Advances in Non-Destructive Early Assessment of Fruit Ripeness towards Defining Optimal Time of Harvest and Yield Prediction-A Review

Automated lesion detection in cotton leaf visuals using deep learning

Cotton is one of the major cash crop in the agriculture led economies across the world. Cotton leaf diseases affects its yield globally. Determining cotton lesions on leaves is difficult when the area is big and the size of lesions is varied. Automated cotton lesion detection is quite useful; however, it is challenging due to fewer disease class, limited size datasets, class imbalance problems, and need of comprehensive evaluation metrics. We propose a novel deep learning based method that augments the data using generative adversarial networks (GANs) to reduce the class imbalance issue and an ensemble-based method that combines the feature vector obtained from the three deep learning architectures including VGG16, Inception V3, and ResNet50. The proposed method offers a more precise, efficient and scalable method for automated detection of diseases of cotton crops. We have implemented the proposed method on publicly available dataset with seven disease and one health classes and have achieved highest accuracy of 95% and F-1 score of 98%. The proposed method performs better than existing state of the art methods.

Grape Maturity Estimation Using Time-of-Flight and LiDAR Depth Cameras

This article investigates the potential for using low-cost depth cameras to estimate the maturity of green table grapes after they have been harvested. Time-of-flight (Kinect Azure) and LiDAR (Intel L515) depth cameras were used to capture depth scans of green table grape berries over time. The depth scans of the grapes are distorted due to the diffused scattering of the light emitted from the cameras within the berries. This causes a distance bias where a grape berry appears to be further from the camera than it is. As the grape aged, the shape of the peak corresponding to the grape became increasingly flattened in shape, resulting in an increased distance bias over time. The distance bias variation with time was able to be fitted with an R2 value of 0.969 for the Kinect Azure and an average of 0.904 for the Intel L515. This work shows that there is potential to use time-of-flight and LIDAR cameras for estimating grape maturity postharvest in a non-contact and nondestructive manner.

Evaluation of Color and Pigment Changes in Tomato after 1-Methylcyclopropene (1-MCP) Treatment

The Polar Qualification System (PQS) was applied on hue spectra fingerprinting to describe color changes in tomato during storage. The cultivar 'Pitenza' was harvested at six different maturity stages, and half of the samples were subjected to gaseous 1-methylcyclopropene (1-MCP) treatment. Reference color parameters were recorded with a vision system colorimeter instrument, and the fruit pigment concentration was assessed with the DA-index®. Additionally, acoustic firmness (Stiffness) was measured. All acquired reference parameters were used to grade fruit in the supply chain. The applied 1-MCP treatments were used to control the ripening of climacteric horticultural produce. Both the DA-index® and stiffness values, presented as chlorophyll concentration and acoustic firmness, showed significant differences among maturity stages and treated and control samples and in their kinetics during storage. The machine vision parameter PQS-X was significantly affected by 1-MCP treatment (F = 10.18, p < 0.01), while PQS-Y was primarily affected by storage time (F = 18.18, p < 0.01) and maturity stage (F = 11.15, p < 0.01). A significant correlation was achieved for acoustic firmness with normalized color (r > 0.78) and PQS-Y (r > 0.80), as well as for the DA-index® (r > 0.9). The observed color changes agreed with the reference measurements. The significant statistical effect on the PQS coordinates suggests that hue spectra fingerprinting with this data compression technique is suitable for quality assessment based on color.

Validation study on light scattering changes in kiwifruit during postharvest storage using time-resolved transmittance spectroscopy

Visible and near-infrared spectroscopy has been well studied for characterizing the organic compounds in fruit and vegetables from pre-harvest to late harvest. However, due to the challenge of decoupling of optical properties, the relationship between the collected samples' spectral data and their properties, especially their mechanical properties (e.g., firmness, hardness, and resilience) is hard to understand. This study developed a time-resolved transmittance spectroscopic method to validate the light scattering changing characteristics in kiwifruit during shelf-life and in cold storage conditions. The experimental results demonstrated that the reduced scattering coefficient ([Formula: see text]) of 846 nm inside kiwifruit decreased steadily during postharvest storage and is more evident under shelf-life than in cold storage conditions. Moreover, the correlation between the [Formula: see text] and the storage time was confirmed to be much higher than that using the external color indexes measured using a conventional colorimeter. Furthermore, employing time-resolved profiles at this single wavelength, an efficacious mathematical model has been successfully formulated to classify the stages of kiwifruit softening, specifically early, mid-, and late stages. Notably, classification accuracies of 84% and 78% were achieved for the shelf-life and cold storage conditions, respectively.

