• Miss. Tanishka B. Kadam
• Mrs. Madhura M. Raste
• Mr. Shreeyash P. Manugade
• Miss. Reshma P. Patil
• Miss. Devyani M. Ghatage

In the agricultural supply chain, fruit grading is an essential quality control process that directly impacts product pricing, customer satisfaction, and export potential. Manual fruit grading, which relies heavily on human expertise, is prone to subjectivity, inconsistencies, and delays. This paper introduces a deep learning-based Fruit Grading System that performs intelligent classification and quality grading of fruits using Convolutional Neural Networks (CNNs). The system is designed to identify the fruit type (e.g., apple, banana, orange) and determine its quality level (High, Medium, or Low) based on visual cues like color, texture, and shape. Developed using TensorFlow/Keras, the model is trained on a custom dataset of fruit images with appropriate labeling for both class and grade. The system integrates a user-friendly web interface that allows users to upload fruit images and receive instant classification results via a backend API. By automating the grading process, the system enhances consistency, minimizes human errors, and offers scalability across different environments such as farms, sorting centers, and retail markets. The proposed system has achieved promising performance metrics in both classification tasks, validating the feasibility of using CNNs for real-time fruit grading applications.

Fruit Grading, Deep Learning, CNN, Image Classification, Quality Detection, TensorFlow, Keras, Agricultural Automation.

"Fruit Grading System: Intelligent Classification And Quality Grading Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.g350-g354, June-2025, Available :http://www.jetir.org/papers/JETIR2506644.pdf

"Fruit Grading System: Intelligent Classification And Quality Grading Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. ppg350-g354, June-2025, Available at : http://www.jetir.org/papers/JETIR2506644.pdf