2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems 2008
DOI: 10.1109/btas.2008.4699340
|View full text |Cite
|
Sign up to set email alerts
|

Adapting Starburst for Elliptical Iris Segmentation

Abstract: Fitting an ellipse to the iris boundaries accounts for the projective distortions present in off-axis images of the eye and provides the contour fitting necessary for the dimensionless mapping used in leading iris recognition algorithms. Previous iris segmentation efforts have either focused on fitting circles to pupillary and limbic boundaries or assigning labels to image pixels. This paper approaches the iris segmentation problem by adapting the Starburst algorithm to locate pupillary and limbic feature pixe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
37
0

Year Published

2010
2010
2017
2017

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 64 publications
(37 citation statements)
references
References 17 publications
0
37
0
Order By: Relevance
“…Furthermore, they usually record a failure with large head rotations. Some methods use ellipse fitting [26].…”
Section: Shape-based Methodsmentioning
confidence: 99%
“…Furthermore, they usually record a failure with large head rotations. Some methods use ellipse fitting [26].…”
Section: Shape-based Methodsmentioning
confidence: 99%
“…This is not only applicable to Wildes' method, since several recent techniques are based on the computation of edge maps. For example, [10] implements an ellipse-model fitting method, for which a large number of elliptic candidates are computed, and the best ones are selected by evaluating them against the result of a Canny edge detector over the original image. The incorporation of such techniques into a biometric system risks its correct behavior when moving to less-controllable scenarios.…”
Section: Related Workmentioning
confidence: 99%
“…Its precision directly affects the final tracking precision. Current localization algorithms include Radial Symmetry Transformation (RST) [1], Hough Transformation (HT) [2], StarBurst [3][4][5][6][7], Snake [8] and Circle Difference(CD) [9], and so on.…”
Section: Introductionmentioning
confidence: 99%