Tomato Maturity Detection and Counting Model Based on MHSA-YOLOv8

The online automated maturity grading and counting of tomato fruits has a certain promoting effect on digital supervision of fruit growth status and unmanned precision operations during the planting process. The traditional grading and counting of tomato fruit maturity is mostly done manually, which is time-consuming and laborious work, and its precision depends on the accuracy of human eye observation. The combination of artificial intelligence and machine vision has to some extent solved this problem. In this work, firstly, a digital camera is used to obtain tomato fruit image datasets, taking into account factors such as occlusion and external light interference. Secondly, based on the tomato maturity grading task requirements, the MHSA attention mechanism is adopted to improve YOLOv8's backbone to enhance the network's ability to extract diverse features. The Precision, Recall, F1-score, and mAP50 of the tomato fruit maturity grading model constructed based on MHSA-YOLOv8 were 0.806, 0.807, 0.806, and 0.864, respectively, which improved the performance of the model with a slight increase in model size. Finally, thanks to the excellent performance of MHSA-YOLOv8, the Precision, Recall, F1-score, and mAP50 of the constructed counting models were 0.990, 0.960, 0.975, and 0.916, respectively. The tomato maturity grading and counting model constructed in this study is not only suitable for online detection but also for offline detection, which greatly helps to improve the harvesting and grading efficiency of tomato growers. The main innovations of this study are summarized as follows: (1) a tomato maturity grading and counting dataset collected from actual production scenarios was constructed; (2) considering the complexity of the environment, this study proposes a new object detection method, MHSA-YOLOv8, and constructs tomato maturity grading models and counting models, respectively; (3) the models constructed in this study are not only suitable for online grading and counting but also for offline grading and counting.

Effect of Calcium Foliar Spray Technique on Mechanical Properties of Strawberries

The calcium fertilization of strawberry plants (Fragaria × ananassa Duchesne) was evaluated using two types of nozzles, with two liquid pressure levels and two driving speeds. The calcium content of the leaves and fruit were analyzed via flame photometry. Higher leaf calcium content was found in plots sprayed with standard nozzles, while higher fruit calcium content was observed for those sprayed with air induction nozzles. The fruit quality was assessed by determining the basic physical and mechanical properties, using uniaxial compression tests integrated with surface pressure measurements. Different spraying techniques influenced the mechanical resistance of the fruit. A spraying speed of 5 km/h and an operating pressure of 0.4 MPa significantly increased the firmness of the fruit by ~66%, the critical load level by 36%, and the maximum surface pressure by up to 38%, but did not increase the geometrical parameters of the strawberries. Regular foliar feeding during harvest could improve the mechanical strength of strawberries. An appropriate spraying technique with a calcium agent could effectively improve the mechanical properties of the delicate fruit, which is particularly important for limiting losses during harvesting, transportation, and storage.

Growth and inactivation of Listeria monocytogenes in sterile extracts of fruits and vegetables: Impact of the intrinsic factors pH, sugar and organic acid content

Intrinsic characteristics of fresh produce, such as pH, water activity, acid content and nutrient availability are critical factors in determining the survival and growth of Listeria monocytogenes (Lm). In this study, sterile fresh produce juice was used to analyze Lm growth potential among 14 different commodities and to identify physicochemical characteristics in those juices that affect Lm growth. Significant growth of Lm was observed in juices with pH ≥5.6 and low acidity (0.04-0.07 % titratable acidity (TA)) (cantaloupe, carrot, celery, green pepper, parsley, and romaine lettuce), slight reduction of Lm was observed in juices with pH 4.1 (tomato) and pH 3.9 (mango), and no Lm counts were recovered from juices with pH ≤3.8 and high acidity (0.28-1.17 % TA) (apple, blueberry, grape, peach, and pineapple). Although these acidic fruit juices possessed a high sugar content, the pH and acidity of produce juice seemed to be the primary determinants for Lm growth. The neutralization of acidic juices (i.e., Fuji and Gala apple, blueberry, grape, mango, pineapple, peach, and tomato) enabled Lm growth at 37 °C in all juices except for Gala apple and peach. Strong decline in Lm populations in Gala apple, grape and peach juices might be linked to sensitivity to organic acids, such as malic acid. Furthermore, Lm populations significantly decreased in pH-neutral (7.6) cauliflower juice, suggesting that potential antilisterial substances may play a role in Lm decline in cauliflower juice.

Determining the Stir-Frying Degree of Gardeniae Fructus Praeparatus Based on Deep Learning and Transfer Learning

Gardeniae Fructus (GF) is one of the most widely used traditional Chinese medicines (TCMs). Its processed product, Gardeniae Fructus Praeparatus (GFP), is often used as medicine; hence, there is an urgent need to determine the stir-frying degree of GFP. In this paper, we propose a deep learning method based on transfer learning to determine the stir-frying degree of GFP. We collected images of GFP samples with different stir-frying degrees and constructed a dataset containing 9224 images. Five neural networks were trained, including VGG16, GoogLeNet, Resnet34, MobileNetV2, and MobileNetV3. While the model weights from ImageNet were used as initial parameters of the network, fine-tuning was used for four neural networks other than MobileNetV3. In the training of MobileNetV3, both feature transfer and fine-tuning were adopted. The accuracy of all five models reached more than 95.82% in the test dataset, among which MobileNetV3 performed the best with an accuracy of 98.77%. In addition, the results also showed that fine-tuning was better than feature transfer in the training of MobileNetV3. Therefore, we conclude that deep learning can effectively recognize the stir-frying degree of GFP.

