ResearchSpace

Novelty detection-based internal fingerprint segmentation in optical coherence tomography images

Show simple item record

dc.contributor.author Khutlang, Rethabile
dc.contributor.author Machaka, Pheeha
dc.contributor.author Singh, Ann
dc.contributor.author Nelwamondo, Fulufhelo V
dc.date.accessioned 2017-08-29T12:46:36Z
dc.date.available 2017-08-29T12:46:36Z
dc.date.issued 2017-08
dc.identifier.citation Khutlang, R., Machaka, P., Singh, A. et al. 2017. Novelty detection-based internal fingerprint segmentation in optical coherence tomography images. In: Computed Tomography - Advanced Applications, Intech, p. 189-206. doi.org/10.5772/67594 en_US
dc.identifier.isbn 978-953-51-3368-1
dc.identifier.uri https://www.intechopen.com/books/computed-tomography-advanced-applications
dc.identifier.uri doi.org/10.5772/67594
dc.identifier.uri http://hdl.handle.net/10204/9504
dc.description Copyright: 2017 The Authors. Published under a Creative Commons License. en_US
dc.description.abstract Biometric fingerprint scanners scan the external skin's features onto a 2-D image. The performance of the automatic fingerprint identification system suffers first and foremost if the finger skin is wet, worn out or a fake fingerprint is used. We present an automatic segmentation of the papillary layer method, from images acquired using contact-less 3-D swept source optical coherence tomography (OCT). The papillary contour represents the internal fingerprint, which does not suffer from the external finger problems. It is embedded between the upper epidermis and papillary layers. Speckle noise is first reduced using non-linear filters from the slices composing the 3-D image. Subsequently, the stratum corneum is used to extract the epidermis. The epidermis, with its depth known, is used as the target class of the ensuing novelty detection. The outliers resulting from novelty detection represent the papillary layer. The contour of the papillary layer is segmented as the boundary between target and rejection classes. Using a mixture of Gaussian's novelty detection routine on images pre-processed with a regularized anisotropic diffusion filter, the papillary contours—internal fingerprints—are consistent with those segmented manually, with the modifiedWilliams index above 0.9400. en_US
dc.language.iso en en_US
dc.publisher Intech en_US
dc.relation.ispartofseries Worklist;19415
dc.subject Biometrics en_US
dc.subject Novelty detection en_US
dc.subject Segmentation en_US
dc.subject Internal fingerprint en_US
dc.subject Optical coherence tomography en_US
dc.subject OCT en_US
dc.title Novelty detection-based internal fingerprint segmentation in optical coherence tomography images en_US
dc.type Book Chapter en_US
dc.identifier.apacitation Khutlang, R., Machaka, P., Singh, A., & Nelwamondo, F. V. (2017). Novelty detection-Based internal fingerprint segmentation in optical coherence tomography images., <i>Worklist;19415</i> Intech. http://hdl.handle.net/10204/9504 en_ZA
dc.identifier.chicagocitation Khutlang, Rethabile, Pheeha Machaka, Ann Singh, and Fulufhelo V Nelwamondo. "Novelty detection-based internal fingerprint segmentation in optical coherence tomography images" In <i>WORKLIST;19415</i>, n.p.: Intech. 2017. http://hdl.handle.net/10204/9504. en_ZA
dc.identifier.vancouvercitation Khutlang R, Machaka P, Singh A, Nelwamondo FV. Novelty detection-based internal fingerprint segmentation in optical coherence tomography images.. Worklist;19415. [place unknown]: Intech; 2017. [cited yyyy month dd]. http://hdl.handle.net/10204/9504. en_ZA
dc.identifier.ris TY - Book Chapter AU - Khutlang, Rethabile AU - Machaka, Pheeha AU - Singh, Ann AU - Nelwamondo, Fulufhelo V AB - Biometric fingerprint scanners scan the external skin's features onto a 2-D image. The performance of the automatic fingerprint identification system suffers first and foremost if the finger skin is wet, worn out or a fake fingerprint is used. We present an automatic segmentation of the papillary layer method, from images acquired using contact-less 3-D swept source optical coherence tomography (OCT). The papillary contour represents the internal fingerprint, which does not suffer from the external finger problems. It is embedded between the upper epidermis and papillary layers. Speckle noise is first reduced using non-linear filters from the slices composing the 3-D image. Subsequently, the stratum corneum is used to extract the epidermis. The epidermis, with its depth known, is used as the target class of the ensuing novelty detection. The outliers resulting from novelty detection represent the papillary layer. The contour of the papillary layer is segmented as the boundary between target and rejection classes. Using a mixture of Gaussian's novelty detection routine on images pre-processed with a regularized anisotropic diffusion filter, the papillary contours—internal fingerprints—are consistent with those segmented manually, with the modifiedWilliams index above 0.9400. DA - 2017-08 DB - ResearchSpace DP - CSIR KW - Biometrics KW - Novelty detection KW - Segmentation KW - Internal fingerprint KW - Optical coherence tomography KW - OCT LK - https://researchspace.csir.co.za PY - 2017 SM - 978-953-51-3368-1 T1 - Novelty detection-based internal fingerprint segmentation in optical coherence tomography images TI - Novelty detection-based internal fingerprint segmentation in optical coherence tomography images UR - http://hdl.handle.net/10204/9504 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record