Walid Aydi

A Robust Iris Feature Extraction Approach Based on Monogenic and 2D Log-Gabor Filters

Abstract This article suggests an enhancement of the Masek circle model approach usually used to find a trade-off between modeling complexity, algorithm accuracy, and computational time, mainly for embedded systems where the real-time aspect is a high challenge. Moreover, most commercialized systems (Aoptix, Mkc-series, IriScan, etc.) today frame iris regions by circles. This work led to several novelties: first, in the segmentation process, the corneal reflection removal method based on morphological reconstruction and pixel connectivity was implemented. Second, the picture size reduction was applied according to nearest-neighbor interpolation. Third, the image gradient of the convolved-reduced picture was then generated using four proposed matrices. Fourth, and to reduce the complexity of the traditional method for the detection of the top and lower eyelids, a new method based on the Radon transform and the least squares fitting method was applied. Fifth, eyelashes were detected via the diagonal gradient and thresholding method. Monogenic signal was used in the feature extraction process. Finally, two distance measures were selected as a metric for recognition. Our experimental results using CASIA iris database V3.0 reveal that the proposed method provides a high performance in terms of speed and accuracy. Using dissimilarity modified Hamming distance, the accuracy of iris recognition was improved, with a false acceptance rate equal to 3% and a speed at least eight times as compared with the state of the art.

Improved Masek approach for iris localization

Iris recognition technology has become famous in security applications because of its accuracy, safety and noninvasive biometric technologies. It demonstrates its efficiency as biometric-based authentication. This technology take advantages of random variations in the visible features of iris which is the colored part surrounding the pupil. Iris segmentation is the first and the key step at any iris recognition system. It directly affects the recognition rates. Divers methods have been suggested in the literature. Some of these methods assume iris by circle models, elliptic or none regularly form. The circle contour sampling parameter has been investigated to find a tradeoff between speed and accuracy [10] especially for embedded systems where real time aspect is a big challenge. Moreover most commercially systems today estimate iris region by circle. In this work we propose to enhance Masek algorithm which is circle model method. Our experimental results using CASIA iris database V3.0 illustrate significant improvement in the performance (30% in time computation and 4% in accuracy).

A comparative study of GOM, uLBP, VLC and fractional Eigenfaces for face recognition

This paper compares four methods of feature extraction: Fractional Eigenfaces and Vander Lugt Correlator as global methods, and Gabor Ordinal Measures and Uniform Local Binary Pattern as local ones. We evaluate the four methods on the standard FERET probe data sets in order to study the robustness of these techniques against illumination variation, facial expression variation and aging. The Gabor ordinal measures as a combination of Gabor filters and ordinal measures outperforms the others methods on the four test sets in terms of recognition rate.

A fast and accurate eyelids and eyelashes detection approach for iris segmentation

Iris segmentation step is an essential process in iris recognition system. This step becomes much more difficult due to the presence of eyelids and eyelashes. This paper contributes to fast and robust eyelids and eyelash detection algorithm. The main contributions are: (1) Proposition of robust eyelids detection algorithm based on the Radon transform and polynomial curve fitting, using Least Squares Fitting method. (2) Eyelashes detection using diagonal gradient and thresholding process. The proposed method was evaluated on the CASIA V3 database and compared to the previous work. As the experimental results show that the proposed algorithm provides an encouraging performance in terms of accuracy and computational complexity. Moreover our method is very useful for iris recognition system which requires excluding the bits generated from eyelashes regions during iris matching stage.

Active Contour without Edges Vs GVF Active Contour for Accurate Pupil Segmentation

Iris localization is a critical step for an iris recognition system because it directly affects the recognition rates. Consequently, in order to have reasonably accurate measures, we should estimate as many iris boundaries as possible which are defined by papillary and ciliary regions. Due to the contraction which is an intrinsic propriety of the pupil and the variations in the shooting angle, the pupil will not be a regular circle. So an active contour is suitable to accurately locate the iris boundaries. In this paper we focused on iris/pupil boundary and we proposed a new algorithm based on an active contour without edges applied in gray level image. First, we develop a new method to locate and fill the corneal reflection which is used not only to remove the highlight points that appear inside the pupil but also as an initial contour generator for the snake. Second, we propose to use the active contour without edges for precise pupil segmentation. This kind of snake can detect objects whose boundaries are not necessarily defined by gradient. Our algorithm seems to be robust to occlusion, specular reflection, variation in illumination and improves its efficiency in precision and time computation compared with AIPF and Gvf active contour. Another advantage is that the initial curve can be anywhere in the image and the contour will be automatically detected. The proposed algorithm is 2.36 faster than GVF snake-based method for accurate pupil contour detection and integrodifferential method with accuracy up to 99.62% using CASIA iris database V3.0 and up to 100% with CASIA iris database V1.0.

A robust feature extraction method based on monogenic filter for iris recognition system

Iris recognition system is an attractive technology for identity authentication. This technology takes advantages of random variations in the features of the iris. Usually, each iris recognition system has four modules: segmentation, normalization, encoding and matching. Iris texture analysis or and matching are two essential processes in iris recognition. First, in this paper we propose to use a combined of monogenic filter and 1D log gabor filter to extract the iris signature. Second, two types of distances measures are chosen as a metric for recognition. Experimental results on CASIA iris database V3.0 demonstrates that the proposed method provides the high performance in speed and accuracy compared to the state of the art.

Efficient iris texture analysis method based on Gabor ordinal measures

With the remarkably increasing interest directed to the security dimension, the iris recognition process is considered to stand as one of the most versatile technique critically useful for the biometric identification and authentication process. This is mainly due to every individual’s unique iris texture. A modestly conceived efficient approach relevant to the feature extraction process is proposed. In the first place, iris zigzag “collarette” is extracted from the rest of the image by means of the circular Hough transform, as it includes the most significant regions lying in the iris texture. In the second place, the linear Hough transform is used for the eyelids’ detection purpose while the median filter is applied for the eyelashes’ removal. Then, a special technique combining the richness of Gabor features and the compactness of ordinal measures is implemented for the feature extraction process, so that a discriminative feature representation for every individual can be achieved. Subsequently, the modified Hamming distance is used for the matching process. Indeed, the advanced procedure turns out to be reliable, as compared to some of the state-of-the-art approaches, with a recognition rate of 99.98%, 98.12%, and 95.02% on CASIAV1.0, CASIAV3.0, and IIT Delhi V1 iris databases, respectively.

An efficient iris texture analysis based on HAAR wavelet 2D Log Gabor and monogenic filter

Human iris is a perfect part of the body for biometric identification. In fact, iris patterns are unique and stable that is why two people never occur to have the same iris texture even if they are twins. In this paper, we tried to improve the Rais algorithm feature extraction method. On the one hand, we selected this algorithm thanks to its simplicity as compared to other algorithms that use complex techniques of segmentation such as snake. On the other hand, it has impressive results for some databases like CASIA V1.0 and CASIA V3.0. To enhance Rais algorithm, we suggested using the HAAR wavelet, and the combined 2D Log Gabor filter along with the monogenic filter for feature extraction. Thus, our approach achieved a trade-off between the richness of the HAAR and Gabor features and the distinctiveness of the monogenic features. Daubechies wavelet and the Histogram of Oriented Gradient (HOG) were also tested. The experimental results on the CASIA iris database V3.0 show that the proposed method, using the HAAR wavelet, the combined monogenic filter and 2D Log Gabor filter yields a recognition rate of 94.45 %.