Preparation of Methylcellulose Film-Based CO2 Indicator for Monitoring the Ripeness Quality of Mango Fruit cv. Nam Dok Mai Si Thong

Day-to-day advancements in food science and technology have increased. Indicators, especially biopolymer-incorporated organic dye indicators, are useful for monitoring the ripeness quality of agricultural fruit products. In this investigation, methylcellulose films—containing pH dye-based indicators that change color depending on the carbon dioxide (CO₂) levels—were prepared. The level of CO₂ on the inside of the packaging container indicated the ripeness of the fruit. Changes in the CO₂ level, caused by the ripeness metabolite during storage, altered the pH. The methylcellulose-based film contained pH-sensitive dyes (bromothymol blue and methyl red), which responded (through visible color change) to CO₂ levels produced by ripeness metabolites formed during respiration. The indicator solution and indicator label were monitored for their response to CO₂. In addition, a kinetic approach was used to correlate the response of the indicator label to the changes in mango ripeness. Color changes (the total color difference of a mixed pH dye-based indicator), correlated well with the CO₂ levels in mango fruit. In the ‘Nam Dok Mai Si Thong’ mango fruit model, the indicator response correlated with respiration patterns in real-time monitoring of ripeness at various constant temperatures. Based on the storage test, the indicator labels exhibited color changes from blue, through light bright green, to yellow, when exposed to CO₂ during storage time, confirming the minimal, half-ripe, and fully-ripe levels of mango fruit, respectively. The firmness and titratable acidity (TA) of the fruit decreased from 44.54 to 2.01 N, and 2.84 to 0.21%, respectively, whereas the soluble solid contents (SSC) increased from 10.70 to 18.26% when the fruit ripened. Overall, we believe that the application of prepared methylcellulose-based CO₂ indicator film can be helpful in monitoring the ripeness stage, or quality of, mango and other fruits, with the naked eye, in the food packaging system.

Convolutional Neural Networks for Estimating the Ripening State of Fuji Apples Using Visible and Near-Infrared Spectroscopy

The quality of fresh apple fruits is a major concern for consumers and manufacturers. Classification of these fruits according to their ripening stage is one of the most decisive factors in determining their quality. In this regard, the aim of this work is to develop a new method for non-destructive classification of the ripening state of Fuji apples using hyperspectral information in the visible and near-infrared (Vis/NIR) regions. Spectra of 172 apple samples in the range from 450 to 1000 nm were studied, which were selected from four different ripening stages. A convolutional neural network (CNN) model was proposed to perform the classification of the samples. The proposed method was compared with three alternative methods based on artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (KNN). The results revealed that the CNN method outperformed the alternative methods, achieving a correct classification rate (CCR) of 96.5%, compared with an average of 89.5%, 95.93%, and 91.68% for ANN, SVM, and KNN, respectively. These results will help in the development of a new device for fast and accurate estimation of the quality of apples.

Prediction of Oil Palm Yield Using Machine Learning in the Perspective of Fluctuating Weather and Soil Moisture Conditions: Evaluation of a Generic Workflow

Current development in precision agriculture has underscored the role of machine learning in crop yield prediction. Machine learning algorithms are capable of learning linear and nonlinear patterns in complex agro-meteorological data. However, the application of machine learning methods for predictive analysis is lacking in the oil palm industry. This work evaluated a supervised machine learning approach to develop an explainable and reusable oil palm yield prediction workflow. The input data included 12 weather and three soil moisture parameters along with 420 months of actual yield records of the study site. Multisource data and conventional machine learning techniques were coupled with an automated model selection process. The performance of two top regression models, namely Extra Tree and AdaBoost was evaluated using six statistical evaluation metrics. The prediction was followed by data preprocessing and feature selection. Selected regression models were compared with Random Forest, Gradient Boosting, Decision Tree, and other non-tree algorithms to prove the R2 driven performance superiority of tree-based ensemble models. In addition, the learning process of the models was examined using model-based feature importance, learning curve, validation curve, residual analysis, and prediction error. Results indicated that rainfall frequency, root-zone soil moisture, and temperature could make a significant impact on oil palm yield. Most influential features that contributed to the prediction process are rainfall, cloud amount, number of rain days, wind speed, and root zone soil wetness. It is concluded that the means of machine learning have great potential for the application to predict oil palm yield using weather and soil moisture data.

