螺纹钢表面缺陷检测算法研究-机械工程专业毕业论文.docxVIP

万方数据 万方数据 Abstract The appearance of the rebar surface complex characteristics, the author of this paper, based on the theory of machine vision technology research, the test study on the appearance quality of the rebar and concrete by Matlab7.0 combined with vc + + 6.0 programming tools, realized the complex background of the appearance quality of the rebar detection algorithm research. Joint of rebar front and side image processing, the appearance quality of the rebar is studied, the effect of the processing method designed the subpixel edge location method based on projection of center of gravity, provides reference for rebar online detection. This paper studies the main work is as follows: For rebar in common noise type, smooth denoising processing methods were studied, through a variety of algorithms process of the comparison of the experimental results, final selection processing speed, good processing effect is median filter smoothing method to suppress the rebar images contain noise. To the need of rebar size calculation, respectively for rebar positive image and profile image for different image processing process. For rebar profile image feature analysis, made the image processing. According to the processing procedure, and analyzes the rebar profile image binarization segmentation algorithm, by contrast, treatment effect dajin method (OTSU method) is chosen as the rebar profile image binarization segmentation algorithm; Using edge operator for edge extraction, choose Canny edge operator for edge detection; After get the rebar profile image edge, the use of subpixel edge location method based on projection of center of gravity of rebar profile image on the analysis and calculation, the size of the rebar image of cross rib height and rebar diameter size. Analysising of the characteristic of rebar positive image,to make the image processing. Rebar are analyzed based on the processing flow, the algorithm of edge detection, through edge operator for edge extrac