3D printing fault detection method based on edge detection and morphological image processing

Abstract

The invention relates to a 3D printing fault detection method based on edge detection and morphological image processing. The method comprises the following following steps: s1, collecting an object image A printed in a 3D mode under a preset working condition through an industrial camera; s2, sharpening the image A by using a Prewitt operator to obtain an image B; s3, converting the image B into a binary image C by using an Otsu algorithm; s4, performing closed operation on the image C, and bridging small cracks to obtain an image D; s5, performing open operation on the image D, and removing isolated small points, burrs and small bridges to obtain an image E; s6, obtaining a 4-connected region of the image E by adopting a bwperim algorithm, and performing contour extraction of a binary image to obtain an image G; S7, reading the uplink contour position and the downlink contour position of the image, and subtracting the positions of the upper row and the lower row on the same column to obtain the line width of the object at the position; and S8, counting the position number with the continuous line width of 0, wherein the position number is the breakpoint number. According to the 3D printing fault detection method based on edge detection and morphological image processing provided by the invention, breakpoint faults existing in the 3D printing process can be simply and quickly detected and processed.

Description

technical field [0001] The invention belongs to the field of image processing and 3D printers, in particular to a 3D printing fault detection method based on edge detection and morphological image processing. Background technique [0002] As an important part of the world economy, my country has given strong support to the development of the 3D printing industry from multiple levels such as development goals, industry standards, financial support, and major project approval. Defects generated in the 3D printing process not only affect the appearance and performance of parts, but also cause waste of time and materials, and seriously restrict the further development of 3D printing technology. For a long time, quality inspection has relied on manual judgment based on experience, and the resulting quality judgment results will be biased. The pace of on-site inspection is fast, and there is no complete accumulation of quality data records, and the bonus that big data can bring t...

AI Technical Summary

Problems solved by technology

[0008] The technical problem mainly solved by the present invention is to use machine vision method to carry out intelligent monitoring of 3D printing automatic production line. In the detection process, the machine vision system is used to detect the number, position and unreasonable line width of breakpoints, and automatically eliminate defective 3D products according to the detection results

Images