Using computer vision for automated grading and sorting of fruits and vegetables

The agri-food sector is undergoing a technological revolution, with computer vision emerging as a key enabler in the automated grading and sorting of fruits and vegetables. Traditionally reliant on labour-intensive and subjective manual grading, the industry now leverages image processing, artificial intelligence, and machine learning to assess produce quality with enhanced precision, consistency, and efficiency. Computer vision systems evaluate features like size, shape, color, texture, and defects-enabling real-time classification and reducing post-harvest waste. Advanced deep learning models such as CNNs, YOLO, and MobileNetV2 have demonstrated classification accuracies exceeding 95%, significantly outperforming traditional methods. These innovations not only cut operational costs but also improve market value, food safety, and sustainability. However, challenges like lighting sensitivity, high setup costs, and integration complexities persist. Despite these barriers, the technology’s benefits-faster throughput, reduced human error, better quality control, and enhanced decision-making-underscore its transformative potential. The paper explores current applications, underlying technologies, and prospects of computer vision in agriculture. As the sector evolves, the convergence of AI and imaging technologies promises to reshape food production and supply chains, ensuring higher standards and promoting sustainable agricultural practices worldwide.

Illustrations explain the paper; charts are replotted from the paper's own table values.

Replotted from source data

↗ Enlarge

Accuracy: Lemon vs Tomato vs Apple vs Banana vs PeachClose ×

Replotted from Table 2 (page 4) of the original paper. Every bar is the paper's own table value.

Open full-size image ↗

Introduction

The agri-food sector is experiencing a significant transformation thanks to the integration of computer vision technology, particularly in how fruits and vegetables are evaluated for quality and sorted for distribution. Manual grading processes, which have been the norm, tend to be labour-intensive, often resulting in product evaluation inefficiencies and inconsistencies. Yet, due to recent progress in artificial intelligence and imaging technologies, automated systems are enhancing both accuracy and productivity. Consider, for example, the automated mango classification and grading process shown in, which uses sophisticated machinery to evaluate metrics such as weight, volume, and firmness. Real-time analysis of produce is also made easier by computer vision, decreasing waste and improving food safety, according to (Taneja A et al., 2023) [15] . Experts widely agree (Dadlani M et al., 2023) [16] that these technologies could significantly change the agri-food industry.

Importance of grading and sorting in agriculture

Grading and sorting--they're key in today's agriculture. I mean, it's all about making sure we've got quality produce to eat and sell. Retailers need to meet expectations, and grading helps by categorizing things by size, shape, all that. Plus, think of all the waste we cut down! Machine vision's been a game-changer too, hasn't it? Non-destructive assessments are the way to go, keeping the value of fruits and veggies up while we sort them out effectively. Reviews lately (D Baswaraj et al., 2023) [7] really dig into image acquisition and classification, exploring how these innovations give the grading process a boost. And don't forget volume determination--tech helps a ton with sorting accuracy, especially with stuff like multispectral scanning (Affeldt et al., 2009) [8] . All in all, computer vision not only makes things easier on the farm but also does its part for sustainability by wasting less food.

Fig 1: Impact of computer vision on fruit grading and sorting

The bar chart illustrates the impact of computer vision on fruit grading and sorting. It highlights significant improvements in various performance metrics, with sorting accuracy and market value preservation achieving the highest values, while throughput increase shows a minimal impact.

Overview of traditional methods

Grading fruits and vegetables has historically depended on manual labor and basic techniques. This dependence introduces limitations concerning both efficiency and accuracy. Human graders usually examine the produce to assess size, shape, color, and any surface flaws. Subjectivity and grader fatigue can easily lead to grading inconsistencies over extended work periods. In addition, current manual approaches may not be able to handle the processing speeds that modern agricultural standards need. While various electronic advancements help determine produce size, as noted in some reviews (Affeldt et al., 2009) [8] , traditional practices still heavily influence the industry. Although there have been significant innovations in non-invasive analysis techniques-think computer vision and spectroscopyimplementing these new systems is happening slowly (Hernando C, et al., 2010) [6] . This mix of traditional and emerging methods presents a pivotal point for enhancements in sorting and grading, potentially enabling automated solutions. The stages of mango classification, as illustrated in, perfectly show the shift from manual to automated grading systems.

