Classification of Carbide Distributions using Scale Selection and Directional Distributions

Klaus Wiltschi, Tony Lindeberg and Axel Pinz

Proc. 4th International Conference on Image Processing (ICIP'97), Santa Barbara, California, vol. II, pp. 122--125, Oct. 1997.

Extended version available as Technical Report ISRN KTH/NA/P-97/10-SE from KTH, S-100 44 Stockholm, Sweden.

Abstract

In the production of high speed steel, the rolling affects the micro-structure of the steel, which in turn influences the mechanical properties. Specifically, the distribution of carbide is essential, since cracks propagate within the carbide agglomerations. In current quality control, the properties of the steel are assessed manually by comparison with a standard chart, containing representative patterns for each steel class.

Interestingly, the standard technique for classifying carbide distributions is two-dimensional. The first dimension basically corresponds to scale (``degree'' -- the size of the largest carbide agglomeration) and the the second dimension basically reflects the directional distribution (``type'' ---how strongly the net structure of carbide has been stretched).

In this paper, we present an automatic method for such classification based on scale-space operations, in which the size information is measured using recently developed techniques for feature detection with automatic scale selection and the directional information is computed from second-moment descriptors (Lindeberg 1994). Combined with a morphological verification scheme a pattern classifier is proposed, which shares large similarities with current manual techniques.

Compared to previous work (Wiltschi and Pinz 1995), the proposed scheme has the advantage that the significant scale of the carbide agglomeration is calculated explicitly, and the method is much less sensitive to the variance of spatial connectivity than a morphological approach.

From a theoretical viewpoint, the proposed scheme also has the attractive property that it is based on similar visual-front-end operations as a large class of computer vision modules.

PDF: (ICIP'97) (Technical report)

Background material: (Review paper on scale-space representation and automatic scale selection) (TR on feature detection with automatic scale selection) (Monograph on scale-space theory)

Further work: (Integrated system for analysing carbide distributions)