Multi-scale edge detection and feature binding : An integrated approach

M. A Brown; K. T Blackwell; H. G Khalak; G. S Barbour; T. P Vogl

doi:10.1016/S0031-3203(97)00101-5

Back

Multi-scale edge detection and feature binding : An integrated approach

Journal article

Open access

Peer reviewed

Multi-scale edge detection and feature binding : An integrated approach

M. A Brown, K. T Blackwell, H. G Khalak, G. S Barbour and T. P Vogl

Pattern recognition, Vol.31(10), pp.1479-1490

10/01/1998

DOI: 10.1016/S0031-3203(97)00101-5

Files and links (1)

url

https://doi.org/10.1016/S0031-3203(97)00101-5View

Published (Version of record) Open Access

Abstract

One of the central problems in image recognition is the extraction of salient “features” in a manner robust to variation in position, orientation, and scale and suitable for further processing. Because real-world images contain distinct features at various resolutions, effective extraction may require the combination of edge and other information across several scales, which is itself a difficult problem. Our analysis suggests that these two problems are fundamentally interdependent, and can be addressed in an integrated framework. We demonstrate improved results by combining edge detection and feature binding at each scale. This is accomplished by extending elements of the Sajda–Finkel neural-network model of perceptual binding to the multi-scale feature-extraction task.

Applied Sciences

Algorithmics. Computability. Computer arithmetics

Artificial intelligence

Computer science; control theory; systems

Exact sciences and technology

Pattern recognition. Digital image processing. Computational geometry

Theoretical computing

Details

Title: Subtitle: Multi-scale edge detection and feature binding : An integrated approach
Creators: M. A Brown - Environmental Research Institute of Michigan
K. T Blackwell - Environmental Research Institute of Michigan
H. G Khalak - Environmental Research Institute of Michigan
G. S Barbour - Environmental Research Institute of Michigan
T. P Vogl - Environmental Research Institute of Michigan
Resource Type: Journal article
Publication Details: Pattern recognition, Vol.31(10), pp.1479-1490
DOI: 10.1016/S0031-3203(97)00101-5
ISSN: 0031-3203
eISSN: 1873-5142
Publisher: Elsevier Science
Language: English
Date published: 10/01/1998
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute
Record Identifier: 9984446408702771

Metrics

3 Record Views

9 Times Cited - Web of Science

See more details