Distortion invariant object recognition by matching hierarchically labeled graphs
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 155-159 vol.1
- https://doi.org/10.1109/ijcnn.1989.118574
Abstract
A graph-matching process of object recognition is proposed. It is applied to face recognition. Gray-level images are represented by a resolution hierarchy of local Gabor components, which are all scaled and rotated versions of each other. The components centered on one image point form a Gabor jet. A single jet provides a distortion-insensitive local representation of part of an image. Object recognition is achieved by matching image point jets to jets in stored prototype patterns. For a selected image jet the best matches are determined, under a constraint preserving spatial arrangement. The procedure amounts to labeled graph matching, with Gabor jets forming labels to nodes and topology determining links. A contrast-insensitive similarity measure provides for invariance with respect to lighting conditions. The authors have formulated the matching procedure as an optimization task solved by diffusion of match points. This diffusion is controlled by a potential determined by jet similarity and the topology-preserving constraint. The algorithm implements a neural network architecture.<>Keywords
This publication has 10 references indexed in Scilit:
- An approach to image recognition using sparse filter graphsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Pattern recognition and associative memory as dynamical processes in a synergetic systemBiological Cybernetics, 1988
- Recognition of topological features of graphs and images in neural networksJournal of Physics A: General Physics, 1988
- Neural networks: translation-, rotation- and scale-invariant pattern recognitionJournal of Physics A: General Physics, 1988
- Pattern recognition by labeled graph matchingNeural Networks, 1988
- A Neural Network for Invariant Pattern RecognitionEurophysics Letters, 1987
- A Neural Network for the Retrieval of Superimposed Connection PatternsEurophysics Letters, 1987
- How patterned neural connections can be set up by self-organizationProceedings of the Royal Society of London. B. Biological Sciences, 1976
- Position, rotation, and scale invariant optical correlationApplied Optics, 1976
- Theory of communicationJournal of the Institution of Electrical Engineers - Part I: General, 1947