Purpose and scope of the essay

This essay sets out to consider how computer vision is changing automated fruit and vegetable grading and sorting.

It looks at technological advances, naturally, but also what these changes mean for agriculture. The essay examines where computer vision techniques are today and show how this tech improves efficiency, precision, and quality when food is being processed. Machine learning algorithms, along with imaging systems, for example, are improving produce quality assessment, as some works show regarding real-time intelligent detection equipment (Leal A, et al., 2024) [12] . Images, like, also offer visual representations of automated grading systems, emphasizing how effective fruit categorization and sorting happens. Ultimately, this exploration is meant to advocate for the use of these technologies, because they appear to promise great benefits in how we manage resources and ensure sustainability in the food industry.

Technology Behind Computer Vision

Computer vision advancements have really shaken things up in farming, especially when it comes to sorting fruits and veggies. Using fancy algorithms and machine learning, these systems can now look at produce and figure out things like size, shape, color, and even texture. Take, for example, those automated systems using cameras to sort fruit, like you see in (Taneja A, et al., 2023) [15] . They grab data in real time, which makes sorting faster and cuts down on mistakes people might make, boosting productivity overall. What's more, studies have shown that adding artificial intelligence to these systems helps streamline the whole supply chain and makes sure food is safer, so only the best stuff gets to your plate. All these changes show just how important tech is for making the agri-food industry more sustainable and efficient (Dadlani M, et al., 2023) [16] . It's a big deal and the progress keeps rolling on.

Basics of image processing

Within the field of image processing, especially when it comes to computer vision aiding agricultural tasks, a few key methods form the foundation for automatically grading and sorting our fruits and veggies. Core techniques like obtaining images, making them clearer, separating objects, and pulling out specific details, all help systems analyze visual information successfully. For example, high-res cameras grab detailed pictures of the produce when acquiring an image, and enhancement methods boost image quality to make analysis easier. Segmentation lets us pinpoint individual fruits, setting them apart from everything else, just like in the automated sorting system seen in (Taneja A, et al., 2023) [15] (Dadlani M, et al., 2023) [16] . Feature extraction homes in on measuring traits like color, shape, and texture; these are vital for correctly classifying what we see. As AI keeps changing how we farm, these essential image processing steps stay incredibly important for keeping grading consistent and efficient.

Machine learning algorithms used in computer vision

When it comes to automatically grading fruits and vegetables, machine learning algorithms are important for making classification more accurate and efficient. Things like convolutional neural networks (CNNs) use images to figure out what produce is, based on color, shape, and size. Studies lately have shown that pre-trained models, like DenseNet-201 and Xception, can get classification accuracies of over 99% using big datasets such as Fruits-360, which shows they're good at sorting (Salim F et al., 2023) [11] . Also, by using image-processing techniques with machine learning, these systems can check things like firmness and even aroma, which is crucial for making sure fruit is good quality (Dhiman P et al., 2023) [19] . Advanced methods, like the ones in, illustrate that system automation, which is driven by machine learning algorithms, can really cut down on labor costs and boost how well grading is done. It helps deal with big problems in agricultural technology.

EfficientNet

A family of models balancing accuracy and efficiency, applied in fruit sorting tasks to achieve good results while maintaining computational efficiency.

([xeroai.com] (https://xeroai.com/industries/fruit-sorting-and-monitoring-using-deeplearning/?utm_source=openai))

Role of deep learning in enhancing accuracy

Deep learning really steps up the game for computer vision in the automatic grading and sorting of fruits and vegetables. These systems, powered by advanced neural networks, can look at produce images and spot tiny differences in size, color, and blemishes. It's like they have super-vision! In fact, integrating AI into agriculture has been a gamechanger for better crops and quality, helping us keep up with the need for safer farming methods (Kashyap GS et al., 2024) [17] . Machine vision is also becoming a go-to for fixing problems with old-school harvesting, making picking both efficient and non-destructive (Zhang J et al., 2024) [10] .

