Application of machine-vision techniques to fish-quality assessment

1H NMR spectroscopy as a tool to probe potential biomarkers of the drying-salting process: A proof-of-concept study with the Amazon fish pirarucu

Dry-salted pirarucu (Arapaima gigas) plays an important cultural role in the Amazon region - South America. In this study, we explored the changes in the chemical composition of pirarucu meat following the drying-salting process via 1H NMR spectroscopy. Combining multivariate and univariate statistical analyses yielded a robust differentiation of metabolites involved in the process. VIP score (>1), p-value (<0.05), and AUC (>0.7) were considered to selecting compounds that had significant fluctuations in their contents along the process. Our results pointed out acetate, lactate, succinate, and creatinine as metabolites undergoing significant changes during the drying-salting process. Creatinine was not detected in fresh samples. The investigation of multiple components delves deeper into the molecular nuances of the salting-drying process's impact on fish meat, providing a more comprehensive understanding of the possible chemical transformations and how the matrix's quality control and nutritional aspects should be addressed.

Research progress of chilled meat freshness detection based on nanozyme sensing systems

It is important to develop rapid, accurate, and portable technologies for detecting the freshness of chilled meat to meet the current demands of meat industry. This report introduces freshness indicators for monitoring the freshness changes of chilled meat, and systematically analyzes the current status of existing detection technologies which focus on the feasibility of using nanozyme for meat freshness sensing detection. Furthermore, it examines the limitations and foresees the future development trends of utilizing current nanozyme sensing systems in evaluating chilled meat freshness. Harmful chemicals are produced by food spoilage degradation, including biogenic amines, volatile amines, hydrogen sulfide, and xanthine, which have become new freshness indicators to evaluate the freshness of chilled meat. The recognition mechanisms are clarified based on the special chemical reaction with nanozyme or directly inducting the enzyme-like catalytic activity of nanozyme.

Explainable AI: Machine Learning Interpretation in Blackcurrant Powders

Recently, explainability in machine and deep learning has become an important area in the field of research as well as interest, both due to the increasing use of artificial intelligence (AI) methods and understanding of the decisions made by models. The explainability of artificial intelligence (XAI) is due to the increasing consciousness in, among other things, data mining, error elimination, and learning performance by various AI algorithms. Moreover, XAI will allow the decisions made by models in problems to be more transparent as well as effective. In this study, models from the 'glass box' group of Decision Tree, among others, and the 'black box' group of Random Forest, among others, were proposed to understand the identification of selected types of currant powders. The learning process of these models was carried out to determine accuracy indicators such as accuracy, precision, recall, and F1-score. It was visualized using Local Interpretable Model Agnostic Explanations (LIMEs) to predict the effectiveness of identifying specific types of blackcurrant powders based on texture descriptors such as entropy, contrast, correlation, dissimilarity, and homogeneity. Bagging (Bagging_100), Decision Tree (DT0), and Random Forest (RF7_gini) proved to be the most effective models in the framework of currant powder interpretability. The measures of classifier performance in terms of accuracy, precision, recall, and F1-score for Bagging_100, respectively, reached values of approximately 0.979. In comparison, DT0 reached values of 0.968, 0.972, 0.968, and 0.969, and RF7_gini reached values of 0.963, 0.964, 0.963, and 0.963. These models achieved classifier performance measures of greater than 96%. In the future, XAI using agnostic models can be an additional important tool to help analyze data, including food products, even online.

Efficiency of Identification of Blackcurrant Powders Using Classifier Ensembles

In the modern times of technological development, it is important to select adequate methods to support various food and industrial problems, including innovative techniques with the help of artificial intelligence (AI). Effective analysis and the speed of algorithm implementation are key points in assessing the quality of food products. Non-invasive solutions are being sought to achieve high accuracy in the classification and evaluation of various food products. This paper presents various machine learning algorithm architectures to evaluate the efficiency of identifying blackcurrant powders (i.e., blackcurrant concentrate with a density of 67 °Brix and a color coefficient of 2.352 (E520/E420) in combination with the selected carrier) based on information encoded in microscopic images acquired via scanning electron microscopy (SEM). Recognition of blackcurrant powders was performed using texture feature extraction from images aided by the gray-level co-occurrence matrix (GLCM). It was evaluated for quality using individual single classifiers and a metaclassifier based on metrics such as accuracy, precision, recall, and F1-score. The research showed that the metaclassifier, as well as a single random forest (RF) classifier most effectively identified blackcurrant powders based on image texture features. This indicates that ensembles of classifiers in machine learning is an alternative approach to demonstrate better performance than the existing traditional solutions with single neural models. In the future, such solutions could be an important tool to support the assessment of the quality of food products in real time. Moreover, ensembles of classifiers can be used for faster analysis to determine the selection of an adequate machine learning algorithm for a given problem.

