Search Results (140)

Accurate apple yield estimation is essential for effective orchard management, market planning, and ensuring growers’ income. However, complex orchard conditions, such as dense foliage occlusion and overlapping fruits, present challenges to large-scale yield estimation. This study introduces APYOLO, an enhanced apple detection algorithm based on an improved YOLOv11, integrated with the DeepSORT tracking algorithm to improve both detection accuracy and operational speed. APYOLO incorporates a multi-scale channel attention (MSCA) mechanism and an enhanced multi-scale prior distribution intersection over union (EnMPDIoU) loss function to enhance target localization and recognition under complex environments. Experimental results demonstrate that APYOLO outperforms the original YOLOv11 by improving mAP@0.5, mAP@0.5–0.95, accuracy, and recall by 2.2%, 2.1%, 0.8%, and 2.3%, respectively. Additionally, the combination of a unique ID with the region of line (ROL) strategy in DeepSORT further boosts yield estimation accuracy to 84.45%, surpassing the performance of the unique ID method alone. This study provides a more precise and efficient system for apple yield estimation, offering strong technical support for intelligent and refined orchard management. Full article

Orah mandarin (Citrus reticulata cv. Orah) lacks systematic grading treatment after harvesting, resulting in a high fresh fruit loss rate and affecting the economic value. There are many drawbacks to traditional manual and mechanical sorting. Therefore, intelligent, rapid, non-destructive surface defect detection technology is significant. In addition to the fruit size, surface defects (e.g., canker, sunburn) are another important criterion for grading fruit. To overcome the challenges in detecting surface defects of orah mandarin, like multi-scale features, significant size differences, and slow convergence speed, we propose the YOLOv8-Orah detection model based on YOLOv8n. Path Aggregation Network (PANet) is replaced by a Focusing Diffusion Pyramid Network (FDPN), and the Diffusion and Spatial Interaction (DASI) module is introduced to effectively fuse and enhance features of different scales and improve detection accuracy. The Bottleneck in the C2f module is replaced by the Hybrid Dilated Residual Attention Block (HDRAB) module to reduce missed detections and false detections. We also introduce the NWD-CIoU joint bounding box loss to accelerate the convergence speed and improve the detection accuracy of small defects. The experimental results show that the improved YOLOv8-Orah model performs well in terms of precision, recall, and average precision, reaching 81.9%, 78.8%, and 84.2%, respectively. Compared with the original YOLOv8n, the improved model increased by 4.0%, 1.7%, and 3.0%, respectively. Meanwhile, the parameter count decreased by 7.76%. Compared with other mainstream models, YOLOv8-Orah achieves a good balance between detection accuracy and computational efficiency. The results technically support defect detection in postharvest orah mandarin and real-time grading of their quality. Meanwhile, it can promote the intelligent development of the bergamot industry. Full article

The classification of agricultural products is of great importance for quality control, optimized marketing, efficient logistics, research progress, consumer satisfaction, and sustainability. Dragon fruit has many varieties that need to be identified quickly and accurately for packaging and marketing. Considering the increasing demand for dragon fruit, it is obvious that an automated classification system has significant commercial and scientific value by increasing sorting efficiency and reducing manual labor costs. This study aimed to classify four commonly produced dragon fruit varieties according to their color, mechanical, and physical properties using machine learning models. Data were collected from 224 dragon fruits (53 American beauty, 57 Dark star, 65 Vietnamese white, and 49 Pepino dulce variety). Classification was performed using measurable physical and mechanical properties obtained through digital image processing, colorimetry, electronic weighing, and stress–strain testing. These methods provided objective and reproducible data collection for the models. Three models—Random Forest, Gradient Boosting, and Support Vector Classification—were implemented and their performances were evaluated using accuracy, precision, recall, Matthews’s correlation coefficient, Cohen’s Kappa, and F1-Score. The Random Forest model showed the highest performance in all metrics, achieving 98.66% accuracy, while the Support Vector Classification model had the lowest success. The superior performance of the Random Forest model can be attributed to its ability to handle complex, nonlinear relationships among multiple variables while preventing overfitting through ensemble learning. However, potential challenges in dragon fruit classification include variations due to environmental factors, genetic variation, and hybridization. Future research can focus on incorporating biochemical or genetic markers and improving real-time classification for industrial applications. Full article

