Selection of Optimal Wavelength Features for Decay Detection in Citrus Fruit Using the ROC Curve and Neural Networks

Rating pome fruit quality traits using deep learning and image processing

Quality assessment of pome fruits (i.e. apples and pears) is used not only for determining the optimal harvest time but also for the progression of fruit-quality attributes during storage. Therefore, it is typical to repeatedly evaluate fruits during the course of a postharvest experiment. This evaluation often includes careful visual assessments of fruit for apparent defects and physiological symptoms. A general best practice for quality assessment is to rate fruit using the same individual rater or group of individual raters to reduce bias. However, such consistency across labs, facilities, and experiments is often not feasible or attainable. Moreover, while these visual assessments are critical empirical data, they are often coarse-grained and lack consistent objective criteria. Granny, is a tool designed for rating fruit using machine-learning and image-processing to address rater bias and improve resolution. Additionally, Granny supports backward compatibility by providing ratings compatible with long-established standards and references, promoting research program continuity. Current Granny ratings include starch content assessment, rating levels of peel defects, and peel color analyses. Integrative analyses enhanced by Granny's improved resolution and reduced bias, such as linking fruit outcomes to global scale -omics data, environmental changes, and other quantitative fruit quality metrics like soluble solids content and flesh firmness, will further enrich our understanding of fruit quality dynamics. Lastly, Granny is open-source and freely available.

Research and Application Validation of a Feature Wavelength Selection Method Based on Acousto-Optic Tunable Filter (AOTF) and Automatic Machine Learning (AutoML)

Near-infrared spectroscopy has been widely applied in various fields such as food analysis and agricultural testing. However, the conventional method of scanning the full spectrum of the sample and then invoking the model to analyze and predict results has a large amount of collected data, redundant information, slow acquisition speed, and high model complexity. This paper proposes a feature wavelength selection approach based on acousto-optical tunable filter (AOTF) spectroscopy and automatic machine learning (AutoML). Based on the programmable selection of sub nm center wavelengths achieved by the AOTF, it is capable of rapid acquisition of combinations of feature wavelengths of samples selected using AutoML algorithms, enabling the rapid output of target substance detection results in the field. The experimental setup was designed and application validation experiments were carried out to verify that the method could significantly reduce the number of NIR sampling points, increase the sampling speed, and improve the accuracy and predictability of NIR data models while simplifying the modelling process and broadening the application scenarios.

Near-Infrared Hyperspectral Imaging Pipelines for Pasture Seed Quality Evaluation: An Overview

Near-infrared (800–2500 nm; NIR) spectroscopy coupled to hyperspectral imaging (NIR-HSI) has greatly enhanced its capability and thus widened its application and use across various industries. This non-destructive technique that is sensitive to both physical and chemical attributes of virtually any material can be used for both qualitative and quantitative analyses. This review describes the advancement of NIR to NIR-HSI in agricultural applications with a focus on seed quality features for agronomically important seeds. NIR-HSI seed phenotyping, describing sample sizes used for building high-accuracy calibration and prediction models for full or selected wavelengths of the NIR region, is explored. The molecular interpretation of absorbance bands in the NIR region is difficult; hence, this review offers important NIR absorbance band assignments that have been reported in literature. Opportunities for NIR-HSI seed phenotyping in forage grass seed are described and a step-by-step data-acquisition and analysis pipeline for the determination of seed quality in perennial ryegrass seeds is also presented.

A Novel Deep Learning Model for Detection of Severity Level of the Disease in Citrus Fruits

Citrus fruit diseases have an egregious impact on both the quality and quantity of the citrus fruit production and market. Automatic detection of severity is essential for the high-quality production of fruit. In the current work, a citrus fruit dataset is preprocessed by rescaling and establishing bounding boxes with labeled image software. Then, a selective search, which combines the capabilities of both an extensive search and graph-based segmentation, is applied. The proposed deep neural network (DNN) model is trained to detect targeted areas of the disease with its severity level using citrus fruits that have been labeled with the help of a domain expert with four severity levels (high, medium, low and healthy) as ground truth. Transfer learning using VGGNet is applied to implement a multi-classification framework for each class of severity. The model predicts the low severity level with 99% accuracy, and the high severity level with 98% accuracy. The model demonstrates 96% accuracy in detecting healthy conditions and 97% accuracy in detecting medium severity levels. The result of the work shows that the proposed approach is valid, and it is efficient for detecting citrus fruit disease at four levels of severity.

