A high-precision thread parameter measurement method based on AGW-Foerstner dynamic calibration and neural network error compensation
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Abstract To address the limitation of measurement accuracy caused by the structural complexity of threads, this paper proposes an improved Foerstner corner detection method based on adaptive gradient weighting (AGW-Foerstner), combined with corner-level dynamic calibration and a neural network error compensation strategy, to effectively enhance measurement precision. First, the covariance matrix is weighted by gradient magnitude to accurately locate crest and root points of the thread. Second, a local homography matrix is employed to dynamically calculate the pixel equivalent for each corner. Finally, by deeply integrating vision-based measurements with a neural network error compensation model, a residual prediction network is constructed, where key measured parameters such as major diameter and pitch diameter serve as inputs and true values as outputs, thereby achieving error correction. Experimental results validate the applicability of the proposed method across thread samples of different specifications, showing a significant reduction in measurement errors of critical parameters. This approach realized stable high-precision measurement and provides a practical solution for industrial thread inspection.
Fields of Study & Subjects
Advanced Measurement and Metrology Techniques
Industrial Vision Systems and Defect Detection
Image and Object Detection Techniques
Publication details
- Journal / source
- Engineering Research Express
- Volume
- 8
- Issue
- 8
- Pages
- 085509–085509
- Publication date
- 30 March 2026
- Language
- EN