TWO-DIMENSIONAL OBJECT RECOGNITION USING MULTIRESOLUTION MODELS.

Charles F. Neveu*, Charles R. Dyer, Roland T. Chin

*Corresponding author for this work

Research output: Contribution to journalJournal Articlepeer-review

20 Citations (Scopus)

Abstract

A multiresolution, model-based matching technique is described for coarse-to-fine object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the object, leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid.

Original languageEnglish
Pages (from-to)52-65
Number of pages14
JournalComputer Vision, Graphics, & Image Processing
Volume34
Issue number1
DOIs
Publication statusPublished - 1986
Externally publishedYes

Fingerprint

Dive into the research topics of 'TWO-DIMENSIONAL OBJECT RECOGNITION USING MULTIRESOLUTION MODELS.'. Together they form a unique fingerprint.

Cite this