Xinfeng Li
Papers
1
Total Citations
8
H-Index
1
About
Xinfeng Li is a researcher whose work sits at the intersection of industrial robotics, computer vision, and advanced image processing. Their key research areas include defect detection, automated manufacturing, and the application of probabilistic models to real-world engineering challenges. Li’s most notable contribution is a novel defect segmentation method for fiber splicing on industrial robot systems. By combining the Gaussian Mixture Model (GMM) with the Graph Cut Model (GCM), they developed a robust technique to accurately segment defects in hot images of plastic-surfaced fibers—a critical step for quality control in automated production lines. This work, published in 2012 and cited 8 times, demonstrates a practical fusion of machine learning and graph theory to solve a difficult industrial problem. Li’s research exemplifies how sophisticated algorithms can be tailored to enhance the precision and reliability of robotic systems, making a tangible impact on manufacturing efficiency. Their approach continues to inform subsequent work in defect segmentation and automated visual inspection.
Research Focus
Key Achievements
Top Papers
- 1