On the segmentation of fingerprint images: How to select the parameters of a block-wise variance method

Ishmael S. Msiza, Fulufhelo V. Nelwamondo, Tshilidzi Marwala

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Fingerprint image segmentation is the process of separating the fingerprint ridge area - that is, the foreground - from the background of the captured image. It is an important process because it prevents a fingerprint recognition system from analysing the unnecessary fragments of the captured image. This is the reason why segmentation should be executed during the initial stages of the fingerprint analysis process. This manuscript presents a method based on the gray-level variance of the captured image, where this variance is calculated per block of image pixels, instead of doing it for each image pixel. This then necessitates careful and informed choices for the values of - both - the gray-level variance threshold, and the pixel-block size. This manuscript solely focuses on studying the effects of these two variable parameters, and the results indicate that the choice of their respective values should be well-informed.

Original languageEnglish
Title of host publicationProceedings of the 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
Pages1107-1113
Number of pages7
Publication statusPublished - 2012
Event2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012 - Las Vegas, NV, United States
Duration: 16 Jul 201219 Jul 2012

Publication series

NameProceedings of the 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
Volume2

Conference

Conference2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
Country/TerritoryUnited States
CityLas Vegas, NV
Period16/07/1219/07/12

Keywords

  • Fingerprint segmentation
  • Gray-level variance
  • Pixel-block size
  • Variance threshold

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'On the segmentation of fingerprint images: How to select the parameters of a block-wise variance method'. Together they form a unique fingerprint.

Cite this