Prediction of banana quality indices from color features using support vector regression

Banana fruit bruise detection using fractal dimension based image processing

The study used the fractal dimension (FD), browning incidence, and grayscale values using machine vision to describe the bruise magnitude and quality of mechanically damaged 'Fard' bananas bruised from 20, 40, 60 cm drop heights by 66, 98, and 110 g ball weights conditioned at different storage temperatures (5, 13, 22 °C) after 48 h. Conventional analyses like bruise area (BA), bruise volume (BV), and bruise susceptibility (BS) were also conducted. A correlation was performed to determine the relationship between image processing and conventional assessment of bruise damage in bananas. Weight, firmness, color, sugar content, and acidity were investigated. The results demonstrated that bananas bruised from the highest force and stored at 5 and 22 °C reported the lowest FD with values of 1.7162 and 1.7403, respectively. Increasing the level of damage reduced the fractal dimension and grayscale values and increased browning incidence and bruise susceptibility values after 48 h of storage. The total color change values showed a strong Pearson's correlation coefficient (r≥-0.81) with image analysis fractal dimension and grayscale values. The findings also indicated that higher bruising and temperature can induce weight loss, firmness reduction, lightness, and yellowness increment, and sugar and acidity changes. Overall, the fractal image analysis conducted in this study was highly effective in describing the bruising magnitude of bananas under different conditions.

Prediction of Bioactive Compounds and Antioxidant Activity in Bananas during Ripening Using Non-Destructive Parameters as Input Data

Vegetable quality parameters are established according to standards primarily based on visual characteristics. Although knowledge of biochemical changes in the secondary metabolism of plants throughout development is essential to guide decision-making about consumption, harvesting and processing, these determinations involve the use of reagents, specific equipment and sophisticated techniques, making them slow and costly. However, when non-destructive methods are employed to predict such determinations, a greater number of samples can be tested with adequate precision. Therefore, the aim of this work was to establish an association capable of modeling between non-destructive-physical and colorimetric aspects (predictive variables)-and destructive determinations-bioactive compounds and antioxidant activity (variables to be predicted), quantified spectrophotometrically and by HPLC in 'Nanicão' bananas during ripening. It was verified that to predict some parameters such as flavonoids, a regression equation using predictive parameters indicated the importance of R2, which varied from 83.43 to 98.25%, showing that some non-destructive parameters can be highly efficient as predictors.

Key steps for improving bacterial SERS signals in complex samples: Separation, recognition, detection, and analysis

Rapid and reliable detection of pathogenic bacteria is absolutely essential for research in environmental science, food quality, and medical diagnostics. Surface-enhanced Raman spectroscopy (SERS), as an emerging spectroscopic technique, has the advantages of high sensitivity, good selectivity, rapid detection speed, and portable operation, which has been broadly used in the detection of pathogenic bacteria in different kinds of complex samples. However, the SERS detection method is also challenging in dealing with the detection difficulties of bacterial samples in complex matrices, such as interference from complex matrices, confusion of similar bacteria, and complexity of data processing. Therefore, researchers have developed some technologies to assist in SERS detection of bacteria, including both the front-end process of obtaining bacterial sample data and the back-end data processing process. The review summarizes the key steps for improving bacterial SERS signals in complex samples: separation, recognition, detection, and analysis, highlighting the principles of each step and the key roles for SERS pathogenic bacteria analysis, and the interconnectivity between each step. In addition, the current challenges in the practical application of SERS technology and the development trends are discussed. The purpose of this review is to deepen researchers' understanding of the various stages of using SERS technology to detect bacteria in complex sample matrices, and help them find new breakthroughs in different stages to facilitate the detection and control of bacteria in complex samples.

Prediction of banana maturity based on the sweetness and color values of different segments during ripening

To predict the maturity of bananas, the present study used non-destructive methods to analyze changes in the sweetness and color of the stalks, middles, and tips of bananas during ripening. The results indicated that the respective maturation of these three segments did not occur simultaneously, as indicated by the differential enzyme activity and gene expression levels recorded in these segments. A principal component analysis and cluster plots were used to review the classification of banana maturity, highlighting that banana maturation can be divided into six stages. Two distinct maturity prediction algorithms were established using random forest, artificial neural network, and support vector machines, and they also indicated that dividing the maturity of bananas into six stages was adequate. These findings contribute to the development of quality evaluation and of a rapid grading system for processing, which improves the quality and sale of banana fruits and the related processed products.

