Nanoscale measurement with pattern recognition of an ultra-precision diamond machined polar microstructure

Abstract

Due to the low resolution of pattern recognition and disorganized textures of the surfaces of most natural objects observed under a microscope, computer vision technology has not been widely applied in precision positioning measurement on machine tools, which needs high resolution and accuracy. This paper presents a systematic method to solve the surface recognition problem which makes use of ultra-precision diamond machining to produce a functional and polar-coordinate surface named ‘polar microstructure’. The unique characteristic of a polar microstructure is the distinctive pattern of any locations including rotation in the global surface which provides the feasibility of achieving precise absolute positions by matching the patterns by utilizing computer vision technology. A polar microstructure which possesses orientation characteristics is also able to measure the displacement of rotation angle. A series of simulation experiments including feature point extraction, orientation detection as well as resolution of pattern recognition was conducted, and the results show that a polar microstructure can achieve a resolution of 9.35 nm which is capable of providing a novel computer vision-based nanometric precision measurement method which can be applied in positioning on machine tools in the future.