Spectral Clustering for Segmentation of Fingerprint Images
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE credits
Student thesis
Abstract [en]
Fingerprint recognition systems are one of the oldest biometric recognition systems, which are under constant development. Presence of noise in fingerprint severely affects performance of recognition systems. Fingerprint segmentation is one of the important part in recognition systems; they eliminate noisy background in the image improving performance of fingerprint recognition systems.
This thesis focuses on proposing a new algorithm for segmentation of fingerprint images using data clustering technique known as spectral clustering. The algorithm is based on block wise segmentation of fingerprint images. The criteria considered for segregating blocks into foreground and background are variance and double gradient of the image. The data in the blocks is clustered using spectral clustering technique.
Performance of the developed algorithm is evaluated using FVC2000, FVC2002, FVC2004 databases. Two sub-databases from each database are selected and relative sizes of the masks are compared to the hand annotated masks of the respective databases. From results, it is observed that double gradient is slightly better than variance in using as parameter for performing fingerprint segmentation
Place, publisher, year, edition, pages
2017. , p. 52
Keywords [en]
Segmentation, Clustering, Fingerprints, K-means, Spectral Clustering, Variance, Image gradient
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-13824OAI: oai:DiVA.org:bth-13824DiVA, id: diva2:1068184
External cooperation
Sällberg Technologies e.U.
Subject / course
ET2566 Master's Thesis (120 credits) in Electrical Engineering with emphasis on Signal processing
Educational program
ETASX Master of Science Programme in Electrical Engineering with emphasis on Signal Processing
Presentation
2016-09-30, Platon, J3506,, Blekinge Institute of Technology, Karlskrona, 14:00 (English)
Supervisors
Examiners
2017-01-252017-01-25Bibliographically approved