A Hybrid Deep Learning And Machine Learning Framework for Food reshness and Spoilage Detection using Mobilenetv2 and Image Segmentation

Read full text Summarise with VIRAT
Authors: Kaleeswari Kaleeswari, Ananthi Ananthi
Cited by: 0
References: 4

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

Identifying food degradation has pinpoint the precise areas impacted by become essential for maintaining supply chain quality, reducing waste, and ensuring food safety. Traditional freshness assessment techniques are primarily based on manual inspection, which is often inaccurate, time consuming, and unreliable. The automated food freshness assessment approach proposed in this paper integrates deep learning– based feature extraction, machine learning classification, and image segmentation techniques. The proposed method determines food quality using a logistic regression classifier and extracts high-level visual features through a pre-trained convolutional neural network (CNN). In addition, a spoilage analysis module employs pixel-level evaluation to identify affected regions and estimate the severity level. Experimental results indicate that the system is suitable for real- time automated food monitoring applications, as it effectively visualizes spoiled areas while achieving high classification accuracy.

Fields of Study & Subjects

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

Publication details

Journal / source
International Journal of Science Strategic Management and Technology
Volume
02
Issue
03
Pages
1–9
Publication date
25 March 2026
Language
EN