WO2017185507A1 - Method and device for identifying multiple fingerprints - Google Patents

Abstract

A method and device for identifying multiple fingerprints. The method comprises: collecting, from a fingerprint detection area of a terminal apparatus, a fingerprint image comprising two or more fingerprints (S1); identifying the fingerprints in the fingerprint image to acquire a first fingerprint and a second fingerprint (S2); computing a distance between the first fingerprint and the second fingerprint (S3); computing an angle between the first fingerprint and the second fingerprint (S4); and when the first fingerprint and the second fingerprint match prestored fingerprint templates, and errors between the computed distance and angle and a prestored distance and angle are less than or equal to preconfigured errors, unlocking the terminal apparatus (S5).

Description

Multi-fingerprint identification method and device Technical field

The present application relates to, but is not limited to, the field of image recognition technology, and in particular, to a method and device for identifying multiple fingerprints.

Background technique

With the development of fingerprint recognition technology, many terminal devices, such as smart phones, tablet computers, etc., are equipped with fingerprint recognition modules, which can realize functions such as screen unlocking through fingerprint recognition.

At present, the fingerprint identification module mainly collects fingerprint information through a fixed acquisition area, in order to fix the collection area and identify the fingerprint information of the entire area. At present, the fingerprint contact version of the smartphone on the market is about 1 square centimeter, and forms a concave surface with the body, which is convenient for the finger to judge the recognition area.

The fingerprint identification area of a typical terminal device is often small, just enough to accommodate a finger, and multiple fingerprints cannot be simultaneously identified. This kind of fingerprint recognition technology tends to be relatively simple and cannot meet more fingerprint recognition needs and better experience.

Therefore, there is currently a multi-fingerprint recognition technology. However, the multi-fingerprint recognition technology in the related art often recognizes multiple fingerprints as a whole, which is substantially different from a single fingerprint recognition, and still cannot satisfy the user. More needs.

Summary of the invention

The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.

In order to solve the above technical problem, an embodiment of the present invention provides a method and a device for identifying multiple fingerprints, so as to fully utilize the combination relationship between different fingerprints, and provide more fingerprint encryption and fingerprint recognition functions to the user.

A method for identifying multiple fingerprints, comprising:

Acquiring a fingerprint image from a fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprint.

Identifying the fingerprint in the fingerprint image to acquire the first fingerprint and the second fingerprint.

Calculating a distance between the first fingerprint and the second fingerprint.

Calculating an angle between the first fingerprint and the second fingerprint.

When the first fingerprint and the second fingerprint are both matched with the pre-stored fingerprint template, and the calculated distance between the distance and the angle and the pre-stored distance and angle is less than or equal to the preset When the error value is used, the terminal device is unlocked.

Optionally, identifying the fingerprint in the fingerprint image, obtaining the first fingerprint, and having the second fingerprint include:

Detecting an edge of the fingerprint in the fingerprint image, acquiring a first fingerprint having a first edge and a second fingerprint having a second edge.

Optionally, detecting an edge of the fingerprint in the fingerprint image includes:

The fingerprint image is subjected to grayscale processing to obtain a fingerprint grayscale image.

The fingerprint grayscale image is filtered by using a preset Gaussian function to obtain a filtered image that filters out noise.

A gradient magnitude and a gradient direction corresponding to each pixel in the filtered image are calculated.

A maximum value pixel point is determined in the filtered image based on the calculated gradient magnitude and the gradient direction.

A pixel point whose gray value is greater than or equal to a preset threshold is selected from the maximum value pixel points, and the selected pixel point is determined as an edge pixel point of the fingerprint.

Optionally, calculating a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image includes:

Calculating a first-order lateral partial derivative matrix and a first-order longitudinal partial derivative matrix corresponding to each pixel in the filtered image according to a preset lateral convolution operator and a longitudinal convolution operator.

Calculating a gradient magnitude and a gradient direction corresponding to each pixel according to the first equation according to the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix;

The first equation includes:

Q[i,j]=arctan(Q[i,j]/P[i,j]);

Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.

Optionally, determining the maximum value pixel points in the filtered image according to the calculated gradient magnitude and the gradient direction comprises:

Selecting a preset pixel point in the filtered image, and selecting a preset number of pixel points adjacent to the preset pixel point along a gradient direction of the preset pixel point, according to the calculated gradient amplitude Determining a relationship between a gray value of the preset pixel point and a gray value of each of the selected preset number of pixel points; when the gray value of the preset pixel point is greater than or equal to When the gray value of each of the preset number of pixels is selected, the preset pixel is determined as a maximum pixel.

