Identification of curvature features with use of boundary-skeleton model of image

Authors:
Ivan Reyer;Ksenia Zhukova
Affiliations:
Dorodnicyn Computing Centre of RAS, Moscow, Russia;Dorodnicyn Computing Centre of RAS, Moscow, Russia
Venue:
ISCGAV'07 Proceedings of the 7th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision
Year:
2007

Citing 11
Cited 1

On the Detection of Dominant Points on Digital Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
Human face profile recognition by computer

Pattern Recognition
Multiscale representation and matching of curves using codons

CVGIP: Graphical Models and Image Processing
Parts of Visual Form: Computational Aspects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Numerical methods for approximating digitized curves by piecewise circular arcs

Proceedings of the 6th international congress on Computational and applied mathematics
Shape representation and recognition from multiscale curvature

Computer Vision and Image Understanding
Curvature scale space image in shape similarity retrieval

Multimedia Systems
Qualitative Outline Theory

IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Robust Metric and Alignment for Profile-Based Face Recognition: An Experimental Comparison

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Recognition of face profiles from the mugshot database using a hybrid connectionist/HMM approach

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Facial action recognition for facial expression analysis from static face images

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Shape approximation using circular grids

WSEAS Transactions on Information Science and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method of identification of curvature features for shape description and recognition is suggested. The method is based on the relation between local boundary features and the skeleton structure of a plain domain. It uses a continuous boundary-skeleton model of an image. The model consists of a boundary of a polygonal figure approximating a raster image, and a skeleton of the figure. To reveal curvature features the skeleton base representing fundamental structure of the image is used. A procedure of profile line segmentation from a face image based on the suggested method is presented.