The Need for Machines for the Nondestructive Quality Assessment of Potatoes with the Use of Artificial Intelligence Methods and Imaging Techniques

This article describes chemical and physical parameters, including their role in the storage, trade, and processing of potatoes, as well as their nutritional properties and health benefits resulting from their consumption. An analysis of the share of losses occurring during the production process is presented. The methods and applications used in recent years to estimate the physical and chemical parameters of potatoes during their storage and processing, which determine the quality of potatoes, are presented. The potential of the technologies used to classify the quality of potatoes, mechanical and ultrasonic, and image processing and analysis using vision systems, as well as their use in applications with artificial intelligence, are discussed.

Cutting Techniques in the Fish Industry: A Critical Review

Fish and fishery products are among the most important sources of nutritional components for human health, including high-quality proteins, essential vitamins, minerals, and healthy polyunsaturated fatty acids. Fish farming and processing technologies are continuously evolving to improve and enhance the appearance, yield, and quality of fish and fish products from farm to fork throughout the fish supply chain, including growth, postharvest, treatment, storage, transportation, and distribution. Processing of fish involves a period of food withdrawal, collection and transportation, the process of stunning, bleeding, chilling, cutting, packaging, and byproduct recycling. Cutting is a set of crucial operations in fish processing to divide the whole fish into smaller pieces for producing fish products (e.g., fish fillets, steaks, etc.). Various techniques and machinery have been introduced in the field to advance and automate cutting operations. This review aims to provide a comprehensive review of fish cutting techniques, machine vision and artificial intelligence applications, and future directions in fish industries. This paper is expected to stimulate research on enhancing fish cutting yield, product diversity, safety and quality, as well as providing advanced solutions for engineering problems encountered in the fish industry.

Applications of Fluorescence Spectroscopy, RGB- and MultiSpectral Imaging for Quality Determinations of White Meat: A Review

Fluorescence spectroscopy, color imaging and multispectral imaging (MSI) have emerged as effective analytical methods for the non-destructive detection of quality attributes of various white meat products such as fish, shrimp, chicken, duck and goose. Based on machine learning and convolutional neural network, these techniques can not only be used to determine the freshness and category of white meat through imaging and analysis, but can also be used to detect various harmful substances in meat products to prevent stale and spoiled meat from entering the market and causing harm to consumer health and even the ecosystem. The development of quality inspection systems based on such techniques to measure and classify white meat quality parameters will help improve the productivity and economic efficiency of the meat industry, as well as the health of consumers. Herein, a comprehensive review and discussion of the literature on fluorescence spectroscopy, color imaging and MSI is presented. The principles of these three techniques, the quality analysis models selected and the research results of non-destructive determinations of white meat quality over the last decade or so are analyzed and summarized. The review is conducted in this highly practical research field in order to provide information for future research directions. The conclusions detail how these efficient and convenient imaging and analytical techniques can be used for non-destructive quality evaluation of white meat in the laboratory and in industry.

The use of image analysis techniques for the study of muscle melanisation in sand flathead (Platycephalus bassensis)

Muscle melanisation in sand flathead is visible as black spots in the normally white flesh of fish. It is widespread in Tasmania, including at the Tamar Estuary, with increasing frequency of reporting by recreational fishers. The phenomenon is more prevalent in areas impacted by heavy metal pollution and has been linked to heavy metal accumulation. In this study, image processing software ImageJ was employed to study the phenomenon and to establish an objective rating system. A longitudinal profile plot was used to study the greying of the fillet. The degree of melanisation was rated based on the percentage surface area melanised on the surface and in transverse sections of fillets. A muscle melanisation scoring system for sand flathead was established based on visual interpretation using the macroscopic melanisation scoring criteria: melanisation scores 0 = <0.5%, 1 = 0.5-5%, 2 = 5-20%, and 3 = >20% (% = melanised surface area in proportion to the whole fillet). A refined image analysis technique was developed to quantify the percentage of melanised muscle surface area and the muscle melanisation scoring system was statistically validated. Sand flathead fillet with higher melanisation score was shown to be linked to increased intensity of greyness and greater numbers and size of black spots on the surface of fillets and within the flesh. The greying and black spots were primarily concentrated at the anterior region of fillet and around the dorsal vertebrae zone on transverse section of fillets. Overall, findings from this study established the use of image analysis techniques to validate visual inspection and to give a standardised and objective method to determine the degree of melanisation in sand flathead. As muscle melanisation appears to be linked to heavy metal pollution, the standardised scoring system would facilitate future research for environmental pollution and monitoring purposes.

Advanced applications of chemo-responsive dyes based odor imaging technology for fast sensing food quality and safety: A review

Public attention to foodquality and safety has been increased significantly. Therefore, appropriate analytical tools are needed to analyze and sense the food quality and safety. Volatile organic compounds (VOCs) are important indicators for the quality and safety of food products. Odor imaging technology based on chemo-responsive dyes is one of the most promising methods for analysis of food products. This article reviews the sensing and imaging fundamentals of odor imaging technology based on chemo-responsive dyes. The aim is to give detailed outlines about the theory and principles of using odor imaging technology for VOCs detection, and to focus primarily on its applications in the field of quality and safety evaluation of food products, as well as its future applicability in modern food industries and research. The literatures presented in this review clearly demonstrated that imaging technology based on chemo-responsive dyes has the exciting effect to inspect such as quality assessment of cereal , wine and vinegar flavored foods , poultry meat, aquatic products, fruits and vegetables, and tea. It has the potential for the rapid, reliable, and inline assessment of food safety and quality by providing odor-image-basedmonitoring tool. Practical Application: The literatures presented in this review clearly demonstrated that imaging technology based on chemo-responsive dyes has the exciting effect to inspect such as quality assessment of cereal , wine and vinegar flavored foods, poultry meat, aquatic products, fruits and vegetables, and tea.

Development of an android app for estimating the water quality parameters in fish pond

In this research, a new android app for smartphones for estimating some water quality parameters in carp fish ponds such as pH, electrical conductivity (EC), total dissolved solids (TDS), and turbidity is presented. Contact imaging was used to acquire images from the samples. To estimate pH, EC, TDS, and turbidity values, 12 features were extracted from each image. Features were used as input to the artificial neural network models. The performance of the models was evaluated by the R² and RMSE parameters. Based on the results, the network with a structure of 12-15-4 was selected as the best model. The values of R² for estimating pH, TDS, EC, and turbidity were 0.913, 0.993, 0.994, and 0.958, respectively, while the corresponding values for the RMSE were 0.054, 1.835, 3.766, and 0.262, respectively. Finally, this model was successfully implemented on an app named WaterApp on the android smartphone. For testing the app on the smartphone, the performance of the model was evaluated again using new images. According to the results, the R² values for validation data by the developed WaterApp for pH, EC, TDS, and turbidity were 0.88, 0.913, 0.884, and 0.944, respectively.

Recent Advances in Reducing Food Losses in the Supply Chain of Fresh Agricultural Produce

Fruits and vegetables are highly nutritious agricultural produce with tremendous human health benefits. They are also highly perishable and as such are easily susceptible to spoilage, leading to a reduction in quality attributes and induced food loss. Cold chain technologies have over the years been employed to reduce the quality loss of fruits and vegetables from farm to fork. However, a high amount of losses (≈50%) still occur during the packaging, pre-cooling, transportation, and storage of these fresh agricultural produce. This study highlights the current state-of-the-art of various advanced tools employed to reducing the quality loss of fruits and vegetables during the packaging, storage, and transportation cold chain operations, including the application of imaging technology, spectroscopy, multi-sensors, electronic nose, radio frequency identification, printed sensors, acoustic impulse response, and mathematical models. It is shown that computer vision, hyperspectral imaging, multispectral imaging, spectroscopy, X-ray imaging, and mathematical models are well established in monitoring and optimizing process parameters that affect food quality attributes during cold chain operations. We also identified the Internet of Things (IoT) and virtual representation models of a particular fresh produce (digital twins) as emerging technologies that can help monitor and control the uncharted quality evolution during its postharvest life. These advances can help diagnose and take measures against potential problems affecting the quality of fresh produce in the supply chains. Plausible future pathways to further develop these emerging technologies and help in the significant reduction of food losses in the supply chain of fresh produce are discussed. Future research should be directed towards integrating IoT and digital twins for multiple shipments in order to intensify real-time monitoring of the cold chain environmental conditions, and the eventual optimization of the postharvest supply chains. This study gives promising insight towards the use of advanced technologies in reducing losses in the postharvest supply chain of fruits and vegetables.

