Adaptive fast algorithm for rail defect segmentation based on two-dimensional Otsu

Abstract

The invention discloses a rail defect segmentation self-adaptive fast algorithm based on two-dimensional Otsu, which comprises establishing a two-dimensional Otsu segmentation direct division map, dividing an image to be segmented into a target region and a background region, and setting an adaptive threshold search interval. A pixel point of a threshold retrieval area is partitioned, for the graylevel of each region, Compare the mean variance of each region, find out the region where the best threshold point is, then calculate the inter-class variance of each pixel gray value in this region,and get the maximum inter-class variance value, the corresponding gray value is the best segmentation threshold value, according to the best segmentation threshold value, the image is binarized intothe target region and the background region. When the rail defect image is segmented, the threshold search interval is adaptively set to reduce redundancy calculation in the threshold search process,meanwhile, the threshold interval narrows the gap between the background and the target area, reduces the interference caused by the noise point to the threshold determination, and solves the problemthat the defect in the small area is difficult to be segmented.

Description

technical field [0001] The invention belongs to the technical field of image segmentation algorithms, in particular to a two-dimensional Otsu-based self-adaptive fast algorithm for rail defect segmentation. Background technique [0002] Image segmentation is an important method to extract the target area. The threshold segmentation algorithm based on the maximum inter-class variance (Otsu) is a kind of threshold method. Otsu is a global threshold segmentation algorithm with fast and stable performance. The one-dimensional Otsu threshold segmentation algorithm calculates the variance sum of each gray level to two types of gray levels, and selects the threshold when the variance is the largest as the optimal threshold, so as to divide the image into two types: target and background. Although the one-dimensional Otsu threshold segmentation algorithm The segmentation speed is fast, but only the gray information of the image is combined, the accuracy of the segmentation is not id...

AI Technical Summary

Problems solved by technology

The one-dimensional Otsu threshold segmentation algorithm calculates the variance sum of each gray level to two types of gray levels, and selects the threshold when the variance is the largest as the optimal threshold, so as to divide the image into two types: target and background. Although the one-dimensional Otsu threshold segmentation algorithm The segmentation speed is fast, but only the grayscale information of the image is combined, the accuracy of the segmentation is not ideal, and the segmentation effect on noisy images is not good

Two-dimensional Otsu introduces spatial neighborhood information, but studies have pointed out that Otsu fails when the target area is much smaller than the background area, that is, two-dimensional Otsu fails for small-area defect images, and the existing Otsu recursive algorithm needs to calculate the variance of each gray level For calculation, the algorithm complexity is still relatively large

Images