A fuzzy inference system applied to defect detection in flat steel production

Abstract

Recently in many industrial fields the exploitation of vision systems for quality control had a considerable increase, which is mainly due to the technological progress experienced by such systems, that, with respect to the past, made their performance more appealing and more reliable while the associated costs are decreased. The advantages of these kind of systems in terms of savings in human resources and improved quality monitoring have become far more evident, by encouraging their adoption in a wide variety of production cycles.The present paper deals with the elaboration and information extraction from images, that represent portions of the surface of flat steel products, and describes an algorithm for defect detection and classification. The overall classification procedure is composed of a preliminary part that is mostly related to image processing and analysis, which aims at pointing out the defect (independently on the class it belongs to), as well as to the extraction of relevant features of the detected defect; the second part exploits a fuzzy inference system in order to analyze the type of defect and solves a classification problem that presently can be addressed only with the support of a human operator. Fuzzy inference systems are suitable to this application because they are able to mimic and reproduce the human reasoning.

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

“…The difference of gray level between the defect area and the background results in an obvious edge at the boundary, which can be applied to detect surface defects of metal planar materials. Owing to the discontinuity of pixels at the edge of the image, researchers usually employ local image differentiation technology to obtain edge detection operators, and the commonly used edge detection templates of metal planar materials surface defects include Prewitt [ 43 ], Sobel [ 39 , 44 ], and Canny [ 45 ] operators, Figure 4 shows the detection results of these primitive operators on the same defect sample. These operators also have their own shortcomings, and many researchers have optimized them to achieve better results.…”

Automated Visual Defect Detection for Flat Steel Surface: A Survey

“…It is investigated that Sobel is specialized in weighing the influence of pixel position to reduce the ambiguity of edge, but it is sensitive to uneven illumination on flat steel surface, which easily leads to false edge detection. In order to avoid the false detection, Borselli et al [27] modified Sobel operator by applying thresholding to convert the grayscale image to binary matrix. Further, Shi et al in [28] developed eight directional templates to obtain more comprehensive edge information than the original Sobel operator which only has horizontal and vertical directions.…”

Automated Visual Defect Classification for Flat Steel Surface: A Survey

“…Otsu is a classical adaptive threshold method for separating defects from the background in flat steel images [59,69,70], which obtains a threshold value based on the characteristic of the large variance between the background and foreground. Different from the threshold methods, the methods based on edge detection use the first or second derivative to detect edge points by taking advantage of the property of discontinuous pixel values in adjacent regions, such as Robert [71], Sobel [72,73], Prewitt [74], Canny [55] and Kirsch [52,53]. The grayscale of steel strip images is ordinarily nonuniform, the gray value variation cross the background and the defect is sometimes gradual, and the size of defect area is very small, not easy to be recognized by the computer.…”