FIT3D: Real-time Flatness Inspection Algorithm for Ceramic Tiles using the Structured Light 3D Scanner

Abstract

Accurate inspection of surface flatness is important for ceramic tile quality control. Manual inspection and displacement sensors provide incomplete surface information. FIT3D uses structured light 3D scans and a support vector machine model to determine minimum zone planes, with convex hull acceleration to enable real-time processing. Experiments on public datasets and a real-world case study demonstrate effectiveness.

Juan Du

Assistant Professor

My research interests include knowledge-infused data science for quality improvement, industrial data analytics and machine learning, and system informatics and control for manufacturing applications.