Current State of Hyperspectral Remote Sensing for Early Plant Disease Detection: A Review

The development of hyperspectral remote sensing equipment, in recent years, has provided plant protection professionals with a new mechanism for assessing the phytosanitary state of crops. Semantically rich data coming from hyperspectral sensors are a prerequisite for the timely and rational implementation of plant protection measures. This review presents modern advances in early plant disease detection based on hyperspectral remote sensing. The review identifies current gaps in the methodologies of experiments. A further direction for experimental methodological development is indicated. A comparative study of the existing results is performed and a systematic table of different plants' disease detection by hyperspectral remote sensing is presented, including important wave bands and sensor model information.

Variety Identification of Chinese Walnuts Using Hyperspectral Imaging Combined with Chemometrics

Chinese walnuts have extraordinary nutritional and organoleptic qualities, and counterfeit Chinese walnut products are pervasive in the market. The aim of this study was to investigate the feasibility of hyperspectral imaging (HSI) technique to accurately identify and visualize Chinese walnut varieties. Hyperspectral images of 400 Chinese walnuts including 200 samples of Ningguo variety and 200 samples of Lin’an variety were acquired in range of 400–1000 nm. Spectra were extracted from representative regions of interest (ROIs), and principal component analysis (PCA) of spectra showed that the characteristic second principal component (PC2) was potentially effective in variety identification. The PC transformation was also conducted to hyperspectral images to make an exploratory visualization according to pixel-wise PC scores. Three different modeling methods including partial least squares-discriminant analysis (PLS-DA), k-nearest neighbor (KNN), and support vector machine (SVM) were individually employed to develop classification models. Results indicated that raw full spectra constructed PLS-DA model performed best with correct classification rates (CCRs) of 97.33%, 95.33%, and 92.00% in calibration, cross-validation, and prediction sets, respectively. Successful projects algorithm (SPA), competitive adaptive reweighted sampling (CARS), and PC loadings were individually used for effective wavelengths selection. Subsequently, simplified PLS-DA model based on wavelengths selected by CARS yielded the best 96.33%, 95.67% and 91.00% CCRs in the three sets. This optimal CARS-PLS-DA model acquired a sensitivity of 93.62%, a specificity of 88.68%, the area under the receiver operating characteristic curve (AUC) value of 0.91, and Kappa coefficient of 0.82 in prediction set. Classification maps were finally generated by classifying the varieties of each pixel in multispectral images at CARS-selected wavelengths, and the general variety was then readily discernible. These results demonstrated that features extracted from HSI had outstanding ability, and could be applied as a reliable tool for the further development of an on-line identification system for Chinese walnut variety.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

Imaging spectroscopy has emerged as a reliable analytical method for effectively characterizing and quantifying quality attributes of agricultural products. By providing spectral information relevant to food quality properties, imaging spectroscopy has been demonstrated to be a potential method for rapid and non-destructive classification, authentication, and prediction of quality parameters of various categories of tubers, including potato and sweet potato. The imaging technique has demonstrated great capacities for gaining rapid information about tuber physical properties (such as texture, water binding capacity, and specific gravity), chemical components (such as protein, starch, and total anthocyanin), varietal authentication, and defect aspects. This paper emphasizes how recent developments in spectral imaging with machine learning have enhanced overall capabilities to evaluate tubers. The machine learning algorithms coupled with feature variable identification approaches have obtained acceptable results. This review briefly introduces imaging spectroscopy and machine learning, then provides examples and discussions of these techniques in tuber quality determinations, and presents the challenges and future prospects of the technology. This review will be of great significance to the study of tubers using spectral imaging technology.

