review · IEEE Access
Manual inspection of fruit for pest and disease damage is time-consuming, inconsistent, and subjective, directly lowering market value and farmer revenues from processing, sales, and exports. Automated systems using segmentation, image processing, machine learning, and deep learning offer rapid and precise identification of surface damage. A review of 32 journal and conference articles spanning 13 years evaluates past research addressing the limitations of manual visual checks. While machine learning and automated classification have demonstrated promising outcomes for the horticulture industry, technical gaps remain. Future progress depends on creating fully automated systems that operate seamlessly, particularly mobile phone-based tools capable of overcoming real-world issues such as occlusion when assessing fruit on the plant or during handling.
Fruit quality heavily influences market value and consumer demand. Because human inspection is slow and error-prone, pests and diseases regularly cause significant financial losses for growers. Developing effective automated diagnostic tools can safeguard yields, ensure consistent quality standards, and strengthen agricultural incomes by catching infections early in production, processing, and export workflows.
The reviewed approaches point towards automated fruit quality assessment tools for horticultural growers, processors, and exporters. The clearest operational path lies in mobile phone-based detection software for field use. However, because existing systems struggle with occlusion and are not yet fully autonomous, the technology remains at an applied research stage rather than ready for immediate commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Automation improves the quality of fruits through quick and accurate detection of pest and disease infections thus contributing to the country’s economic growth and productivity. Although humans can identify the fruit damage caused by pests and diseases, methods used are inconsistent, time-consuming, and variable. The surface features of fruits typically observed by consumers who seek their health benefits, affect their market value. The issue of pest and disease infections further deteriorates fruits’ quality, becoming a mounting stressor on farmers as they affect the potential income that could have been realised from production, processing and export. This article reviews various studies on detecting and classifying damages in fruits. Specifically, we review articles where state-of-the-art approaches under segmentation, image processing, machine learning, and deep learning have proved effective in developing automated systems that address hurdles associated with manual methods of assessing damage using visual experiences. This survey reviews 32 Journal and Conference articles spanning 13 years obtained electronically through Google Scholar, Scopus, IEEE, ScienceDirect, and general internet searches. This survey further presents a detailed discussion of related studies done in the past while emphasizing their strengths and limitations and presenting future research directions. It also reveals that much as the use of automated detection and classification of fruit damage has yielded promising results in the horticulture industry, more research is still needed with systems required to fully automate the detection and classification processes, especially those that are mobile phone-based towards addressing occlusion challenges.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3362230
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