Fruit sorting and quality inspection using computer vision is a key tool to ensure quality and safety in the fruit industry. This study presents a systematic literature review, following the PRISMA methodology, with the aim of identifying different fields of application, typical hardware configurations, and the techniques and algorithms used for fruit sorting. In this study, 56 articles published between 2015 and 2024 were analyzed, selected from relevant databases such as Web of Science and Scopus. The results indicate that the main fields of application include orchards, industrial processing lines, and final consumption points, such as supermarkets and homes, each with specific technical requirements. Regarding hardware, RGB cameras and LED lighting systems predominate in controlled applications, although multispectral cameras are also important in complex applications such as foreign material detection. Processing techniques include traditional algorithms such as Otsu and Sobel for segmentation and deep learning models such as ResNet and VGG, often optimized with transfer learning for classification. This systematic review could provide a basic guide for the development of fruit quality inspection and classification systems in different environments. Full article

Accurately detecting apple fruit can crucially assist in estimating the fruit yield in apple orchards in complex scenarios. In such environments, the factors of density, leaf occlusion, and fruit overlap can affect the detection and counting accuracy. This paper proposes an improved YOLOv7-Tiny-PDE network model based on the YOLOv7-Tiny model to detect and count apples from data collected by drones, considering various occlusion and lighting conditions. First, within the backbone network, we replaced the simplified efficient layer aggregation network (ELAN) with partial convolution (PConv), reducing the network parameters and computational redundancy while maintaining the detection accuracy. Second, in the neck network, we used a dynamic detection head to replace the original detection head, effectively suppressing the background interference and capturing the background information more comprehensively, thus enhancing the detection accuracy for occluded targets and improving the fruit feature extraction. To further optimize the model, we replaced the boundary box loss function from CIOU to EIOU. For fruit counting across video frames in complex occlusion scenes, we integrated the improved model with the DeepSort tracking algorithm based on Kalman filtering and motion trajectory prediction with a cascading matching algorithm. According to experimental results, compared with the baseline YOLOv7-Tiny, the improved model reduced the total parameters by 22.2% and computation complexity by 18.3%. Additionally, in data testing, the p-value improved by 0.5%; the R-value rose by 2.7%; the mAP and F1 scores rose by 4% and 1.7%, respectively; and the MOTA value improved by 2%. The improved model is more lightweight and can preserve a high detection accuracy well, and hence, it can be applied to detection and counting tasks in complex orchards and provides a new solution for fruit yield estimation using lightweight devices. Full article

Visible/near-infrared spectroscopy is widely used for non-destructive fruit quality detection, but the high cost of spectrometers (400–1100 nm range) in sorting equipment limits its accessibility. This study proposes a dual-channel co-spectroscopy method to address this issue. Using apples’ soluble solids content as the research target, a dual-channel platform was constructed to optimize parameters for full-transmission spectral signal acquisition. Spectral data were collected using dual channels (400–700 nm and 700–1100 nm bands, separated by filters) and a single channel (400–1100 nm range). Preprocessing methods (MSC, SNV, FD, SD, SG) and feature extraction algorithms (CARS, SPA, UVE) were applied, followed by PLSR modeling. The dual-channel method with Raw spectrum + FD + CARS + PLSR achieved optimal results, with R²_v = 0.88, RMSEP = 0.39 for the 400–700 nm band, and R²_v = 0.94, RMSEP = 0.33 for the 700–1100 nm band. The single-channel method with Raw spectrum + MSC + CARS + PLSR achieved R²_v = 0.90, RMSEP = 0.36. These findings validate dual-channel co-spectroscopy as a cost-effective, accurate solution for non-destructive fruit quality detection, providing a practical approach to reduce spectrometer costs and enhance sorting system efficiency. Full article

