Abstract-Continuous casting is a highly efficient process used to produce most of the world steel production tonnage, but can cause cracks in the semi-finished steel product output. These cracks may cause problems further down the production chain, and detecting them early in the process would avoid unnecessary and costly processing of the defective goods. In order for a crack detection system to be accepted in industry, however, false detection of cracks in non-defective goods must be avoided. This is further complicated by the presence of scales; a brittle, often cracked, top layer originating from the casting process.We present an approach for an automated on-line crack detection system, based on 3D profile data of steel slab surfaces, utilizing morphological image processing and statistical classification by logistic regression. The initial segmentation successfully extracts 80% of the crack length present in the data, while discarding most potential pseudo-defects (non-defect surface features similar to defects). The subsequent statistical classification individually has a crack detection accuracy of over 80% (with respect to total segmented crack length), while discarding all remaining manually identified pseudo-defects. Taking more ambiguous regions into account gives a worst-case false classification of 131 mm within the 30 600 mm long sequence of 150 mm wide regions used as validation data. The combined system successfully identifies over 70% of the manually identified (unambiguous) crack length, while missing only a few crack regions containing short crack segments.The results provide proof-of-concept for a fully automated crack detection system based on the presented method.
Mathematical Morphology is a common strategy for non-linear filtering of image data. In its traditional form the filters used, known as structuring elements, have constant shape once set. Such rigid structuring elements are excellent for detecting patterns of a specific shape, but risk destroying valuable information in the data as they do not adapt in any way to its structure.We present a novel method for adaptive morphological filtering where the local structure tensor, a well-known method for estimation of structure within image data, is used to construct adaptive elliptical structuring elements which vary from pixel to pixel depending on the local image structure. More specifically, their shape varies from lines in regions of strong single-directional characteristics to disks at locations where the data has no prevalent direction.
Fully automated online measurement of the size distribution of limestone particles on conveyor belt is presented based on 3D range data collected every minute during 13 hours of production. The research establishes the necessary measurement technology to facilitate automatic control of rock crushing or particle agglomeration processes to improve both energy efficiency and product quality. 3D data from laser triangulation is used to provide high resolution data of the surface of the stream of rocks. The 3D data is unaffected by color variation in the material and is not susceptible to scale or perspective distortion common in 2D imaging. Techniques are presented covering; sizing of particles, determination of non-overlapped and overlapped particles, and mapping of sizing results to distributions comparable to sieving. Detailed variations in the product sieve-size are shown with an abrupt change when the size range of the limestone particles was changed.
Image segmentations have been performed to identify the surface fragmentation of rock piles using 3D surface data, and quantified. The advantages for fragmentation measurement using image analysis are significant and include: quantifying image segmentation performance in isolation of the downstream processes of fragment classification and size distribution calculation, utilisation of 3D data to overcome various limitations of photographic-based image analysis, and the capacity to use 3D fragment data to eliminate the misclassification of partially visible fragments as smaller entirely visible fragments. The segmentation results have been quantified by comparison with the 3D surface data of each individual rock fragment. Mathematical morphology and image segmentation algorithms have been extended from greyscale image based definitions and applied to irregularly spaced 3D coordinate surface data. 3D coordinate surface data can now be morphologically processed directly in 3D, segmented, visualized and directly compared to the actual surface fragmentation in order to quantify the results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.