The application discloses a transparent material stress
birefringence online polarization defect classification method and relates to the field of transparent material optical detection. The method comprises the following steps: collecting an original polarization image of a to-be-detected transparent material, pre-
processing the original polarization image, and generating a calibrated polarization image; canceling vibration
noise in the light path of the calibrated polarization
image based on an
optical phase conjugation technology to obtain a pure polarization
light field signal; calculating a retardation
distribution diagram of the transparent material according to the pure polarization
light field signal, performing topological
data analysis on the retardation
distribution diagram, and extracting a macroscopic topological
feature vector; and dividing the macroscopic topological
feature vector into macroscopic
layout features reflecting the overall topological structure of a
stress field and microscopic morphological features reflecting the local geometric morphology of a defect according to feature sources and physical meanings. The application realizes high-precision defect classification and effectively solves the problem of low classification precision caused by large vibration interference and insufficient feature representation in online detection.