Scale-space primal sketch: construction and experiments

We present a multi-scale representation of grey-level shape, called the scale-space primal sketch, that makes explicit features in scale-space as well as the relations between features at different levels of scale. The representation gives a qualitative description of the image structure that allows for extraction of significant image structure — stable scales and regions of interest-in a solely bottom-up data-driven manner. Hence, it can be seen as preceding further processing, which can then be properly tuned. Experiments on real imagery demonstrate that the proposed theory gives intuitively reasonable results.

[1]  D. Watt.  Visual Processing: Computational Psychophysical and Cognitive Research , 1990 .

[2]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[3]  Fredrik Bergholm,et al.  Edge Focusing , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[5]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[6]  Stephen M. Pizer,et al.  A Multiresolution Hierarchical Approach to Image Segmentation Based on Intensity Extrema , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Andrew P. Witkin,et al.  Uniqueness of the Gaussian Kernel for Scale-Space Filtering , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Kjell Brunnström,et al.  On scale and resolution in the analysis of local image structure , 1990, ECCV.

[9]  R. Haralick,et al.  The Topographic Primal Sketch , 1983 .

[10]  D Marr,et al.  Early processing of visual information. , 1976, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[11]  Jan-Olof Eklundh,et al.  Guiding Early Visual Processing with a Scale-Space Primal Sketch , 1990 .

[12]  Kjell Brunnström,et al.  On scale and resolution in active analysis of local image structure , 1990, Image Vis. Comput..

[13]  James L. Crowley,et al.  A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jan-Olof Eklundh,et al.  Scale detection and region extraction from a scale-space primal sketch , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[15]  Azriel Rosenfeld,et al.  Multiresolution object detection and delineation , 1987 .

[16]  Jan-Olof Eklundh,et al.  On the computation of a scale-space primal sketch , 1991, J. Vis. Commun. Image Represent..

[17]  Tony Lindeberg,et al.  Scale-Space for Discrete Signals , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  B. Julesz,et al.  Human factors and behavioral science: Textons, the fundamental elements in preattentive vision and perception of textures , 1983, The Bell System Technical Journal.

[19]  Tony Lindeberg,et al.  Discrete Scale-Space Theory and the Scale-Space Primal Sketch , 1991 .

[20]  Arthur C. Sanderson,et al.  Multiple Resolution Representation and Probabilistic Matching of 2-D Gray-Scale Shape , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Walter F. Bischof,et al.  Parsing scale-space and spatial stability analysis , 1988, Comput. Vis. Graph. Image Process..