Automated Systems Based on Machine Vision for Inspecting Citrus Fruits from the Field to Postharvest—a Review

Application of Hyperspectral Technology with Machine Learning for Brix Detection of Pastry Pears

Sugar content is an essential indicator for evaluating crisp pear quality and categorization, being used for fruit quality identification and market sales prediction. In this study, we paired a support vector machine (SVM) algorithm with genetic algorithm optimization to reliably estimate the sugar content in crisp pears. We evaluated the spectral data and actual sugar content in crisp pears, then applied three preprocessing methods to the spectral data: standard normal variable transformation (SNV), multivariate scattering correction (MSC), and convolution smoothing (SG). Support vector regression (SVR) models were built using processing approaches. According to the findings, the SVM model preprocessed with convolution smoothing (SG) was the most accurate, with a correlation coefficient 0.0742 higher than that of the raw spectral data. Based on this finding, we used competitive adaptive reweighting (CARS) and the continuous projection algorithm (SPA) to select key representative wavelengths from the spectral data. Finally, we used the retrieved characteristic wavelength data to create a support vector machine model (GASVR) that was genetically tuned. The correlation coefficient of the SG-GASVR model in the prediction set was higher by 0.0321 and the root mean square prediction error (RMSEP) was lower by 0.0267 compared with those of the SG-SVR model. The SG-CARS-GASVR model had the highest correlation coefficient, at 0.8992. In conclusion, the developed SG-CARS-GASVR model provides a reliable method for detecting the sugar content in crisp pear using hyperspectral technology, thereby increasing the accuracy and efficiency of the quality assessment of crisp pear.

Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees

In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning.

Different spectral sensitivities of ON- and OFF-motion pathways enhance the detection of approaching color objects in Drosophila

Color and motion are used by many species to identify salient objects. They are processed largely independently, but color contributes to motion processing in humans, for example, enabling moving colored objects to be detected when their luminance matches the background. Here, we demonstrate an unexpected, additional contribution of color to motion vision in Drosophila. We show that behavioral ON-motion responses are more sensitive to UV than for OFF-motion, and we identify cellular pathways connecting UV-sensitive R7 photoreceptors to ON and OFF-motion-sensitive T4 and T5 cells, using neurogenetics and calcium imaging. Remarkably, this contribution of color circuitry to motion vision enhances the detection of approaching UV discs, but not green discs with the same chromatic contrast, and we show how this could generalize for systems with ON- and OFF-motion pathways. Our results provide a computational and circuit basis for how color enhances motion vision to favor the detection of saliently colored objects.

Advancement of non-destructive spectral measurements for the quality of major tropical fruits and vegetables: a review

The quality of tropical fruits and vegetables and the expanding global interest in eating healthy foods have resulted in the continual development of reliable, quick, and cost-effective quality assurance methods. The present review discusses the advancement of non-destructive spectral measurements for evaluating the quality of major tropical fruits and vegetables. Fourier transform infrared (FTIR), Near-infrared (NIR), Raman spectroscopy, and hyperspectral imaging (HSI) were used to monitor the external and internal parameters of papaya, pineapple, avocado, mango, and banana. The ability of HSI to detect both spectral and spatial dimensions proved its efficiency in measuring external qualities such as grading 516 bananas, and defects in 10 mangoes and 10 avocados with 98.45%, 97.95%, and 99.9%, respectively. All of the techniques effectively assessed internal characteristics such as total soluble solids (TSS), soluble solid content (SSC), and moisture content (MC), with the exception of NIR, which was found to have limited penetration depth for fruits and vegetables with thick rinds or skins, including avocado, pineapple, and banana. The appropriate selection of NIR optical geometry and wavelength range can help to improve the prediction accuracy of these crops. The advancement of spectral measurements combined with machine learning and deep learning technologies have increased the efficiency of estimating the six maturity stages of papaya fruit, from the unripe to the overripe stages, with F1 scores of up to 0.90 by feature concatenation of data developed by HSI and visible light. The presented findings in the technological advancements of non-destructive spectral measurements offer promising quality assurance for tropical fruits and vegetables.

Monitoring Freeze-Damage in Grapefruit by Electric Bioimpedance Spectroscopy and Electric Equivalent Models

Grapefruit is a cold-sensitive citrus fruit, and freezing can spoil the harvest when the fruit is still on the tree and even later during manufacturing and transport due to inappropriate postharvest management. This study performed a specific Electric Impedance Spectroscopy (EIS) analysis and statistical data treatment to obtain an EIS and Artificial Neural Networks (ANN)-based model for early freeze-damage detection in grapefruit showing a Correct Correlation Rate of 100%. Additionally, Cryo-Field Emission Scanning Electron Microscopy observations were conducted on both fresh and frozen/thawed samples, analyzing the different impedance responses in order to understand the biological changes in the tissue. Finally, a modified Hayden electric equivalent model was parameterized to simulate the impedance response electrically and link the electric behavior of biological tissue to the change in its properties due to freezing. The developed technique is introduced as an alternative to the traditional ones, as it is fast, economic, and easy to carry out.

