Automated fruit quality assessment in Indian agriculture using computer vision

View at publisher Summarise with VIRAT
Authors: Suguna Thangavel, S. Kannadhasan, Gopalakrishnan Vasudevan
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

India’s rapidly expanding population is fueled by the country’s rising need for a variety of fruits and vegetables. Automation in agriculture has become essential to meeting this demand while maintaining quality and production. Conventional techniques for evaluating the quality of fruit depend on human specialists, who are labor-intensive, prone to mistakes, and often inconsistent because of weariness or subjective judgment. Furthermore, human grading limits scalability and increases operating expenses, especially in a market that places a high value on accuracy and efficiency. By combining cutting-edge technology, automation provides a workable answer to these problems and allows for quicker, more accurate, and more economical fruit sorting. Using advances in computer vision and machine learning, researchers have created a variety of methods for classifying and assessing the quality of fruits. These technologies examine fruit characteristics that are important indicators of quality, including size, shape, color, texture, and surface flaws. Fruit grading is essential for both classifying them and enhancing their commercial worth and consumer appeal. Automated grading systems use reliable algorithms for feature extraction and categorization, substituting data-driven, objective procedures for human judgment. This research examines the creation of grading algorithms based on machine learning for an automated fruit grading system. It highlights how crucial efficient feature extraction methods are to guaranteeing the precision and dependability of these systems. By employing techniques such as image processing, neural networks, and classification algorithms, automated grading systems can revolutionize agricultural practices in India. These systems not only streamline the grading process but also contribute to the economic growth of the agricultural sector by enhancing productivity, reducing costs, and maintaining quality standards. This research aims to provide a comprehensive overview of automated fruit grading systems, focusing on their key components and the role of machine learning in achieving efficient and reliable grading outcomes.

Fields of Study & Subjects

Smart Agriculture and AI Industrial Vision Systems and Defect Detection Advanced Neural Network Applications

Publication details

Journal / source
AIP conference proceedings
Volume
3341
Pages
020004–020004
Publication date
1 January 2026
Language
EN