Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection

Wenfeng Li; Aolin Li; Ruilin Li

doi:10.47297/taposatWSP2633-456921.20260703

PDF
Export
Share
Collection
Album

Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection

Volume 7, Issue 3

Views: 0 Downloads: 3

Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection
Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection
1.MTI(Suzhou)Intelligent Technology Co., Ltd, Suzhou, Jiangsu, 215100, China
2.Beijing Jianhua Experimental Yizhuang School, Beijing, 100039, China
3.Beijing University of Posts and Telecommunications, Beijing, 100876, China
Vol. 7, Issue 3, Pages: 104-109(2026)
Published：30 March 2026
DOI：10.47297/taposatWSP2633-456921.20260703
Accepted：

Scan QR Code

Li Wenfeng,Li Aolin,Li Ruilin.Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection[J].Theory and Practice of Science and Technology,2026,07(03):104-109.
DOI：

Li Wenfeng,Li Aolin,Li Ruilin.Research on the Application of Optical Flow Method in Complex Local Deformation Edge Defect Detection[J].Theory and Practice of Science and Technology,2026,07(03):104-109. DOI： 10.47297/taposatWSP2633-456921.20260703.

摘要

Abstract

In the quality control process of the label printing industry

accurately identifying complex and variable local edge defects has become a core challenge. The dynamic variations

irregular shapes

and subtle printing deformations of these defects pose significant obstacles to traditional inspection methods. Consequently

this study introduces optical flow tracking technology. We firstly employ the optical flow method to achieve high-precision alignment and mapping between the image to be inspected and the reference standard image. Following this

we conduct a meticulous extraction of edge regions and ultimately adopt grayscale analysis and defect judgment for defect detection. Experimental results demonstrate that our approach achieves an precision rate of 95.66% and a recall rate of 98.60%

markedly enhancing the efficiency of label printing quality control.

关键词

Keywords

references

Lucas B D .An Iterative Image Registration Technique with an Application to Stereo Vision (DARPA)[J].Proc IJCAI, 1981, 81(3):674-679.

Horn B K P , Schunck B G .Determining optic flow[J].International Journal of Artificial Intelligence, 1981:185–203.

T. Brox, A. Bruhn, N. Papenberg, and J. Weickert: High accuracy optical flow estimation based on a theory for warping. In T. Pajdla and J. Matas, editors, Computer Vision - ECCV 2004, volume 3024 of Lecture Notes in Computer Science, pages 25--36. Springer, Berlin, 2004.

A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger, and C. Schnörr: Variational optical flow computation in real-time. IEEE Transactions on Image Processing, 14 ( 5 ): 608 - 615 , May 2005.

Nagel H H, Enkelmann W. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1986, 8(05): 565-593.

Trottenberg U, Oosterlee C W, Schuller A. Multigrid[M]. Elsevier, 2000.

Shao X Q, Yang Y and Liu Y L. 2021. Review of opti cal flow algorithms in fluid motion estimation. Journal of Image and Graphics, 26 ( 02 ): 355 - 367 .

Wang G N. Development of Die-cutting Product Edge Defect Detection Algorithm Based on Embedded GPU[D]. Zhejiang University, 2020.

Kuo C F J, Chiu C H, Peng K C. Application of wavelet transform in optical thin film defect automatic inspection system[C]//2011 International Conference on Wavelet Analysis and Pattern Recognition. IEEE, 2011: 230-233.

Xu C, Shi N, Zhou L, et al. Defect analysis and detection of micro nano structured optical thin film[C]//AOPC 2017: Optoelectronics and Micro/Nano-Optics. SPIE, 2017, 10460: 431-437.

Feng R T, Du Q Y, Luo H, et al. A registration algorithm based on optical flow modification for multi-temporal remote sensing images covering the complex-terrain region[J]. National Remote Sensing Bulletin, 2021, 25(2): 630-640.

Qian G Y, Chui Q S, Xia E Y, et al. Solar Panel Edge Defect Detection Software System based on MMX[J]. Measurement Technique, 2010(7): 31-35.

Ding J. A Rapid Algorithm for Defect Detection of Solar Cell Edges[J]. Software Engineering and Applications, 2013, 2: 26.

Zhang M L. Multi-Directional Image Fuzzy Edge Defect Online Detection Method Simulation[J]. Computer Simulation, 2018, 35(11): 444-447.

Fang X M, Yan W X, Ding L. Edge defect detection technology of square carpet based on machine vision[J]. Electronic Design Engineering, 2018, 26(3): 55-59.

Chen J R, Liu X, He J Z. Development of edge defect detection experimental device based on machine vision[J]. Automation and Instrumentation, 2021, 2: 116-118,122.

Tang Y N. Method for Detecting Roundness and Edge Defect of Daily-use Ceramics Based on VisionPro[J]. Electronic Test, 2016 (7): 58-60.

Huang X, Chen Q, Wang D J, et al. Research on Float Glass Edge Defect Detection[J]. China Glass, 2015 (6): 7-10.

Zhao Q, Huang Y, Zhao C H. Solar Cell Edge Defect Detection Algorithm Based on Convex Hull[J]. Computer Measurement & Control, 2020, 28(6): 129-134.

Dong J W. Design and Implementation on Edge Defect Detection System of Strip Based on Gaussian Kernel Function[D]. Huazhong University of Science and Technology, 2013.

Wang B, Luo Z Y, Liu D Y, et al. Real time image recognition and width measurement of edge defect in steel strip[J]. Nondestructive Testing, 1997, 19(7): 188-190.