Edge Detection based on Gray Correlation

Xiyu Liang

《International Core Journal of Engineering》 7卷6期 (2021/06) Pp. 7-12

https://doi.org/10.6919/ICJE.202106_7(6).0002

摘要

In the edge detection algorithm, being able to accurately detect the edge of the target object is the premise of extracting the target object. For the scratch detection of high-speed train axles, accurate edge detection can improve the basis for subsequent 3D reconstruction and size measurement of scratches. In this paper, an edge detection template based on gray correlation is designed for the axles of high-speed trains, which can accurately locate the edges of scratches; for scratches at different angles, filters in different directions are added. By comparing the filtering results of different rotation angles, the angle with the best result is selected as the rotation angle of the pixel. This method not only has excellent edge positioning performance, but also can eliminate most of the noise in the image and improve the effect of edge extraction.

關鍵字

Edge Detection ； Gray Correlation ； Roberts Operator ； Prewitt Operator

參考文獻

Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-self TV cameras and lenses[J]. IEEE J. Robot. Automat. RA-3, 1987, 4.

Lages U . Collision avoidance system for fixed obstacles-fuzzy controller network for robot driving of an autonomous vehicle[C]// Intelligent Transportation Systems. IEEE, 2001.

Wang Z X, Wang W. The research on edge detection algorithm of lane[J]. EURASIP Journal on Image and Video Processing, 2018, 2018(1).

Pawar K B, Nalbalwar S L. Distributed canny edge detection algorithm using morphological filter[C]// 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). IEEE, 2016.

He K, Sun J, Tang X. Guided Image Filtering[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(6):1397-1409.