Abstract
Polarization-maintaining fiber is widely used in fiber optic gyro sensors. However, in the production process of the fiber coil, it is difficult to manually address the defect detection of polarization-maintaining fiber. Recognition of tiny cracks on the fiber with the diameter of 135 or 165 microns is a complex issue. In this paper, a method of defect detection used in splitting fiber process is proposed. First, it verified the more suitable algorithm of feature extraction for PM fibers through experiments. Next, Gabor filtering is used to extract features of minor defects. The united features which are composed of the HOG features of original image and the uniform LBP features of processed image are extracted. Finally, genetic algorithm is applied to optimize the parameters of SVM, and the optimized SVM with united features achieve PM fiber defect detection. The experimental results indicate that the proposed method can effectively identify defects on the surface of the PM fiber. The recognition rate for tiny defects reaches over 90%, and the recognition rate for serious defects reaches 99%.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
