A reliable iris recognition algorithm based on reverse biorthogonal wavelet transform

Szewczyk, Rafał; Grabowski, Kamil; Napieralska, M.; Sankowski, W.; Zubert, Mariusz; Napieralski, A.

doi:10.1016/j.patrec.2011.08.018

Cited by 72 publications

(33 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the performance of iris recognition systems become limited when the amplitude of the iris template is considered in the recognition algorithm, because the amplitude is sensitive to the light reflections, occlusions, illumination change. Therefore, most of the iris recognition frameworks in practice are based on the phase information [30], where to bypass the amplitude effect, the iris template is binarized. Binarizing the iris template, which is refereed to as the iriscode, removes the effect of the amplitude information.…”

Section: Iris Codementioning

confidence: 99%

“…In the authentication or recognition phase, iris-codes are compared using bit-based metrics such as Hamming distance. Several prominent iris authentication frameworks are built through this general framework [8,30,14,16]. Figure 1 presents a normalized iris image, the corresponding normalized mask, and the corresponding iris-code generated using algorithm described in [14].…”

Section: Iris Codementioning

confidence: 99%

See 1 more Smart Citation

Adversarial Examples to Fool Iris Recognition Systems

Soleymani

Dabouei

Dawson

et al. 2019

2019 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Adversarial examples have recently proven to be able to fool deep learning methods by adding carefully crafted small perturbation to the input space image. In this paper, we study the possibility of generating adversarial examples for code-based iris recognition systems. Since generating adversarial examples requires back-propagation of the adversarial loss, conventional filter bank-based iris-code generation frameworks cannot be employed in such a setup. Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure. This trained surrogate network is then deployed to generate the adversarial examples using the iterative gradient sign method algorithm [15]. We consider non-targeted and targeted attacks through three attack scenarios. Considering these attacks, we study the possibility of fooling an iris recognition system in white-box and black-box frameworks.

show abstract

Section: Iris Codementioning

confidence: 99%

Section: Iris Codementioning

confidence: 99%

Adversarial Examples to Fool Iris Recognition Systems

Soleymani

Dabouei

Dawson

et al. 2019

2019 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

show abstract

“…Hollingsworth et al 16 proposed a metric called the fragile bit distance, which quantitatively measures the coincidence of the fragile bit patterns in two iris codes. Szewczyk et al 17 focused on the analysis of the noisy iris data. A fusion approach to unconstrained iris recognition has been proposed.…”

Section: Related Workmentioning

confidence: 99%

Iris pattern recognition based on cumulative sums and majority vote methods

Viriri

Tapamo

2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Iris recognition is proving to be one of the most reliable biometric authentication systems. Since biometric authentication systems store multiple templates per user, there is need to optimize their computational and storage complexities by creating a single reliable specimen iris template per user. In this article, we propose two majority vote-based strategies for the creation of a single iris template per user. An algorithm based on cumulative-sums grey change analysis is used to extract the iris texture features for template creation. The experimental results on the CASIA and UBIRIS iris databases show that the approach is effective and efficient, with a recognition rate of 99.6%.

show abstract

“…For iris localization, which is the process of detecting the inner (iris/pupil) and the outer (iris/sclera) boundaries in the eye image, several techniques have been proposed, such as Integrodifferential operator [3,5] a combination of Hough transform and region-based active contours [6], and thresholding [7]. In iris normalization, most of the algorithms applied Daugman rubber sheet model [3,5,[7][8][9][10]. Most of the methods performed well for ideal conditions in a very constrained environment [2,3].…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, different methods have been applied to extract features from normalized iris images, such as approaches based on Gabor filters [3], Wavelet transforms [8][9][10]18] Curvelet transforms [5] and 1-D circular profiles [19]. Even though, the wavelet transform is popular, powerful and familiar among the iris image processing techniques, it has its own limitations in capturing directional information such as smooth contours and the directional edges of the image.…”

Section: Introductionmentioning

confidence: 99%

Iris Recognition using Robust Localization and Nonsubsampled Contourlet Based Features

Khalighi

Pak

Tirdad

et al. 2014

J Sign Process Syst

View full text Add to dashboard Cite

The conventional iris recognition methods do not perform well for the datasets where the eye image may contain nonideal data such as specular reflection, off-angle view, eyelid, eyelashes and other artifacts. This paper gives contributions for a reliable iris recognition method using a new scale-, shift-and rotationinvariant feature-extraction method in time-frequency and spatial domains. Indeed, a 2-level nonsubsampled contourlet transform (NSCT) is applied on the normalized iris images and a gray level co-occurrence matrix (GLCM) with 3 different orientations is computed on both spatial image and NSCT frequency subbands. Moreover, the effect of the occluded parts is reduced by performing an iris localization algorithm followed by a four regions of interest (ROI) selection. The extracted feature set is transformed and normalized to reduce the effect of extreme values in the feature vector. Next, significant features for iris recognition are selected by a two-step method composed by a filtering stage and wrapper based selection. Finally, the selected feature set is classified using support vector machine (SVM). The proposed iris identification method was tested on the public iris datasets CASIA Ver.1 and CASIA Ver.4-lamp showing a state-of-the-art performance.

show abstract

A reliable iris recognition algorithm based on reverse biorthogonal wavelet transform

Cited by 72 publications

References 21 publications

Adversarial Examples to Fool Iris Recognition Systems

Adversarial Examples to Fool Iris Recognition Systems

Iris pattern recognition based on cumulative sums and majority vote methods

Iris Recognition using Robust Localization and Nonsubsampled Contourlet Based Features

Contact Info

Product

Resources

About