Harnessing deep learning, these automated grading setups not only make things run smoother but also ensure we're getting top-notch produce, marking a big step forward in how we handle food. Generally speaking, this tech leads to better food on our tables and less waste in the fields.

Hardware requirements for implementation

When thinking about using computer vision to automatically grade fruits and veggies, you absolutely need strong hardware to get the job done right. At the core of this setup, high-resolution cameras are a must. Why? Because judging quality depends on really good pictures of the produce. Also, you've got to have serious processing power, like with graphic processing units (GPUs), to crunch all that data in real time. This lets machine learning algorithms do their thing, sorting fruits and vegetables like a pro. It's also super important to hook everything up to mechanical sorting systems. Think conveyor belts and actuators working handin-hand with the computer vision data. That's how you get top-notch sorting speed and accuracy. You can see an example of this kind of setup in, where a computer vision system checks out fruits as they move along a conveyor belt. It just goes to show how all the hardware pieces need to fit together perfectly for smooth and efficient automated grading. Plus, research in (Leal A, et al., 2024) [12] and (Kashyap GS et al., 2024) [17] gives us even more to consider about matching hardware power to the latest computer vision methods.

Applications in grading fruits and vegetables

Within the agri-food sector, the incorporation of computer vision offers a truly transformative path forward for the grading and sorting of produce. Automated systems, powered by complex algorithms, bring greater efficiency and precision when assessing qualities such as size, color, and even firmness, which greatly diminishes the margin for human errors. Consider, for example, an automated mango grading setup: it doesn't just weigh the fruit; instead, it uses imaging techniques to determine volume, infer aroma, and even gauge texture, thereby conducting a complete quality assessment (Taneja A et al., 2023) [15] . These types of improvements highlight AI's potential to bring considerable changes to agricultural practices, improving productivity and simultaneously reducing waste. Systems like these are growing in importance, especially where maintaining high quality standards is important in a market that is increasingly shaped by consumers seeking consistent quality and eco-friendly practices ((Dadlani M et al., 2023)) [16] . As more growers implement these innovative tools, the future of fruit and vegetable grading can look forward to improved speed and reliability, resulting in a more efficient supply chain overall. Color analysis for ripeness assessment Employing color analysis to determine ripeness is a key step forward in the automated grading and sorting processes for fruits and vegetables. Computer vision systems, for instance, can examine the color characteristics of produce; this gives immediate insight into the quality and maturity of the produce being assessed. To illustrate, differences in a fruit's spectral reflectance can be quantified, leading to precise categorization that's based on different stages of ripeness. This assessment accuracy improves not only sorting efficiency, it also minimizes waste-something vital in today's market where consumer demand is, generally, high. Furthermore, as noted in recent studies, machine vision tech has a transformative effect on agricultural practices. The tech contributes to more sustainable farming by cutting down on labor expenses while boosting productivity (Zhang J, et al., 2024) [10] (Salim F, et al., 2023) [11] . The integration of such technologies, through processes like those in, showcases the promise of food quality assurance innovation.

Size and shape measurement for quality control

In automated fruit and vegetable grading setups, getting the size and shape right is super important, especially for keeping quality consistent. Why? Because these things really affect what shoppers think and whether stuff sells [extractedKnowledge1]. So, tech like computer visionyou know, with 3D imaging and smart machine learningmakes grabbing and checking this data way easier. This quick checking helps spot bad bits and weird shapes, making sure only the good stuff gets processed. (Dhiman P et al., 2023) [19] (Dadlani M et al., 2023) [16] .

Detection of defects and diseases

For agricultural production, spotting defects and diseases in produce is essential for quality and safety. Computer vision methods have become key for early detection. They use complex algorithms to analyze visuals and find slight changes that suggest spoilage or disease. These systems look at aspects such as color, texture, and size, allowing for accurate assessment during processing. As noted in the review of non-destructive methods, image analysis and other advanced techniques can accurately assess both external and internal quality, which improves sorting accuracy and efficiency. Integrating these technologies into automated grading systems speeds up production and cuts down on waste by making sure only the best produce gets to consumers. An example of this is detailed in, where a computer vision model sorts mangoes by various quality standards, highlighting the effectiveness of automated defect detection.

