CN116434352A - Fingerprint library generation method, fingerprint identification device and storage medium - Google Patents
Fingerprint library generation method, fingerprint identification device and storage medium Download PDFInfo
- Publication number
- CN116434352A CN116434352A CN202310690277.0A CN202310690277A CN116434352A CN 116434352 A CN116434352 A CN 116434352A CN 202310690277 A CN202310690277 A CN 202310690277A CN 116434352 A CN116434352 A CN 116434352A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- fingerprint image
- image
- library
- standard
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000010586 diagram Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 abstract description 9
- 210000003811 finger Anatomy 0.000 description 9
- 210000003813 thumb Anatomy 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 3
- 241000282376 Panthera tigris Species 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
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
- G06V40/50—Maintenance of biometric data or enrolment thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
Abstract
The application provides a fingerprint library generation method, a fingerprint identification device and a storage medium. The fingerprint library generating method comprises the following steps: acquiring a current fingerprint image with a first overlapping area smaller than a preset area with each standard fingerprint image in a fingerprint library, and taking the current fingerprint image as a standby fingerprint image; when the number of standard fingerprint images in the fingerprint library is smaller than the preset number, adding the standby fingerprint images into the fingerprint library to serve as standard fingerprint images; when the number of standard fingerprint images in the fingerprint library is equal to the preset number, for the standby fingerprint images and all the standard fingerprint images, acquiring second overlapping areas of each fingerprint image and other fingerprint images, and determining and deleting the fingerprint image with the smallest sum of the second overlapping areas so as to enable the fingerprint images with the preset number to be reserved in the fingerprint library. The fingerprint image in the fingerprint database can be continuously updated, the quality of the fingerprint image in the fingerprint database is improved, the fingerprint collection area corresponding to the fingerprint database is increased, and the rejection rate and the false recognition rate of fingerprint verification are reduced.
Description
Technical Field
The application relates to the technical field of fingerprint identification, in particular to a fingerprint database generation method, a fingerprint identification device and a storage medium.
Background
With the wide application of biometric identification technology, more and more electronic devices adopt fingerprint identification technology to perform identity verification, namely fingerprint verification, on users, and unlocking, waking up, mobile payment and the like of the electronic devices are realized. The fingerprint verification process is to match the collected fingerprint image with the fingerprint image stored in the fingerprint library in advance, and the fingerprint is considered to pass verification when the fingerprint image is matched with the fingerprint image. When a user fingerprint image is input into a fingerprint library, the acquired fingerprint image has low precision or a region acquired by the fingerprint is concentrated due to changes such as temperature and humidity, so that the quality of the fingerprint image in the fingerprint library is low, and the rejection rate (FRR, false rejection rate) and the false recognition rate (FAR, false acceptance rate) in the fingerprint verification process are high. The rejection rate refers to the ratio of fingerprints that match scores of the same fingerprint are lower than corresponding thresholds and are considered as different fingerprints, in short, the ratio of fingerprints that should be successfully matched with each other is regarded as the ratio of fingerprints that cannot be matched with each other; the false recognition rate refers to the ratio of fingerprints that are considered to be identical because the matching score of different fingerprints is greater than the corresponding threshold, and in short, the ratio of fingerprints that should not be successfully matched is regarded as the ratio of fingerprints that are matched. The rejection rate is high or the false recognition rate is high, so that a user can recognize the fingerprint by pressing the fingerprint for many times, and the use experience of the user is affected.
Disclosure of Invention
In view of this, the application provides a fingerprint database generating method, a fingerprint identification device and a storage medium, which can solve the problems of poor fingerprint image quality and high rejection rate and false recognition rate caused by concentrated fingerprint acquisition areas in the fingerprint database.
The fingerprint library generation method provided by the application comprises the following steps:
acquiring at least one current fingerprint image successfully matched with a standard fingerprint image in a fingerprint library;
determining a first overlapping area of the current fingerprint image and each standard fingerprint image in a fingerprint library;
acquiring a current fingerprint image with the first overlapping area smaller than a preset area as a standby fingerprint image;
when the number of standard fingerprint images in the fingerprint library is smaller than a preset number, taking the standby fingerprint image as a standard fingerprint image and adding the standard fingerprint image into the fingerprint library;
and when the number of the standard fingerprint images in the fingerprint library is equal to the preset number, acquiring second overlapping areas of each fingerprint image and other fingerprint images for the standby fingerprint images and all the standard fingerprint images, and determining and deleting the fingerprint image with the smallest sum of the second overlapping areas so as to ensure that the preset number of fingerprint images are reserved in the fingerprint library.