•

Sweetness and color during ripening were assessed along banana fingers.

•

A new maturity prediction model was established for bananas.

•

Banana maturity was divided in six stages.

•

The theoretical basis for developing a maturity grading detection device was set.

Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy

Stone cells are a distinctive characteristic of pears and their formation negatively affects the quality of the fruit. To evaluate the stone cell content (SCC) of Korla fragrant pears, we developed a Vis/NIR spectroscopy system that allowed for the adjustment of the illuminating angle. The successive projective algorithm (SPA) and the Monte Carlo uninformative variable elimination (MCUVE) based on the sampling algorithm were used to select characteristic wavelengths. The particle swarm optimization (PSO) algorithm was used to optimize the combination of penalty factor C and kernel function parameter g. Support vector regression (SVR) was used to construct the evaluation model of the SCC. The SCC of the calibration set ranged from 0.240% to 0.657% and that of the validation set ranged from 0.315% to 0.652%. The SPA and MCUVE were used to optimize 57 and 83 characteristic wavelengths, respectively. The combinations of C and g were (6.2561, 0.2643) and (2.5133, 0.1128), respectively, when different characteristic wavelengths were used as inputs of SVR, indicating that the first combination had good generalization ability. The correlation coefficients of the SPA-SVR model after pre-processing the standardized normal variate (SNV) for both sets were 0.966 and 0.951, respectively. These results show that the SNV-SPA-SVR model satisfied the requirements of intelligent evaluation of SCC in Korla fragrant pears.

Prediction of the ripening stages of papayas using discriminant analysis and support vector machine algorithms

BACKGROUND

Evaluation of the quality properties of papaya becomes essential due to the acceleration of the fruit shelf-life senescence and the deterioration factor of the expected postharvest operations. In this study, the colour features in RGB, normalised RGB, HSV and L*a*b* channels were extracted and correlated with mechanical properties, moisture content (MC), total soluble solids (TSS) and pH for the prediction of quality properties at five ripening stages of papaya (R1-R5).

RESULTS

The mean values of colour features in RGB R m , G m , B m , normalised RGB R nm , G nm , B nm HSV H m , S m , V m , and L*a*b* L m , a m , b m were the best estimator for predicting TSS with R²  ≥ 0.90. All colour channels also showed satisfactory accuracies of R² ≥ 0.80 in predicting the bioyield force, apparent modulus and mean force. The highest average classification accuracy was obtained using linear discriminant analysis (LDA) with an average accuracy of more than 82%. The study showed that LDA, linear support vector machine, quadratic discriminant analysis and quadratic support vector machine obtained the correct classification of up to 100% for R5, whereas R1, R2, R3 and R4 gave classification accuracies in the range 83.75-91.85%, 85.6-90.25%, 85.75-90.85% and 77.35-87.15%, respectively. This indicates that R5 colour information was obviously different from R1-R4. The mean values of the HSV channel indicated the best performance to predict the ripening stages of papaya, compared to RGB, normalised RGB and L*a*b* channels, with an average classification accuracy of more than 80%.

CONCLUSION

The study has shown the versatility of a machine vision system in predicting the quality changes in papaya. The results showed that the machine vision system can be used to predict the ripening stages as well as classifying the fruits into different ripening stages of papayas. © 2021 Society of Chemical Industry.

Safety of Food and Food Warehouse Using VIBHISHAN

Food is one of the integral parts of human life making the quality of food one of the prime factors in its selection for consumption. In order to maintain the food quality, it must be taken care of from the very first step where its quality may be affected, that is, warehouses. Food safety and safety of its warehouses is one of the major concerns, because many people lose their lives due to poor food quality. A robot that can ensure the safety of both food and warehouse can be one of the possible solutions, because taking care of huge warehouses is a tedious task and sometimes food present inside the warehouse gets unnoticed and thus get contaminated. Also safety of warehouses from intruders can be done by a robot, in any condition where it is difficult for human beings. This robot would be cheap and efficient and also make sure of safety, keeping the food intact and ensuring its fine quality.