Real-time processing and feedback mechanisms

In automated agriculture, especially for fruits and vegetables, real-time processing and feedback are key to grading and sorting. Using computer vision, systems can quickly assess attributes like color, size, and texture, giving immediate feedback on quality. This boosts efficiency and reduces human mistakes and damage. For example, imaging cameras provide constant data streams, sorting produce by quality standards, as shown in. AI enhances this by adjusting to different fruit characteristics, refining grading methods as discussed in (Leal A et al., 2024) [12] and (Zhang J et al., 2024) [10] . Consequently, these mechanisms are critical for transforming fruit processing into an efficient, accurate, and automated operation.

Benefits of automated grading and sorting

Integrating automated grading and sorting into agricultural workflows presents a range of advantages, primarily boosting both overall efficiency and, of course, food quality. These systems, leveraging advanced computer vision, offer an ability to accurately evaluate produce like fruits and vegetables across key attributes like size, color, and even texture. In most cases, this reduces potential human error and bias during grading. Expediting sorting is a key advantage, making it both cheaper and faster, while also cutting labor costs tied to traditional manual sorting. Current studies show the integration of machine learning further optimizes food processing. This allows for enhanced decision-making and precise predictions regarding produce quality ((Salim F, et al., 2023) [11] , (Pandey VK, et al., 2023)) [18] . The organized efficiency provided by these technologies in maintaining elevated benchmarks in food safety and high consumer satisfaction is underscored by the visual representation of a fruit sorting mechanism in a processing line (see), which plays a critical role in maintaining high standards in food safety and consumer satisfaction.

Benefit Description

Benefit Description

Increased Efficiency

Automated systems process large volumes of produce faster than manual methods, reducing spoilage and enhancing profitability. For instance, optical sorting systems can handle high volumes efficiently, reducing labor dependency by up to 50%. ([globalgrowthinsights.com], (https://www.globalgrowthinsights.com/market-reports/automated-food-sorting-equipment-market-104326?utm_source=openai)) Improved Consistency and Quality Control AI-powered systems maintain consistent grading standards, ensuring uniformity in product quality. This consistency helps build consumer trust and meets market expectations. ([linkedin.com], (https://www.linkedin.com/pulse/smart-sorting-role-ai-agricultural-product-grading-xis-ai-hwtee/?utm_source=openai))

Cost Savings Automated sorting reduces labor costs and minimizes waste by accurately identifying and removing subpar products. For example, in the Netherlands, the use of automated systems led to a 30% reduction in labor costs in the tomato industry. ([wechronicle.com], (https://wechronicle.com/food/exploring-the-innovation-of-automated-food-sorting-and-grading-systems/?utm_source=openai)) Enhanced Data Collection and Decision-Making Automated systems collect valuable data on product characteristics, aiding in informed decision-making and improved crop management. This data-driven approach supports better planning and forecasting. ([vexolabs.com], (https://www.vexolabs.com/blogs/how-ai-is-improving-crop-sorting-and-grading-processes?utm_source=openai))

Sustainability and Reduced Waste

By accurately sorting and grading produce, automated systems minimize waste and reduce the environmental impact of agriculture. This leads to more efficient use of resources and supports sustainable practices. ([mdpi.com], (https://www.mdpi.com/2071-1050/16/22/10084?utm_source=openai))

Increased efficiency and speed in operations In agricultural automation, the enhancement of operational efficiency and speed is really key, most notably when grading and sorting produce. Integrating computer vision refines these operations by facilitating real-time analysis, speeding things up while reducing errors from people. Automated systems quickly check size, color, and quality, which accelerates decision-making and makes the workflow better. As noted in existing work, these advancements not only lower labor costs from manual grading, but they also lead to more consistent product quality and enhance market value of farm outputs, as highlighted by studies in automated fruit picking (Zhang J, et al., 2024) [10] . Additionally, using machine learning with computer vision sharpens sorting accuracy, which helps with more precise operation adjustments (Mohyuddin G, et al., 2024) [14] . The transition to automated sorting systems signifies a big step forward in agricultural efficiency, overall.

