Authors:
Laura Antanas
;
Martijn van Otterlo
;
José Oramas
;
Tinne Tuytelaars
and
Luc De Raedt
Affiliation:
Katholieke Universiteit Leuven, Belgium
Keyword(s):
Hierarchical image understanding, Relational instance-based learning, Structured representations.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Case-Based Reasoning
;
Computer Vision, Visualization and Computer Graphics
;
Enterprise Information Systems
;
Image Understanding
;
Knowledge Acquisition and Representation
;
Object Recognition
;
Pattern Recognition
;
Software Engineering
;
Symbolic Systems
;
Theory and Methods
Abstract:
Understanding images in terms of hierarchical and logical structures is crucial for many semantic tasks, including image retrieval, scene understanding and robot vision. This paper combines compositional hierarchies, qualitative spatial relations, relational instance-based learning and robust feature extraction in one framework. For each layer in the hierarchy, substructures in the images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures, by making use of qualitative spatial relations. The approach is applied to street view images. We employ a four-layer hierarchy in which subsequently corners, windows and doors, and individual houses are detected.