Machine part rolling anomaly detection method based on watershed segmentation

The invention relates to the technical field of roller anomaly detection, in particular to a machine part rolling anomaly detection method based on watershed segmentation, and the method comprises the steps: obtaining a gray level histogram of a roller surface gray level image, carrying out the fitt...

Full description

Saved in:
Bibliographic Details
Main Authors ZHAO AIMEI, ZHENG HAIZHEN
Format Patent
LanguageChinese
English
Published 30.08.2022
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention relates to the technical field of roller anomaly detection, in particular to a machine part rolling anomaly detection method based on watershed segmentation, and the method comprises the steps: obtaining a gray level histogram of a roller surface gray level image, carrying out the fitting of a Gaussian mixture model according to the gray level histogram, and obtaining a plurality of gray level value sets; respectively taking each gray value in each gray value set as a threshold value, segmenting the roller surface gray image and performing distance change to obtain a distance transformation image; calculating the foreground rate of each pixel point according to the pixel value of the pixel point on each distance transformation image, and marking the pixel point according to the foreground rate to obtain a marked image; segmenting the roller surface grayscale image based on the marked image by using a watershed segmentation method to obtain a feature image; and identifying the feature image by us
Bibliography:Application Number: CN202210473360