CI: 0.343–0.741, p < 0.001) and reduced meat color b^* (WMD = −0.194, 95% CI: −0.344 to −0.044, p = 0.011). Linseed supplementation increased IMF content (WMD = 0.307%, 95% CI: 0.047–0.566, p = 0.021), decreased meat color L^* (WMD = −1.740, 95% CI: −3.267 to −0.213, p = 0.026), and pH 24 h (WMD = 0.034, 95% CI: −0.049 to −0.018, p < 0.001). We discovered an increase on the IMF content in both high and low concentration PUFA supplementation (WMD = 0.461%, 95% CI: −0.344 to −0.044, p < 0.001; WMD = 0.456%, 95% CI: 0.276–0.635, p < 0.001). Furthermore, we also found the effects of PUFA supplementation on meat color L^* and pH 24 h are concentration- and stage-dependent. PUFA supplementation can improve the meat quality of pigs, which mainly emerges in greatly increasing IMF content.

Current State of Metabolomics Research in Meat Quality Analysis and Authentication

In the past decades, as an emerging omic, metabolomics has been widely used in meat science research, showing promise in meat quality analysis and meat authentication. This review first provides a brief overview of the concept, analytical techniques, and analysis workflow of metabolomics. Additionally, the metabolomics research in quality analysis and authentication of meat is comprehensively described. Finally, the limitations, challenges, and future trends of metabolomics application in meat quality analysis and meat authentication are critically discussed. We hope to provide valuable insights for further research in meat quality.

Using segmental bioimpedance analysis to estimate soft tissue and chemical composition of retail cuts and carcasses of lambs

This study evaluated the potential of segmental bioimpedance analysis (SBIA) to estimate the composition of retail cuts and their predictability to infer on the carcass composition in lambs. Leg, rib, shoulder, neck, and loin from thirty-one lamb carcasses were evaluated. A single-frequency bioelectrical impedance analyzer at 50 kHz was used to perform measurements. The models for estimating soft tissue showed the highest accuracy in the retail cuts. Lean and fat weight of the lamb cuts or of the carcasses were predicted with R² of calibration ranging from 86.6 to 99.1% and from 67.5 to 95.4%, respectively. Segmental bioimpedance analysis is an accurate technology to assess physical and chemical components in retail cuts of lamb. Despite that, shoulder was the most representative cut; all cuts evaluated through SBIA were valuable to estimate the components of the edible portion of lamb carcasses.

A Review on Meat Quality Evaluation Methods Based on Non-Destructive Computer Vision and Artificial Intelligence Technologies

Increasing meat demand in terms of both quality and quantity in conjunction with feeding a growing population has resulted in regulatory agencies imposing stringent guidelines on meat quality and safety. Objective and accurate rapid non-destructive detection methods and evaluation techniques based on artificial intelligence have become the research hotspot in recent years and have been widely applied in the meat industry. Therefore, this review surveyed the key technologies of non-destructive detection for meat quality, mainly including ultrasonic technology, machine (computer) vision technology, near-infrared spectroscopy technology, hyperspectral technology, Raman spectra technology, and electronic nose/tongue. The technical characteristics and evaluation methods were compared and analyzed; the practical applications of non-destructive detection technologies in meat quality assessment were explored; and the current challenges and future research directions were discussed. The literature presented in this review clearly demonstrate that previous research on non-destructive technologies are of great significance to ensure consumers’ urgent demand for high-quality meat by promoting automatic, real-time inspection and quality control in meat production. In the near future, with ever-growing application requirements and research developments, it is a trend to integrate such systems to provide effective solutions for various grain quality evaluation applications.