Rapid and Non-Destructive Techniques for the Discrimination of Ripening Stages in Candonga Strawberries

Electronic nose (e-nose), attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy and image analysis (IA) were used to discriminate the ripening stage (half-red or red) of strawberries (cv Sabrosa, commercially named Candonga), harvested at three different times (H1, H2 and H3). Principal component analysis (PCA) performed on the e-nose, ATR-FTIR and IA data allowed us to clearly discriminate samples based on the ripening stage, as in the score space they clustered in distinct regions of the plot. Moreover, a correlation analysis between the e-nose sensor and 57 volatile organic compounds (VOCs), which were overall detected in all the investigated fruit samples by headspace solid-phase microextraction coupled to gas chromatography-mass spectrometry (HS-SPME/GC-MS), allowed us to distinguish half-red and red strawberries, as the e-nose sensors gave distinct responses to samples with different flavours. Three suitable broad bands were individuated by PCA in the ATR-FTIR spectra to discriminate half-red and red samples: the band centred at 3295 cm⁻¹ is generated by compounds that decline, whereas those at 1717 cm⁻¹ and at 1026 cm⁻¹ stem from compounds that accumulate during ripening. Among the chemical parameters (titratable acidity, total phenols, antioxidant activity and total soluble solid) assayed in this study, only titratable acidity was somehow correlated to ATR-FTIR and IA patterns. Thus, ATR-FTIR spectroscopy and IA might be exploited to rapidly assess titratable acidity, which is an objective indicator of the ripening stage.

Rapid Identification of Apple Maturity Based on Multispectral Sensor Combined with Spectral Shape Features

The rapid and convenient detection of maturity is of great significance to determine the harvest time and postharvest storage conditions of apples. In this study, a portable visible and near-infrared (VIS/NIR) analysis device prototype was developed based on a multispectral sensor and applied to ‘Fuji’ apple maturity detection. The multispectral data of apples with maturity variation was measured, and the prediction model was established by a least-square support vector machine and linear discriminant analysis. Due to the low resolution of the multispectral data, regular preprocessing methods cannot improve the prediction accuracy. Instead, the spectral shape features (spectral ratio, spectral difference, and normalized spectral intensity difference) were used for preprocessing and model establishment, and the combination of the three features effectively improved the model performance with a prediction accuracy of 88.46%. In addition, the validation accuracy of the optimal model was 84.72%, and the area under curve (AUC) value of each maturity level was higher than 0.8972. The results show that the multispectral sensor is an appliable choice for the development of the portable detection device of apple maturity, and the data processing method proposed in this study provides a potential solution to improve the detection accuracy for multispectral sensors.

Optimization Model for Selective Harvest Planning Performed by Humans and Robots

This paper addresses the formulation of an individual fruit harvest decision as a nonlinear programming problem to maximize profit, while considering selective harvesting based on fruit maturity. A model for the operational level decision was developed and includes four features: time window constraints, resource limitations, yield perishability, and uncertainty. The model implementation was demonstrated through numerical studies that compared decisions for different types of worker and analyzed different robotic harvester capabilities for a case study of sweet pepper harvesting. The results show the influence of the maturity classification capabilities of the robot on its output, as well as the improvement in cycle times needed to reach the economic feasibility of a robotic harvester.

A Review on the Commonly Used Methods for Analysis of Physical Properties of Food Materials

The chemical composition of any food material can be analyzed well by employing various analytical techniques. The physical properties of food are no less important than chemical composition as results obtained from authentic measurement data are able to provide detailed information about the food. Several techniques have been used for years for this purpose but most of them are destructive in nature. The aim of this present study is to identify the emerging techniques that have been used by different researchers for the analysis of the physical characteristics of food. It is highly recommended to practice novel methods as these are non-destructive, extremely sophisticated, and provide results closer to true quantitative values. The physical properties are classified into different groups based on their characteristics. The concise view of conventional techniques mostly used to analyze food material are documented in this work.

Automatic Classification of the Ripeness Stage of Mango Fruit Using a Machine Learning Approach

Most mango farms classify the maturity stage manually by trained workers using external indicators such as size, shape, and skin color, which can lead to human error or inconsistencies. We developed four common machine learning (ML) classifiers, the k-mean, naïve Bayes, support vector machine, and feed-forward artificial neural network (FANN), all of which were aimed at classifying the ripeness stage of mangoes at harvest. The ML classifiers were trained on biochemical data and then tested on physical and electrical data.The performance of the ML models was compared using fourfold cross validation. The FANN classifier performed the best, with a mean accuracy of 89.6% for unripe, ripe, and overripe classes, when compared to the other classifiers.

Fruit ripening: dynamics and integrated analysis of carotenoids and anthocyanins

BACKGROUND

Fruits are vital food resources as they are loaded with bioactive compounds varying with different stages of ripening. As the fruit ripens, a dynamic color change is observed from green to yellow to red due to the biosynthesis of pigments like chlorophyll, carotenoids, and anthocyanins. Apart from making the fruit attractive and being a visual indicator of the ripening status, pigments add value to a ripened fruit by making them a source of nutraceuticals and industrial products. As the fruit matures, it undergoes biochemical changes which alter the pigment composition of fruits.