Chemometrics in Tandem with Hyperspectral Imaging for Detecting Authentication of Raw and Cooked Mutton Rolls

Authentication assurance of meat or meat products is critical in the meat industry. Various methods including DNA- or protein-based techniques are accurate for assessing meat authenticity, however, they are destructive, expensive, or laborious. This study explores the feasibility of chemometrics in tandem with hyperspectral imaging (HSI) for identifying raw and cooked mutton rolls substitution by pork and duck rolls. Raw or cooked samples (n = 180) of three meat species were prepared to collect hyperspectral images in range of 400-1000 nm. Spectra were extracted from representative regions of interest (ROIs), and spectral principal component analysis (PCA) revealed that PC1 and PC2 were effective for the identification. Different methods including standard normal variable (SNV), first and second derivatives, and normalization were individually employed for spectral preprocessing, and modeling methods of partial least squares-discriminant analysis (PLS-DA) and support vector machines (SVM) were also individually applied to develop classification models for both the raw and the cooked. Results showed that PLS-DA model developed by raw spectra presented the highest 100% correct classification rate (CCR) of success in all sets. After that, effective wavelengths selected by successive projections algorithm (SPA) built optimal simplified models which didn't influence the modeling results compared with full spectra regardless of the meat roll states. Therefore, SPA-PLS-DA models were subsequently used to visualize the raw and cooked meat rolls classification. As a consequence, the general meat species of both raw and cooked meat rolls were readily discernible in pixel-wise manner by generating classification maps. The results showed that HSI combined with chemometrics can be used to identify the authentication of raw and cooked mutton rolls substituted by pork and duck rolls accurately. This promising methodology provides a reference which can be extended to the classification or grading of other meat rolls.

Quantitative detection of soluble solids content, pH, and total phenol in Cabernet Sauvignon grapes based on near infrared spectroscopy

Determination of Cabernet Sauvignon grapes quality plays an important role in commercial processing. In this research, a rapid approach based on near infrared spectroscopy was proposed to the determination of soluble solids content (SSC), pH, and total phenol content (TPC) in entire bunches of Cabernet Sauvignon grapes. Standardized normal variate (SNV) and competitive adaptive weighted sampling (CARS), genetic algorithm (GA), and synergy interval partial least squares (si-PLS) were used to optimize the spectral data. With optimal combination input, the prediction accuracy of partial least squares regression (PLSR) and support vector regression (SVR) models was compared. The results showed that these models based on variable optimization method could predict well the SSC, pH, and TPC of Cabernet Sauvignon grapes. The correlation coefficient of prediction for SSC, pH, and TPC had reached more than 0.85. This work provides an alternative to analyze the chemical parameters in whole bunch of Cabernet Sauvignon grape.

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.

Advanced Analysis of Roots and Tubers by Hyperspectral Techniques

Hyperspectral techniques in terms of spectroscopy and hyperspectral imaging have become reliable analytical tools to effectively describe quality attributes of roots and tubers (such as potato, sweet potato, cassava, yam, taro, and sugar beet). In addition to the ability for obtaining rapid information about food external or internal defects including sprout, bruise, and hollow heart, and identifying different grades of food quality, such techniques have also been implemented to determine physical properties (such as color, texture, and specific gravity) and chemical constituents (such as protein, vitamins, and carotenoids) in root and tuber products with avoidance of extensive sample preparation. Developments of related quality evaluation systems based on hyperspectral data that determine food quality parameters would bring about economic and technical values to the food industry. Consequently, a comprehensive review of hyperspectral literature is carried out in this chapter. The spectral data acquired, the multivariate statistical methods used, and the main breakthroughs of recent studies on quality determinations of root and tuber products are discussed and summarized. The conclusion elaborates the promise of how hyperspectral techniques can be applied for non-invasive and rapid evaluations of tuber quality properties.

