CN112101213A - Method for acquiring fingerprint direction information - Google Patents
Method for acquiring fingerprint direction information Download PDFInfo
- Publication number
- CN112101213A CN112101213A CN202010966749.7A CN202010966749A CN112101213A CN 112101213 A CN112101213 A CN 112101213A CN 202010966749 A CN202010966749 A CN 202010966749A CN 112101213 A CN112101213 A CN 112101213A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- direction information
- image
- acquiring
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
A method for acquiring fingerprint direction information belongs to the technical field of image processing. The invention aims to solve the problems that the fingerprint direction information extracted from the fingerprint image direction information is inaccurate, the calculation amount for extracting the fingerprint direction information is large, and the running speed is slow. The method comprises the steps of firstly, establishing a two-dimensional mathematical model of the fingerprint; secondly, preprocessing the fingerprint image; step three, analyzing the fingerprint signal; and step four, acquiring the direction information of the existing fingerprint graph according to the sobel algorithm. The invention aims at the problems of inaccurate fingerprint direction information extracted from the fingerprint image direction information, large calculation amount for extracting the fingerprint direction information and slow running speed, and adopts the method for acquiring the fingerprint direction information of the preprocessed fingerprint image by using the sobel algorithm.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a fingerprint image processing technology in a fingerprint identification technology.
Background
Since the application of biometrics to identification technologies, fingerprint identification technologies have been developed as a more stable, mature and widely applied authentication method. At present, the research of the fingerprint identification technology has obtained better results and is widely applied, the fingerprint direction information is taken as an intermediate link of a fingerprint system and has the effect of starting and ending, the fingerprint direction information is usually extracted by adopting a preset direction approximation algorithm at present, the extracted fingerprint direction information can be caused by the fingerprint image direction information extracted by the algorithm to be inaccurate, the calculated amount of the method is larger, and the operation speed is slow.
Disclosure of Invention
The invention aims to extract fingerprint direction information with high accuracy and improve the running speed of acquiring the fingerprint direction information for acquiring high-quality fingerprint image information.
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention.
A method for acquiring fingerprint direction information comprises the following steps:
establishing a two-dimensional mathematical model of a fingerprint;
secondly, preprocessing the fingerprint image;
step three, analyzing the fingerprint signal;
and step four, acquiring the direction information of the existing fingerprint graph according to the sobel algorithm.
Preferably: the specific method for establishing the two-dimensional mathematical model of the fingerprint in the first step is as follows: the noise of each pixel point is stored in the image by a specific gray value, and a two-dimensional teaching model formula of the fingerprint is established as follows:
a (x, y) is a gray compensation value of the fingerprint image, b (x, y) is an amplitude of the modulation signal,
phase information of the fingerprint; n (x, y) is noise in the fingerprint image.
Preferably: in the second step, the specific method for preprocessing the fingerprint image comprises the following steps:
step 1, smoothing an original fingerprint image by adopting a Gaussian low-pass filter to eliminate noise:
and 2, calculating a gray compensation value by using an average filter:
preferably: in the third step, the specific method for analyzing the fingerprint signal is as follows: the amplitude b (x, y) and phase
Separating to obtain a signal g (x, y) only with amplitude and phase left;
dividing the fingerprint image I into subblocks of W and M N blocks, wherein the values of M and N depend on the size of the fingerprint image, and respectively operating each block;
step b, calculating the mean value Med (k, l) of the gray level of each sub-block
The gray value of the ith row and jth column of pixel points in the image subblock of the I (I, j) is 1,2,3.. M, and l is 1,2,3.. N, and Med (k, l) represents the gray value of the W × W subblock;
step c. calculating the gray variance Var (k, l) of each sub-block
Preferably: in the fourth step, a specific method for acquiring the direction information of the existing fingerprint graph according to the sobel algorithm comprises the following steps:
d, dividing the fingerprint image into blocks with the size of W x W, and calculating a first-order partial derivative of each pixel point;
step e, calculating the direction information of each image:
the sobel operator utilizes the pixel points of the neighborhood to calculate the gray value:
wherein A is the original image, GxAnd GyImages representing lateral and longitudinal edge detection, respectively;
the magnitude of the gradient is calculated using the above two equations, such as the following:
the gradient direction is calculated with the following formula:
the technical scheme of the invention has the following beneficial effects: according to the method for acquiring the fingerprint direction information, provided by the invention, the fingerprint image information is enhanced through preprocessing the fingerprint image, the accuracy of fingerprint extraction is improved, the time for post-processing the fingerprint information and the matching time are reduced, and the accuracy of the fingerprint direction information and the running speed for extracting the fingerprint direction information can be improved through extracting the fingerprint direction information by a sobel algorithm.
