Hierarchical scene structure representations to facilitate image understanding
Alianna J. Maren, M. Ali · 1988
H.._.ierarchical S. cene Structures (HSS) can be used to represent the perceptual structures found in segmented images which arise from inter-region relationships between the image segments.These relationships include continuation of boundaries, proximity, enclosure, and similarity of shape, intensity, size, and directionality.Our prototype system for HSS creation works with a subset of three of these relationships; proximity, similarity, and continuation.Incorporating this perceptual organizing information into a structured, symbolic scene representation strongly increases the available information about the scene.This information can be used to improve pattern recognition, and extensions may address problems in 3-D modeling, multi-temporal correlations, and multisensor information fusion. INTRODUCTION AND PROB-LEM STATEMENTResearch in machine and biological vision, aided by recent results in the fields of perception, parallel processing, neural networks, and knowledge-based systems, has made it possible to conceptualize the major issues in machine vision in terms of crucial transitions between representation levels in visual systems.The most significant ones are the: