A structural approach to fingerprint classification
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 578-585 vol.3
- https://doi.org/10.1109/icpr.1996.547013
Abstract
A new structural approach to the fingerprint classification problem is presented. The fingerprint directional image is segmented in regions by minimizing the variance of the element directions within the regions. From the segmentation of the directional image a relational graph compactly summarising the macro-structure of the fingerprint is derived. Inexact graph matching techniques can be adopted to compare the obtained graph with the model graphs in order to classify the fingerprint, according to a given classification scheme.Keywords
This publication has 14 references indexed in Scilit:
- Classifying fingerprint images using neural network: deriving the classification statePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Dynamic clustering of maps in autonomous agentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Map learning and clustering in autonomous systemsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Computing the Minimum Error Distance of Graphs in 0(n3) Time with Precedence Graph GrammarsPublished by Springer Nature ,1988
- Segmentation of fingerprint images using the directional imagePattern Recognition, 1987
- Fingerprint pattern classificationPattern Recognition, 1984
- Inexact graph matching for structural pattern recognitionPattern Recognition Letters, 1983
- Structural Descriptions and Inexact MatchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1981
- Type Classification of Fingerprints: A Syntactic ApproachIEEE Transactions on Pattern Analysis and Machine Intelligence, 1980
- A syntactic approach to fingerprint pattern recognitionPattern Recognition, 1975