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Food quality and safety are strongly related to human health. Food quality varies with variety and geographical origin, and food fraud is becoming a threat to domestic and global markets. Visible/infrared spectroscopy and hyperspectral imaging techniques, as rapid and non-destructive analytical methods, have been widely utilized to trace food varieties and geographical origins. In this review, we outline recent research progress on identifying food varieties and geographical origins using visible/infrared spectroscopy and hyperspectral imaging with the help of machine learning techniques. The applications of visible, near-infrared, and mid-infrared spectroscopy as well as hyperspectral imaging techniques on crop food, beverage, fruits, nuts, meat, oil, and some other kinds of food are reviewed. Furthermore, existing challenges and prospects are discussed. In general, the existing machine learning techniques contribute to satisfactory classification results. Follow-up researches of food varieties and geographical origins traceability and development of real-time detection equipment are still in demand.

Recent developments in the objective measurement of carcass and meat quality for industrial application

This paper summarises the contents of this Special Edition. The papers cover a range of advanced technologies for the objective measurement of carcass characteristics that influence the yield and potential eating quality of beef and lamb carcasses. All the research has been carried out in Australia and New Zealand and has been centrally funded with collaboration between various groups. This Special Edition is timely since the meat industry is coming under pressure on environmental grounds in addition to health warnings about excessive meat consumption. In this respect it is encouraging that so many of the papers relate to eating quality. The emphasis on objective methods is also important as moving away from traditional subjective grading will improve accuracy and consistency and thereby increase efficiency. Some differences in the approach taken in other parts of the world are discussed.

Artificial Intelligence Empowered Multispectral Vision Based System for Non-Contact Monitoring of Large Yellow Croaker (Larimichthys crocea) Fillets

A non-contact method was proposed to monitor the freshness (based on TVB-N and TBA values) of large yellow croaker fillets (Larimichthys crocea) by using a visible and near-infrared hyperspectral imaging system (400-1000 nm). In this work, the quantitative calibration models were built by using feed-forward neural networks (FNN) and partial least squares regression (PLSR). In addition, it was established that using a regression coefficient on the data can be further compressed by selecting optimal wavelengths (35 for TVB-N and 18 for TBA). The results validated that FNN has higher prediction accuracies than PLSR for both cases using full and selected reflectance spectra. Moreover, our FNN based model has showcased excellent performance even with selected reflectance spectra with rp = 0.978, R2p = 0.981, and RMSEP = 2.292 for TVB-N, and rp = 0.957, R2p = 0.916, and RMSEP = 0.341 for TBA, respectively. This optimal FNN model was then utilized for pixel-wise visualization maps of TVB-N and TBA contents in fillets.

Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review

Non-destructive testing techniques have gained importance in monitoring food quality over the years. Hyperspectral imaging is one of the important non-destructive quality testing techniques which provides both spatial and spectral information. Advancement in machine learning techniques for rapid analysis with higher classification accuracy have improved the potential of using this technique for food applications. This paper provides an overview of the application of different machine learning techniques in analysis of hyperspectral images for determination of food quality. It covers the principle underlying hyperspectral imaging, the advantages, and the limitations of each machine learning technique. The machine learning techniques exhibited rapid analysis of hyperspectral images of food products with high accuracy thereby enabling robust classification or regression models. The selection of effective wavelengths from the hyperspectral data is of paramount importance since it greatly reduces the computational load and time which enhances the scope for real time applications. Due to the feature learning nature of deep learning, it is one of the most promising and powerful techniques for real time applications. However, the field of deep learning is relatively new and need further research for its full utilization. Similarly, lifelong machine learning paves the way for real time HSI applications but needs further research to incorporate the seasonal variations in food quality. Further, the research gaps in machine learning techniques for hyperspectral image analysis, and the prospects are discussed.

•

Artificial neural network has been intensively used for Hyperspectral image (HSI) analysis.

•

Support vector machines and random forest techniques are gaining momentum for HSI analysis.

•

Deep learning applications has potential for implementation in real time HSI analysis.

•

Lifelong machine learning needs further research to incorporate the seasonal variations in food quality.