Fig 3: Improvements in grading methods

The chart displays improvements in fruit grading and sorting processes across three methods: traditional manual grading, automated grading with computer vision, and automated grading using deep learning models. It highlights significant increases in throughput, reduced labor requirements, and enhanced defect detection accuracy with the automated methods compared to manual grading.

Reduction of human error and bias

Employing computer vision for fruit and vegetable grading and sorting markedly diminishes both human error and inherent biases, thereby improving the precision of operations across the board. Manual grading, which has been used traditionally, often is subjective because it is influenced by individual human preferences and inconsistent standards. This subjectivity can create disparities in product quality and, as a result, market value. Making the transition to automated systems, illustrated in the sorted mango classification example in, replaces human judgment with algorithmic precision to make sure produce evaluation is standardized. These systems take advantage of imaging technology for assessing characteristics objectively such as size, color, and texture to ensure consistent sorting results. As automated grading progresses, it fosters an atmosphere that effectively does away with human biases stemming from fatigue, or differing levels of experience; in doing so, it enhances reliability and efficiency in the agricultural sector (Singh K, et al., 2025) [4] . Not only does this change maximize productivity, but it also fosters a more equitable and transparent grading process.

Cost-effectiveness in the long run

The ongoing cost-effectiveness of using computer vision in agriculture for the automated grading and sorting of produce like fruits and vegetables is becoming more and more important. Labor costs are going up, and there are demands for better agricultural efficiency, so using automated systems can cut down on the need for manual labor, as well as improve how accurate and fast the sorting process is. For example, the techniques in (Leal A, et al., 2024) [12] show how the industry is moving toward automation. This minimizes waste and maximizes the quality of produce through better sorting. AI-driven solutions in agriculture, like those in (Kashyap GS et al., 2024) [17] , show how machine learning can optimize how resources are used, which lowers operational costs in the long run. A good visual example of this can be seen in, where a computer vision model sorts apples effectively, showing a practical way it can create economic benefits. Overall, these improvements show a transformative approach to agricultural productivity and sustainability.

Improved consistency in product quality

The use of computer vision in agriculture, specifically for grading fruits and vegetables, has really changed how consistent product quality is, offering a more efficient solution than the old manual ways. By using these advanced imaging systems, producers are better able to judge important qualities, like color and shape, which matter a lot to consumers and market standards. Take, for instance, the automated sorting system shown in [extractedKnowledge1]; it's a good example of how real-time analysis can sort produce more evenly, which cuts down on the differences you often see with manual sorting. This precision doesn't just make the product better; it also cuts down on waste, since substandard items are found and taken out right away. Plus, using this kind of tech fits with the broader push to make agricultural practices better, as noted in (Leal A et al., 2024) [12] and (Licardo JT et al., 2024) [13] . As these improvements keep happening, they should keep improving both how efficiently and the quality in the food production world.

Conclusion

To summarize, deploying computer vision tech has really shaken up how fruits and veggies get graded and sorted on farms. This leads to boosted efficiency, better quality, and less waste. Producers can now automate a lot of stuff and keep product standards consistent, plus take some pressure off those labour-intensive manual sorting tasks. For instance, those automated systems, like the ones you can see in, show how analyzing visuals in real-time can drive sorting decisions based on things like color, shape, and size which streamlines the whole supply chain. As studies show, AI and computer vision advancements just keep opening new doors in agriculture, making things more productive and sustainable (Taneja A et al., 2023) [15] (Dadlani M et al., 2023) [16] . So, this move towards automated grading is more than just changing how things are done; it's a key move toward a more efficient food system.