Optionally, calculating a distance between the first fingerprint and the second fingerprint includes:

The center point of the fingerprint is determined according to the first expression.

Determining a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint.

The first expression includes:

among them,

Is the abscissa of the center point of the fingerprint,

Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint.

Determining a relative distance between a center point of the first fingerprint and the second fingerprint as a distance between the first fingerprint and the second fingerprint includes:

Calculating a relative distance between a center point of the first fingerprint and the second fingerprint according to a second expression; the second expression includes:

Where (Xa, Ya) is the center point coordinate of the first fingerprint, and (Xb, Yb) is the center point coordinate of the second fingerprint.

Optionally, calculating an angle between the first fingerprint and the second fingerprint includes:

Determining an angle of a texture of the first fingerprint and the second fingerprint with a vertical direction as a direction angle of the first fingerprint and the second fingerprint;

If the direction angles of the first fingerprint and the second fingerprint are θA and θB, respectively, the relative angle between the first fingerprint and the second fingerprint is θ=|θA-θB| The relative angle between the first fingerprint and the second fingerprint is determined as an angle between the fingerprints.

A multi-fingerprint identification device includes: a fingerprint collection unit, a fingerprint recognition unit, a distance calculation unit, an angle calculation unit, and an unlocking unit.

The fingerprint collection unit is configured to collect a fingerprint image from the fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprints.

The fingerprint identification unit is configured to identify the fingerprint in the fingerprint image, and acquire the first fingerprint and the second fingerprint.

The distance calculation unit is configured to calculate a distance between the first fingerprint and the second fingerprint.

An angle calculation unit is configured to calculate an angle between the first fingerprint and the second fingerprint.

An unlocking unit configured to match the first fingerprint and the second fingerprint with a pre-stored fingerprint template, and calculate an error between the distance and the angle and a pre-stored distance and angle When the preset error value is less than or equal to, the terminal device is unlocked.

Optionally, the fingerprint identification unit comprises an edge detection module.

The fingerprint identification unit identifies the fingerprint in the fingerprint image, and acquiring the first fingerprint and having the second fingerprint includes:

The edge detection module is configured to detect an edge of the fingerprint in the fingerprint image, and acquire a first fingerprint having a first edge and a second fingerprint having a second edge.

Optionally, the edge detection module includes a grayscale processing submodule, a filtering submodule, a gradient calculation submodule, a maximum value pixel determination submodule, and a screening submodule.

The detecting, by the edge detecting module, the edge of the fingerprint in the fingerprint image comprises:

The grayscale processing submodule is configured to perform grayscale processing on the fingerprint image to obtain a fingerprint grayscale image.

The filtering submodule is configured to filter the fingerprint grayscale image by using a preset Gaussian function to obtain a filtered image that filters out noise.

The gradient calculation sub-module is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image.

A maximum value pixel determination sub-module is arranged to determine a maximum value pixel point in the filtered image based on the calculated gradient magnitude and the gradient direction.

The screening sub-module is configured to filter, from the maximum-value pixel, a pixel point whose gray value is greater than or equal to a preset threshold, and determine the selected pixel point as an edge pixel point of the fingerprint.

Optionally, the gradient calculation sub-module includes: a partial derivative matrix calculation sub-module and an amplitude direction calculation sub-module.

The gradient calculation sub-module calculates a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image, including:

The partial derivative matrix calculation submodule is configured to calculate a first-order lateral partial derivative matrix and a first-order vertical partial derivative matrix corresponding to each pixel in the filtered image according to a preset lateral convolution operator and a longitudinal convolution operator .

The amplitude direction calculation submodule is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel according to the first equation according to the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix.

The first equation includes:

Q[i,j]=arctan(Q[i,j]/P[i,j]);

Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.

Optionally, the maximum value pixel point determining submodule comprises: a gray value comparison submodule.

The maximum value pixel point determination sub-module is based on the calculated gradient magnitude and the gradient square Determining the maximum value pixel points in the filtered image includes:

a gray value comparison sub-module, configured to select a preset pixel point in the filtered image, and select a preset number of pixel points adjacent to the preset pixel point along a gradient direction of the preset pixel point, Determining, according to the calculated gradient magnitude, a magnitude relationship between a grayscale value of the preset pixel point and a gray value of each of the selected preset number of pixel points; when the preset When the gray value of the pixel is greater than or equal to the gray value of each of the selected preset number of pixels, the preset pixel is determined as the maximum pixel.