Fish Quality Index Method: Principles, weaknesses, validation, and alternatives-A review

Fish is a high nutritional value matrix of which production and consumption have been increasing in the last years. Advancements in the efficient evaluation of freshness are essential to optimize the quality assessment, to improve consumer safety, and to reduce raw material losses. Therefore, it is necessary to use rapid, nondestructive, and objective methodologies to evaluate the quality of this matrix. Quality Index Method (QIM) is a tool applied to indicate fish freshness through a sensory evaluation performed by a group of assessors. However, the use of QIM as an official method for quality assessment is limited by the protocol, sampling size, specificities of the species, storage conditions, and assessor's experience, which make this method subjective. Also, QIM may present divergences regarding the development of microorganisms and chemical analysis. In this way, novel quality evaluation methods such as electronic noses, electronic tongues, machine vision system, and colorimetric sensors have been proposed, and novel technologies such as proteomics and mitochondrial analysis have been developed. In this review, the weaknesses of QIM were exposed, and novel methodologies for quality evaluation were presented. The consolidation of these novel methodologies and their use as methods of quality assessment are an alternative to sensory methods, and their understanding enables a more effective fish quality control.

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.

Hyperspectral imaging with multivariate analysis for technological parameters prediction and classification of muscle foods: A review

Muscle foods are very important for a well-balanced daily diet. Due to their perishability and vulnerability, there is a need for quality and safety evaluation of such foods. Hyperspectral imaging (HSI) coupled with multivariate analysis is becoming increasingly popular for the non-destructive, non-invasive, and rapid determination of important quality attributes and the classification of muscle foods. This paper reviews recent advances of application of HSI for predicting some significant muscle foods parameters, including color, tenderness, firmness, springiness, water-holding capacity, drip loss and pH. In addition, algorithms for the rapid classification of muscle foods are also reported and discussed. It will be shown that this technology has great potential to replace traditional analytical methods for predicting various quality parameters and classifying muscle foods.

Potential application of machine vision technology to saffron (Crocus sativus L.) quality characterization

Saffron quality characterization is an important issue in the food industry and of interest to the consumers. This paper proposes an expert system based on the application of machine vision technology for characterization of saffron and shows how it can be employed in practical usage. There is a correlation between saffron color and its geographic location of production and some chemical attributes which could be properly used for characterization of saffron quality and freshness. This may be accomplished by employing image processing techniques coupled with multivariate data analysis for quantification of saffron properties. Expert algorithms can be made available for prediction of saffron characteristics such as color as well as for product classification.

Recent advances in methods and techniques for freshness quality determination and evaluation of fish and fish fillets: a review

The freshness quality of fish plays an important role in human health and the acceptance of consumers as well as in international fishery trade. Recently, with food safety becoming a critical issue of great concern in the world, determination and evaluation of fish freshness is much more significant in research and development. This review renovates and concentrates recent advances of evaluating methods for fish freshness as affected by preharvest and postharvest factors and highlights the determination methods for fish freshness including sensory evaluation, microbial inspection, chemical measurements of moisture content, volatile compounds, protein changes, lipid oxidation, and adenosine triphosphate (ATP) decomposition (K value), physical measurements, and foreign material contamination detection. Moreover, the advantages and disadvantages of these methods and techniques are compared and discussed and some viewpoints about the current work and future trends are also presented.

Non-destructive prediction of thiobarbituricacid reactive substances (TBARS) value for freshness evaluation of chicken meat using hyperspectral imaging

This study examined the potential of hyperspectral imaging (HSI) for rapid prediction of 2-thiobarbituric acid reactive substances (TBARS) content in chicken meat during refrigerated storage. Using the spectral data and the reference values of TBARS, a partial least square regression (PLSR) model was established and yielded acceptable results with regression coefficients in prediction (Rp) of 0.944 and root mean squared errors estimated by prediction (RMSEP) of 0.081. To simplify the calibration model, ten optimal wavelengths were selected by successive projections algorithm (SPA). Then, a new SPA-PLSR model based on the selected wavelengths was built and showed good results with Rp of 0.801 and RMSEP of 0.157. Finally, an image algorithm was developed to achieve image visualization of TBARS values in some representative samples. The encouraging results of this study demonstrated that HSI is suitable for determination of TBARS values for freshness evaluation in chicken meat.