Summary of key points discussed

The agricultural world has seen a revolution in fruit and vegetable grading and sorting thanks to computer vision technology. This integration boosts both productivity and quality control. Recent progress underscores just how effective non-invasive techniques like machine vision can be; they notably improve the accuracy of quality assessments for fruit, reducing human error in most cases (Hernando C et al., 2010) [6] . Discussions often highlight process automation, particularly systems using sophisticated algorithms for real-time data analysis and decision-making. Take, for example, automated sorting lines, such as the one illustrated in, showing how visual analysis can streamline categorization in commercial environments, lowering waste and ensuring product quality consistency. Furthermore, exploration into challenges-like the variability in fruit appearance and the necessity for advanced machine learning models-point toward promising areas for future research (D Baswaraj et al., 2023) [7] . Ultimately, incorporating these technologies seems set to enhance the efficiency of fruit and vegetable processing operations quite a bit.

Image 2: Automated sorting system utilizing computer vision for efficient categorization.

Final thoughts on the impact of technology on food production

To summarize, the use of technology in how we grow food, especially using computer vision to automatically grade and sort what we harvest, is a major step forward for agriculture. This progress makes things more efficient and accurate, so that consumers mostly get the best stuff. Being able to quickly check many things about fruit-like how big it is, how much it weighs, and its color-makes sorting easier and cuts down on how much we spend on labor, which helps make our food systems more sustainable. The photo showing how mangoes are graded shows pretty clearly how automation helps with careful evaluations, hinting at even more uses for different kinds of food. Furthermore, as noted in the research, understanding AI and being able to read data is really important for how we teach kids in the future; it means we need to get students ready to use these technologies (Kim J et al., 2022) [20] . In most cases, continued studies and improvements in these areas will keep changing how food is made, making sure it's both efficient and good quality as the industry changes (Dadlani M et al., 2023) [16] .