Chronological Expression of PITX2 and SIX1 Genes and the Association between Their Polymorphisms and Chicken Meat Quality Traits

Meat quality is closely related to the development of skeletal muscle, in which PITX2 and SIX1 genes play important regulatory roles. The present study firstly provided the data of chronological expression files of PITX2 and SIX1 genes in the post-hatching pectoral muscle and analyzed the association of their polymorphisms with the meat quality traits of Wuliang Mountain Black-bone (WLMB) chickens. The results showed that both PITX2 and SIX1 genes were weakly expressed in the second and third weeks, and then increased significantly from the third week to the fourth week. Furthermore, there was a significant positive correlation between the expression levels of the two genes. Twelve and one SNPs were detected in the chicken PITX2 and SIX1 genes, respectively, of which four SNPs (g.9830C > T, g.10073C > T, g.13335G > A, g.13726A > G) of the PITX2 gene and one SNP (g.564G > A) of the SIX1 gene were significantly associated with chicken meat quality traits. For the PITX2 gene, chickens with the CT genotype of g.9830C > T showed the highest meat color L*, shear force (SF), pH, and the lowest electrical conductivity (EC), and drip loss (DL) (p < 0.05 or p < 0.01); chickens with the CC genotype of g.10073C > T had the lowest L*, pH, and the highest DL (p < 0.01). For the SIX1 gene, chickens with the GG genotype of g.564G > A had the highest (p < 0.05) SF and pH. Furthermore, pH had a significant correlation with all the other meat quality traits. The current study could contribute to the research of regulatory mechanisms of meat quality and lay the foundation for improving meat quality based on marker-assisted selection in chickens.

Comparison of smartphone and lab-grade NIR spectrometers to measure chemical composition of lamb and beef

Context Near-infrared reflectance spectroscopy (NIRS) has been extensively investigated for non-destructive and rapid determination of pH and chemical composition of meat including water, crude protein, intramuscular fat (IMF) and stable isotopes. Smaller, cheaper NIRS sensors that connect to a smartphone could enhance the accessibility and uptake of this technology by consumers. However, the limited wavelength range of these sensors could restrict the accuracy of predictions compared with benchtop laboratory NIRS models. Aims To compare the precision and accuracy metrics of predicting pH, water, crude protein and IMF of three sample presentations and two sensors. Methods Fresh intact (FI) store-bought beef and lamb steak samples (n = 43) were ground and freeze-dried (FD), and then oven-dried to create freeze-dried oven-dried (FDOD) samples. All three forms of sample presentation (FI, FD, FDOD) were scanned using the smartphone and benchtop NIRS sensors. Key results The IMF was the best predicted trait in FD and FDOD forms by the smartphone NIRS (R2 &gt;0.75; RPD &gt;1.40) with limited differences between the two sensors. However, predictions on FI meat were poorer for all traits regardless of the NIRS scanner used (R2 ≤ 0.67; RPD ≤ 1.58) and not suitable for use in research or industry. Conclusion The smartphone NIRS sensor showed accuracy and precision comparable to benchtop NIRS to predict meat composition. However, these preliminary results found that neither of the two sensors reliably predicted quality attributes for industry or consumer applications. Implications Miniaturised NIRS sensors connected to smartphones could provide a practical solution to measure some meat quality attributes such as IMF, but the accuracy depends on sample presentation.

MARGRA Lamb Eating Quality and Human Health-Promoting Omega-3 Long-Chain Polyunsaturated Fatty Acid Profiles of Tattykeel Australian White Sheep: Linebreeding and Gender Effects