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.

Making Sense of Light: The Use of Optical Spectroscopy Techniques in Plant Sciences and Agriculture

As a result of the development of non-invasive optical spectroscopy, the number of prospective technologies of plant monitoring is growing. Being implemented in devices with different functions and hardware, these technologies are increasingly using the most advanced data processing algorithms, including machine learning and more available computing power each time. Optical spectroscopy is widely used to evaluate plant tissues, diagnose crops, and study the response of plants to biotic and abiotic stress. Spectral methods can also assist in remote and non-invasive assessment of the physiology of photosynthetic biofilms and the impact of plant species on biodiversity and ecosystem stability. The emergence of high-throughput technologies for plant phenotyping and the accompanying need for methods for rapid and non-contact assessment of plant productivity has generated renewed interest in the application of optical spectroscopy in fundamental plant sciences and agriculture. In this perspective paper, starting with a brief overview of the scientific and technological backgrounds of optical spectroscopy and current mainstream techniques and applications, we foresee the future development of this family of optical spectroscopic methodologies.

Optimization of the Appearance Quality in CO2 Processed Ready-to-Eat Carrots through Image Analysis

A high-pressure CO₂ process applied to ready-to-eat food products guarantees an increase of both their microbial safety and shelf-life. However, the treatment often produces unwanted changes in the visual appearance of products depending on the adopted process conditions. Accordingly, the alteration of the visual appearance influences consumers' perception and acceptability. This study aims at identifying the optimal treatment conditions in terms of visual appearance by using an artificial vision system. The developed methodology was applied to fresh-cut carrots (Daucus carota) as the test product. The results showed that carrots packaged in 100% CO₂ and subsequently treated at 6 MPa and 40 °C for 15 min maintained an appearance similar to the fresh product for up to 7 days of storage at 4 °C. Mild appearance changes were identified at 7 and 14 days of storage in the processed products. Microbiological analysis performed on the optimal treatment condition showed the microbiological stability of the samples up to 14 days of storage at 4 °C. The artificial vision system, successfully applied to the CO₂ pasteurization process, can easily be applied to any food process involving changes in the appearance of any food product.

Strawberry Fungal Leaf Scorch Disease Identification in Real-Time Strawberry Field Using Deep Learning Architectures

Plant health is the basis of agricultural development. Plant diseases are a major factor for crop losses in agriculture. Plant diseases are difficult to diagnose correctly, and the manual disease diagnosis process is time consuming. For this reason, it is highly desirable to automatically identify the diseases in strawberry plants to prevent loss of crop quality. Deep learning (DL) has recently gained popularity in image classification and identification due to its high accuracy and fast learning. In this research, deep learning models were used to identify the leaf scorch disease in strawberry plants. Four convolutional neural networks (SqueezeNet, EfficientNet-B3, VGG-16 and AlexNet) CNN models were trained and tested for the classification of healthy and leaf scorch disease infected plants. The performance accuracy of EfficientNet-B3 and VGG-16 was higher for the initial and severe stage of leaf scorch disease identification as compared to AlexNet and SqueezeNet. It was also observed that the severe disease (leaf scorch) stage was correctly classified more often than the initial stage of the disease. All the trained CNN models were integrated with a machine vision system for real-time image acquisition under two different lighting situations (natural and controlled) and identification of leaf scorch disease in strawberry plants. The field experiment results with controlled lightening arrangements, showed that the model EfficientNet-B3 achieved the highest classification accuracy, with 0.80 and 0.86 for initial and severe disease stages, respectively, in real-time. AlexNet achieved slightly lower validation accuracy (0.72, 0.79) in comparison with VGGNet and EfficientNet-B3. Experimental results stated that trained CNN models could be used in conjunction with variable rate agrochemical spraying systems, which will help farmers to reduce agrochemical use, crop input costs and environmental contamination.