Image 3: Diagram of automated mango classification and grading process

Figures and tables from the paper

↗ Enlarge

Figure 1Close ×

Impact of computer vision on fruit grading and sorting

Open full-size image ↗

Original paper figureSource PDF · page 2 ↗

↗ Enlarge

Table 1Close ×

Machine learning algorithms in computer vision for fruit and vegetable sorting

Open full-size image ↗

Original paper figureSource PDF · page 3 ↗

↗ Enlarge

Table 2Close ×

Computer vision applications in fruit and vegetable grading

Open full-size image ↗

Original paper figureSource PDF · page 4 ↗

↗ Enlarge

Figure 2Close ×

Performance of deep learning models in fruit quality assessment

Open full-size image ↗

Original paper figureSource PDF · page 4 ↗

↗ Enlarge

Table 3Close ×

Benefits of automated grading and sorting of fruits and vegetables

Open full-size image ↗

Original paper figureSource PDF · page 6 ↗

↗ Enlarge

Figure 3Close ×

Improvements in grading methods

Open full-size image ↗

Original paper figureSource PDF · page 6 ↗

↗ Enlarge

Figure 4Close ×

Comparison of grading methods

Open full-size image ↗

Original paper figureSource PDF · page 8 ↗

1. Barbosa Júnior MR, Santos RG, Sales LA, Oliveira LP. Advancements in agricultural ground robots for specialty crops: an overview of innovations, challenges, and prospects. Plants. 2024;13:1-20. DOI: 10.3389/plants.c7376bfb.
2. Nandhini E, VG. A comprehensive analysis of image processing methods for agricultural product quality control. In: 2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES); 2024, p. 1-7. DOI: 10.1109/icses.2024.ae2cbea.
3. Lalam R, Lavanya K, Nadella V, Kiran BR. Automatic sorting and grading of fruits based on maturity and size using machine vision and artificial intelligence. J Sci. Res Rep. 2025;37(3):1-12. DOI: 10.9734/jsrr.2025.9373cdb.
4. Singh K, Singh J, Rani R. Computer vision approach for vegetable quality assessment. In: 2025 7th International Conference on Intelligent Sustainable Systems (ICISS); 2025, p. 1-5. DOI: 10.1109/iciss.2025.a683413.
5. Evaluating agricultural production line efficiency using TOPSIS: A comparative analysis of crops and processing stages. Agric Biol Food Sci. 2025;5(1):1-10. DOI: 10.1016/abfs.2025.c21a7e8.
6. Correa H, Diezma-Iglesias B, García-Ramos FJ, Hernández-Sánchez N, et al. Sensors for product characterization and quality of specialty crops: A review. Span J Agric Res. 2010;8(4):1007-1026. DOI: 10.5424/sjar/2010084-1244.
7. Baswaraj D, et al. Importance of machine vision framework with nondestructive approach for fruit classification and grading: A review. J Food Qual. 2023;2023:1-15. DOI: 10.1155/2023/591405212.
8. Affeldt HA, Aggarwal P, Aleixos N, Aloimonos Y, Andaur C, Bato P, et al. Non-destructive technologies for fruit and vegetable size determination: A review. Comput Electron Agric. 2009;69(1):1-14. DOI: 10.1016/j.compag.2009.148653.
9. Torricelli A, Ketelaere DB, Nicolaï BM, Herremans E, Hertog MLATM, Verboven P, et al. Nondestructive measurement of fruit and vegetable quality. Trends Food Sci Technol. 2014;35(1):2-13. DOI: 10.1016/j.tifs.2013.552512.
10. Zhang J, Kang N, Qu Q, Zhou L, Zhang H. Automatic fruit picking technology: A comprehensive review of research advances. Artif Intell Rev. 2024;57:1-35. DOI: 10.1007/s10462-023-10674-2.
11. Salim F, Saeed F, Basurra S, Qasem SN, Al-Hadhrami T. DenseNet-201 and Xception pre-trained deep International Journal of Agriculture and Food Science https://www.agriculturaljournals.com learning models for fruit recognition. Electronics. 2023;12(14):3132. DOI: 10.3390/electronics12143132.
12. Leal A, Gutber Jena A, Bamola A, Mishra S, Jain I, Pathak N, et al. State of the art non-destructive approaches for maturity index determination in fruits and vegetables: Principles, applications, and future directions. Food Prod Process Nutr. 2024;6:15. DOI: 10.1186/s43014-023-00205-5.
13. Licardo JT, Domjan M, Orehovački T. Intelligent robotics: A systematic review of emerging technologies and trends. Electronics. 2024;13(3):542. DOI: 10.3390/electronics13030542.
14. Mohyuddin G, Khan MA, Haseeb A, Mahpara S, Waseem M, Saleh AM. Evaluation of machine learning approaches for precision farming in smart agriculture system: A comprehensive review. IEEE Access. 2024;12:60155-60184. DOI: 10.1109/access.2024.3390581.
15. Taneja A, Nair G, Joshi M, Sharma S, Sharma S, Režek Jambrak A, Roselló-Soto E, et al. Artificial intelligence: implications for the agri-food sector. Agronomy. 2023;13(5):1397. DOI: 10.3390/agronomy13051397.
16. Dadlani M, Yadava DK. Seed science and technology. Singapore: Springer; 2023. DOI: 10.1007/978-981-195888-5885.
17. Kashyap GS, Kamani P, Kanojia M, Wazir S, Malik K, Sehgal VK, Dhakar R. Revolutionizing agriculture: A comprehensive review of artificial intelligence techniques in farming. Res Square [Pre-Print]. 2024. DOI: 10.21203/rs.3.rs-3984385/v1.
18. Pandey VK, Srivastava S, Dash KK, Singh R, Shaikh AM, Kovács B, Harsányi E. Machine learning algorithms and fundamentals as emerging safety tools in preservation of fruits and vegetables: A review. Processes. 2023;11(6):1720. DOI: 10.3390/pr11061720.
19. Dhiman P, Kaur A, Balasaraswathi VR, Gulzar Y, Alwan AA, Hamid Y. Image acquisition, preprocessing and classification of citrus fruit diseases: A systematic literature review. Sustainability. 2023;15(12):9643. DOI: 10.3390/su15129643.
20. Kim J, Lee HK, Cho YH. Learning design to support student-AI collaboration: Perspectives of leading teachers for AI in education. Educ Inf Technol. 2022;27(5):6069-6104. DOI: 10.1007/s10639-02110831-6.