Optionally, the matching of the standard fingerprint image with the at least one current fingerprint image in the fingerprint library is successful includes: and the current fingerprint image belongs to the same finger or has a preset relation with the standard fingerprint image.
Optionally, the means for acquiring any one of the first overlapping area and the second overlapping area includes:
aligning fingerprint feature points of the first fingerprint image and the second fingerprint image;
acquiring a block direction diagram of the second fingerprint image and a block direction diagram of a superposition part of the first fingerprint image and the second fingerprint image after fingerprint feature points are aligned, wherein the block direction diagram comprises a plurality of image blocks and the ridge line direction of each image block;
and obtaining the superposition area of the first fingerprint image and the second fingerprint image according to the ratio of the superposition part to the number of the blocks of the second fingerprint image.
Optionally, the method for obtaining the ridge line direction of any one of the tiles includes:
acquiring color difference values of each pixel in the block and adjacent pixels in the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction;
accumulating color difference values of all pixels in the block in the horizontal direction, in the vertical direction, in the first diagonal direction and in the second diagonal direction;
respectively giving corresponding weight coefficients to the included angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction according to the sum of the color difference values in the horizontal direction, the sum of the color difference values in the vertical direction, the sum of the color difference values in the first diagonal direction and the sum of the color difference values in the second diagonal direction;
and the sum of products of included angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction and corresponding weight coefficients is used as the ridge line direction of the block.
Optionally, the aligning the fingerprint feature points of the first fingerprint image and the second fingerprint image includes:
calculating the rotation angle of the first fingerprint image according to the direction deviation of the fingerprint feature points in the first fingerprint image and the second fingerprint image;
calculating the coordinates of the central points of the first fingerprint image and the second fingerprint image;
calculating a difference value of coordinates of a central point of the first fingerprint image and the second fingerprint image, and taking the difference value as a translation distance of the first fingerprint image;
and rotating the first fingerprint image according to the rotation angle and moving the first fingerprint image according to the translation distance so as to align fingerprint feature points of the first fingerprint image and the second fingerprint image.
Optionally, calculating the center point coordinates of any one of the first fingerprint image and the second fingerprint image includes: and calculating the coordinate mean value of the fingerprint feature points in the fingerprint image as the center point coordinate.
Optionally, the determining the fingerprint image with the smallest sum of the second overlapping areas includes:
obtaining scores corresponding to the second overlapping areas of the fingerprint images according to preset corresponding relations, wherein the preset corresponding relations comprise one-to-one corresponding relations between the overlapping areas and the scores;
and obtaining the sum of the scores corresponding to the fingerprint images, and selecting the corresponding fingerprint image according to the sum of the scores as the fingerprint image with the minimum sum of the second overlapping areas.
Optionally, the preset area is 80% of the area of the standard fingerprint image.
The application provides a fingerprint identification device, include:
the fingerprint acquisition module is used for acquiring fingerprint images;
a fingerprint identification module for executing the fingerprint library generation method as described in any one of the above.
The fingerprint identification device comprises a memory and a processor, wherein the memory stores a fingerprint library generating program, and the fingerprint library generating program realizes the fingerprint library generating method when being executed by the processor.
A storage medium provided herein stores a computer program that, when executed by a processor, implements a fingerprint library generation method as described in any one of the above.
As described above, the present fingerprint image with overlapping areas smaller than the preset area is obtained as the standby fingerprint image; when the number of standard fingerprint images in the fingerprint library is smaller than the preset number, adding the standby fingerprint images into the fingerprint library; when the number of standard fingerprint images in the fingerprint library is equal to the preset number, the overlapping areas of each fingerprint image and other fingerprint images are acquired for all the fingerprint images in the standby fingerprint image and the fingerprint library, and the fingerprint image with the smallest sum of the overlapping areas is deleted, which is equivalent to the fingerprint image with the larger sum of the overlapping areas in the fingerprint library. The fingerprint image acquisition method and the fingerprint image acquisition device can continuously update the fingerprint image in the fingerprint library, input the fingerprint image with smaller overlapping area, enable the fingerprint acquisition area corresponding to the fingerprint image in the fingerprint library to be larger, and are beneficial to reducing the rejection rate and the false recognition rate; furthermore, only the fingerprint image with larger sum of overlapping areas is reserved in the fingerprint library, so that the fingerprint image in the fingerprint library has good overlapping quality, the fingerprint image has good quality, the corresponding fingerprint acquisition areas are continuous, the rejection rate and the false recognition rate are reduced, and the fingerprint acquisition times during fingerprint verification are reduced.