Health-conscious consumers increasingly demand healthier, tastier, and more nutritious meat, hence the continuous need to meet market specifications and demand for high-quality lamb. We evaluated the longissimus dorsi muscle of 147 Tattykeel Australian White (TAW) sheep fed on antioxidant-rich ryegrass pastures exclusive to MAGRA lamb brand for meat eating quality parameters of intramuscular fat (IMF) content, fat melting point (FMP) and omega-3 long-chain polyunsaturated fatty acids (n-3 LC-PUFA). The aim was to assess the impact of linebreeding and gender on pasture-fed lamb eating quality and to test the hypothesis that variation in healthy lamb eating quality is a function of lamb gender and not its antioxidant status or inbreeding coefficient (IC). After solid-phase extraction and purification, phenolics and antioxidant enzyme activities were analysed by high-performance liquid chromatography and mass spectrometry. IMF and fatty acid composition were determined using solvent extraction and gas chromatography, respectively. IC was classified into low (0-5%), medium (6-10%) and high (>10%) and ranged from 0-15.6%. FMP and IMF ranged from 28 to 39 °C and 3.4% to 8.2%, with overall means of 34.6 ± 2.3 °C and 4.4 ± 0.2%, respectively, and n-3 LC-PUFA ranged from "source" to "good source" levels of 33-69 mg/100 g. Ewes had significantly (P ˂ 0.0001) higher IMF, C22:5n-3 (DPA), C22:6n-3 (DHA), C18:3n-6, C20:3, C22:4n-6, C22:5n-6, total monounsaturated (MUFA), PUFA and Σn-3 fatty acids and lower total saturated fatty acids (SFA) and FMP, than rams. As IC increased, there were no differences in FMP and IMF. Folin-Ciocalteu total phenolics, ferric reducing antioxidant power and antioxidant activities of glutathione peroxidase, catalase and superoxide dismutase enzymes did not differ by either gender or IC. This study provides evidence that IC is inconsequential in affecting antioxidant status, IMF, FMP and n-3 LC-PUFA in linebred and pasture-fed TAW sheep because the observed variation in individual fatty acids was mainly driven by gender differences between ewes and rams, hence the need to accept the tested hypothesis. This finding reinforces the consistent healthy eating quality of MARGRA lamb brand from TAW sheep regardless of its linebred origin.

Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features

Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel Isos-bestic wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of 94.0%.

Myoglobin-Based Classification of Minced Meat Using Hyperspectral Imaging

Minced meat substitution is one of the most common frauds which not only affects consumer health but impacts their lifestyles and religious customs as well. A number of methods have been proposed to overcome these frauds; however, these mostly rely on laboratory measures and are often subject to human error. Therefore, this study proposes novel hyperspectral imaging (400–1000 nm) based non-destructive isos-bestic myoglobin (Mb) spectral features for minced meat classification. A total of 60 minced meat spectral cubes were pre-processed using true-color image formulation to extract regions of interest, which were further normalized using the Savitzky–Golay filtering technique. The proposed pipeline outperformed several state-of-the-art methods by achieving an average accuracy of 88.88%.

Genetics of Omega-3 Long-Chain Polyunsaturated Fatty Acid Metabolism and Meat Eating Quality in Tattykeel Australian White Lambs

Meat eating quality with a healthy composition hinges on intramuscular fat (IMF), fat melting point (FMP), tenderness, juiciness, flavour and omega-3 long-chain polyunsaturated fatty acids (n-3 LC-PUFA) content. These health-beneficial n-3 LC-PUFA play significant roles in optimal cardiovascular, retinal, maternal and childhood brain functions, and include alpha linolenic (ALA), eicosapentaenoic (EPA), docosahexaenoic (DHA) and docosapentaenoic (DPA) acids. The primary objective of this review was to access, retrieve, synthesise and critically appraise the published literature on the synthesis, metabolism and genetics of n-3 LC-PUFA and meat eating quality. Studies on IMF content, FMP and fatty acid composition were reviewed to identify knowledge gaps that can inform future research with Tattykeel Australian White (TAW) lambs. The TAW is a new sheep breed exclusive to MARGRA brand of lamb with an outstanding low fat melting point (28-39°C), high n-3 LC-PUFA EPA+DHA content (33-69mg/100g), marbling (3.4-8.2%), tenderness (20.0-38.5N) and overall consumer liking (7.9-8.5). However, correlations between n-3 LC-PUFA profile, stearoyl-CoA desaturase (SCD), fatty acid binding protein 4 (FABP4), fatty acid synthase (FASN), other lipogenic genes and meat quality traits present major knowledge gaps. The review also identified research opportunities in nutrition-genetics interactions aimed at a greater understanding of the genetics of n-3 LC-PUFA, feedlot finishing performance, carcass traits and eating quality in the TAW sheep. It was concluded that studies on IMF, FMP and n-3 LC-PUFA profiles in parental and progeny generations of TAW sheep will be foundational for the genetic selection of healthy lamb eating qualities and provide useful insights into their correlations with SCD, FASN and FABP4 genes.

