This project aims to develop an automated contamination detection system using advanced computer vision technologies in food production environments.

High-resolution imaging and deep learning models are applied to identify contamination patterns, foreign materials, and microbial risks in food products. The system is trained using diverse datasets to improve detection accuracy and adaptability across different food types.

The implementation of this system enhances inspection efficiency and reduces human error in quality control processes. It also supports real-time monitoring and rapid response to contamination risks.

This research contributes to improving food safety assurance and supports the integration of automated inspection systems in industrial applications.