The invention belongs to the field of
polarization maintaining optical fiber fusion splicers, and discloses an
optical fiber end
face detection method and
system based on variance. The method comprises the steps of acquiring an
optical fiber end face image, wherein the acquisition direction of a camera is perpendicular to the central axis of an
optical fiber; the collected images are preprocessed;
processing the preprocessed image by adopting a P parameter binarization
algorithm to obtain a binarized image; performing two-
dimensional modeling on the binarized image, and establishing a rectangular coordinate
system by taking the length of the binarized image as an x axis and the width as a y axis to obtain a two-dimensional image matrix; performing variance calculation on the data of the x-axis coordinate value of the two-dimensional image matrix corresponding to the optical
fiber end face, comparing the calculated variance value with a standard value, and judging whether the optical
fiber end face is smooth or not; according to the method, an image of an optical
fiber end face is collected, and the variance value of the image is calculated by using an
image processing technology, so that the smoothness of the optical fiber end face is evaluated, and the optical fiber
welding quality is judged. All the modules work cooperatively, and automatic detection of the optical fiber end face is achieved.