Shape Representation Using a Generalized Potential Field Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Corner detection via topographic analysis of vector-potential
Pattern Recognition Letters
Scale-Space Vector Fields for Feature Analysis
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
3D part segmentation: a new physics-based approach
ISCV '95 Proceedings of the International Symposium on Computer Vision
The curling vector field transform of gray-scale images: a magneto-static inspired approach
WSEAS Transactions on Computers
Neural architectures optimization and genetic algorithms
WSEAS Transactions on Computers
Dealings with problem hardness in genetic algorithms
WSEAS Transactions on Computers
WSEAS Transactions on Mathematics
The curl source reverse as a magneto-statics inspired transform for image structure representation
ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers
Force field feature extraction for ear biometrics
Computer Vision and Image Understanding
Crossing genetic and swarm intelligence algorithms to generate logic circuits
WSEAS Transactions on Computers
The relative potential field as a novel physics-inspired method for image analysis
WSEAS Transactions on Computers
WSEAS TRANSACTIONS on COMMUNICATIONS
Hi-index | 0.00 |
In this paper, the spatial property of the magneto-static field generated by the stable current is discussed and exploited in image analysis. The region-division feature of the magnetic field generated by a current element on 2D plane is investigated experimentally for some simple test images. The virtual edge current in gray-scale images is presented by a magneto-static analogy, which is composed of the tangent edge vectors as a discrete form of the physical current element. The virtual magnetic field generated by the edge current in digital images is investigated experimentally, which is applied in region border detection and region division. A novel image segmentation method is proposed based on the virtual magnetic field generated by the edge current. The experimental results prove the effectiveness of the proposed method, and also indicate the promising application of the physics-inspired methods in image processing tasks.