Assessment of Grain Harvest Moisture Content Using Machine Learning on Smartphone Images for Optimal Harvest Timing

Grain moisture content (GMC) is a key indicator of the appropriate harvest period of rice. Conventional testing is time-consuming and laborious, thus not to be implemented over vast areas and to enable the estimation of future changes for revealing optimal harvesting. Images of single panicles were shot with smartphones and corrected using a spectral–geometric correction board. In total, 86 panicle samples were obtained each time and then dried at 80 °C for 7 days to acquire the wet-basis GMC. In total, 517 valid samples were obtained, in which 80% was randomly used for training and 20% was used for testing to construct the image-based GMC assessment model. In total, 17 GMC surveys from a total of 201 samples were also performed from an area of 1 m² representing on-site GMC, which enabled a multi-day GMC prediction. Eight color indices were selected using principal component analysis for building four machine learning models, including random forest, multilayer perceptron, support vector regression (SVR), and multivariate linear regression. The SVR model with a MAE of 1.23% was the most suitable for GMC of less than 40%. This study provides a real-time and cost-effective non-destructive GMC measurement using smartphones that enables on-farm prediction of harvest dates and facilitates the harvesting scheduling of agricultural machinery.

Predicting sensory evaluation of spinach freshness using machine learning model and digital images

The visual perception of freshness is an important factor considered by consumers in the purchase of fruits and vegetables. However, panel testing when evaluating food products is time consuming and expensive. Herein, the ability of an image processing-based, nondestructive technique to classify spinach freshness was evaluated. Images of spinach leaves were taken using a smartphone camera after different storage periods. Twelve sensory panels ranked spinach freshness into one of four levels using these images. The rounded value of the average from all twelve panel evaluations was set as the true label. The spinach image was removed from the background, and then converted into a gray scale and CIE-Lab color space (L*a*b*) and Hue, Saturation and Value (HSV). The mean value, minimum value, and standard deviation of each component of color in spinach leaf were extracted as color features. Local features were extracted using the bag-of-words of key points from Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elementary Features). The feature combinations selected from the spinach images were used to train machine learning models to recognize freshness levels. Correlation analysis between the extracted features and the sensory evaluation score showed a positive correlation (0.5 < r < 0.6) for four color features, and a negative correlation (‒0.6 < r < ‒0.5) for six clusters in the local features. The support vector machine classifier and artificial neural network algorithm successfully classified spinach samples with overall accuracy 70% in four-class, 77% in three-class and 84% in two-class, which was similar to that of the individual panel evaluations. Our findings indicate that a model using support vector machine classifiers and artificial neural networks has the potential to replace freshness evaluations currently performed by non-trained panels.

Comparison of the Performance of Partial Least Squares and Support Vector Regressions for Predicting Fatty Acids and Fatty Acid Classes in Marine Oil Dietary Supplements by Using Vibrational Spectroscopic Data

ABSTRACT

Simple, fast, and accurate analytical techniques for verifying the accuracy of label declarations for marine oil dietary supplements containing eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) are required because of the increased consumption of these products. We recently developed broad-based partial least squares regression (PLS-R) models to quantify six fatty acids (FAs) and FA classes by using the spectroscopic data from a portable Fourier transform infrared (FTIR) device and a benchtop Fourier transform near infrared (FT-NIR) spectrometer. We developed an improved quantification method for these FAs and FA classes by incorporating a nonlinear calibration approach based on the machine learning technique support vector machines. For the two spectroscopic methods, high accuracy in prediction was indicated by low root mean square error of prediction and by correlation coefficients (R2) close to 1, indicating excellent model performance. The percent accuracy of the support vector regression (SV-R) model predicted values for EPA and DHA in the reference material was 90 to 110%. In comparison to PLS-R, SV-R accuracy for prediction of FA and FA class concentrations was up to 2.4 times higher for both ATR-FTIR and FT-NIR spectroscopic data. The SV-R models also provided closer agreement with the certified and reference values for the prediction of EPA and DHA in the reference standard. Based on our findings, the SV-R methods had superior accuracy and predictive quality for predicting the FA concentrations in marine oil dietary supplements. The combination of SV-R with ATR-FTIR and/or FT-NIR spectroscopic data can potentially be applied for the rapid screening of marine oil products to verify the accuracy of label declarations.

