Iris Recognition Using Possibilistic Fuzzy Matching on Local Features

Abstract

In this paper, we propose a novel possibilistic fuzzy matching strategy with invariant properties, which can provide a robust and effective matching scheme for two sets of iris feature points. In addition, the nonlinear normalization model is adopted to provide more accurate position before matching. Moreover, an effective iris segmentation method is proposed to refine the detected inner and outer boundaries to smooth curves. For feature extraction, the Gabor filters are adopted to detect the local feature points from the segmented iris image in the Cartesian coordinate system and to generate a rotation-invariant descriptor for each detected point. After that, the proposed matching algorithm is used to compute a similarity score for two sets of feature points from a pair of iris images. The experimental results show that the performance of our system is better than those of the systems based on the local features and is comparable to those of the typical systems.

Fast and accurate method for complete iris segmentation with active contour and morphology

“…Because the CASIA database contains many identical iris samples [25], therefore, to simplify the analysis we ignored the identical images. Consequently, 1000 images (200 iris classes with 5 images per class) are randomly chosen form the IrisV4-Lamp subset since they contain challenging iris images with nonlinear deformations and noisy characteristics such as light reflections and eyelash occlusion.…”

Unsupervised Learning for the Segmentation of Small Crystalline Particles at the Atomic Level

“…[23] A Gabor filter is a linear filter based on this idea, and it was originally developed for 1D signal analysis. Daugman extended the Gabor filter to two dimensions(2D) and, since then, it has been found to be particularly appropriate for texture analysis, feature extraction, edge detection, image compression and a multitude of image-related fields [22,[24][25][26][27][28] These filters are commonly described as a function produced by a Gaussianshaped kernel times a complex sinusoid. In a spatial domain, a 2D Gabor filter is defined as a Gaussian kernel function (w) modulated by a complex sinusoidal plane wave(s):…”

“…[ 23 ] A Gabor filter is a linear filter based on this idea, and it was originally developed for 1D signal analysis. Daugman extended the Gabor filter to two dimensions(2D) and, since then, it has been found to be particularly appropriate for texture analysis, feature extraction, edge detection, image compression and a multitude of image‐related fields [ 22,24–28 ] These filters are commonly described as a function produced by a Gaussian‐shaped kernel times a complex sinusoid. In a spatial domain, a 2D Gabor filter is defined as a Gaussian kernel function ( w ) modulated by a complex sinusoidal plane wave(s): $$$$\begin{equation} g\left( {x,y} \right) = w\left( {x,y} \right)*s\left( {x,y} \right)\end{equation}$$$$ $$$$\begin{equation}w\left( {x,y} \right) = \frac{1}{{\sqrt {2{{\pi}}\sigma } }}{e^{\frac{{ - 1}}{2}\left( {\frac{{{x^2}}}{{\sigma _x^2}} + \frac{{{y^2}}}{{\sigma _y^2}}} \right)}}\end{equation}$$$$ $$$$\begin{equation}s\left( {x,y} \right) = {e^{ - 2\pi i\left( {{u_0}x + {v_0}y + \varphi } \right)}}\end{equation}$$$$where σ is the standard deviation of the Gaussian, $$\sigma _x^2$$ and $$\sigma _y^2$$ are the variance in x ‐axis and y ‐axis and determines the width of the major and minor axis of the Gaussian envelope.…”

Segmentation of mitochondria in intracellular space

“…The reason for choosing this type of feature extraction is due to the fact that Gabor filtering is well-known as an invariant and effective method for extracting texture features [19]. Furthermore, the Gabor feature is convinced to be welladapted to fiber structure extraction which was contained in variety applications such as fingerprint classification [21], Iris recognition [22], prostate cancer image segmentation and recognition [23], blood vessel detection [20]. This effectiveness can be explained by the property of both frequency and orientation selective which provides a joint optimal resolution in both frequency and spatial domain.…”