Drawings
Fig. 1 is a schematic flow chart of a fingerprint library generating method according to an embodiment of the present application;
fig. 2 is a schematic diagram of a first fingerprint image and a block diagram thereof according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a second fingerprint image and a block diagram thereof according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of alignment of fingerprint feature points of a first fingerprint image and a second fingerprint image and corresponding block direction diagrams according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram showing the relative arrangement of one pixel and adjacent pixels in four directions in a single tile;
fig. 6 is a schematic structural diagram of a fingerprint identification apparatus according to an embodiment of the present application.
Detailed Description
In order to solve the above problems in the prior art, the present application provides a fingerprint library generating method, a fingerprint identification apparatus and a storage medium. The principles of solving the problems are basically the same or similar based on the same conception, and the embodiments of each of the protection subject matters can be referred to each other, and the repetition is omitted.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly described below with reference to specific embodiments and corresponding drawings. It will be apparent that the embodiments described below are only some, but not all, of the embodiments of the present application. The following embodiments and technical features thereof may be combined with each other without conflict, and also belong to the technical solutions of the present application.
Referring to fig. 1, a fingerprint library generating method in an embodiment of the present application includes steps S1 to S6.
S1: and acquiring at least one current fingerprint image successfully matched with the standard fingerprint image in the fingerprint library.
The current fingerprint image refers to a fingerprint image that successfully matches a standard fingerprint image in the fingerprint library. Alternatively, the so-called match success corresponds to at least one of the following:
For example, the fingerprint library is provided with standard fingerprint images of a plurality of fingers, and each finger can be correspondingly provided with one or more standard fingerprint images; the fingerprint image of the thumb of the left hand is collected this time, and if the standard fingerprint image of the thumb of the left hand is arranged in the fingerprint library, the fingerprint image of the thumb of the left hand collected this time can be identified as the current fingerprint image; otherwise, if any standard fingerprint image of the thumb of the left hand is not arranged in the fingerprint library, the fingerprint image of the thumb of the left hand collected at this time cannot be considered as the current fingerprint image, and then, the fingerprint images of other fingers are optionally collected and matched continuously.
Whether the finger belongs to the same finger or not can be judged by referring to the existing fingerprint identification algorithm, and the description is omitted here.
And 2, the condition has a preset relation with the standard fingerprint image.
The preset relationship may include: the fingerprint corresponding to the standard fingerprint image has continuous lines. For example, if a standard fingerprint image of the thumb of the left hand is set in the fingerprint library, the fingerprint image of the thumb of the left hand at the tiger mouth is collected this time, and the fingerprint lines of the thumb of the left hand at the tiger mouth (including palm print lines) are continuous, the fingerprint image can be considered as the current fingerprint image.
S2: and determining a first coincidence area of the current fingerprint image and each standard fingerprint image in the fingerprint library.
S3: and acquiring the current fingerprint image with the first overlapping areas smaller than the preset area as a standby fingerprint image.
Taking 2 current fingerprint images (respectively, the current fingerprint image 1 and the current fingerprint image 2) and N standard fingerprint images in a fingerprint library as examples, the overlapping areas of the current fingerprint image 1 and the N standard fingerprint images are respectively O 11 、O 12 、...、O 1N Obtaining N first overlapping areas; the first overlapping areas of the current fingerprint image 2 and the N standard fingerprint images are respectively O 21 、O 22 、...、O 2N 。
If all the first overlap areas O 11 、O 12 、...、O 1N The current fingerprint image 1 can be used as a standby fingerprint image if the current fingerprint image is smaller than the preset area; if the first overlap area O 21 、O 22 、...、O 2N If only one of them is greater than or equal to the preset area, the current fingerprint image 2 cannot be used as the spare fingerprint image.
The smaller the first overlapping area is, the more fingerprint collection areas corresponding to the current fingerprint image exceed the fingerprint collection areas corresponding to the fingerprint library, and the stronger the performance of the fingerprint collection areas corresponding to the fingerprint library is made up.
Optionally, the areas of the standard fingerprint images corresponding to the same finger in the fingerprint library are the same (for example, the length and the width are the same), and the preset area is 80% of the area of the standard fingerprint image.
S4: when the number of standard fingerprint images in the fingerprint library is smaller than the preset number, the standby fingerprint images are used as standard fingerprint images and added into the fingerprint library.
The preset number may set a maximum number of standard fingerprint images of a finger for the fingerprint library.