HIGHLIGHTS

Prediction of Congou Black Tea Fermentation Quality Indices from Color Features Using Non-Linear Regression Methods

Fermentation is the key process to produce the special color of congou black tea. The machine vision technology is applied to detect the color space changes of black tea's color in RGB, Lab and HSV, and to find out its relevance to black tea's fermentation quality. And then the color feature parameter is used as input to establish physicochemical indexes (TFs, TRs, and TBs) and sensory features' linear and non-linear quantitative evaluation model. Results reveal that color features are significantly correlated to quality indices. Compared with the other two color models (RGB and HSV), CIE Lab model can better reflect the dynamic variation features of quality indices and foliage color information of black tea. The predictability of non-linear models (RF and SVM) is superior to PLS linear model, while RF model presents a slight advantage over the classic SVM model since RF model can better represent the quantitative analytical relationship between image information and quality indices. This research has proved that computer image color features and non-linear method can be used to quantitatively evaluate the changes of quality indices (e.g. sensory quality) and the pigment during black tea's fermentation. Besides, the test is simple, fast, and nondestructive.

Prediction of Moisture Content for Congou Black Tea Withering Leaves Using Image Features and Nonlinear Method

Withering is the first step in the processing of congou black tea. With respect to the deficiency of traditional water content detection methods, a machine vision based NDT (Non Destructive Testing) method was established to detect the moisture content of withered leaves. First, according to the time sequences using computer visual system collected visible light images of tea leaf surfaces, and color and texture characteristics are extracted through the spatial changes of colors. Then quantitative prediction models for moisture content detection of withered tea leaves was established through linear PLS (Partial Least Squares) and non-linear SVM (Support Vector Machine). The results showed correlation coefficients higher than 0.8 between the water contents and green component mean value (G), lightness component mean value (L^*) and uniformity (U), which means that the extracted characteristics have great potential to predict the water contents. The performance parameters as correlation coefficient of prediction set (Rp), root-mean-square error of prediction (RMSEP), and relative standard deviation (RPD) of the SVM prediction model are 0.9314, 0.0411 and 1.8004, respectively. The non-linear modeling method can better describe the quantitative analytical relations between the image and water content. With superior generalization and robustness, the method would provide a new train of thought and theoretical basis for the online water content monitoring technology of automated production of black tea.

Evaluation of Chilling Injury in Mangoes Using Multispectral Imaging

Commodities originating from tropical and subtropical climes are prone to chilling injury (CI). This injury could affect the quality and marketing potential of mango after harvest. This will later affect the quality of the produce and subsequent consumer acceptance. In this study, the appearance of CI symptoms in mango was evaluated non-destructively using multispectral imaging. The fruit were stored at 4 °C to induce CI and 12 °C to preserve the quality of the control samples for 4 days before they were taken out and stored at ambient temperature for 24 hr. Measurements using multispectral imaging and standard reference methods were conducted before and after storage. The performance of multispectral imaging was compared using standard reference properties including moisture content (MC), total soluble solids (TSS) content, firmness, pH, and color. Least square support vector machine (LS-SVM) combined with principal component analysis (PCA) were used to discriminate CI samples with those of control and before storage, respectively. The statistical results demonstrated significant changes in the reference quality properties of samples before and after storage. The results also revealed that multispectral parameters have a strong correlation with the reference parameters of L^* , a^* , TSS, and MC. The MC and L^* were found to be the best reference parameters in identifying the severity of CI in mangoes. PCA and LS-SVM analysis indicated that the fruit were successfully classified into their categories, that is, before storage, control, and CI. This indicated that the multispectral imaging technique is feasible for detecting CI in mangoes during postharvest storage and processing.

PRACTICAL APPLICATION

This paper demonstrates a fast, easy, and accurate method of identifying the effect of cold storage on mango, nondestructively. The method presented in this paper can be used industrially to efficiently differentiate different fruits from each other after low temperature storage.