In order to obtain a highly nutritious extrudate, a combination of pseudocereals, vegetable protein, and banana flour, a fruit with high sensory acceptability, was used. The objective of the research was to produce a multi-component extrudate (ME) based on cañihua and quinoa with the addition of pea protein isolate and banana flour. The response variables evaluated were composition, expansion, hydration, colour, and hardness properties, as well as the microscopy and sensory characteristics of the flakes produced. These flakes were compared with three commercial extrudates, commercial quinoa-based extrudate (QE), commercial corn-based extrudate (CE), and commercial wheat-based extrudate (WE), which had similar characteristics. The ME showed a higher protein content compared to commercial extrudates (13.60%), and it had significant amounts of lipids, fibre, and ash. The expansion of the ME was like commercial quinoa but significantly lower than the CE and the WE in terms of expansion (p < 0.05). Regarding the absorption and solubility indices of the ME, these indicated that it had lower starch fragmentation compared to the commercial CE and WE. In addition, the instrumental hardness of the ME was higher than the commercial ones due to the complex nature of the product. Through scanning electron microscopy (SEM), it was observed that the ME showed some remaining extrusion-resistant starch granules from quinoa and cañihua with the presence of protein bodies. Finally, the flash profile described the ME as having a pronounced flavour, higher hardness, and lower sweetness, and the free sorting task allowed it to be differentiated from commercial extrudates based on its natural appearance and chocolate flavour. Full article

This work evaluated red kiwifruit plants’ spray treatment with cis-3-hexenyl butyrate (HB) as an inductor of some metabolic mechanisms related to fruit ripening, including an increase in anthocyanin content and the red hue color parameter. Considering their key role as ripening parameters for postharvest fruit quality and sorting assessment, the soluble solid content (SSC) and the flesh firmness penetrometer (FFP) were also measured. Treated plants received an application of 50 mM HB, administered exactly 2 and 4 weeks before the commercial harvest. At harvest time and during postharvest fruit ripening, near-infrared (NIR) spectral acquisitions were performed in order to check the feasibility of a rapid and non-destructive prediction of fruit anthocyanin content and SSC, coupled to destructive measurements and chemometric modelling. Regarding technological and chemical results, HB treatment indicates an optimum overall qualitative storage at 30 days. The fruit from treated plants is characterized by good quality parameters, including higher SSC, enhanced red hue (a* value) and increased anthocyanin content, despite similar weight loss to the untreated fruit. The obtained chemometric results underscore the promise and feasibility of NIRs in terms of detecting and estimating anthocyanin content and SSC in red kiwifruit, in order to pursue an evident perspective of improvement. Full article

The current landscape of the food processing industry places a strong emphasis on improving food quality, nutritional value, and processing techniques. This focus arises from consumer demand for products that adhere to high standards of quality, sensory characteristics, and extended shelf life. The emergence of artificial intelligence (AI) and machine learning (ML) technologies is instrumental in addressing the challenges associated with variability in food processing. AI represents a promising interdisciplinary approach for enhancing performance across various sectors of the food industry. Significant advancements have been made to address challenges and facilitate growth within the food sector. This review highlights the applications of AI in agriculture and various sectors of the food industry, including bakery, beverage, dairy, food safety, fruit and vegetable industries, packaging and sorting, and the drying of fresh foods. Various strategies have been implemented across different food sectors to promote advancements in technology. Additionally, this article explores the potential for advancing 3D printing technology to enhance various aspects of the food industry, from manufacturing to service, while also outlining future perspectives. Full article

Population growth, urbanization, and changing consumption patterns are contributing to an increase in household waste production, particularly in sub-Saharan Africa. Composting of biowaste presents a sustainable solution by reducing the volume of waste sent to landfills while enriching the soil. The main objective of this study was to evaluate the suitability of solid household biowaste for composting in market garden crops in Dolisie (the Republic of Congo). Specifically, the study aimed to (i) assess the production and management practices of solid household waste in relation to socio-economic factors, (ii) analyze the chemical composition of solid household biowaste and its concentration of trace elements (TEs), and (iii) determine the potential phytotoxicity of solid household biowaste across different production seasons. In this study, wastes were collected from 40 households over a 60-day period, with daily sorting conducted during both the dry and wet seasons. Using a completely randomized design, various compost application rates were incorporated into the soil to conduct a germination test. The quality of the biowaste and compost was evaluated through physicochemical analyses. Results showed that approximately 90% of high-income households received regular waste collection services and practiced waste separation in contrast to middle- and low-income households. The composition of the biowaste was primarily composed of fruit and vegetable scraps, with slight contamination by chromium and cadmium. Temperature, pH, and humidity levels showed similar trends during compost formation in both the rainy and dry seasons. Germination rates were above 80% in all treatments across both seasons, indicating that the compost was mature. Overall, all physicochemical parameters of the compost met established quality standards, and trace element concentrations were below the recommended thresholds. The study concluded that biowaste, once converted into compost, can be safely applied to agricultural soils without posing any risk of phytotoxicity or contamination to crops. Full article