Taking a preset number of n+1 as an example, 1 standard fingerprint image can be added into the fingerprint library; if the first overlap area O 11 、O 12 、...、O 1N And if the current fingerprint image 1 is smaller than the preset area, the current fingerprint image 1 can be used as a standard fingerprint image and added into a fingerprint library, so that the fingerprint library is expanded.
S5: and when the number of the standard fingerprint images in the fingerprint library is equal to the preset number, acquiring second overlapping areas of each fingerprint image and other fingerprint images for the standby fingerprint image and all the standard fingerprint images.
S6: and determining the fingerprint image with the minimum sum of the second overlapping areas and deleting the fingerprint image so as to ensure that a preset number of fingerprint images are reserved in the fingerprint library.
Taking the preset number as N as an example, N standard fingerprint images are arranged in the fingerprint library, which means that the standard fingerprint images cannot be added in the fingerprint library, but only the standard fingerprint images in the fingerprint library can be updated. Further taking the current fingerprint images 1 and 2 as standby fingerprint images as examples, the N standard fingerprint images are respectively a standard fingerprint image 1 and a standard fingerprint image 2. The method comprises the following steps:
the overlapping areas of the current fingerprint image 1 and the current fingerprint image 2, the standard fingerprint image 1, the standard fingerprint image 2, the standard fingerprint image N are respectively obtained, and n+1 second overlapping areas are obtained;
the overlapping areas of the current fingerprint image 2 and the current fingerprint image 1, the standard fingerprint image 2, the standard fingerprint image N are respectively obtained, and n+1 second overlapping areas are obtained;
overlapping areas of the standard fingerprint image 1 and the current fingerprint image 1, the current fingerprint image 2, the standard fingerprint image N are respectively obtained, and n+1 second overlapping areas are obtained;
and so on, the overlapping areas of the standard fingerprint image N and the current fingerprint image 1, the current fingerprint image 2, the standard fingerprint image N-1 are respectively obtained, and n+1 second overlapping areas are obtained.
In step S6, the sum of the second overlapping areas of any one of the fingerprint images is the sum of n+1 second overlapping areas. If the sum of the second overlapping areas of the current fingerprint image 1 and the sum of the second overlapping areas of the standard fingerprint image N-1 are smaller than the sum of the second overlapping areas of any one of the other N fingerprint images, it may be determined that the fingerprint image with the smallest sum of the second overlapping areas is the current fingerprint image 1 and the standard fingerprint image N-1, and the updated fingerprint library includes: current fingerprint image 2, standard fingerprint image 1, standard fingerprint image 2,..the standard fingerprint image N-2, and standard fingerprint image N.
In step S6, if it is determined that the number of fingerprint images with the smallest sum of the second overlapping areas is larger, that is, the number of fingerprint images finally reserved in the fingerprint library is smaller than the preset number after all the fingerprint images are deleted, other rules may be introduced in the embodiment of the present application to screen the fingerprint images to be deleted, so that the fingerprint library finally reserves the preset number of fingerprint images. The other rules include, but are not limited to, at least one of: the method comprises the steps of reserving a fingerprint image with the effective area of the image being larger than a preset threshold, deleting the fingerprint image with the minimum image contrast, and deleting the fingerprint image with the image contrast being smaller than the preset contrast threshold.
In one implementation, the present application may employ scoring to obtain a second overlapping area of each fingerprint image and other fingerprint images, and determine a fingerprint image with a minimum sum of the second overlapping areas.
Firstly, presetting a one-to-one correspondence relation between a plurality of overlapping areas and a plurality of scores, namely, presetting the correspondence relation, wherein for example, the overlapping area is less than 50%, and the score is 4; the overlapping area is less than 60 percent, and the fraction is 3; the overlapping area is less than 70%, and the fraction is 2; the overlapping area is less than 80 percent, and the fraction is 1; other overlapping areas, the fraction is 0.
And then, obtaining the score corresponding to the second overlapping area of each fingerprint image according to the preset corresponding relation.
And finally, obtaining the sum of the scores corresponding to the fingerprint images, and selecting the corresponding fingerprint image according to the sum of the scores as the fingerprint image with the minimum sum of the second overlapping areas.
In summary, the fingerprint image in the fingerprint library can be continuously updated, and the step S4 is used for inputting the fingerprint image with smaller overlapping area, so that the fingerprint acquisition area corresponding to the fingerprint image in the fingerprint library is larger, the rejection rate is reduced, and the fingerprint acquisition times during fingerprint verification are reduced; further, through steps S5 and S6, only the fingerprint image with a larger sum of overlapping areas is reserved in the fingerprint library, which means that the fingerprint image in the fingerprint library has good overlapping quality, the fingerprint image has good quality and the corresponding fingerprint acquisition area is continuous, which is also beneficial to reducing the rejection rate, thereby reducing the fingerprint acquisition times during fingerprint verification.
