Model-driven photometric stereo for in-process inspection of non-diffuse curved surfaces. Issue 1 (2019)

• Record Type: Journal Article
• Authors: Ren, Mingjun; Xiao, Gaobo; Zhu, Limin; Zeng, Wenhan; Whitehouse, David
• Is Part Of: CIRP annals. Volume 68:Issue 1(2019)
• Page Start: 563
• Page End: 566
• Publication Date: 2019
• Subjects: Surface -- Quality control -- Visual inspection; Production engineering -- Research -- Periodicals; 670.5
• DOI: 10.1016/j.cirp.2019.04.013
• Languages: English
• ISSNs: 0007-8506

Abstract

Abstract: This paper presents an in-process inspection approach for quality control of non-diffuse curved surfaces based upon an evolution of conventional photometric stereo. An inverse reflectance model is proposed to reveal the non-linear reflectance behaviour of general non-diffuse surfaces from images based on a neural network. The model can directly be used to drive a high accurate photometric stereo which only requires a single RGB image with a pre-captured collocated image. This allows the technique to realize in-process inspection of moving surfaces with micro-second level capturing rate. Experimental study confirms the excellent texture recovery and defect detection capabilities in mass production.