Drawings
FIG. 1 is a block diagram of fingerprint image preprocessing;
FIG. 2 is a schematic illustration of an original fingerprint image;
FIG. 3 is a schematic diagram after Gaussian low pass filtering;
FIG. 4 is a schematic diagram after mean filtering;
FIG. 5 is a flow chart of obtaining fingerprint direction information;
Detailed Description
In order that the objects, aspects and advantages of the invention will become more apparent, the invention will be described by way of example only, and in connection with the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, a method for acquiring fingerprint direction information according to the present invention includes the following steps:
establishing a two-dimensional mathematical model of a fingerprint;
secondly, preprocessing the fingerprint image;
step three, analyzing the fingerprint signal;
and step four, acquiring the direction information of the existing fingerprint graph according to the sobel algorithm.
In the fingerprint gray image with the resolution of 500dpi, the gray value variation range of each pixel point is 0-255, the average width of the lines is 8-10 pixels, and the characteristics of the fingerprint image meet the characteristics of amplitude modulation and frequency modulation signals with the amplitude and the frequency varying in a fixed range, so that the fingerprint image can be regarded as a two-dimensional amplitude modulation and frequency modulation signal.
The specific method for establishing the two-dimensional mathematical model of the fingerprint in the first step is as follows: the noise of each pixel point is stored in the image by a specific gray value, and a two-dimensional teaching model formula of the fingerprint is established as follows:
a (x, y) is a gray compensation value of the fingerprint image, b (x, y) is an amplitude of the modulation signal,
phase information of the fingerprint; n (x, y) is noise in the fingerprint image.
The fingerprint image preprocessing is used for removing variables which interfere with later analysis in a fingerprint model, and is the basis of the later analysis. The preprocessing can remove irrelevant variables, retain the original information of the fingerprint image, achieve the effect of enhancing fingerprint line information, reduce the storage space of the post-processing result, enable the post-processing process to be more efficient, improve the accuracy of feature extraction and reduce the time required by matching.
In the second step, the specific method for preprocessing the fingerprint image comprises the following steps:
step 1, smoothing an original fingerprint image by adopting a Gaussian low-pass filter to eliminate noise:
and 2, calculating a gray compensation value by using an average filter:
the noise in the fingerprint is usually high-frequency noise, which is generated during the fingerprint acquisition process in order to obtain information about the fingerprint
Adopting a Gaussian low-pass filter to smooth the original fingerprint image to eliminate noise and remove n (x, y) in a fingerprint model, wherein the working principle of the filter is that
u and v respectively represent horizontal and vertical coordinates on a frequency domain, m and n are origins, the size of sigma is related to the size of a frequency band, and the smaller the sigma is, the narrower the frequency band is; the larger σ, the wider the band.
In the third step, the specific method for analyzing the fingerprint signal is as follows: the amplitude b (x, y) and phase
The separation is performed to obtain a signal g (x, y) that only remains in amplitude and phase.
Dividing the fingerprint image I into subblocks of W and M N blocks, wherein the values of M and N depend on the size of the fingerprint image, and respectively operating each block;
step b, calculating the mean value Med (k, l) of the gray level of each sub-block
The gray value of the ith row and jth column of pixel points in the image subblock of the I (I, j) is 1,2,3.. M, and l is 1,2,3.. N, and Med (k, l) represents the gray value of the W × W subblock;
step c. calculating the gray variance Var (k, l) of each sub-block
And selecting a proper threshold, setting the sub-block gray variance belonging to the fingerprint information as a target area, namely a foreground area when the sub-block gray variance is larger than the threshold, and taking the sub-block gray variance as a background area, wherein the gray value of the background area is 255.