Detection of mycotoxins and toxigenic fungi in cereal grains using vibrational spectroscopic techniques: a review

Nutrition-rich cereal grains and oil seeds are the major sources of food and feed for human and livestock, respectively. Infected by fungi and contaminated with mycotoxins are serious problems worldwide for cereals and oil seeds before and after harvest. The growth and development activities of fungi consume seed nutrients and destroy seed structures, leading to dramatic declines of crop yield and quality. In addition, the toxic secondary metabolites produced by these fungi pose a well-known threat to both human and animals. The existence of fungi and mycotoxins has been a redoubtable problem worldwide for decades but tends to be a severe food safety issue in developing countries and regions, such as China and Africa. Detection of fungal infection at an early stage and of mycotoxin contaminants, even at a small amount, is of great significance to prevent harmful toxins from entering the food supply chains worldwide. This review focuses on the recent advancements in utilising infrared spectroscopy, Raman spectroscopy, and hyperspectral imaging to detect fungal infections and mycotoxin contaminants in cereals and oil seeds worldwide, with an emphasis on recent progress in China. Brief introduction of principles, and corresponding shortcomings, as well as latest advances of each technique, are also being presented herein.

Rapid inspection method for investigating the heat processing conditions employed for chicken meat using Raman spectroscopy

In Japan, the imports of meat products have been increasing every year. Heat processing of meat is the current standard method for ensuring domestic animal health, particularly in case of meat products from areas where infectious diseases are known to have occurred in domestic animals. The Animal Quarantine Service needs to establish a method that detects the temperature at which the meat has been heat-processed (endpoint temperature) to ensure that the standard protocol is followed at the production location. Here, we developed a Raman spectroscopy and multivariate statistics (viz. multivariate curve resolution (MCR))-based simple and rapid method for accurately estimating the end point temperature. We showed that the temperature-dependent secondary structure modification of proteins can serve as an accurate indicator of the temperature of heat processing. This methodology can be easily automated for effective utilization by someone who is not an expert in spectroscopy. We envisage a wider application of this method in food analysis, although the present research investigated the application of this method in chicken meat heat processing analysis.

Meat quality traits of European quails reared under different conditions of temperature and air velocity

This study’s objective was to evaluate the influence of thermal environment and air velocity during the rearing phase on European quail meat quality traits. A total of 1,152 one-day-old European quail chicks were placed inside floor pens within environmental chambers. Each experimental period was approximately 5 wks, with birds slaughtered at 37 d of age. The experimental design consisted of a 2 × 4 factorial arrangement of treatments in completely randomized design with 2 air velocities (0 and 2 m/s) × 4 air temperatures (severe cold [SC], moderate cold, thermal comfort, and moderate heat [MH]). ANOVA, with air velocity and thermal environment as fixed effects, was performed to evaluate the effect of main factors and their interaction on meat quality traits, using the GLM procedure (SAS 9.4). Least square means of treatments effects were compared using Tukey’s test (α = 0.05). Lightness (L∗), redness (a∗), and yellowness (b∗), of quail meat were affected by thermal environment and air velocity (P < 0.05). Initial and final L∗ values were greater for MH (P < 0.05). Meat from birds subjected to 2 m/s air velocity had lower final L∗, but no velocity effect was noted for initial L∗. Quail meat from SC presented higher initial and final a∗ values compared with the other thermal environment groups (P ≤ 0.001). Final a∗ was affected by air velocity (P < 0.05). Initial and final b∗ values for meat from MH were greater, 13.8 and 15.2, respectively, differing from the other treatment environments (P < 0.05). However, air velocity did not influence b∗ values (P > 0.05). Interactions were not significant for pHu (P = 0.993). Thawing loss and shear force were affected by treatments (P < 0.05) but not ultimate pH, drip loss, or sarcomere length. This study demonstrates that thermal environments and air velocity affect quail meat quality traits. Further investigation is recommended to explore effects of air velocity and thermal environment on muscle proteolysis of quail meat quality.