RESULTS

The synthesis, degradation and retention pathways of fruit pigments are mediated by hormonal, genetic, and environmental factors. Manipulation of the underlying regulatory mechanisms during fruit ripening suggests ways to enhance the desired pigments in fruits by biotechnological interventions. Here we report, in-depth insight into the dynamics of a pigment change in ripening and the regulatory mechanisms in action.

CONCLUSIONS

This review emphasizes the role of pigments as an asset to a ripened fruit as they augment the nutritive value, antioxidant levels and the net carbon gain of fruits; pigments are a source for fruit biofortification have tremendous industrial value along with being a tool to predict the harvest. This report will be of great utility to the harvesters, traders, consumers, and natural product divisions to extract the leading nutraceutical and industrial potential of preferred pigments biosynthesized at different fruit ripening stages.

A novel spatially resolved interactance spectroscopy system to estimate degree of red coloration in red-fleshed apple

Reliable information about degree of red coloration in fruit flesh is essential for grading and sorting of red-fleshed apples. We propose a spatially resolved interactance spectroscopy approach as a new rapid and non-destructive technique to estimate degree of red coloration in the flesh of a red-fleshed apple cultivar 'Kurenainoyume'. A novel measurement system was developed to obtain spatially resolved interactance spectra (190-1070 nm) for apple fruits at eight different light source-detector separation (SDS) distances on fruit surface. Anthocyanins in apple were extracted using a solvent extraction technique, and their contents were quantified with a spectrophotometer. Partial least squares (PLS) regression analyses were performed to develop estimation models for anthocyanin content from spatially resolved interactance spectra. Results showed that the PLS models based on interactance spectra obtained at different SDS distances achieved different predictive accuracy. Further, the system demonstrated the possibility to detect the degree of red coloration in the flesh at specific depths by identifying an optimal SDS distance. This might contribute to provide a detailed profile of the red coloration (anthocyanins) that is unevenly distributed among different depths of the flesh. This new approach may be potentially applied to grading and sorting systems for red-fleshed apples in fruit industry.

Current Status of Optical Systems for Measuring Lycopene Content in Fruits: Review

Optical systems are used for analysing the internal composition and the external properties in food. The measurement of the lycopene content in fruits and vegetables is important because of its benefits to human health. Lycopene prevents cardiovascular diseases, cataracts, cancer, osteoporosis, male infertility, and peritonitis. Among the optical systems focused on the estimation and identification of lycopene molecule are high-performance liquid chromatography (HPLC), the colorimeter, infrared near NIR spectroscopy, UV-VIS spectroscopy, Raman spectroscopy, and the systems of multispectral imaging (MSI) and hyperspectral imaging (HSI). The main objective of this paper is to present a review of the current state of optical systems used to measure lycopene in fruits. It also reports important factors to be considered in order to improve the design and implementation of those optical systems. Finally, it was observed that measurements with HPLC and spectrophotometry present the best results but use toxic solvents and require specialized personnel for their use. Moreover, another widely used technique is colorimetry, which correlates the lycopene content using color descriptors, typically those of CIELAB. Likewise, it was identified that spectroscopic techniques and multispectral images are gaining importance because they are fast and non-invasive.

A Method of Evaluating Apple Juice Adulteration with Sucrose Based on Its Electrical Properties and RCC Model

This study aimed to identify possibilities of controlling basic quality attributes (total soluble solids, organic acids, density, pH) and assessing the adulteration of natural dissociating solids with sucrose in apple juice produced from Malus domestica Borkh, var. Cortland, Idared, and Lobo (family Rosaceae Juss), using electrical parameters (conductivity Z, Y; capacity Cp, Cs) and the RCC equivalent electrical model. The feasibility of employing electrical parameters was established based on correlations between selected quality attributes of apple juices varying in sucrose contents in the extract TSSConc (0%, 15%, 20%, 25%, 30%) and their electrical parameters measured in a frequency range of 100 Hz to 100 kHz. The significant (p ≤ 0.01) correlations obtained between the selected physicochemical parameters of juice (TSSConc, OA) and electrical properties point to the feasibility of using them as an alternative quality assessment method to the reference methods (refractometric or potentiometric titration) used by the external supervising bodies. The electrical parameters (including Z100Hz and Y100Hz) measured in the RCC model can, in the future, aid the design of a simple tool for the quantitative determination of apple juice adulteration with sucrose. They also encourage further research of this electrical method as an alternative to traditional analytical methods for evaluating the authenticity or adulteration of commercial fruit juices with sucrose or other sweetening agents.

