Unlock instant, AI-driven research and patent intelligence for your innovation.

Fingerprint image splitting method

A fingerprint image and image technology, which is applied in the field of fingerprint image segmentation, can solve the problem that the residual grain area cannot be accurately separated

Active Publication Date: 2012-12-19
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is easily affected by noise, and cannot accurately separate the residual texture area and the noise area formed by the frictional movement of the finger on the sensor surface

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fingerprint image splitting method
  • Fingerprint image splitting method
  • Fingerprint image splitting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0140] figure 1 It is a schematic diagram of image block in the present invention. The height of the image I is height and the width is width. The image I is divided into b×b (b=8) non-overlapping blocks. The block in the i-th row and j-th column is represented by w(i,j), w(0, 0) is located in the lower left corner. For image block w(i,j), W β (i,j) is an image block whose size is β×β, and the geometric center coincides with the geometric center of w(i,j).

[0141] figure 2 This is the overall flow chart of the present invention:

[0142] Suppose the image is I. Divide the image I into non-overlapping blocks of size b×b (b=8), and use w(i,j) to represent the block in the i-th row and j-th column of I (such as figure 1 Shown), Use f(i,j) to represent the final segmentation result, that is, use f(i,j)=1 to indicate that w(i,j) is the foreground, and f(i,j)=0 to indicate that w(i,j) is background. The steps of the method of the present invention are:

[0143] In the first step,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fingerprint image splitting method and provides a novel finger print image splitting method for solving the splitting problem of a residual mark region. According to the technical scheme, an image is segmented twice, gray static features are adopted in the first segmentation, and a segmentation threshold value is determined by a histogram; the distribution of mark pixelsis analyzed in the second segmentation, and the second segmentation is carried out through statistics on sparse mark pixels; and finally the segmentation results are subjected to post-treatment by utilizing open operation and closed operation. By adopting the method provided by the invention, not only can the residual mark region be classified into a background properly, but also a noise region formed by the movement of fingers on the surface of a sensor can be separated, the segmentation threshold value can be calculated self-adaptively, the method has high commonality, and is suitable for images collected by different sensors.

Description

Technical field [0001] The invention relates to a fingerprint image segmentation method in the field of fingerprint identification in computer science. Background technique [0002] Fingerprint recognition is more and more widely used as a biometric-based identity authentication technology. High-performance fingerprint recognition systems require high accuracy and fast feature extraction and matching algorithms. Feature extraction usually goes through the process of image segmentation, direction calculation, image enhancement, texture extraction and refinement, and minutiae feature extraction and screening. In order to improve the speed and accuracy of feature extraction, the fingerprint image is usually segmented first to remove areas that do not contain real textures, so that the feature extraction stage only needs to analyze the texture area to extract features, and avoid extracting wrong features from non-textured areas. . [0003] The fingerprint segmentation method general...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
Inventor 祝恩殷建平李永官群健赵建民朱信忠
Owner NAT UNIV OF DEFENSE TECH