Optionally, the manner in which the step S2 obtains the first overlapping area and/or the step S5 obtains the second overlapping area includes the following steps S21 to S23. It should be understood that for convenience of description, the present application refers to two fingerprint images having overlapping areas as a first fingerprint image and a second fingerprint image, respectively; here, in step S2, the first fingerprint image may be regarded as a current fingerprint image, and the second fingerprint image may be regarded as a standard fingerprint image in the fingerprint library; in step S5, the first fingerprint image may be a spare fingerprint image and the second fingerprint image may be standard fingerprint images, or the first fingerprint image and the second fingerprint image may be two spare fingerprint images.
Fig. 2 shows a schematic view of a first fingerprint image, fig. 3 shows a schematic view of a second fingerprint image, and fig. 4 shows a schematic view of the first fingerprint image and the second fingerprint image after alignment of fingerprint feature points. As shown in fig. 2 to 4, S21: and aligning the fingerprint feature points of the first fingerprint image and the second fingerprint image.
Alternatively, the rotation angle of the first fingerprint image is calculated from the direction deviations of the fingerprint feature points in the first fingerprint image and the second fingerprint image, for example, from the direction deviations of the corresponding fingerprint feature points (including singular points, end points, fork points, etc.) in the two fingerprint images, and the average value of the direction deviations of these fingerprint feature points is calculated as the rotation angle; then, a rectangular coordinate system shown in fig. 2 to 4 is established, the abscissa x and the ordinate y of which are shown in the arrow direction in the figure, and the center point coordinates (Cx 1, cy 1) of the first fingerprint image and the center point coordinates (Cx 2, cy 2) of the second fingerprint image are calculated, for example, the coordinate mean value of the fingerprint feature points in the single fingerprint image can be used as the corresponding center point coordinates; then, calculating a difference value of coordinates of central points of the first fingerprint image and the second fingerprint image, and taking the difference value as a translation distance of the first fingerprint image, wherein the translation distance comprises a translation distance of an abscissa and a translation distance of an ordinate; the first fingerprint image is rotated according to the rotation angle and moved according to the translation distance, as shown in the left diagram of fig. 4, so that the fingerprint feature points of the first fingerprint image and the second fingerprint image are aligned.
S22: and acquiring a block direction diagram of the second fingerprint image and a block direction diagram of a superposition part of the first fingerprint image and the second fingerprint image after the fingerprint feature points are aligned, wherein the block direction diagram comprises a plurality of image blocks and the ridge line direction of each image block.
As shown in fig. 3, the block direction diagram of the second fingerprint image includes a plurality of tiles and the ridge line direction of each tile; wherein the ridge line direction is in degrees. The plurality of blocks may be regarded as dividing the second fingerprint image into m×n (for example, 13×16 in the figure) blocks arranged in an array in a rectangular coordinate system, and the shapes and sizes of the blocks may be the same.
The ridge line direction of any tile can be obtained as follows:
as shown in fig. 5, each rectangular block represents one pixel. Acquiring color difference values of each pixel in the block and adjacent pixels in the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction; then, the color differences of all pixels in the block in the horizontal direction are accumulated and the sum X of the color difference accumulation is obtained 1 Adding up the color difference values in the vertical direction to obtain the sum X of the color difference value addition 2 Adding the color difference values in the first diagonal direction to obtain a color difference value added sum X 3 Adding the color difference values in the second diagonal direction to obtain a sum X of the color difference value addition 4 The method comprises the steps of carrying out a first treatment on the surface of the According to the sum X of the color difference 1 、X 2 、X 3 、X 4 Respectively giving corresponding weight coefficients to the angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction, for example, according to the sum X of the color difference 1 、X 2 、X 3 、X 4 To calculate the corresponding weight coefficient k 1 、k 2 、k 3 、k 4 And k is 1 +k 2 +k 3 +k 4 =1; the sum S of products of the included angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction and the corresponding weight coefficients is that S=k 1 *S 1 +k 2 *S 2 +k 3 *S 3 +k 4 *S 4 S is taken as the ridge line direction of the block, S 1 、S 2 、S 3 、S 4 Respectively represent the horizontal directionIncluded angles corresponding to the vertical direction, the first diagonal direction and the second diagonal direction, respectively, e.g. S 1 Can be 180 degrees, S 2 Can be 90 degrees, S 3 Can be 45 degrees, S 4 May be 135 deg..
