Application of pyramidal directional filters for biometric identification using conjunctival vasculature patterns

Abstract

Directional pyramidal filter banks as feature extractors for ocular vascular biometrics are proposed. Apart from the red, green, and blue (RGB) format, we analyze the significance of using HSV, YCbCr, and layer combinations (R+Cr)/2, (G+Cr)/2, (B+Cr)/2. For classification, Linear Discriminant Analysis (LDA) is used. We outline the advantages of a Contourlet transform implementation for eye vein biometrics, based on vascular patterns seen on the white of the eye. The performance of the proposed algorithm is evaluated using Receiver Operating Characteristic (ROC) curves. Area under the curve (AUC), equal error rate (EER), and decidability values are used as performance metrics. The dataset consists of more than 1600 still images and video frames acquired in two separate sessions from 40 subjects. All images were captured from a distance of 5 feet using a DSLR camera with an attached white LED light source. We evaluate and discuss the results of cross matching features extracted from still images and video recordings of conjunctival vasculature patterns. The best AUC value of 0.9999 with an EER of 0.064% resulted from using Cb layer in YCbCr color space. The best (lowest value) EER of 0.032% was obtained with an AUC value of 0.9998 using the green layer of the RGB images.

Method for using visible ocular vasculature for mobile biometrics

“…Since its introduction by Derakhshani and Ross, other researches have been introducing various segmentation, image enhancement, feature extraction, and classification algorithms for conjunctival vasculature biometrics. So far, eyeprint biometric studies have been performed either by utilising UBIRIS v1 RGB dataset, or researchers' in-house ocular images [12,13,[16][17][18][19][20][21][22][23][24][25][26][27][28][29]. Some studies have also reported using multispectral captures [30,31].…”

“…The initial enhancement and registration schemes were reported in [17] using a 50 subject in-house database. The performance of gray-level cooccurence matrix (GLCM) [18] and pyramidal directional filter [19] features were investigated using dSLR captures. In related work [21][22][23][24][25][26][27][28][29], several methods were evaluated on UBIRISv1 database [20] compared with in-house datasets.…”

Ocular surface vasculature recognition using curvelet transform

“…Crihalmeanu et al [20] used multispectral imaging in combination with Speeded Up Robust Features (SURF), pixel-topixel correlation, and minutiae points for feature extraction. In our previous work, we used wavelet packet energies [21], contourlets [10], shearlets [22], and the grey level co-occurrence method (GLCM) [11] for OSV feature extraction. Oh et al [23] used local binary pattern features for OSV recognition.…”

“…In [10], CIBIT‐II dataset was used for OSV recognition using contourlets, with a best EER of 0.04% being reported for short‐term analysis. In this study, using curvelets, an EER of 0.01% was obtained for the same scenario.…”

“…Henceforth, we will refer to the plurality of conjunctival and episcleral vasculature, as seen on the white of the eye, as the OSV. Related previous work supports usage of OSV textural features for biometric authentication [8][9][10][11][12]. OSV patterns also satisfy the widely accepted requirements of biometric traits such as universality, distinctiveness, permanence, collectability, and noncircumvention.…”