Fuzzy C-means measurement of mass base on image features

Mass of an object is an important characteristic for quality assessment. However, in some cases, it is hard to measure the mass of objects with instruments directly. In this paper, we proposed a novel method based on Fuzzy c-means (FCM) to measure the mass of an object by analyzing the deformation degree in a grid pattern. In the spatial field, thin plate spline (TPS) algorithm was adopted to calculate the minimum deformation bending energy in order to give a quantitative analysis of the weight; In frequency domain, the Fast Fourier Transform (FFT) algorithm was used to calculate the spectrum within a deformation frequency area before and after the change of grids, from which the relationship between weight and spectrum was investigated using FCM algorithm. Two different equations evaluated by the above two methods were proposed in order to calculate the mass of an object. Both of them showed a high level of explanatory power of R2 (R2 = 0.9833 and R2 = 0.9698, respectively). The equations were then used to determine the estimated mass. Estimated and measured values were plotted against each other. A high correlation (R2 = 0.9833 and R2 = 0.9698, respectively) was found between actual and calculated mass. Finally, Bland-Altman plot was introduced to access the agreement of the calculated mass and the actual mass. The average bias was –54.408 g and –0.007 g for spatial domain method and frequency domain method, respectively. Theoretical analysis and experiments were performed to verify the effectiveness of our approaches.

Biological control of postharvest fungal decays in citrus: a review

Citrus (Citrus spp.) species produce a variety of fruits that are popular worldwide. Citrus fruits, however, are susceptible to postharvest decays caused by various pathogenic fungi, including Penicillium digitatum, Penicillium italicum, Geotrichum citri-aurantii, Aspergillus niger, and Aspergillus flavus. Decays resulting from infections by these pathogens cause a significant reduction in citrus quality and marketable yield. Biological control of postharvest decay utilizing antagonistic bacteria and fungi has been explored as a promising alternative to synthetic fungicides. In the present article, the isolation of antagonists utilized to manage postharvest decays in citrus is reviewed, and the mechanism of action including recent molecular and genomic studies is discussed as well. Several recently-postulated mechanisms of action, such as biofilm formation and an oxidative burst of reactive oxygen species have been highlighted. Improvements in biocontrol efficacy of antagonists through the use of a combination of microbial antagonists and additives are also reviewed. Biological control utilizing bacterial and yeast antagonists is a critical component of an integrated management approach for the sustainable development of the citrus industry. Further research will be needed, however, to explore and utilize beneficial microbial consortia and novel approaches like CRISPR/Cas technology for management of postharvest decays.

Deciphering the Metabolic Pathways of Pitaya Peel after Postharvest Red Light Irradiation

Red light irradiation can effectively prolong the shelf-life of many fruit. However, little is known about red light-induced metabolite and enzyme activities. In this study, pitaya fruit was treated with 100 Lux red light for 24 h. Red light irradiation significantly attenuated the variation trend of senescence traits, such as the decrease of total soluble solid (TSS) and TSS/acidity (titratable acidity, TA) ratio, the increase of TA, and respiratory rate. In addition, the reactive oxygen species (ROS) related characters, primary metabolites profiling, and volatile compounds profiling were determined. A total of 71 primary metabolites and 67 volatile compounds were detected and successfully identified by using gas chromatography mass spectrometry (GC-MS). Red light irradiation enhanced glycolysis, tricarboxylic acid (TCA) cycle, aldehydes metabolism, and antioxidant enzymes activities at early stage of postharvest storage, leading to the reduction of H₂O₂, soluble sugars, organic acids, and C-6 and C-7 aldehydes. At a later stage of postharvest storage, a larger number of resistance-related metabolites and enzyme activities were induced in red light-treated pitaya peel, such as superoxide dismutase (SOD), ascorbate peroxidase (APX), 1,1-diphenyl-2-picryl-hydrazyl (DPPH) radical-scavenging, reducing power, fatty acids, and volatile aroma.

A Phenotype-Based Approach for the Substrate Water Status Forecast of Greenhouse Netted Muskmelon

Cultivation substrate water status is of great importance to the production of netted muskmelon (Cucumis melo L. var. reticulatus Naud.). A prediction model for the substrate water status would be beneficial in irrigation schedule guidance. In this study, the machine learning random forest model was used to forecast plant substrate water status given the phenotypic traits throughout the muskmelon growing season. Here, two varieties of netted muskmelon, "Wanglu" and "Arus", were planted in a greenhouse under four substrate water treatments and their phenotypic traits were measured by taking the images within the visible and near-infrared spectrums, respectively. Results showed that a simplified model outperformed the original model in forecasting speed, while it only uses the top five most significant contribution traits. The forecast accuracy reached up to 77.60%, 94.37%, and 90.01% for seedling, vine elongation, and fruit growth stages, respectively. Combining the imaging phenotypic traits and machine learning technique would provide a robust forecast of water status around the plant root zones.

