Toward Pose Invariant and Completely Contactless Finger Knuckle Recognition
Author:
- 22 July 2019
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 1 (3) , 201-209
Abstract
In order to advance application of finger knuckle modality in new domains, especially using widely popular smartphones, completely contactless and pose invariant knuckle identification are highly desirable. Earlier work in the literature incorporates finger knuckle images under fixed poses, which is not realistic for completely contactless biometrics applications. This paper makes a first such attempt to investigate the possibility of recognizing completely contactless finger knuckle images acquired under varying poses. New approach to automatically normalize and align contactless finger knuckle images is introduced, and the performance of a specialized matcher is investigated to achieve superior performance. A new database from 221 different subjects' contactless finger knuckle images is also developed and made available in public domain to advance much needed research in this area. Experimental results illustrated in this paper are promising and validate the usefulness of normalization and matching algorithms to recognize finger knuckle with different poses. Spatial and spectral domain features can provide complimentary cues and are simultaneously employed for the performance improvement. Such performance improvement only serves as the baseline for much needed further improvement in recognition accuracy for database presented in this paper.Keywords
This publication has 18 references indexed in Scilit:
- Personal Identification Using Minor Knuckle Patterns From Palm Dorsal SurfaceIEEE Transactions on Information Forensics and Security, 2016
- Palmprint verification using binary orientation co-occurrence vectorPattern Recognition Letters, 2009
- Contrast context histogram—An efficient discriminating local descriptor for object recognition and image matchingPattern Recognition, 2008
- A Palmprint Recognition Algorithm Using Phase-Only CorrelationIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2008
- The Relation between the ROC Curve and the CMC2006
- A novel R486Q mutation in BMPR1B resulting in either a brachydactyly type C/symphalangism-like phenotype or brachydactyly type A2European Journal of Human Genetics, 2006
- Finger surface as a biometric identifierComputer Vision and Image Understanding, 2005
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- The Spemann Organizer Signal noggin Binds and Inactivates Bone Morphogenetic Protein 4Cell, 1996
- ANALYZING ORIENTED PATTERNS1987