Abstract

To address the problem of feature texture loss in defective images of zirconia bearing balls on unbalanced illumination backgrounds, a coupled algorithm of the local gamma function transform-block interpolation balancing equation is designed. A combination of a light reflection imaging model and a three-dimensional Gaussian surround function is used to extract the illumination estimate of the original image. Subsequent illumination balance correction is performed in the value color space. The contrast between the edges of the feature texture and the background is analyzed to construct a locally adaptive gamma function transformation model. We establish local block interpolation balance equations to eliminate the effects caused by illumination that is too high or too low. The experimental results show that the information entropy of the images after illumination correction changes in the range of 5% or less. The standard deviation and mean gradient can be increased by 15.21% and 14.78%, respectively.

© 2022 Optica Publishing Group

Machine vision system based on a coupled image segmentation algorithm for surface-defect detection of a Si₃N₄ bearing roller

Dahai Liao, Mingshuai Yin, Hongbin Luo, Jun Li, and Nanxing Wu
J. Opt. Soc. Am. A 39(4) 571-579 (2022)

Automatic detection method for BGA defects based on x-ray imaging

Kai Xiao, Qin Li, and Yang Chen
Appl. Opt. 61(21) 6356-6365 (2022)

Interferometer for measuring the surface shape of a ball bearing raceway

Kenji Nunome, Manabu Tsukamoto, Toyohiko Yatagai, and Hiroyoshi Saito
Appl. Opt. 24(22) 3791-3796 (1985)

Algorithm for real-time defect detection of micro pipe inner surface

Xinyu Zhao and Bin Wu
Appl. Opt. 60(29) 9167-9179 (2021)

Deviation-based wavefront correction using the SPGD algorithm for high-resolution optical remote sensing

Makoto Hirose, Norihide Miyamura, and Seichi Sato
Appl. Opt. 61(23) 6722-6728 (2022)