Multimode fibers with core diameters of 50 μm and 62.5 μm are the core media for short-distance, low-cost, and high-bandwidth optical transmission scenarios. Currently, the detection of their end-face defects is still mainly based on manual microscopic inspection. Most of the existing machine vision detection schemes are aimed at polarization-maintaining fibers (POL), which are easily interfered with by impurities and have insufficient accuracy and efficiency. This study introduces the information entropy in information theory as a constraint for feature selection, proposes the WGMOS digital image detection method, and optimizes the entire process of image acquisition, correction, filtering, adaptive segmentation, and feature extraction. By minimizing the information entropy of background noise and maximizing the information content of defect features, interference is suppressed. Experiments show that compared with the POL detection method, this scheme can exclude more impurities, with the image equalization value increased by ≥38.20% and the signal-to-noise ratio increased by ≥6.0%. It can achieve efficient and accurate detection of multimode fiber end-face defects.
Optical modules serve as the core transmission interfaces for artificial intelligence computing networks and digital communications. In recent years, demand for these modules has experienced explosive growth. During mass production, the requirements for the accuracy of surface defect detection and noise resistance have continued to rise. Existing POL detection models are susceptible to environmental noise interference; effective defect information is easily overwhelmed by noise entropy, and these models exhibit a high false negative rate for low-contrast and minute defects. This paper proposes a traditional image processing detection scheme that incorporates information entropy constraints. All experimental samples were collected from actual industrial mass production lines. The core process includes: noise suppression during the calibration stage using an entropy-weighted Hough transform; Canny edge detection combined with local entropy filtering for contour localization; and defect fusion recognition based on Hu similarity matching and entropy difference verification. Experimental results show that, compared to traditional POL methods, the proposed approach (WOMC) achieves an average improvement of 35.77% in image clarity and approximately a 2.25-fold increase in detection rate under Gaussian and salt-and-pepper noise conditions. According to statistical analysis of the experiments, this method achieved an accuracy of 96.67%, a recall rate of 97.32%, and a false positive rate of 3.31% in defect detection. In addition, the comprehensive performance score of this detection model reached 96.99%. Moreover, it does not require the deployment of deep-learning models, has a low computing power cost, and is suitable for the detection requirements of large-scale mass production.