Citation

Kamarudin, Puteri Nur Farzanah Faghira and Abd Rahman, Noor Ziela and Hashim, Nik Mohd Zarifie (2025) CNN-Powered Real-Time Classification of Milk Spoilage via RGB Images. In: 2025 Multimedia University Engineering Conference (MECON), 21-23 July 2025, Cyberjaya, Malaysia.

Text IEEE Xplore Full-Text PDF_35.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Milk spoilage is a significant concern in food safety and public health, particularly in regions lacking reliable refrigeration or quality monitoring systems. This paper presents a real-time application for detecting milk spoilage using RGB image data. Using a custom Convolutional Neural Network (CNN) model deployed with TensorFlow and OpenCV, the system classifies milk as either ‘good’, spoiled’, or ‘others’ based on visual indicators. The proposed model was trained on a selfcollected dataset of labeled milk. This study proves that the custom CNN proposed model managed to achieve the greatest accuracy of 99% among different models evaluated. The realtime detection system demonstrates fast and accurate inference, making it suitable for practical use in household, retail, and supply chain environments. This study contributes to the growing body of intelligent food quality monitoring systems by offering a lightweight, efficient, and scalable solution for imagebased milk spoilage detection.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Convolutional Neural Network, milk spoilage
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	17 Mar 2026 07:17
Last Modified:	17 Mar 2026 08:07
URII:	http://shdl.mmu.edu.my/id/eprint/15525

Downloads

Edit (login required)