Using Deep Learning for Image-Based Potato Tuber Disease Detection

Many plant diseases have distinct visual symptoms, which can be used to identify and classify them correctly. This article presents a potato disease classification algorithm that leverages these distinct appearances and advances in computer vision made possible by deep learning. The algorithm uses a deep convolutional neural network, training it to classify the tubers into five classes: namely, four disease classes and a healthy potato class. The database of images used in this study, containing potato tubers of different cultivars, sizes, and diseases, was acquired, classified, and labeled manually by experts. The models were trained over different train-test splits to better understand the amount of image data needed to apply deep learning for such classification tasks. The models were tested over a data set of images taken using standard low-cost RGB (red, green, and blue) sensors and were tagged by experts, demonstrating high classification accuracy. This is the first article to report the successful implementation of deep convolutional networks, popular in object identification, to the task of disease identification in potato tubers, showing the potential of deep learning techniques in agricultural tasks.

Plant Disease Diagnosis for Smart Phone Applications with Extensible Set of Diseases

A plant disease diagnosis method that can be implemented with the resources of a mobile phone application, that does not have to be connected to a remote server, is presented and evaluated on citrus diseases. It can be used both by amateur gardeners and by professional agriculturists for early detection of diseases. The features used are extracted from photographs of plant parts like leaves or fruits and include the color, the relative area and the number of the lesion spots. These classification features, along with additional information like weather metadata, form disease signatures that can be easily defined by the end user (e.g., an agronomist). These signatures are based on the statistical processing of a small number of representative training photographs. The extracted features of a test photograph are compared against the disease signatures in order to select the most likely disease. An important advantage of the proposed approach is that the diagnosis does not depend on the orientation, the scale or the resolution of the photograph. The experiments have been conducted under several light exposure conditions. The accuracy was experimentally measured between 70% and 99%. An acceptable accuracy higher than 90% can be achieved in most of the cases since the lesion spots can recognized interactively with high precision.

Midinfrared Multispectral Detection for Real-Time and Noninvasive Analysis of the Structure and Composition of Materials

In situ material identification and object tracking have been demonstrated using a mid-infrared (mid-IR) robotic scanning system. This detection method is capable of inspecting materials noninvasively because the mid-IR spectrum overlaps with numerous characteristic absorption bands corresponding to various chemical function groups. The scanning system consisted of a fiber probe connected to a mid-IR tunable laser with a wavelength tuning range of λ = 2.45-3.75 μm. For the high-speed performance of the scanning system to be evaluated, a testing platform was constructed with an object plate rapidly rotating at ω = 231 rpm. The objects on the plate were SU-8 epoxy-based resin and polydimethylsiloxane, which were mid-IR absorptive while visibly transparent. Applying mid-IR multispectral scanning, the system was able to simultaneously track the object position and identify the composition by interpreting the spectral and spatial intensity variation. The mid-IR robotic scanning method thus provides a visualization system critical for process inspection in automatic manufacturing and high-throughput biomedical screening.

Smart Agricultural Machine with a Computer Vision-Based Weeding and Variable-Rate Irrigation Scheme

This paper proposes a scheme that combines computer vision and multi-tasking processes to develop a small-scale smart agricultural machine that can automatically weed and perform variable rate irrigation within a cultivated field. Image processing methods such as HSV (hue (H), saturation (S), value (V)) color conversion, estimation of thresholds during the image binary segmentation process, and morphology operator procedures are used to confirm the position of the plant and weeds, and those results are used to perform weeding and watering operations. Furthermore, the data on the wet distribution area of surface soil (WDAS) and the moisture content of the deep soil is provided to a fuzzy logic controller, which drives pumps to perform variable rate irrigation and to achieve water savings. The proposed system has been implemented in small machines and the experimental results show that the system can classify plant and weeds in real time with an average classification rate of 90% or higher. This allows the machine to do weeding and watering while maintaining the moisture content of the deep soil at 80 ± 10% and an average weeding rate of 90%.

Case Studies in Modelling, Control in Food Processes

This chapter discusses the importance of modelling and control in increasing food process efficiency and ensuring product quality. Various approaches to both modelling and control in food processing are set in the context of the specific challenges in this industrial sector and latest developments in each area are discussed. Three industrial case studies are used to demonstrate the benefits of advanced measurement, modelling and control in food processes. The first case study illustrates the use of knowledge elicitation from expert operators in the process for the manufacture of potato chips (French fries) and the consequent improvements in process control to increase the consistency of the resulting product. The second case study highlights the economic benefits of tighter control of an important process parameter, moisture content, in potato crisp (chips) manufacture. The final case study describes the use of NIR spectroscopy in ensuring effective mixing of dry multicomponent mixtures and pastes. Practical implementation tips and infrastructure requirements are also discussed.