The Scale-Space Primal Sketch: Construction and Experiments
Tony Lindeberg and Jan-Olof EklundhTechnical report ISRN KTH/NA/P--89/20--SE.
Shortened version in Machine Vision and Applications, 4(3), 135--144, 1991.
AbstractWe outline a method to analyse aerosol images using the scale-space representation. The pictures, which are photographs of an aerosol generated by a fuel injector, contain phenomena, that by a human observer are perceived as periodic or oscillatory structures. The presence of these structures is not immediately apparent, since the periodicity manifests itself at a coarse level of scale while the dominating objects in the images are small dark blobs, i.e., fine scale objects. Experimentally we illustrate that the scale-space theory provides an objective method to bring out these events. However, in this form the method still relies on a subjective observer in order to extract and verify the existence of the periodic phenomena.
Then, we extend the analysis by adding a recently developed image analysis concept called the ``scale-space primal sketch''. With this tool we are able to extract significant structures from a grey-level image automatically without any strong a priori assumptions about neither the shape nor the scale (size) of the primitives. Experiments demonstrate that the periodic drop clusters we perceived in the image are detected by the algorithm as significant image structures. These results provide objective evidence verifying the existence of the oscillatory phenomena.
Keywords: blob detection, perceptual grouping, segmentation, cluster analysis, scale-space