ResearchSpace

Quality-based fingerprint segmentation

Show simple item record

dc.contributor.author Mngenge, NA
dc.contributor.author Nelwamondo, Fulufhelo V
dc.contributor.author Malumedzha, T
dc.contributor.author Msimang, N
dc.date.accessioned 2012-09-28T07:40:29Z
dc.date.available 2012-09-28T07:40:29Z
dc.date.issued 2012-06
dc.identifier.citation Mngenge, NA, Nelwamondo, FV, Malumedzha, T and Msimang, N. Quality-based fingerprint segmentation. 9th International Conference on Image Analysis and Recognition (ICIAR 2012), Aveiro, Portugal, 25-27 June 2012, pp. 54-63 en_US
dc.identifier.isbn 978-3-642-31297-7
dc.identifier.isbn 978-3-642-31298-4
dc.identifier.uri http://link.springer.com/chapter/10.1007/978-3-642-31298-4_7?null
dc.identifier.uri http://www.springerlink.com/content/9463312r6xt87720/?MUD=MP
dc.identifier.uri http://hdl.handle.net/10204/6109
dc.description Copyright: 2012 Springer-Verlag. 9th International Conference on Image Analysis and Recognition (ICIAR 2012), Aveiro, Portugal, 25-27 June 2012. This is an ABSTRACT ONLY. en_US
dc.description.abstract The need for segmentation of low quality fingerprints in forensics, high security and civilian applications is constantly increasing. Most segmentation algorithms proposed in the literature normally deal with separation of the background from the foreground. However, low quality foreground regions must also be removed to lower errors in feature extraction, matching and decision modules. In this research work, a quality based fingerprint segmentation algorithm is proposed. The proposed algorithm is block-wise, it utilizes the auto-correlation matrix of gradients and its eigenvalue to compute the score quality measure of each block. The score quality measures both local contrast and orientation in each block. The threshold is computed by taking the mean for all the scores assigned to each block. It was evaluated on FVC 2002 and NIST High Resolution 27A databases. Its performance compared to other algorithms was evaluated by independent fingerprint quality measure algorithm. The results from both FVC and NIST databases show that the proposed algorithm results are promising. en_US
dc.language.iso en en_US
dc.publisher Springer-Verlag en_US
dc.relation.ispartofseries Workflow;9605
dc.subject Fingerprint segmentation en_US
dc.subject Forensics en_US
dc.subject Fingerprint segmentation algorithm en_US
dc.subject Eigenvalues en_US
dc.subject Auto-correlation en_US
dc.subject Local contrast en_US
dc.subject Local orientation en_US
dc.subject Gradients en_US
dc.title Quality-based fingerprint segmentation en_US
dc.type Article en_US
dc.identifier.apacitation Mngenge, N., Nelwamondo, F. V., Malumedzha, T., & Msimang, N. (2012). Quality-based fingerprint segmentation. http://hdl.handle.net/10204/6109 en_ZA
dc.identifier.chicagocitation Mngenge, NA, Fulufhelo V Nelwamondo, T Malumedzha, and N Msimang "Quality-based fingerprint segmentation." (2012) http://hdl.handle.net/10204/6109 en_ZA
dc.identifier.vancouvercitation Mngenge N, Nelwamondo FV, Malumedzha T, Msimang N. Quality-based fingerprint segmentation. 2012; http://hdl.handle.net/10204/6109. en_ZA
dc.identifier.ris TY - Article AU - Mngenge, NA AU - Nelwamondo, Fulufhelo V AU - Malumedzha, T AU - Msimang, N AB - The need for segmentation of low quality fingerprints in forensics, high security and civilian applications is constantly increasing. Most segmentation algorithms proposed in the literature normally deal with separation of the background from the foreground. However, low quality foreground regions must also be removed to lower errors in feature extraction, matching and decision modules. In this research work, a quality based fingerprint segmentation algorithm is proposed. The proposed algorithm is block-wise, it utilizes the auto-correlation matrix of gradients and its eigenvalue to compute the score quality measure of each block. The score quality measures both local contrast and orientation in each block. The threshold is computed by taking the mean for all the scores assigned to each block. It was evaluated on FVC 2002 and NIST High Resolution 27A databases. Its performance compared to other algorithms was evaluated by independent fingerprint quality measure algorithm. The results from both FVC and NIST databases show that the proposed algorithm results are promising. DA - 2012-06 DB - ResearchSpace DP - CSIR KW - Fingerprint segmentation KW - Forensics KW - Fingerprint segmentation algorithm KW - Eigenvalues KW - Auto-correlation KW - Local contrast KW - Local orientation KW - Gradients LK - https://researchspace.csir.co.za PY - 2012 SM - 978-3-642-31297-7 SM - 978-3-642-31298-4 T1 - Quality-based fingerprint segmentation TI - Quality-based fingerprint segmentation UR - http://hdl.handle.net/10204/6109 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record