Iris quality assessment and bi-orthogonal wavelet based encoding for recognition

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription AbstractA binary iriscode is a very compact representation of an iris image. For a long time it was assumed that the iriscode did not contain enough information to allow for the reconstruction of the original iris. The present work proposes a novel probabilistic approach based on genetic algorithms to reconstruct iris images from binary templates and analyzes the similarity between the reconstructed synthetic iris image and the original one. The performance of the reconstruction technique is assessed by empirically estimating the probability of successfully matching the synthesized iris image against its true counterpart using a commercial matcher. The experimental results indicate that the reconstructed images look reasonably realistic. While a human expert may not be easily deceived by them, they can successfully deceive a commercial matcher. Furthermore, since the proposed methodology is able to synthesize multiple iris images from a single iriscode, it has other potential applications including privacy enhancement of iris-based systems.

show abstract

“…• Contrast: Local Contrast (LC) [56]. This quality feature is adapted from the technique presented in [56] for occlusion estimation.…”

Section: Results: Quality Assessmentmentioning

confidence: 99%

“…This quality feature is adapted from the technique presented in [56] for occlusion estimation. A square region covering the iris and pupil is divided into a 10 × 10 cell grid.…”

Section: Results: Quality Assessmentmentioning

confidence: 99%

Iris image reconstruction from binary templates: An efficient probabilistic approach based on genetic algorithms

Galbally

Ross

Gomez‐Barrero

et al. 2013

Computer Vision and Image Understanding

123

View full text Add to dashboard Cite

show abstract

“…• High Frequency Power 4 (IQF15) [1], it estimates the defocus of the image by computing the second order derivative (using a discrete approximation of the modified Laplacian) in order to high pass the iris images.…”

Section: Focus Featuresmentioning

confidence: 99%

Iris liveness detection based on quality related features

Galbally

Ortiz-Lopez

Fiérrez

et al. 2012

2012 5th IAPR International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

A new liveness detection scheme for iris based on quality related measures is presented. The novel anti-spoofing technique is tested on a database comprising over 1,600 real and fake (high quality printed images) iris samples proving to have a very high potential as an effective protection scheme against direct attacks. Furthermore, the liveness detection method presented has the added advantage over previously studied techniques of needing just one iris image (the same used for verification) to decide whether it comes from a real or fake eye.

show abstract

“…These include efforts to determine the focus of the image [1,2], the degree of occlusion and blur [1], or to produce localized quality metrics from the energy of wavelet responses to regions of the iris [2]. Methods for combining metrics have included linear combinations [3], sometimes with weights proportional to the distance of the iris region under consideration to the center of the pupil for the reason that inner regions tend to offer more texture and less occlusion by eyelashes [2].…”

Section: Introductionmentioning

confidence: 99%

Learning to predict match scores for iris image quality assessment

Happold

2014

IEEE International Joint Conference on Biometrics

View full text Add to dashboard Cite

Individual image quality metrics that focus on a particular form of image degradation have the virtue of being readily decipherable but also the drawback of not relating directly to the purpose for which the image is used. We describe here a method for learning the quality of iris images from the output of iris matching algorithms. We extract a large number of image quality features forming a high dimensional feature vector and label each training image with the match score for its corresponding genuine image in the enrolled database. We then train a Random Forest regressor to predict this match score, and in the course of training apply feature selection to dramatically reduce the feature vector dimensionality. A comparison of several alternative methods of feature selection is given. Our method demonstrates that the effects of image quality degradation on match scores can be predicted from image features. The predicted genuine match score serves as a quality metric, enabling filtering of poor quality images before enrollment or identification.

show abstract

Iris quality assessment and bi-orthogonal wavelet based encoding for recognition

Cited by 46 publications

References 18 publications

Iris image reconstruction from binary templates: An efficient probabilistic approach based on genetic algorithms

Iris image reconstruction from binary templates: An efficient probabilistic approach based on genetic algorithms

Iris liveness detection based on quality related features

Learning to predict match scores for iris image quality assessment

Contact Info

Product

Resources

About