Fingerprint image segmentation method based on linear density calculation
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A fingerprint image and line density technology, applied in image analysis, calculation, image enhancement, etc.
Inactive Publication Date: 2017-06-27
MINNAN NORMAL UNIV
View PDF2 Cites 3 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, neither method is suitable for low-quality fingerprint images with complex
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Example Embodiment
[0050] Example 1
[0051] see Figure 1 to Figure 1 3, a kind of fingerprint image segmentation method based on line density calculation of the present invention comprises the following steps:
[0052] A1. Separation of fingerprint image features to obtain a contour map;
[0053] A2. Find the starting point of the lines that may exist in the contour map;
[0054] A3. Starting from the starting point of each line, find a line in the contour map;
[0055] A4. Determine the fingerprint center on the line density map;
[0056] A5. Convex hull processing is performed on the area (ie mask) obtained after the fingerprint center is determined.
[0057] Preferably, said step A1 includes the following steps:
[0058] B1. Using fast cartoon texture decomposition, the image is decomposed into a cartoon part containing the background and a texture part containing details;
[0059] B2. Binarize the texture part of the image; convert a black-and-white or colored image into an image with ...
Example Embodiment
[0081] Example 2
[0082] The invention provides a fingerprint image segmentation method based on linear density calculation, comprising the following steps:
[0083] F1, use the fast cartoon texture decomposition, the figure 1 The raw fingerprint image shown is decomposed into figure 2 The textured part shown and image 3 The shown background cartoon part, wherein the value of parameter sigma in this embodiment is 3;
[0084] F2. For the previously decomposed texture image, first perform binarization processing, and the processed image is as follows Figure 4 As shown, the value of the binarization threshold V in this embodiment is 127. Then, the deburring process is performed to obtain the contour map, and the processed image is as follows Figure 5 shown;
[0085] F3. Determine the starting point of the line search, take the central pixel point of the continuous white pixel point area in the contour map as the starting point of the line, such as Image 6 The white p...
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
Login to view more
Abstract
The invention discloses a fingerprint image segmentation method based on linear density calculation. The method comprises the following steps: the original fingerprint image is subjected to cartoon texture decomposition, a cartoon part containing a background and a texture part containing details are decomposed; the texture part is subjected to binaryzation and deburring treatment, and a contour map of the fingerprint image is acquired; lines are searched in the contour map; the image is divided to n*n pixel square grids, the number of points recorded in each grid is counted, and an image linear density is obtained; a fingerprint center is judged, the area of the fingerprint is obtained, that is, a mask area is obtained; and the mask area is subjected to convex hull treatment (or approximate convex hull treatment), and segmentation on the fingerprint foreground area and the background area of the fingerprint image is completed. On the basis of image cartoon texture decomposition, in view of a fingerprint image with each quality, a brand new method, that is, a linear density method is used for recognition and segmentation on the fingerprint area, and the segmentation efficiency and the segmentation accuracy of a low-quality fingerprint image can be effectively improved.
Description
technical field [0001] The invention designs a fingerprint image segmentation method based on linear density calculation, which belongs to the technical field of fingerprint identification. Background technique [0002] In the process of fingerprint extraction from the field to matching with the fingerprint database, fingerprint image segmentation is an extremely critical step. A good fingerprint image segmentation can remove other background noise while retaining the effective features of the fingerprint, and divide the image into two parts, the fingerprint area and the non-fingerprint area, so as to perform further optimization. At present, the segmentation algorithm for high-quality fingerprint images with simple background has been perfected day by day, but the segmentation of low-quality fingerprint images with complex background and many miscellaneous points basically needs to be done manually. Not only is this a waste of manpower, but the fingerprint area recognized ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more