By the above-described means, a block diagram of the overlapping portion can also be obtained, as shown in the right diagram of fig. 4. For the block of the non-overlapping part of the figure, the ridge line direction is directly marked as-1 instead of the above manner.
S23: and obtaining the superposition area of the first fingerprint image and the second fingerprint image according to the ratio of the superposition part to the number of the blocks of the second fingerprint image.
As shown in the right graph of fig. 4, the ridge line direction of the overlapping portion is located within 0-180 ° and is regarded as an effective image block, the number of the effective image blocks is 138, and the number of the image blocks of the second fingerprint image is 208, so that the overlapping area of the first fingerprint image and the second fingerprint image is 138/208=66%.
It should be appreciated that the manner in which the first overlap area and/or the second overlap area are calculated is not limited thereto. Geometric algorithms based on adding, deleting or translating fingerprint images, etc., may also be employed, for example.
As shown in fig. 6, another fingerprint recognition device 60 is provided in the embodiment of the present application, which includes a fingerprint acquisition module 61 and a fingerprint recognition module 62. The fingerprint acquisition module 61 is used for acquiring fingerprint images; the fingerprint identification module 62 is configured to perform the fingerprint library generating method according to any of the above embodiments.
The embodiment of the application also provides another fingerprint identification device, which comprises a memory and a processor, wherein the memory stores a fingerprint library generating program, and the fingerprint library generating program realizes the fingerprint library generating method according to any embodiment when being executed by the processor.
The embodiment of the application is not limited to the specific form of the fingerprint identification device, for example, the fingerprint identification device may be a fingerprint identification device, a fingerprint sensor, a fingerprint processor, etc. which are built in various electronic devices, and may be produced, transported, sold, etc. in the form of an independent module or device; as another example, the fingerprint recognition device may also be the electronic device itself.
Electronic devices include, but are not limited to, terminals with fingerprint library generation or fingerprint identification capabilities, such as smartphones, PDAs (Personal Digital Assistant, personal digital assistants or tablet computers), and wearable devices with fingerprint library generation or fingerprint identification capabilities worn on limbs or embedded in clothing, jewelry, accessories.
The embodiment of the application further provides a storage medium storing a computer program, where the computer program is executed by a processor to implement the fingerprint library generating method according to any one of the embodiments above.
The storage medium and the fingerprint identification device can respectively generate the beneficial effects of the fingerprint library generation method of the corresponding embodiment, which are not described herein.
It should be understood that the fingerprint identification apparatus 60 and the storage medium provided in the embodiments of the present application are respectively complete devices, and also have structures of known devices, and only the components related to the above fingerprint library update in the devices are described herein, and the other components are not described in detail.
The foregoing description is only a partial embodiment of the present application and is not intended to limit the scope of the patent application, and it is intended that all equivalent structural modifications made by those skilled in the art using the present description and accompanying drawings be included in the scope of the patent application.
Although the terms first, second, etc. are used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. In addition, the singular forms "a", "an" and "the" are intended to include the plural forms as well. The terms "or" and/or "are to be construed as inclusive, or mean any one or any combination. An exception to this definition will occur only when a combination of elements, functions, steps or operations are in some way inherently mutually exclusive.
Claims (10)
1. A fingerprint library generation method, comprising:
acquiring at least one current fingerprint image successfully matched with a standard fingerprint image in a fingerprint library;
determining a first overlapping area of the current fingerprint image and each standard fingerprint image in a fingerprint library;
acquiring a current fingerprint image with the first overlapping area smaller than a preset area as a standby fingerprint image;
when the number of standard fingerprint images in the fingerprint library is smaller than a preset number, taking the standby fingerprint image as a standard fingerprint image and adding the standard fingerprint image into the fingerprint library;
and when the number of the standard fingerprint images in the fingerprint library is equal to the preset number, acquiring second overlapping areas of each fingerprint image and other fingerprint images for the standby fingerprint images and all the standard fingerprint images, and determining and deleting the fingerprint image with the smallest sum of the second overlapping areas so as to ensure that the preset number of fingerprint images are reserved in the fingerprint library.
2. The method of claim 1, wherein the at least one current fingerprint image successfully matched with the standard fingerprint image in the fingerprint library comprises:
and the current fingerprint image belongs to the same finger or has a preset relation with the standard fingerprint image.