A Machine Vision Rapid Method to Determine the Ripeness Degree of Olive Lots

The degree of olive maturation is a very important factor to consider at harvest time, as it influences the organoleptic quality of the final product, for both oil and table use. The Jaén index, evaluated by measuring the average coloring of olive fruits (peel and pulp), is currently considered to be one of the most indicative methods to determine the olive ripening stage, but it is a slow assay and its results are not objective. The aim of this work is to identify the ripeness degree of olive lots through a real-time, repeatable, and objective machine vision method, which uses RGB image analysis based on a k-nearest neighbors classification algorithm. To overcome different lighting scenarios, pictures were subjected to an automatic colorimetric calibration method—an advanced 3D algorithm using known values. To check the performance of the automatic machine vision method, a comparison was made with two visual operator image evaluations. For 10 images, the number of black, green, and purple olives was also visually evaluated by these two operators. The accuracy of the method was 60%. The system could be easily implemented in a specific mobile app developed for the automatic assessment of olive ripeness directly in the field, for advanced georeferenced data analysis.

Multimodal Deep Learning and Visible-Light and Hyperspectral Imaging for Fruit Maturity Estimation

Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.

Remote Sensing and Machine Learning in Crop Phenotyping and Management, with an Emphasis on Applications in Strawberry Farming

Measurement of plant characteristics is still the primary bottleneck in both plant breeding and crop management. Rapid and accurate acquisition of information about large plant populations is critical for monitoring plant health and dissecting the underlying genetic traits. In recent years, high-throughput phenotyping technology has benefitted immensely from both remote sensing and machine learning. Simultaneous use of multiple sensors (e.g., high-resolution RGB, multispectral, hyperspectral, chlorophyll fluorescence, and light detection and ranging (LiDAR)) allows a range of spatial and spectral resolutions depending on the trait in question. Meanwhile, computer vision and machine learning methodology have emerged as powerful tools for extracting useful biological information from image data. Together, these tools allow the evaluation of various morphological, structural, biophysical, and biochemical traits. In this review, we focus on the recent development of phenomics approaches in strawberry farming, particularly those utilizing remote sensing and machine learning, with an eye toward future prospects for strawberries in precision agriculture. The research discussed is broadly categorized according to strawberry traits related to (1) fruit/flower detection, fruit maturity, fruit quality, internal fruit attributes, fruit shape, and yield prediction; (2) leaf and canopy attributes; (3) water stress; and (4) pest and disease detection. Finally, we present a synthesis of the potential research opportunities and directions that could further promote the use of remote sensing and machine learning in strawberry farming.

Tomato Growth State Map for the Automation of Monitoring and Harvesting

To realize smart agriculture, we engaged in its systematization, from monitoring to harvesting tomato fruits using robots. In this paper, we explain a method of generating a map of the tomato growth states to monitor the various stages of tomato fruits and decide a harvesting strategy for the robots. The tomato growth state map visualizes the relationship between the maturity stage, harvest time, and yield. We propose a generation method of the tomato growth state map, a recognition method of tomato fruits, and an estimation method of the growth states (maturity stages and harvest times). For tomato fruit recognition, we demonstrate that a simple machine learning method using a limited learning dataset and the optical properties of tomato fruits on infrared images exceeds more complex convolutional neural network, although the results depend on how the training dataset is created. For the estimation of the growth states, we conducted a survey of experienced farmers to quantify the maturity stages into six classifications and harvest times into three terms. The growth states were estimated based on the survey results. To verify the tomato growth state map, we conducted experiments in an actual tomato greenhouse and herein report the results.

Developing an Automatic Color Determination Procedure for the Quality Assessment of Mangos (Mangifera indica) Using a CCD Camera and Color Standards

Color is one of the key sensory characteristics in the evaluation of the quality of mangos (Mangifera indica) especially with regard to determining the optimal level of ripeness. However, an objective color determination of entire fruits can be a challenging task. Conventional evaluation methods such as colorimetric or spectrophotometric procedures are primarily limited to a homogenous distribution of the color. Accordingly, a direct assessment of the mango quality with regard to color requires more pronounced color determination procedures. In this study, the color of the peel and the pulp of the mango cultivars “Nam Dokmai”, “Mahachanok”, and “Kent” was evaluated and categorized into various levels of ripeness using a charge-coupled device (CCD) camera in combination with a computer vision system and color standards. The color evaluation process is based on a transformation of the RGB (red, green, and blue) color space values into the HSI (hue, saturation, and intensity) color system and the Natural Color Standard (NCS). The results showed that for pulp color codes, 0560-Y20R and 0560-Y40R can be used as appropriate indicators for the ripeness of the cultivars “Nam Dokmai” and “Mahachanok”. The peels of these two mango cultivars present two distinct colors (1050-Y40R and 1060-Y40R), which can be used to determine the fruit maturity during the post-ripening process. However, in the case of the cultivar “Kent”, peel color detection was not an applicable approach for determining ripeness; thus, the determination of the pulp color with the color code 0550-Y20R gave promising results.

