Abstract This paper proposes a method to estimate the surface shape of a transparent plate using a reflection image on the plate. The reflection image on a transparent plate is a complex image that consists of a reflection on the surface and on the rear surface of the plate. A displacement between the two reflection images holds the range information to the object, which can be extracted from a single complex image. The displacement in the complex image depends not only on the object range but also on the normal vectors of the plate surfaces, plate thickness, relative refraction index, and the plate position. These parameters can be estimated using multiple planar targets with random texture at known distances. Experimental results show that the proposed method can detect microscopic surface shape differences between two different commercially available transparent acrylic plates.
Microscopic Surface Shape Estimation of a Transparent Plate Using a Complex Image
Computer Vision – ACCV 2007 ; 4 ; 176-185
Lecture Notes in Computer Science ; 4844 , 4
2007-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Stereo Vision , Optical Center , Complex Image , Range Estimation , Reflection Image Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Biometrics , Algorithm Analysis and Problem Complexity
European Patent Office | 2020
|