Sensory quality evaluation for appearance of needle-shaped green tea based on computer vision and nonlinear tools

Tea is one of the three greatest beverages in the world. In China, green tea has the largest consumption, and needle-shaped green tea, such as Maofeng tea and Sparrow Tongue tea, accounts for more than 40% of green tea (Zhu et al., 2017). The appearance of green tea is one of the important indexes during the evaluation of green tea quality. Especially in market transactions, the price of tea is usually determined by its appearance (Zhou et al., 2012). Human sensory evaluation is usually conducted by experts, and is also easily affected by various factors such as light, experience, psychological and visual factors. In the meantime, people may distinguish the slight differences between similar colors or textures, but the specific levels of the tea are hard to determine (Chen et al., 2008). As human description of color and texture is qualitative, it is hard to evaluate the sensory quality accurately, in a standard manner, and objectively. Color is an important visual property of a computer image (Xie et al., 2014; Khulal et al., 2016); texture is a visual performance of image grayscale and color changing with spatial positions, which can be used to describe the roughness and directivity of the surface of an object (Sanaeifar et al., 2016). There are already researchers who have used computer visual image technologies to identify the varieties, levels, and origins of tea (Chen et al., 2008; Xie et al., 2014; Zhu et al., 2017). Most of their research targets are crush, tear, and curl (CTC) red (green) broken tea, curly green tea (Bilochun tea), and flat-typed green tea (West Lake Dragon-well green tea) as the information sources. However, the target of the above research is to establish a qualitative evaluation method on tea quality (Fu et al., 2013). There is little literature on the sensory evaluation of the appearance quality of needle-shaped green tea, especially research on a quantitative evaluation model (Zhou et al., 2012; Zhu et al., 2017).

Prediction of Firmness and pH for "Golden Delicious" Apple Based on Elasticity Index from Modal Analysis

An experimental modal test system was established to extract the natural frequencies of "Golden Delicious" apple, after which the elasticity index was calculated to predict the apple quality parameters based on the orthogonal polynomials method. The elasticity index in every vibration mode changed dramatically (P = 0.01) along time revolution. The multivariate regression methods were used to model the predictive relationship between the elasticity index and the apple quality parameters. The models of the apple juice pH based on support vector regression presented adequate determination coefficients of calibration set (Q²  = 0.68) and prediction set (R²  = 0.55), respectively. The models based on partial least squares regression could be used for predicting the apple firmness parameter offset gradient (Q²  = 0.76 and R²  = 0.72). It helped understanding the fruit dynamic properties of the fruit and spontaneously obtaining the fruit chemical parameters. A nondestructive and portable device was viable for fruit quality estimation by the modal test system during storage, transport, and even growth on the tree.

PRACTICAL APPLICATION

A nondestructive and portable device was provided for fruit quality detection during storage, transport and even growth based on experimental modal analysis. A systematic statistical analysis method about outlier detection, data set partitioning, parameter optimization, and multiple regression models were provided.

Chemometric Analysis of the Volatile Compounds Generated by Aspergillus carbonarius Strains Isolated from Grapes and Dried Vine Fruits

Ochratoxin A (OTA) contamination in grape production is an important problem worldwide. Microbial volatile organic compounds (MVOCs) have been demonstrated as useful tools to identify different toxigenic strains. In this study, Aspergillus carbonarius strains were classified into two groups, moderate toxigenic strains (MT) and high toxigenic strains (HT), according to OTA-forming ability. The MVOCs were analyzed by GC-MS and the data processing was based on untargeted profiling using XCMS Online software. Orthogonal projection to latent structures discriminant analysis (OPLS-DA) was performed using extract ion chromatogram GC-MS datasets. For contrast, quantitative analysis was also performed. Results demonstrated that the performance of the OPLS-DA model of untargeted profiling was better than the quantitative method. Potential markers were successfully discovered by variable importance on projection (VIP) and t-test. (E)-2-octen-1-ol, octanal, 1-octen-3-one, styrene, limonene, methyl-2-phenylacetate and 3 unknown compounds were selected as potential markers for the MT group. Cuparene, (Z)-thujopsene, methyl octanoate and 1 unknown compound were identified as potential markers for the HT groups. Finally, the selected markers were used to construct a supported vector machine classification (SVM-C) model to check classification ability. The models showed good performance with the accuracy of cross-validation and test prediction of 87.93% and 92.00%, respectively.