Autofluorescence excitation-emission matrices as a quantitative tool for the assessment of meat quality

Commercially produced meat is currently graded by a complex and partly subjective multiparameter methodology; a quantitative method of grading, using small samples would be desirable. Here, we investigate the correlation between commercial grades of beef and spectral signatures of native fluorophores in such small samples. Beef samples of different commercial grades were characterized by fluorescence spectroscopy complemented by biochemical and histological assessment. The excitation-emission matrices of the specimens reveal five prominent native autofluorescence signatures in the excitation range from 250 to 350 nm, derived mainly from tryptophan and intramuscular fat. We found that these signatures reflect meat grade and can be used for its determination.

High-quality panchromatic image acquisition method for snapshot hyperspectral imaging Fourier transform spectrometer

The acquisition of high-quality panchromatic images is vital to the multi-spectral images pan sharpening, especially to snapshot imaging spectrometers with a low spatial resolution. As an aperture-division snapshot imaging spectrometer, a snapshot hyperspectral imaging Fourier transform spectrometer has the characteristic that images of all the sub-apertures share almost the same spatial information with a small shift. With these sub-images, super-resolution is possible. In this paper, a high-quality panchromatic image acquisition method is proposed. A pre-trained deep learning network is utilized without enlarging the instrument size. The training dataset is obtained experimentally, and the network is designed to realize the contrast enhancement and super-resolution simultaneously. The experimental results demonstrate that the proposed method performs well in high-quality panchromatic image acquisition.

Meat quality evaluation based on computer vision technique: A review

Nowadays people tend to include more meat in their diet thanks to the improvement in standards of living as well as an increase in awareness of meat nutritive values. To ensure public health, therefore, there is a need for a rise in worldwide meat production and consumption. Further attention is also required as to how the safety and the quality of meat production process should be assessed. Classical methods of meat quality assessment, however, have some disadvantages; expensive and time-consuming. This study intends to introduce an alternative method known as Computer Vision (CV) for the assessment of various quality parameters of muscle foods. CV has several advantages over the traditional methods. It is non-destructive, easy, and quick, hence, more efficient in meat quality assessments. This study aims to investigate different quality characteristics of some muscle foods using CV. It closes with a discussion on the future challenges and expected opportunities of the practical application of CV in the meat industry.

Comparison of various chemometric analysis for rapid prediction of thiobarbituric acid reactive substances in rainbow trout fillets by hyperspectral imaging technique

This study explores the potential application of hyperspectral imaging (HSI; 430-1,010 nm) coupled with different linear and nonlinear models for rapid nondestructive evaluation of thiobarbituric acid-reactive substances (TBARS) value in rainbow trout (Oncorhynchus mykiss) fillets during 12 days of cold storage (4 ± 2°C). HSI data and TBARS value of fillets were obtained in the laboratory. The primary prediction models were established based on linear partial least squares regression (PLSR) and least squares support vector machine (LS-SVM). In full spectral range, the prediction capability of LS-SVM ( R P 2  = 0.829; RMSEP = 0.128 mg malondialdehyde [MDA]/kg) was better than PLSR ( R P 2  = 0.748; RMSEP = 0.155 mg MDA/kg) model and LS-SVM model exhibited satisfactory prediction performance ( R P 2  > 0.82). To simplify the calibration models, a combination of uninformative variable elimination and backward regression (UB) was used as variable selection. Nine wavelengths were selected. Various chemometric analysis methods including linear PLSR and multiple linear regression and nonlinear LS-SVM and back-propagation artificial neural network (BP-ANN) were compared. The simplified models showed better capability than those were built based on the whole dataset in prediction of TBARS values. Moreover, the nonlinear models were preferred over linear models. Among the four chemometric algorithms, the best and weakest models were LS-SVM and PLSR model, respectively. UB-LS-SVM model was the optimal models for predicting TBARS value in rainbow trout fillets ( R P 2  = 0.831; RMSEP = 0.125 mg MDA/kg). The establishing of lipid-oxidation prediction model in rainbow trout fish was complicated, due to the fluctuations of TBARS values during storage. Therefore, further researches are needed to improve the prediction results and applicability of HIS technique for prediction of TBARS value in rainbow trout fish.

