Design of Burr Detection Based on Image Processing

Abstract

Traditional burr detection methods are increasingly unable to meet the requirements of deburring in terms of accuracy and efficiency. In this paper, machine vision is adopted. Firstly, the image of the workpiece is preprocessed, and appropriate edge detection operators are selected to detect the basic edge of the burr. Then, the closed burr edge is generated by detecting the slow changing area with the regional growth. Finally, the edge is judged to be burr by comparing the contour and other methods. Experiments show that this method has the advantages of fast, high efficiency and strong stability in the study of burr detection, and can meet the requirements of the project.

Measurement of Micro Burr and Slot Widths through Image Processing: Comparison of Manual and Automated Measurements in Micro-Milling

“…In a similar study about the milling process and burr detection, workpieces with different thicknesses and hardness were used. While burrs can be measured very easily after milling thick workpieces, the burrs formed in workpieces less than 2.5 mm thick could not be measured completely by image processing [ 52 ]. In the present study, the burrs are in micron sizes and all of the burrs could be measured with over approximately 90% accuracy.…”

“…In addition, image processing studies could only be carried out based on the results where manual measurement was not performed and machinability tests were carried out on a macro scale [ 40 ]. Moreover, there is a low accuracy result of a study in which the measurement of all burrs could not be performed despite the macro-scale milling process [ 52 ]. In the present study, in micron-scale, the measurement of the burrs could be carried out precisely and with high accuracy.…”

Data Specifications for Battery Manufacturing Digitalization: Current Status, Challenges, and Opportunities

“…Classical algorithms such as the Canny edge detector [144] and Hough transformation [145] have already enabled high-precision online monitoring in edge recognition and blur detection. [146] However, feature extraction and task objectives are built separately within the traditional CV framework. The main challenge for the CV is to extract the features of the image.…”

Burr Detection Using Image Processing in Milling Workpieces

“…There are works that use image processing in order to detect burr formation. In this sense, there is a method that searches the best-fitting rectangle to the position of the burr [3], while other searches over the horizontal axis [14]. This work proposes a new method based on the use of a vision system in order to detect the burr formation on machined workpieces.…”