In the process of smart orchard construction, accurate detection of target fruit is an important guarantee to realize intelligent management of orchards. Green apple detection technology greatly diminishes the need for manual labor, cutting costs and time, while enhancing the automation and efficiency of sorting processes. However, due to the complex orchard environment, the ever-changing posture of the target fruit, and the difficulty of detecting green target fruit similar to the background, they bring new challenges to the detection of green target fruit. Aiming at the problems existing in green apple detection, this study takes green apples as the research object, and proposes a green apple detection model based on optimized deformable DETR. The new method first introduces the ResNeXt network to extract image features to reduce information loss in the feature extraction process; secondly, it improves the accuracy and optimizes the detection results through the deformable attention mechanism; and finally, it uses a feed-forward network to predict the detection results. The experimental results show that the accuracy of the improved detection model has been significantly improved, with an overall AP of 54.1, AP₅₀ of 80.4, AP₇₅ of 58.0, AP_s of 35.4 for small objects, AP_m of 60.2 for medium objects, and AP_l of 85.0 for large objects. It can provide a theoretical reference for green target detection of other fruit and vegetables green target detection. Full article

Fluorescence imaging has emerged as a powerful tool for detecting surface damage in fruits, yet its application to vegetables such as green bell peppers remains underexplored. This study investigates the fluorescent characteristics of minor mechanical damage, specifically 5 × 5 mm cuts in the exocarp of green bell peppers, which conventional digital imaging techniques fail to classify accurately. Chlorophyll fluorescence imaging was combined with machine learning algorithms—including logistic regression (LR), artificial neural networks (ANN), random forests (RF), k-nearest neighbors (kNN), and the support vector machine (SVM) to classify damaged and sound fruit. The machine learning models demonstrated a high classification accuracy, with calibration and prediction accuracies exceeding 0.86 and 0.96, respectively, across all algorithms. These results underscore the potential of fluorescence imaging as a non-invasive, rapid, and cheaper method for assessing mechanical damage in green bell peppers, offering valuable applications in quality control and postharvest management. Full article

Many traditional fruit vendors still rely on manual sorting to pick out high-quality apples. This process is not only time-consuming but can also damage the apples. Meanwhile, automated detection technology is still in its early stage and lacks full reliability. To improve this technology, we propose a novel method, which incorporates a learnable scaling factor and residual connection to enhance the Multi-Head Attention mechanism. In our approach, a learnable scaling factor is first applied to adjust the attention weights dynamically, and then a residual connection combines the scaled attention output with the original input to preserve essential features from the initial data. By integrating Multi-Head Attention with Convolutional Neural Networks (CNNs) using this method, we propose a lightweight deep learning model called “Learnable Residual Multi-Head Attention Networks Fusion with CNNs” to detect defective apples. Compared to existing models, our proposed model has lower memory usage, shorter training time, and higher detection precision. On the test set, the model achieves an accuracy of 97.5%, a recall of 98%, and a specificity of 97%, along with the lowest detection time of 46 ms. Experimental results show that the proposed model using our method is highly promising for commercial sorting, as it reduces labor costs, increases the supply of high-quality apples, and boosts consumer satisfaction. Full article

