Skip to main content

Table 1 Comparing localization accuracy of different methods using Ubiris database. The whole table entries are taken from reference [19], excluding the last row which contains the results obtained using our approach.

From: A New User Dependent Iris Recognition System Based on an Area Preserving Pointwise Level Set Segmentation Approach

Methodology

Parameters

Session 1, %

Session 2, %

Degradation

Daugman

Original methodology

6.99

Daugman

Histogram equalization preprocessing

4.69

Daugman

Threshold preprocessing (128)

1.22

Wildes

Original methodology

2.00

Wildes

Shen and Castan edge detector

0.82

Wileds

Zero crossing edge detector

1.88

Caumus and Wileds

Original methodology, number of directions  = 8

7.49

Martin-Roche et al.

Original methodology

5.99

Tuceryan

Total clusters  = 5

3.56

Proenca et al.

Fuzzy K-means  + position, intensity

0.14

Our Proposed method

Pointwise level set approach with area preserving capability

0.1