Integration of spectral and textural features of visible and near-infrared hyperspectral imaging for differentiating between normal and white striping broiler breast meat

White striping (WS), an emerging muscle myopathy in poultry industry, is gaining increasing attention globally. In this study, visible and near-infrared hyperspectral imaging (HSI, 400-1000 nm) was investigated for developing an optical sensing technique to differentiate WS broiler breast fillets (pectoralis major) from normal fillets. The minimum noise fraction (MNF), followed by an inverse MNF (IMNF), was conducted to improve the signal-to-noise ratio of hyperspectral images during the pre-processing process. Three regions of interest (ROIs) were selected at cranial, middle and caudal locations within each fillet image. Spectral principal component analysis (PCA) revealed that PC₂ and PC₃ were effective for the differentiation and key wavelengths (450, 492, 541, 581, 629, 869 and 980 nm) were selected from the corresponding PC loadings. Spatial texture features on corresponding score images were obtained using gray level co-occurrence matrix (GLCM) and grayscale histogram statistics (GHS), respectively. Partial least squares discriminant analysis (PLS-DA) models were evaluated with various inputs including spectral (full and key wavelengths), textural and fused features. GLCM features improved performance of multispectral imaging with the highest correct classification rate (CCR) of 91.7%, AUC value (0.917), and Kappa coefficient (0.833) for prediction set. Considering the complexity and heterogeneity of meat samples at different locations, the optimal sampling location was also analyzed and results provided the evidence that the cranial location worked most effectively for the differentiation between normal and WS samples. Overall, results confirmed the great potential of HSI in range of 400-1000 nm in differentiation between normal and WS chicken breast meat.

Recent Applications of Multispectral Imaging in Seed Phenotyping and Quality Monitoring-An Overview

As a synergistic integration between spectroscopy and imaging technologies, spectral imaging modalities have been emerged to tackle quality evaluation dilemmas by proposing different designs with effective and practical applications in food and agriculture. With the advantage of acquiring spatio-spectral data across a wide range of the electromagnetic spectrum, the state-of-the-art multispectral imaging in tandem with different multivariate chemometric analysis scenarios has been successfully implemented not only for food quality and safety control purposes, but also in dealing with critical research challenges in seed science and technology. This paper will shed some light on the fundamental configuration of the systems and give a birds-eye view of all recent approaches in the acquisition, processing and reproduction of multispectral images for various applications in seed quality assessment and seed phenotyping issues. This review article continues from where earlier review papers stopped but it only focused on fully-operated multispectral imaging systems for quality assessment of different sorts of seeds. Thence, the review comprehensively highlights research attempts devoted to real implementations of only fully-operated multispectral imaging systems and does not consider those ones that just utilized some key wavelengths extracted from hyperspectral data analyses without building independent multispectral imaging systems. This makes this article the first attempt in briefing all published papers in multispectral imaging applications in seed phenotyping and quality monitoring by providing some examples and research results in characterizing physicochemical quality traits, predicting physiological parameters, detection of defect, pest infestation and seed health.

Advances in Sheep and Goat Meat Products Research

The main goal of this chapter was to review the state of the art in the recent advances in sheep and goat meat products research. Research and innovation have been playing an important role in sheep and goat meat production and meat processing as well as food safety. Special emphasis will be placed on the imaging and spectroscopic methods for predicting body composition, carcass and meat quality. The physicochemical and sensory quality as well as food safety will be referenced to the new sheep and goat meat products. Finally, the future trends in sheep and goat meat products research will be pointed out.