A 3D measurement method for specular surfaces based on polarization image sequences and machine learning. Issue 1 (2020)

• Record Type: Journal Article
• Authors: Kong, Lingbao; Sun, Xiang; Rahman, Mustafizur; Xu, Min
• Is Part Of: CIRP annals. Volume 69:Issue 1(2020)
• Page Start: 497
• Page End: 500
• Publication Date: 2020
• Subjects: Measurement -- 3D-Image processing -- Machine learning; Production engineering -- Research -- Periodicals; 670.5
• DOI: 10.1016/j.cirp.2020.04.098
• Languages: English
• ISSNs: 0007-8506

Abstract

Abstract: Image highlights caused by specular reflections always conceal or attenuate the feature information of the samples in vision measurement. This paper investigates countermeasures to highlighted specular surface measurements. A measurement system is developed to capture a series of images with different polarization angles, the highlighted regions of which are taken as the trained samples for a back-propagation neural network, while the initial weights of the neural network are set as Gaussian distributions. Experimental results show that the proposed method can efficiently increase the stereo matching accuracy and hence recover the information in highlighted regions in vision measurements of specular surfaces.