DETECTING SALIENT BLOB-LIKE IMAGE STRUCTURES AND THEIR SCALES WITH A SCALE-SPACE PRIMAL SKETCH - A METHOD FOR FOCUS-OF-ATTENTION

This article presents: (i) a multiscale representation of grey-level s hape called the scale-space primal sketch, which makes explicit both f eatures in scale-space and the relations between structures at differe nt scales, (ii) a methodology for extracting significant blob-like ima ge structures from this representation, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrat ing how the proposed method can be used for guiding later-stage visual processes. The representation gives a qualitative description of imag e structure, which allows for detection of stable scales and associate d regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrat e that the proposed theory gives intuitive results.