Growth Stage Classification and Harvest Scheduling of Snap Bean Using Hyperspectral Sensing: A Greenhouse Study

The agricultural industry suffers from a significant amount of food waste, some of which originates from an inability to apply site-specific management at the farm-level. Snap bean, a broad-acre crop that covers hundreds of thousands of acres across the USA, is not exempt from this need for informed, within-field, and spatially-explicit management approaches. This study aimed to assess the utility of machine learning algorithms for growth stage and pod maturity classification of snap bean (cv. Huntington), as well as detecting and discriminating spectral and biophysical features that lead to accurate classification results. Four major growth stages and six main sieve size pod maturity levels were evaluated for growth stage and pod maturity classification, respectively. A point-based in situ spectroradiometer in the visible-near-infrared and shortwave-infrared domains (VNIR-SWIR; 400–2500 nm) was used and the radiance values were converted to reflectance to normalize for any illumination change between samples. After preprocessing the raw data, we approached pod maturity assessment with multi-class classification and growth stage determination with binary and multi-class classification methods. Results from the growth stage assessment via the binary method exhibited accuracies ranging from 90–98%, with the best mathematical enhancement method being the continuum-removal approach. The growth stage multi-class classification method used raw reflectance data and identified a pair of wavelengths, 493 nm and 640 nm, in two basic transforms (ratio and normalized difference), yielding high accuracies (~79%). Pod maturity assessment detected narrow-band wavelengths in the VIS and SWIR region, separating between not ready-to-harvest and ready-to-harvest scenarios with classification measures at the ~78% level by using continuum-removed spectra. Our work is a best-case scenario, i.e., we consider it a stepping-stone to understanding snap bean harvest maturity assessment via hyperspectral sensing at a scalable level (i.e., airborne systems). Future work involves transferring the concepts to unmanned aerial system (UAS) field experiments and validating whether or not a simple multispectral camera, mounted on a UAS, could incorporate < 10 spectral bands to meet the need of both growth stage and pod maturity classification in snap bean production.

Pre-dispersive near-infrared light sensing in non-destructively classifying the brix of intact pineapples

Exported fresh intact pineapples must fulfill the minimum internal quality requirement of 12 degree brix. Even though near-infrared (NIR) spectroscopic approaches are promising to non-destructively and rapidly assess the internal quality of intact pineapples, these approaches involve expensive and complex NIR spectroscopic instrumentation. Thus, this research evaluates the performance of a proposed pre-dispersive NIR light sensing approach in non-destructively classifying the Brix of pineapples using K-fold cross-validation, holdout validation, and sensitive analysis. First, the proposed pre-dispersive NIR sensing device that consisted of a light sensing element and five NIR light emitting diodes with peak wavelengths of 780, 850, 870, 910, and 940 nm, respectively, was developed. After that, the diffuse reflectance NIR light of intact pineapples was non-destructively acquired using the developed NIR sensing device before their Brix values were conventionally measured using a digital refractometer. Next, an artificial neural network (ANN) was trained and optimized to classify the Brix values of pineapples using the acquired NIR light. The results of the sensitivity analysis showed that either one wavelength that was near to the water absorbance or chlorophyll band was redundant in the classification. The performance of the trained ANN was tested using new pineapples with the optimal classification accuracy of 80.56%. This indicates that the proposed pre-dispersive NIR light sensing approach coupled with the ANN is promising to be an alternative to non-destructively classifying the internal quality of fruits.

Non-destructive assessment of flesh firmness and dietary antioxidants of greenhouse-grown tomato (Solanum lycopersicum L.) at different fruit maturity stages

Non-destructive methods have been widely recognized for evaluating fruit quality traits of many horticultural crops and food processing industry. Destructive (analytical) test, and non-destructive evaluation of the quality traits were investigated and compared for 'Red Rose' tomato (Solanum lycopersicum L.) fruit grown under protected environment. Fresh tomato fruit at five distinctive maturity stages namely; breaker (BK), turning (TG), pink (PK), light-red (LR), and red (RD) were labeled and scanned using the handheld near infra-red (NIR) enhanced spectrometer at a wavelength range of 285-1200 nm. The labeled tomato samples were then measured analytically for flesh firmness, lycopene, β-carotene, total phenolic content (TPC) and total flavonoids content (TFC). The results revealed that quality traits could be estimated using NIR spectroscopy with a relatively high coefficient of determination (R2): 0.834 for total phenolic content, 0.864 for lycopene, 0.790 for total flavonoid content, 0.708 for β-carotene; and 0.679 for flesh firmness. The accumulation of Lyco and β-Car rapidly increased in tomatoes harvested between the TG and the LR maturity stages. Harvesting tomatoes at BK maturity stage resulted in significantly higher flesh firmness than harvesting at the later maturity stages. Tomato fruits had the lowest TPC and TFC contents at the earliest maturity stage (BK), while they had intermediate TPC and TFC levels at LR and RD maturity stages. NIR spectroscopic measurements of fruit firmness and lipophilic antioxidants in tomato fruit at various maturity stages were partially in accordance with those estimated by destructive (analytical) methods. Based on these findings, we recommend using non-destructive NIR spectroscopy as an effective tool for predicting tomato fruit quality during harvest stage and postharvest processing.

