Semantic Hierarchies for Recognizing Objects and Parts
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper describes the construction and use of a novel representation for the recognition of objects and their parts, the semantic hierarchy. Its advantages include improved classification performance, accurate detection and localization of object parts and sub-parts, and explicitly identifying the different appearances of each object part. The semantic hierarchy algorithm starts by constructing a minimal feature hierarchy and proceeds by adding semantically equivalent representatives to each node, using the entire hierarchy as a context for determining the identity and locations of added features. Part detection is obtained by a bottom-up top-down cycle. Unlike previous approaches, the semantic hierarchy learns to represent the set of possible appearances of object parts at all levels, and their statistical dependencies. The algorithm is fully automatic and is shown experimentally to substantially improve the recognition of objects and their parts.Keywords
This publication has 7 references indexed in Scilit:
- Statistical Learning of Visual Feature HierarchiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Object Recognition with Features Inspired by Visual CortexPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Identifying Semantically Equivalent Object FragmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Hierarchical Part-Based Visual Object CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Feature hierarchies for object classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Bayesian Data AnalysisPublished by Taylor & Francis ,2003
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989