Postharvest internal disorders (IDs) in mango fruit present a significant challenge to the industry, with their underlying causes still unclear. This study investigated the relationship between fruit maturity and the susceptibility of vapor heat-treated (VHT) ‘B74’ mangoes to IDs in three experiments. In the first experiment, fruit were categorized into three maturity groups based on dry matter content (DMC): <15%, 15–17%, and >17%, using a handheld near-infrared device. Half of the fruit in each group underwent VHT, while the remainder were untreated controls. Flesh cavity with white patches (FCWP) was the only disorder observed exclusively in VHT fruit. The incidence and severity of FCWP was significantly higher (p < 0.05) in fruit with <15% DMC, with 12.4% incidence and a severity score of 0.2 on a 0–3 scale (0: healthy and 3: severely affected), compared to more mature fruit. In the second experiment, the fruits were harvested at early and late maturity stages, with average DMC values of 14.5% and 17.4%, respectively. The fruit was subjected to no VHT, VHT, and VHT following a 12 h pre-conditioning period at 37 ± 1 °C. Consistent with the first experiment, FCWP was observed only in VHT fruit, with early-harvested fruit displaying a significantly higher (p < 0.05) FCWP incidence (26.9%) and severity (0.3) compared to late-harvested fruit (8.3% incidence and 0.1 severity). Pre-conditioning significantly reduced FCWP, particularly in early-harvested fruit. In the third experiment, fruit maturity sorted based on density was assessed, followed by VHT and simulated sea freight under controlled (CA) and ambient atmospheres. Fruit density did not effectively differentiate maturity considering DMC as a maturity indicator. Storage conditions significantly reduced (p < 0.05) flesh browning incidence from 71.1% under ambient conditions to 33.3% under CA. This study highlights fruit maturity as a key factor in the susceptibility of ‘B74’ mangoes to postharvest IDs following VHT. Therefore, sorting fruit based on DMC at harvest or at the packing facility prior to VHT serves as a valuable decision support for reducing IDs in VHT fruit. Further research will explore advanced technologies to enable rapid and efficient fruit sorting based on DMC. Full article

Recognizing and classifying localized lesions on apple fruit surfaces during automated sorting is critical for improving product quality and increasing the sustainability of fruit production. This study is aimed at developing sustainable methods for fruit sorting by applying hyperspectral analysis and machine learning to improve product quality and reduce losses. The employed hyperspectral technologies and machine learning algorithms enable the rapid and accurate detection of defects on the surface of fruits, enhancing product quality and reducing the number of rejects, thereby contributing to the sustainability of agriculture. This study seeks to advance commercial fruit quality control by comparing hyperspectral image classification algorithms to detect apple lesions caused by pathogens, including sunburn, scab, and rot, on three apple varieties: Honeycrisp, Gala, and Jonagold. The lesions were confirmed independently using expert judgment, real-time PCR, and 3D fluorimetry, providing a high accuracy of ground truth data and allowing conclusions to be drawn on ways to improve the sustainability and safety of the agrocenosis in which the fruits are grown. Hyperspectral imaging combined with mathematical analysis revealed that Venturia inaequalis is the main pathogen responsible for scab, while Botrytis cinerea and Penicillium expansum are the main causes of rot. This comparative study is important because it provides a detailed analysis of the performance of both supervised and unsupervised classification methods for hyperspectral imagery, which is essential for the development of reliable automated grading systems. Support Vector Machines (SVM) proved to be the most accurate, with the highest average adjusted Rand Index (ARI) scores for sunscald (0.789), scab (0.818), and rot (0.854), making it the preferred approach for classifying apple lesions during grading. K-Means performed well for scab (0.786) and rot (0.84) classes, but showed limitations with lower metrics for other lesion types. A design and technological scheme of an optical system for identifying micro- and macro-damage to fruit tissues is proposed, and the dependence of the percentage of apple damage on the rotation frequency of the sorting line rollers is obtained. The optimal values for the rotation frequency of the rollers, at which the damage to apples is less than 5%, are up to 6 Hz. The results of this study confirm the high potential of hyperspectral data for the non-invasive recognition and classification of apple diseases in automated sorting systems with an accuracy comparable to that of human experts. These results provide valuable insights into the optimization of machine learning algorithms for agricultural applications, contributing to the development of more efficient and accurate fruit quality control systems, improved production sustainability, and the long-term storage of fruits. Full article