Detection and classification of citrus green mold caused by Penicillium digitatum using multispectral imaging

BACKGROUND

Fungal decay is a prevalent condition that mainly occurs during transportation of products to consumers (from harvest to consumption) and adversely affects postharvest operations and sales of citrus fruit. There are a variety of methods to control pathogenic fungi, including UV-assisted removal of fruit with suspected infection before storage, which is a time-consuming task and associated with human health risks. Therefore it is essential to adopt efficient and dependable alternatives for early decay detection. In this study, detection of orange decay caused by Penicillium genus fungi was examined using spectral imaging, a novel automated inspection technique for agricultural products.

RESULTS

The reflectance parameter (including mean reflectance) and reflectance distribution parameters (including standard deviation and skewness) of surfaces were extracted from decayed and rotten regions of infected samples and healthy regions of non-infected samples. The classification accuracy of rotten, decayed and healthy regions at 4 and 5 days after fungal inoculation was 98.6 and 100% respectively using the mean and skewness of 500 nm, 800 nm, 900 nm and modified normalized difference vegetation index (MNDVI) spectra.

CONCLUSION

Comparison of results between healthy and infected samples showed that early real-time detection of Penicillium digitatum using multispectral imaging was possible within the near-infrared (NIR) range. © 2018 Society of Chemical Industry.

Applying hyperspectral imaging to explore natural plant diversity towards improving salt stress tolerance

Salinity represents an abiotic stress constraint affecting growth and productivity of plants in many regions of the world. One of the possible solutions is to improve the level of salt resistance using natural genetic variability within crop species. In the context of recent knowledge on salt stress effects and mechanisms of salt tolerance, this review present useful phenomic approach employing different non-invasive imaging systems for detection of quantitative and qualitative changes caused by salt stress at the plant and canopy level. The focus is put on hyperspectral imaging technique, which provides unique opportunities for fast and reliable estimate of numerous characteristics associated both with various structural, biochemical and physiological traits. The method also provides possibilities to combine plant and canopy analyses with a direct determination of salinity in soil. The future perspectives in salt stress applications as well as some limits of the method are also identified.

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.

Advances in feature selection methods for hyperspectral image processing in food industry applications: a review

There is an increased interest in the applications of hyperspectral imaging (HSI) for assessing food quality, safety, and authenticity. HSI provides abundance of spatial and spectral information from foods by combining both spectroscopy and imaging, resulting in hundreds of contiguous wavebands for each spatial position of food samples, also known as the curse of dimensionality. It is desirable to employ feature selection algorithms for decreasing computation burden and increasing predicting accuracy, which are especially relevant in the development of online applications. Recently, a variety of feature selection algorithms have been proposed that can be categorized into three groups based on the searching strategy namely complete search, heuristic search and random search. This review mainly introduced the fundamental of each algorithm, illustrated its applications in hyperspectral data analysis in the food field, and discussed the advantages and disadvantages of these algorithms. It is hoped that this review should provide a guideline for feature selections and data processing in the future development of hyperspectral imaging technique in foods.

Recent Progress of Hyperspectral Imaging on Quality and Safety Inspection of Fruits and Vegetables: A Review

Objective quality assessment and efficacious safety surveillance for agricultural and food products are inseparable from innovative techniques. Hyperspectral imaging (HSI), a rapid, nondestructive, and chemical-free method, is now emerging as a powerful analytical tool for product inspection by simultaneously offering spatial information and spectral signals from one object. This paper focuses on recent advances and applications of HSI in detecting, classifying, and visualizing quality and safety attributes of fruits and vegetables. First, the basic principles and major instrumental components of HSI are presented. Commonly used methods for image processing, spectral pretreatment, and modeling are summarized. More importantly, morphological calibrations that are essential for nonflat objects as well as feature wavebands extraction for model simplification are provided. Second, in spite of the physical and visual attributes (size, shape, weight, color, and surface defects), applications from the last decade are reviewed specifically categorized into textural characteristics inspection, biochemical components detection, and safety features assessment. Finally, technical challenges and future trends of HSI are discussed.