FreshGuard: AI-Powered Fruit Spoilage Detection System

Author(s)	Pragati Vitthal Akhare, Vaishnavi Dattatray Dherange, Siddhesh Kishor Londhe, Pallavi Vaijinath Shinde, Pooja Dehankar Sherje
Country	India
Abstract	Fruit spoilage is a major challenge in the agricultural supply chain, causing economic losses and reduced food quality. To address the limitations of manual inspection in high-speed conveyor systems, this research introduces FreshGuard, an AI-powered fruit spoilage detection system. It uses a MobileNetV2-based CNN trained on a fresh and rotten fruit dataset to classify fruits like apples, bananas, and oranges based on color, texture, and decay patterns. The model is deployed on a Raspberry Pi 4 for real-time edge-based detection without cloud dependency. A Pi Camera captures images, while IR sensors trigger detection as fruits move on a conveyor belt. Spoiled fruits are automatically separated using a motorized system with a servo mechanism. The system achieves 98.6% accuracy with inference time under one second, offering a cost-effective and reliable solution for automated fruit quality inspection.
Keywords	Fruit spoilage detection, Raspberry Pi, Deep Learning, MobileNetV2, Computer Vision, Conveyor belt automation, Smart Agriculture, Edge AI
Field	Engineering
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-30
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.70993

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research