Scholarlink

This research delves into the essential aspects of identifying crucial variables and establishing a comprehensive categorization system for citrus fruits based on their varieties and quality. Citrus fruits play a pivotal role in the global fruit trade, with both growers and consumers placing significant importance on the ability to recognize, classify, and assess them. The study involves a thorough analysis of key factors influencing the categorization and evaluation of citrus fruits. To ensure the credibility and distinctiveness of the findings, these criteria are determined through a meticulous blend of extensive study, laboratory analysis, and field observations. The investigation commences by scrutinizing the external characteristics of citrus fruits, including size, shape, and color. By quantifying these attributes, a foundational framework for classifying citrus fruits is established. Additionally, a comprehensive examination of the chemical composition of citrus fruits is conducted, emphasizing features such as sugar concentration, acidity, and fragrance compounds that significantly impact taste and overall quality. The paper presents comprehensive insights into the utilization of a machine learning model to train datasets for determining the quality of various citrus fruits, such as Orange, Lime, Lemon, Grapefruit, Pomelo, Tangerine, Kumquats, and Clementine, and classifying the same. The developed machine learning model using linear regression demonstrates an accuracy of 89% in distinguishing whether a given fruit is a citrus fruit and further categorizing it based on the provided data.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Citrus Fruit Classification and Quality Assessment Through Advanced Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Sindhu Menon,
  • Keerthi Shree,
  • Nagarjun Reddy,
  • Bharath Jangam,
  • B. K. Bhoomika

摘要

This research delves into the essential aspects of identifying crucial variables and establishing a comprehensive categorization system for citrus fruits based on their varieties and quality. Citrus fruits play a pivotal role in the global fruit trade, with both growers and consumers placing significant importance on the ability to recognize, classify, and assess them. The study involves a thorough analysis of key factors influencing the categorization and evaluation of citrus fruits. To ensure the credibility and distinctiveness of the findings, these criteria are determined through a meticulous blend of extensive study, laboratory analysis, and field observations. The investigation commences by scrutinizing the external characteristics of citrus fruits, including size, shape, and color. By quantifying these attributes, a foundational framework for classifying citrus fruits is established. Additionally, a comprehensive examination of the chemical composition of citrus fruits is conducted, emphasizing features such as sugar concentration, acidity, and fragrance compounds that significantly impact taste and overall quality. The paper presents comprehensive insights into the utilization of a machine learning model to train datasets for determining the quality of various citrus fruits, such as Orange, Lime, Lemon, Grapefruit, Pomelo, Tangerine, Kumquats, and Clementine, and classifying the same. The developed machine learning model using linear regression demonstrates an accuracy of 89% in distinguishing whether a given fruit is a citrus fruit and further categorizing it based on the provided data.