Abstract
Aiming at the problem of large recognition errors in traditional metal material pitting defect recognition methods, this research aims to improve the recognition performance of metal material pitting defects, and proposes a metal material pitting defect recognition method based on visual signal processing. The rail material parameters are set according to the schematic diagram of the U71Mn rail imitation, and the defective metal material imitation model is constructed according to the distribution position of each crack of the U71Mn rail, and then the optical signal of the metal material pitting defect is collected according to the geometric model imaged by the camera. The image of metal material pitting defects undergoes visual signal processing to extract the details of the image in different directions and scales. Based on this, the Mallet algorithm is used to decompose the image of metal material pitting corrosion defects, and the low-frequency components and high-dimensional components of multiple resolutions and multiple features are obtained, and specific fusion rules are selected to select the components of each layer obtained by decomposition, and then wavelet Inverse transformation, complete the fusion and analysis of visual signals of pitting defects in metal materials. Experimental results show that the recognition method of metal material pitting defects based on visual signal processing has high recognition performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.