Investigating the Influence of Infrared Drying Method on Linden (Tilia platyphyllos Scop.) Leaves: Kinetics, Color, Projected Area, Modeling, Total Phenolic, and Flavonoid Content

The Linden (Tilia platyphyllos Scop.) is a highly popular herbal plant due to its central nervous system properties. In this study, thin layer drying kinetics of linden leave samples were experimentally investigated in an infrared (IR) dryer. In order to select the appropriate model for predicting the drying kinetics of linden leaves, eleven thin layer semi theoretical, theoretical, and empirical models, widely used in describing the drying behavior of agricultural products, were fitted to the experimental data. Moreover, the color, projected area (PA), total phenolic content (TPC), and total flavonoid content (TFC) were investigated. The results showed that the drying time decreased from 50 min to 20 min. with increased IR temperature from 50-70 °C. Therewithal, the Midilli model gave the most suitable data for 50 °C, 60 °C. Moreover, Verma et al. and Diffusion approximation models showed good results for 70 °C. The lightness and greenness of the dried linden leaves were significantly changed compared with fresh samples. The PA of dried sample decreased similar to the drying time. In addition, the drying temperature effect on the effective diffusion diffusivity (D_eff) and activation energy (E_a) were also computed. The D_eff ranges from 4.13 × 10^-12 to 5.89 × 10^-12 and E_a coefficient was 16.339 kJ/mol. Considering these results, the Midilli et al. model is above the 50 °C, 60 °C, and the Verma et al. and Diffusion to 70 °C, for explaining the drying behavior of linden leaves under IR drying. Moreover, it can be said that the Page model can be used, if it is desired, to express the drying behaviors, partially with the help of a simple equation material by drying. TPC and TFC values were statistically < 0.001 higher in dried samples compared to fresh samples; however, no change has been recorded of TPC and TFC values at different temperatures (50 °C, 60 °C, 70 °C).

Direct estimation of NIR reflection spectra utilizing a snapshot-type spectrometer with photonic crystal multi-spectral filter arrays

We fabricated 16-, 25-, 36-, and 64-channel distributed passband-type multi-spectral filter arrays by utilizing a multilayer-type photonic crystal and integrated them onto a CCD to form a snapshot-type spectroscopic sensor. Reflection spectra from target objects (fruits) under broadband light illumination were estimated directly using the Wiener estimation method. A root mean square error of the reflectivity on the order of 2∼5% was obtained under optical shot noise with 6×6 pixel binning. A number of constituent filters of 36 was sufficient for this type of fruit spectral measurement. We also visualized reflection images at specified wavelengths by applying the estimation method to a multiple filter region on the sensor.

Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed Gouda cheese

The aim of the study was to compare the ability of multiple linear regression (MLR) and Artificial Neural Network (ANN) to predict the overall quality of spreadable Gouda cheese during storage at 8 °C, 20 °C and 30 °C. The ANN used five factors selected by Principal Component Analysis, which was used as input data for the ANN calculation. The datasets were divided into three subsets: a training set, a validation set, and a test set. The multiple regression models were highly significant with high determination coefficients: R2 = 0.99, 0.87 and 0.87 for 8, 20 and 30 °C, respectively, which made them a useful tool to predict quality deterioration. Simultaneously, the artificial neural networks models with determination coefficient of R2 = 0.99, 0.96 and 0.96 for 8, 20 and 30 °C, respectively were built. The models based on ANNs with higher values of determination coefficients and lower RMSE values proved to be more accurate. The best fit of the model to the experimental data was found for processed cheese stored at 8 °C.

Role of biological control agents and physical treatments in maintaining the quality of fresh and minimally-processed fruit and vegetables

Fruit and vegetables are an important part of human diets and provide multiple health benefits. However, due to the short shelf-life of fresh and minimally-processed fruit and vegetables, significant losses occur throughout the food distribution chain. Shelf-life extension requires preserving both the quality and safety of food products. The quality of fruit and vegetables, either fresh or fresh-cut, depends on many factors and can be determined by analytical or sensory evaluation methods. Among the various technologies used to maintain the quality and increase shelf-life of fresh and minimally-processed fruit and vegetables, biological control is a promising approach. Biological control refers to postharvest control of pathogens using microbial cultures. With respect to application of biological control for increasing the shelf-life of food, the term biopreservation is favored, although the approach is identical. The methods for screening and development of biocontrol agents differ greatly according to their intended application, but the efficacy of all current approaches following scale-up to commercial conditions is recognized as insufficient. The combination of biological and physical methods to maintain quality has the potential to overcome the limitations of current approaches. This review compares biocontrol and biopreservation approaches, alone and in combination with physical methods. The recent increase in the use of meta-omics approaches and other innovative technologies, has led to the emergence of new strategies to increase the shelf-life of fruit and vegetables, which are also discussed herein.