IRIS LOCATION METHOD BASED ON MATHEMATICAL MORPHOLOGY AND IMPROVED HOUGH TRANSFORM

2020 ◽  
pp. 2150001
Author(s):  
Pan Mei-Sen ◽  
Xiong Qi
Keyword(s):  
Mathematical Morphology ◽  
Hough Transform ◽  
Outer Boundary ◽  
Binary Image ◽  
Connected Region ◽  
Canny Operator ◽  
Location Method ◽  
Iris Image ◽  
Boundary Method ◽  
Mean Filter

An iris location method based on mathematical morphology and improved Hough transform is proposed in this paper. When locating the iris inner boundary, an iris inner boundary method based on mathematical morphology and circle fitting is proposed. The iris image is first preprocessed to get a binary image by the gray stretch transform or the circular region mean filter, and then the type of the connected region selected as the iris inner boundary in the binary image is determined by the ratio of the width to the length. On the foundation, the different method is used to extract the parameters of the connected region and the iris inner boundary is obtained. When locating the iris outer boundary, an iris outer boundary method based on the improved Hough transform is put forward. First, the Gaussian filter is used to deal with the iris image, the filtered image is reduced, Canny operator is employed for edge detection, an annular region centered at the center of the iris inner boundary of the reduced image is cropped to explore a circle by Hough transform, and the center and the radius of the iris outer boundary are worked out. The experimental results reveal that this proposed method has the advantages of fast speed, high accuracy, strong robustness and practicability.

A NEW IRIS LOCATION METHOD

2020 ◽  
Vol 32 (06) ◽  
pp. 2050046
Author(s):  
Pan Mei-Sen ◽  
Xiong Qi
Keyword(s):  
Good Accuracy ◽  
Outer Boundary ◽  
Gaussian Function ◽  
Variation Coefficient ◽  
Structural Elements ◽  
Location Method ◽  
Radial Gradient ◽  
Iris Image ◽  
Simple Implementation ◽  
Gradient Amplitude

A new iris location method is presented in this paper. When locating the iris inner boundary, a method for locating the iris inner boundary based on the variation coefficient and multiple disk-structural elements is proposed. The variation coefficient of the iris image is first calculated to be used for the image gray stretch, then the mathematical morphology operations with multiple disk-structural elements are applied to tackle the binary iris image, finally the connected region in line with geometric features of the circle is picked up and its center and radius are calculated, namely for obtaining the iris inner boundary. When positioning the iris outer boundary, a method for locating the iris outer boundary based on the variation coefficient and the gradient amplitude is presented. First, the Gaussian function is employed to filter the iris image using the variation coefficient as its standard deviation, then for each pixel on a circle which is centered at each neighborhood pixel near the circle enter of the iris inner boundary and has a radius with greater than that of the inner boundary, the radial gradient amplitude and tangential gradient amplitude of are computed, finally the iris outer boundary is determined on the maximum of the tangential gradient amplitude. The experiments reveal that this proposed method is effective, and has a fairly simple implementation, a low computational load, a fast location and good accuracy.

Counting of Microscopic Cells Based on Grads Hough Transform

2011 ◽  
Vol 383-390 ◽  
pp. 7607-7612 ◽  
Author(s):  
Jian Jun Chen ◽  
Yi Jun Gao ◽  
Zhao Ju Deng
Keyword(s):  
Mathematical Morphology ◽  
Hough Transform ◽  
Boundary Tracking ◽  
Image Gradient ◽  
Gradient Information ◽  
Automatic Counting ◽  
Counting Methods

In order to improve the accuracy and efficiency of automatic counting of microscopic cells, the method based on the Hough transform has been proposed. And the standard Hough transform has been improved using image gradient information. Compared with the traditional counting methods based on mathematical morphology and boundary tracking tags, the accuracy of the counting accuracy has been greatly improved. The results show the accuracy and efficiency of counting of the microscopic cells based on grads Hough transform is improved.

scholarly journals Image Denoising Based on Dilated Singularity Prior

2012 ◽  
Vol 2012 ◽  
pp. 1-15 ◽  
Author(s):  
Shaoxiang Hu ◽  
Zhiwu Liao ◽  
Wufan Chen
Keyword(s):  
Em Algorithm ◽  
Image Denoising ◽  
Mathematical Morphology ◽  
Visual Quality ◽  
Spatial Domain ◽  
Experimental Results ◽  
Canny Operator ◽  
Nonlocal Means ◽  
Spatial Image ◽  
Noisy Images

In order to preserve singularities in denoising, we propose a new scheme by adding dilated singularity prior to noisy images. The singularities are detected by canny operator firstly and then dilated using mathematical morphology for finding pixels “near” singularities instead of “on” singularities. The denoising results for pixels near singularities are obtained by nonlocal means in spatial domain to preserve singularities while the denoising results for pixels in smooth regions are obtained by EM algorithm constrained by a mask formed by downsampled spatial image with dilated singularity prior to suiting the sizes of the subbands of wavelets. The final denoised results are got by combining the above two results. Experimental results show that the scheme can preserve singularity well with relatively high PSNR and good visual quality.

An Improved Iris Localization Algorithm Based on Curve Fitting

2013 ◽  
Vol 380-384 ◽  
pp. 1176-1179
Author(s):  
Yi Huang ◽  
Xiao Ping Zeng
Keyword(s):  
Curve Fitting ◽  
Outer Boundary ◽  
Regions Of Interest ◽  
Localization Algorithm ◽  
Iris Localization ◽  
Iris Image ◽  
The Third ◽  
Boundary Points ◽  
Maximum Variance ◽  
Improved Algorithm

Iris localization is to detect outer-and-inner boundaries of iris in an iris image. In the paper, an improved algorithm was proposed to quickly and effectively locate outer-and-inner boundaries. As for this algorithm, the first is to block an iris image and extract its sub-image blocks which cover pupil; the second is to set a binary threshold of pupil by adopting the method of Maximum Variance between Clusters; the third is to get the value outer-boundary-points of iris, on the basis of gray gradient of key Regions-of-interest; the last is to select some characteristic pixels in regions of interest respectively and fit outer-and-inner boundaries of iris according to curve fitting.

scholarly journals On hearing the shape of an arbitrary doubly-connected region in R2

1990 ◽  
Vol 31 (4) ◽  
pp. 472-483 ◽  
Author(s):  
E. M. E. Zayed
Keyword(s):  
Asymptotic Expansion ◽  
Spectral Function ◽  
Basic Problem ◽  
Outer Boundary ◽  
Connected Region ◽  
Two Dimensional ◽  
Complete Knowledge ◽  
Impedance Condition

AbstractThe basic problem in this paper is that of determining the geometry of an arbitrary doubly-connected region in R2 together with an impedance condition on its inner boundary and another impedance condition on its outer boundary, from the complete knowledge of the eigenvalues for the two-dimensional Laplacian using the asymptotic expansion of the spectral function for small positive t.

Sign in / Sign up

Export Citation Format

Share Document