IJET 2026 Vol.18(2): 69-73
DOI: 10.7763/IJET.2026.V18.1346
Sub-pixel Edge Detection Algorithm Using Dynamic PCA-Hessian Method
Wang Shibo1, Wang Yan1,3,*, Li Wenhui1,3,*, Yin Xiaoming1,3, Xu Min1,3, Zheng Zhongpeng1,3, and Xie GuiJiu2
1. College of Mechanical Engineering, Tianjin University of Science and Technology, Tianjin, China
2. College of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China
3. Tianjin Key Laboratory of Integrated Design and Online Monitoring of Light Industry and Food Engineering Machinery Equipment, Tianjin, China
Email: satansdestiny@163.com(W.Y.)
*Corresponding author
Manuscript received May 2, 2026; accepted May 15, 2026; published June 15, 2026
Abstract—To address the issue of insufficient localization accuracy in traditional edge detection methods applied to the complex texture background of the flame-retardant composite material A500H11, this study proposes a high-precision subpixel edge detection and line connection optimization algorithm. Building upon the Steger algorithm, this method introduces a Sigmoid function to adaptively adjust the analysis window based on local gradient magnitudes. It combines the noise suppression capability of Principal Component Analysis with the directional advantage of the Hessian matrix to achieve dynamic hybrid correction of subpixel coordinates. To further enhance edge continuity and integrity, a multi-strategy post-processing workflow is designed, incorporating neighborhood constraints, dynamic programming for path optimization, and B-spline interpolation. Experimental results demonstrate that the average displacement error and standard deviation of the proposed algorithm for scratches and cracks are both below 0.3 pixels, with the proportion of high-precision points exceeding 80%. Compared with morphological post-processing methods, the edge continuity index is improved by an average of 69.6%, and the contour integrity score is enhanced by an average of 15.5%. This method effectively overcomes complex texture interference, achieving high-precision and high-continuity subpixel edge extraction, thereby providing a viable solution for visual inspection under low-contrast and high-texture background conditions.
Keywords—Edge detection; Sub-pixel positioning; PCA; Hessian matrix; Post-processing optimization
Cite: Wang Shibo, Wang Yan, Li Wenhui, Yin Xiaoming, Xu Min, Zheng Zhongpeng, and Xie GuiJiu, "Sub-pixel Edge Detection Algorithm Using Dynamic PCA-Hessian Method," International Journal of Engineering and Technology, vol. 18, no. 2, pp. 69-73, 2026.
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (
CC BY 4.0).
