Comments on "ground from figure discrimination"

Authors:
Paul L. Rosin
Affiliations:
Department of Computer Science, Cardiff University, Queen's Buildings Newport Road, PO Box 916, Cardiff CF24 3XF, UK
Venue:
Pattern Recognition Letters
Year:
2003

Citing 11
Cited 2

Separating figure from ground with a Boltzmann machine

Vision, brain, and cooperative computation
A neural network architecture for figure-ground separation of connected scenic figures

Neural Networks
Original Contribution: A solution of the figure-ground problem for biological vision

Neural Networks
Dynamic threshold determination by local and global edge evaluation

Graphical Models and Image Processing
Dynamic linking among neural oscillators leads to flexible pattern recognition with figure-ground separation

Neural Networks
Edges: saliency measures and automatic thresholding

Machine Vision and Applications
Ground from figure discrimination

Computer Vision and Image Understanding - Special issue on perceptual organization in computer vision
Evolutionary Approaches to Figure-Ground Separation

Applied Intelligence
Figure-Ground Discrimination: A Combinatorial Optimization Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Figure-ground segmentation using Tabu search

ISCV '95 Proceedings of the International Symposium on Computer Vision
Figure-ground separation by a dynamical system

IEEE Transactions on Image Processing

Unimodal thresholding for edge detection

Pattern Recognition
On candidates selection for hysteresis thresholds in edge detection

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

Two techniques for extracting foreground edges from an edge map are quantitatively tested and compared. Although Amir and Lindenbaum's algorithm (Comput. Vision and Image Understanding 76 (1) (1999) 7) and Venkatesh and Rosin's algorithm (Comput. Vision Graphics Image Process. 57 (2) (1995) 146) operate on very different principles it is shown that their results or of similar quality. The advantage of Venkatesh and Rosin's algorithm is that it is computationally more efficient and does not require tuning parameters.