Finding geometric and relational structures in an image

Abstract

We present a method for extracting geometric and relational structures from raw intensity data. On one hand, low-level image processing extracts isolated features. On the other hand, image interpretation uses sophisticated object descriptions in representation frameworks such as semantic networks. We suggest an intermediate-level description between low-and high-level vision. This description is produced by grouping image features into more and more abstract structures. First, we motivate our choice with respect to what should be represented and we stress the limitations inherent with the use of sensory data. Second, we describe our current implementation and illustrate it with various examples.

Polyhedral object recognition by indexing

“…Image graph extraction has been briefly outlined at the beginning of this section and is described in detail in [35].…”

A morphological dominant points detection and its cellular implementation

“…Approaches in the first group involve first extracting edges as a chain code and then searching for points of maximal curvature [1] [4], or performing a polygonal approximation on the chains and then searching for the line segment intersections [7].…”

Contextual Junction Finder

“…Perceptual groupings of image features have been widely used in computer vision systems to guide scene interpretation and 3D model matching [1,2,5,9,10]. Of all perceptual groupings studied by psychologists [13,4] and computer vision researchers we focus our attention on junctions of line segments -points of co-termination of lines.…”