Research On Plate-profile Recognition Based On Computer Image Processing Technology

The technology of computer image processing involves the basic theories and methods of all kinds of image information processing by means of the computer. Presently, this technology has been widely applied to many fields, such as medical diagnoses, industrial automatic measuring and control, intelligent robot, transportation, communication and geology.The quality of laminose Plate-profile is an important control target during the cold process of plate rolling, which afects and determines the final quality of the plate. Therefore, the technology of plate-profilem recognition plays a very important role in the process of plate rolling. In terms of the practical application of the technology of plate-protle recognition at currently iron and steel factories, the plate-profile is obtained indirectly by measuring the inner-stress of plate during the process of plate rolling. Because of the main shortage of its touch-measuring mode and the factor of outer environment and the sensor, this method can't ensure the reliability of plate-profilem easuring.This paper according to practical requirement of the line at Cold Rolling department, One Steel Group Corporation, analyses and studies the computer image processing technology applying in the plate-profile recognition based on the existing theories of plate-profile. And detailedly introduces image processing technology including image filtering(Mean fliter, gradient preciprocal weight filter, Median filter), edge detection, as first differential(Roberts operator, Sobel operator and Prewitt operator), second differential(Laplacian operator and Kirsch operator), LOG filter and Canny operator. They are studied in theory and practice applying.Wavelet transform is a kind of time-frequency analysis method in signal processing and is becoming more and more popular during these years. Its multi-scale property, localization both in time and frequency domain, sensitivity to the abrupt change of signals, and good to denoising make it an ideal way for edge detection. We use B-spline biorthogonal wavelet to form filter groups, and explore application of edge detection based on multi-scale wavelet transform.In this paper, it designed a processing software under the environment of Visual C++6.0. First, the image is filtered out some noise using Median filter; Second detected the edge by Canny operator; Third selected features by Hough transform; At last we according the features realize the plate-profile's classifying by Decision tree.