Combining fractional‐order edge detection and chaos synchronisation classifier for fingerprint identification

Abstract

This study proposes the combination of fractional-order edge detection (FOED) and a chaos synchronisation classifier for fingerprint identification. Fingerprints have various morphologies and exhibit singular points, which result in fingerprint individuality. Thumbprint images are captured from subjects using an optical fingerprint reader. The identification procedure consists of three stages: image enhancement, feature extraction and pattern identification. The adjustment of grey-scale values is used to enhance the contrast of the image. In order to overcome the limitations of the integral-order method, FOED is used to improve the clarity of the ridge and valley structures in fingerprint images. Using a reference point, it provides a stable sampling window for fingerprint extraction. Multiple CS-based detectors are used to track the differences as dynamic errors between heterogeneous fingerprints, on a one-to-one basis. The maximum-likelihood method performs a comparison of these different dynamic errors to identify individuals. Using 30 laboratory subjects, the proposed hybrid methods have a faster processing time and provide more accurate fingerprint identification.

Virtual‐Reality Simulator System for Double Interventional Cardiac Catheterization Using Fractional‐Order Vascular Access Tracker and Haptic Force Producer

“…Digital image processing comprises image enhancement process, image binarization, edge detection, and femoral arterial/venous vessel location. By feeding the digital images into the computer, as shown in Figure 3 , the image enhancement process is used to modify the gray-scale values using an intensity transformation function to adjust the contrast between certain intensity values [ 20 – 24 ]. Intensity transformation uses a nonlinear mapping function to enhance the image detail of the original image [ 24 ]: where pixel g ( r , c ) is individually processed, M is the mean of all of the gray-level values, σ ( r , c ) is the gray-level variance of each 3 × 3 detection mask, M ( r , c ) is the mean gray-level value for each detection mask, and k is a parameter, 0 < k < 1.…”

“…These gradients can be implemented using a 3 × 3 detection mask. First-order/second-order operators and fractional differential filters include Sobel operator, Robert operator, Laplace operator, and fractional differential gradient masks [ 14 , 23 , 24 ]. The edge detection estimator is used to identify the trajectory of the change in image intensity using a 3 × 3 Laplace operator mask.…”

About Edge Detection in Digital Images

“…Over the last ten years, new approaches to edge detection have been presented, for example dictionary learning [44], [45] or fuzzy logic [46], [47]. The most promising methods are based on fractional derivatives [3,39,43], [48][49][50]. Generalized form of the Grunwald-Letnikov fractional derivative d α f(x) of order α is [51] 0 0…”

“…Mostly it is used for general goals such as image segmentation, boundary detection or object recognition. But edge detectors are also often used for special tasks like fire detection [1], carlicense plate detection [2], fingerprint identification [3], synthetic aperture radar (SAR) image processing [4][5][6], lunar surface crater topology [7], polyp detection in colonoscopy [8], etc.…”

Enhancement of ARFI-VTI Elastography Images in Order to Preliminary Rapid Screening of Benign and Malignant Breast Tumors Using Multilayer Fractional-Order Machine Vision Classifier

“…Therefore, image enhancement process is a key technique to modify gray-scale levels that can adjust the lesion contrast in an ROI for visualizing texture details and morphological features. In this study, fractional-order convolution (FOC) operation [30][31][32][33][34] is applied for image enhancement and segmentation with the application of multiscale image texture enhancement method. Along with enhancing high-frequency and medium-frequency components, the FOC method can significantly retain low-frequency components in a nonlinear manner, which can highlight edge information and texture details and filter noises.…”