3. The method of claim 1, wherein the means for obtaining either of the first overlapping area and the second overlapping area comprises:
aligning fingerprint feature points of the first fingerprint image and the second fingerprint image;
acquiring a block direction diagram of the second fingerprint image and a block direction diagram of a superposition part of the first fingerprint image and the second fingerprint image after fingerprint feature points are aligned, wherein the block direction diagram comprises a plurality of image blocks and the ridge line direction of each image block;
and obtaining the superposition area of the first fingerprint image and the second fingerprint image according to the ratio of the superposition part to the number of the blocks of the second fingerprint image.
4. A method according to claim 3, wherein the manner in which the ridge line direction of any one of the tiles is obtained comprises:
acquiring color difference values of each pixel in the block and adjacent pixels in the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction;
accumulating color difference values of all pixels in the block in the horizontal direction, in the vertical direction, in the first diagonal direction and in the second diagonal direction;
respectively giving corresponding weight coefficients to the included angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction according to the sum of the color difference values in the horizontal direction, the sum of the color difference values in the vertical direction, the sum of the color difference values in the first diagonal direction and the sum of the color difference values in the second diagonal direction;
and the sum of products of included angles corresponding to the horizontal direction, the vertical direction, the first diagonal direction and the second diagonal direction and corresponding weight coefficients is used as the ridge line direction of the block.
5. A method according to claim 3, wherein aligning the minutiae of the first fingerprint image and the second fingerprint image comprises:
calculating the rotation angle of the first fingerprint image according to the direction deviation of the fingerprint feature points in the first fingerprint image and the second fingerprint image;
calculating the coordinates of the central points of the first fingerprint image and the second fingerprint image;
calculating a difference value of coordinates of a central point of the first fingerprint image and the second fingerprint image, and taking the difference value as a translation distance of the first fingerprint image;
and rotating the first fingerprint image according to the rotation angle and moving the first fingerprint image according to the translation distance so as to align fingerprint feature points of the first fingerprint image and the second fingerprint image.
6. The method of claim 5, wherein calculating center point coordinates of any one of the first fingerprint image and the second fingerprint image comprises:
and calculating the coordinate mean value of the fingerprint feature points in the fingerprint image as the center point coordinate.
7. The method of claim 1, wherein the determining a fingerprint image for which the sum of the second overlapping areas is minimal comprises:
obtaining scores corresponding to the second overlapping areas of the fingerprint images according to preset corresponding relations, wherein the preset corresponding relations comprise one-to-one corresponding relations between the overlapping areas and the scores;
and obtaining the sum of the scores corresponding to the fingerprint images, and selecting the corresponding fingerprint image according to the sum of the scores as the fingerprint image with the minimum sum of the second overlapping areas.
8. The method of claim 1, wherein the predetermined area is 80% of the area of the standard fingerprint image.
9. A fingerprint identification device is characterized in that,
the fingerprint recognition device includes:
the fingerprint acquisition module is used for acquiring fingerprint images;
a fingerprint identification module for performing the fingerprint library generation method of any one of claims 1 to 8;
or alternatively, the process may be performed,
the fingerprint recognition device includes:
a memory and a processor, the memory storing a fingerprint library generating program which when executed by the processor implements the fingerprint library generating method of any one of claims 1 to 8.