In the fourth step, a specific method for acquiring the direction information of the existing fingerprint graph according to the sobel algorithm comprises the following steps: d, dividing the fingerprint image into blocks with the size of W x W, and calculating a first-order partial derivative of each pixel point; step e, calculating the direction information of each image:
the sobel operator utilizes the pixel points of the neighborhood to calculate the gray value:
wherein A is the original image, GxAnd GyImages representing lateral and longitudinal edge detection, respectively;
the magnitude of the gradient is calculated using the above two equations, such as the following:
the gradient direction is calculated with the following formula:
Claims (5)
1. a method for obtaining fingerprint direction information, comprising the steps of:
establishing a two-dimensional mathematical model of a fingerprint;
secondly, preprocessing the fingerprint image;
step three, analyzing the fingerprint signal;
and step four, acquiring the direction information of the existing fingerprint graph according to the sobel algorithm.
2. The method for acquiring fingerprint direction information of claim 1, wherein: the specific method for establishing the two-dimensional mathematical model of the fingerprint in the first step is as follows: the noise of each pixel point is stored in the image by a specific gray value, and a two-dimensional teaching model formula of the fingerprint is established as follows:
a (x, y) is a gray compensation value of the fingerprint image, b (x, y) is an amplitude of the modulation signal,
phase information of the fingerprint; n (x, y) is noise in the fingerprint image.
3. The method for acquiring fingerprint direction information of claim 1, wherein: in the second step, the specific method for preprocessing the fingerprint image comprises the following steps:
step 1, smoothing an original fingerprint image by adopting a Gaussian low-pass filter to eliminate noise:
and 2, calculating a gray compensation value by using an average filter:
4. the method for acquiring fingerprint direction information of claim 1, wherein: in the third step, the specific method for analyzing the fingerprint signal is as follows: will amplitude valueb (x, y) and phase
Separating to obtain a signal g (x, y) only with amplitude and phase left;
dividing the fingerprint image I into subblocks of W and M N blocks, wherein the values of M and N depend on the size of the fingerprint image, and respectively operating each block;
step b, calculating the mean value Med (k, l) of the gray level of each sub-block
The gray value of the ith row and jth column of pixel points in the image subblock of the I (I, j) is 1,2,3.. M, and l is 1,2,3.. N, and Med (k, l) represents the gray value of the W × W subblock;
step c. calculating the gray variance Var (k, l) of each sub-block
5. The method for acquiring fingerprint direction information of claim 1, wherein: in the fourth step, a specific method for acquiring the direction information of the existing fingerprint graph according to the sobel algorithm comprises the following steps:
d, dividing the fingerprint image into blocks with the size of W x W, and calculating a first-order partial derivative of each pixel point;
step e, calculating the direction information of each image:
the sobel operator utilizes the pixel points of the neighborhood to calculate the gray value:
wherein A is the original image, GxAnd GyImages representing lateral and longitudinal edge detection, respectively;
the magnitude of the gradient is calculated using the above two equations, such as the following:
the gradient direction is calculated with the following formula:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010966749.7A CN112101213A (en) | 2020-09-15 | 2020-09-15 | Method for acquiring fingerprint direction information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010966749.7A CN112101213A (en) | 2020-09-15 | 2020-09-15 | Method for acquiring fingerprint direction information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101213A true CN112101213A (en) | 2020-12-18 |
Family
ID=73758635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010966749.7A Pending CN112101213A (en) | 2020-09-15 | 2020-09-15 | Method for acquiring fingerprint direction information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101213A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113094657A (en) * | 2021-04-30 | 2021-07-09 | 汪知礼 | Software use limiting method and system based on fingerprint identification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030086396A (en) * | 2002-05-04 | 2003-11-10 | 에버미디어 주식회사 | Recognising human fingerprint method and apparatus independent of location translation , rotation and recoding medium recorded program for executing the method |
| CN101329723A (en) * | 2008-08-04 | 2008-12-24 | 南京理工大学 | Method for rapidly positioning robust of finger print core point |
| CN106059753A (en) * | 2016-03-10 | 2016-10-26 | 西京学院 | Novel fingerprint key generation method for digital signature |
| CN107506742A (en) * | 2017-09-05 | 2017-12-22 | 哈尔滨理工大学 | Direction of fingerprint characteristic-acquisition method based on fringe |
| CN108921186A (en) * | 2018-05-08 | 2018-11-30 | 中国矿业大学 | A kind of fingerprint image categorizing system and method based on twin support vector machines |
-
2020
- 2020-09-15 CN CN202010966749.7A patent/CN112101213A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030086396A (en) * | 2002-05-04 | 2003-11-10 | 에버미디어 주식회사 | Recognising human fingerprint method and apparatus independent of location translation , rotation and recoding medium recorded program for executing the method |
| CN101329723A (en) * | 2008-08-04 | 2008-12-24 | 南京理工大学 | Method for rapidly positioning robust of finger print core point |
| CN106059753A (en) * | 2016-03-10 | 2016-10-26 | 西京学院 | Novel fingerprint key generation method for digital signature |
| CN107506742A (en) * | 2017-09-05 | 2017-12-22 | 哈尔滨理工大学 | Direction of fingerprint characteristic-acquisition method based on fringe |
| CN108921186A (en) * | 2018-05-08 | 2018-11-30 | 中国矿业大学 | A kind of fingerprint image categorizing system and method based on twin support vector machines |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113094657A (en) * | 2021-04-30 | 2021-07-09 | 汪知礼 | Software use limiting method and system based on fingerprint identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194919B (en) | Mobile phone screen defect detection method based on regular texture background reconstruction | |
| CN109509164B (en) | Multi-sensor image fusion method and system based on GDGF | |
| Sun et al. | Automated pavement distress detection using advanced image processing techniques | |
| CN102479383B (en) | Method and device for removing salt and pepper noise | |
| CN104200437A (en) | Image defogging method | |
| CN102819827A (en) | Self-adaption moment matching stripe noise removing method based on gray-level segmentation | |
| CN114549497A (en) | Method for detecting surface defects of walking board based on image recognition and artificial intelligence system | |
| CN108921813A (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| CN110717900A (en) | Pantograph abrasion detection method based on improved Canny edge detection algorithm | |
| CN112101213A (en) | Method for acquiring fingerprint direction information | |
| Xue et al. | Edge detection combining wavelet transform and canny operator based on fusion rules | |
| Wu et al. | Research on crack detection algorithm of asphalt pavement | |
| CN102314687B (en) | Method for detecting small targets in infrared sequence images | |
| CN111147804B (en) | Video frame reconstruction method | |
| CN114529715B (en) | Image identification method and system based on edge extraction | |
| CN106355576A (en) | SAR image registration method based on MRF image segmentation algorithm | |
| CN106951831B (en) | Pedestrian detection tracking method based on depth camera | |
| Xiong et al. | Research on an Edge Detection Algorithm of Remote Sensing Image Based on Wavelet Enhancement and Morphology. | |
| CN111553868B (en) | Tunnel reflectivity image filtering method based on improved sobel operator | |
| CN112084999A (en) | Method for acquiring fingerprint direction information through signal analysis | |
| Zhao et al. | A novel method for moving object detection in intelligent video surveillance systems | |
| CN105989351A (en) | Fingerprint image background segmentation method | |
| CN111738117A (en) | Method for detecting video key frame of electric bucket tooth based on deep learning | |
| CN110782405B (en) | Point target and dark spot image background balancing method based on gradient identification | |
| CN115578760B (en) | Control system and control method based on topographic relief vein recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201218 |