Abstract

With the advancement of intelligent manufacturing, automated defect detection systems are playing an increasingly vital role in improving product quality. However, complex interference factors in real-world industrial environments pose significant challenges to the stability and reliability of detection algorithms. Addressing this critical issue, this study proposes an interference-resistant defect detection algorithm tailored for complex industrial scenarios. By thoroughly analyzing typical interference characteristics in industrial settings, the study develops a comprehensive solution incorporating adaptive preprocessing, robust feature extraction, and intelligent decision optimization. The algorithm innovatively integrates physical models with deep learning techniques, achieving breakthroughs in key areas such as image enhancement, feature representation, and defect recognition. Experimental results demonstrate that the proposed method exhibits superior detection performance under various interference conditions, significantly improving the environmental adaptability and operational stability of industrial inspection systems. This research provides a practical and effective technological pathway for quality control in intelligent manufacturing.