10. A storage medium storing a computer program which, when executed by a processor, implements the fingerprint library generating method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690277.0A CN116434352B (en) | 2023-06-12 | 2023-06-12 | Fingerprint library generation method, fingerprint identification device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690277.0A CN116434352B (en) | 2023-06-12 | 2023-06-12 | Fingerprint library generation method, fingerprint identification device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116434352A true CN116434352A (en) | 2023-07-14 |
| CN116434352B CN116434352B (en) | 2023-09-22 |
Family
ID=87081813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310690277.0A Active CN116434352B (en) | 2023-06-12 | 2023-06-12 | Fingerprint library generation method, fingerprint identification device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434352B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001243465A (en) * | 2000-03-01 | 2001-09-07 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for matching fingerprint image |
| CN1818927A (en) * | 2006-03-23 | 2006-08-16 | 北京中控科技发展有限公司 | Fingerprint identifying method and system |
| KR101180293B1 (en) * | 2011-08-03 | 2012-09-06 | 성균관대학교산학협력단 | Method for extracting direction-pattern feature of fingerprint and method for classifying fingerprint using direction-pattern feature |
| CN105205439A (en) * | 2015-02-13 | 2015-12-30 | 比亚迪股份有限公司 | Method for calculating area of fingerprint overlapping region and electronic device |
| CN106372609A (en) * | 2016-09-05 | 2017-02-01 | 广东欧珀移动通信有限公司 | Fingerprint template update method, fingerprint template update device and terminal equipment |
| US20180268196A1 (en) * | 2017-03-14 | 2018-09-20 | Samsung Electronics Co., Ltd. | Method and apparatus with fingerprint verification |
| CN109543492A (en) * | 2017-09-21 | 2019-03-29 | 比亚迪股份有限公司 | Fingerprint input method and device |
| CN115527241A (en) * | 2022-09-29 | 2022-12-27 | 杭州晟元数据安全技术股份有限公司 | Fingerprint template updating method and device, embedded equipment and storage medium |
-
2023
- 2023-06-12 CN CN202310690277.0A patent/CN116434352B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001243465A (en) * | 2000-03-01 | 2001-09-07 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for matching fingerprint image |
| CN1818927A (en) * | 2006-03-23 | 2006-08-16 | 北京中控科技发展有限公司 | Fingerprint identifying method and system |
| KR101180293B1 (en) * | 2011-08-03 | 2012-09-06 | 성균관대학교산학협력단 | Method for extracting direction-pattern feature of fingerprint and method for classifying fingerprint using direction-pattern feature |
| CN105205439A (en) * | 2015-02-13 | 2015-12-30 | 比亚迪股份有限公司 | Method for calculating area of fingerprint overlapping region and electronic device |
| CN106372609A (en) * | 2016-09-05 | 2017-02-01 | 广东欧珀移动通信有限公司 | Fingerprint template update method, fingerprint template update device and terminal equipment |
| US20180268196A1 (en) * | 2017-03-14 | 2018-09-20 | Samsung Electronics Co., Ltd. | Method and apparatus with fingerprint verification |
| CN109543492A (en) * | 2017-09-21 | 2019-03-29 | 比亚迪股份有限公司 | Fingerprint input method and device |
| CN115527241A (en) * | 2022-09-29 | 2022-12-27 | 杭州晟元数据安全技术股份有限公司 | Fingerprint template updating method and device, embedded equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈文燕 等: "基于密集连接卷积网络的小面积指纹识别方法", 计算机工程与应用, no. 10, pages 139 - 145 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116434352B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101829784B1 (en) | Fingerprint authentication using stitch and cut | |
| US20100080425A1 (en) | Minutiae-based template synthesis and matching | |
| JP3742279B2 (en) | Image collation apparatus, image collation method, and recording medium recording image collation program | |
| JP5574515B2 (en) | Biometric device and method | |
| CN107958443B (en) | Fingerprint image splicing method based on ridge line characteristics and TPS deformation model | |
| CN109829368B (en) | Palm feature recognition method and device, computer equipment and storage medium | |
| US8908934B2 (en) | Fingerprint recognition for low computing power applications | |
| US8781177B2 (en) | Method and computer program product for extracting feature vectors from a palm image | |
| EP1339008A2 (en) | Authentication method, and program and apparatus therefor | |
| KR20170083540A (en) | Creating templates for fingerprint authentication | |
| JP6900664B2 (en) | Image processing equipment, image processing method and image processing program | |
| JP2007094862A (en) | Information generation device, information generation method, information generation program and machine-readable recording medium | |
| EP2833319A1 (en) | Biometric authentication device, biometric authentication method, and biometric authentication computer program | |
| CN110728232A (en) | Hand region-of-interest acquisition method and hand pattern recognition method | |
| CN110248025B (en) | Identity recognition method, device and storage medium for multi-fingerprint and palm print information | |
| WO2017161636A1 (en) | Fingerprint-based terminal payment method and device | |
| US10102416B2 (en) | Biometric authentication device, biometric authentication method and computer-readable non-transitory medium | |
| JP2017174228A (en) | Image processing apparatus, image processing method and image processing program | |
| CN116434352B (en) | Fingerprint library generation method, fingerprint identification device and storage medium | |
| JP4588577B2 (en) | Palmprint authentication apparatus, palmprint authentication program, palmprint authentication method, palmprint image extraction method, and mobile phone terminal provided with palmprint authentication apparatus | |
| CN106156774B (en) | Image processing method and image processing system | |
| Ramoser et al. | Efficient alignment of fingerprint images | |
| CN115527241A (en) | Fingerprint template updating method and device, embedded equipment and storage medium | |
| JP4270842B2 (en) | Fingerprint verification device | |
| JP3742313B2 (en) | Image collation device, image collation method, program, and recording medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |