《机电工程》杂志社科技期刊核心期刊论文投稿机电一体化机械、仪表电工自动化、计算机浙江大学主办

Introduction

International Standard Serial Number:

ISSN 1001-4551

Sponsor:

Zhejiang University;

Zhejiang Machinery and Electrical Group

Edited by:

Editorial of Journal of Mechanical & Electrical Engineering

Chief Editor:

ZHAO Qun

Vice Chief Editor:

TANG ren-zhong,

LUO Xiang-yang

Tel:

86-571-87041360,87239525

Fax:

86-571-87239571

Add:

No.9 Gaoguannong,Daxue Road,Hangzhou,China

P.C:

310009

E-mail:

meem_contribute@163.com

Edge detection algorithm optimization based on edge reconstruction image

Published:2023-10-30 author:DENG Jianxin, HUANG Qiulin, YUAN Bangyi, et al. Browse: 1001 Check PDF documents

Edge detection algorithm optimization based on edge reconstruction image

DENG Jianxin1,2, HUANG Qiulin1,2, YUAN Bangyi1,2, DING Dukun2,3

(1.School of Mechanical Engineering, Guangxi University, Nanning 530003, China;

2.Guangxi Key Lab of

Manufacturing System & Advanced Manufacturing Technology, Nanning 530003, China;

3.School of Electronic Information,

Dongguan Polytechnic, Dongguan 523808, China)

Abstract: Edge detection is a key link in image processing, such as visual positioning, part defect identification and visual measurement, and its detection quality directly affects the accuracy of subsequent image target identification and positioning. Aiming at the problem of selecting the appropriate edge detection algorithms for specific image processing applications, based on the improved image reconstruction method, an image edge detection quality evaluation algorithm based on multi-directional sliding window linear interpolation reconstruction method was proposed. Firstly, using the maximum continuous non-edge rectangular region of the edge image to be processed as the reconstruction search window, a linear interpolation image reconstruction method with multi-directional sliding window was designed. Then, based on the characteristics of image edges, an optimal evaluation method for edge detection algorithms was established, which integrates image structural similarity and edge error detection rate as performance indicators. Finally, the examples were applied to verify the performance of the reconstruction algorithm and the feasibility and correctness of the optimization method through experiments. The results show that the accuracy of the edge image reconstruction algorithm is the highest. In the experiment, the structural similarity of the reconstructed image can reach 0.708 7, and the time consuming is 320.902 1 s. Using the proposed optimization method can quickly screen out the best edge processing algorithm, and the evaluation result is consistent with the human visual evaluation, which is convenient to realize the intelligent optimization of the edge detection algorithm and the intelligent image processing.

Key words: edge reconstruction image; edge detection; image edge detection quality evaluation algorithm; algorithm optimization; structural similarity; accuracy of subsequent image target identification and positioning; human visual evaluation

Advanced Search

Online Office System

Chinese Core Periodicals
Chinese Sci-tech Core Periodicals
SA, INSPEC Indexed
CSA: T Indexed
UPD:Indexed