Optionally, the distance calculation unit includes: a center point determination submodule and a distance determination submodule.

The calculating, by the distance calculation unit, the distance between the first fingerprint and the second fingerprint includes:

The center point determination module is set to determine the center point of the fingerprint according to the following formula:

among them,

Is the abscissa of the center point of the fingerprint,

Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint.

The distance determining sub-module determines a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint, including:

Calculating a relative distance between a center point of the first fingerprint and the second fingerprint according to a second expression;

The second expression includes:

Where (Xa, Ya) is the center point coordinate of the first fingerprint, and (Xb, Yb) is the center point coordinate of the second fingerprint.

Optionally, the angle calculation unit calculates an angle between the first fingerprint and the second fingerprint, including:

An angle between a texture of the first fingerprint and the second fingerprint and a vertical direction is determined as a direction angle of the first fingerprint and the second fingerprint.

If the direction angles of the first fingerprint and the second fingerprint are θA and θB, respectively, the relative angle between the first fingerprint and the second fingerprint is θ=|θA-θB| The relative angle between the first fingerprint and the second fingerprint is determined as an angle between the fingerprints.

A computer readable storage medium storing computer executable instructions that, when executed by a processor, implement the multi-fingerprint identification method.

BRIEF abstract

FIG. 1 is a flowchart of a method for identifying multiple fingerprints according to an embodiment of the present invention;

2 is a schematic structural diagram of a fingerprint identification board according to an embodiment of the present invention;

3 is a schematic diagram of fingerprints collected in an embodiment of the present invention;

FIG. 4 is a functional block diagram of a multi-fingerprint identification device according to an embodiment of the present invention.

Embodiments of the invention

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the features in the embodiments and the embodiments in the present application may be arbitrarily combined with each other.

The steps illustrated in the flowchart of the figures may be executed in a computer system such as a set of computer executable instructions. Also, although logical sequences are shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than the ones described herein.

FIG. 1 is a flowchart of a method for identifying multiple fingerprints according to an embodiment of the present invention. Although the processes described below include multiple operations occurring in a particular order, it should be clearly understood that these processes can include more or fewer operations that can be performed sequentially or in parallel (eg, using a parallel processor or a multi-threaded environment). . As shown in FIG. 1, the method may include steps S1-S5:

S1: Collect a fingerprint image from a fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprints.

Please refer to Figure 2. In this embodiment, a fingerprint identification board may be disposed on the back side of the terminal device, and multiple fingerprint recognition controls may be disposed on the fingerprint identification board. For example, in FIG. 2, two fingerprints may be set on the fingerprint identification board. Identifying controls, the two fingerprint recognition controls can be Fingerprint detection area. In this embodiment, the user can enter the fingerprints of the two fingers into the terminal device through the two fingerprint recognition controls, so that the fingerprint image can be collected from the fingerprint detection area of the terminal device. In implementation, the user can simultaneously place two fingers on two fingerprint recognition controls to capture the fingerprints of the two fingers at the same time. In addition, after using one fingerprint recognition control to collect the fingerprint of one finger, another fingerprint identification control is used to collect the fingerprint of the other finger. That is to say, in the present embodiment, the order of multiple fingerprint collections is not limited, whether it is simultaneous recognition or sequential recognition, and finally, the fingerprints collected by the fingerprint recognition control are displayed on one fingerprint image.

It should be noted that, in this embodiment, only two fingerprint recognition controls and two fingerprints are used for description, but those skilled in the art should know that the technical solutions of the embodiments of the present invention are equally applicable to two or more fingerprint recognition controls. And more than two fingerprints. In the embodiment of the present invention, for the convenience of description, only two fingerprints are used for explanation.

S2: Identify the fingerprint in the fingerprint image, and acquire the first fingerprint and the second fingerprint.

In this embodiment, after the fingerprint image including at least two fingerprints is collected from the fingerprint detection area, the fingerprints in the fingerprint image may be identified to distinguish different fingerprints from each other. In this embodiment, the fingerprint in the fingerprint image may be identified to acquire the first fingerprint and the second fingerprint. In this embodiment, an edge of the fingerprint in the fingerprint image may be detected to acquire a first fingerprint having a first edge and a second fingerprint having a second edge.

Please refer to Figure 3. In Fig. 3, the dotted square frame outside the fingerprint can be used as the edge of the fingerprint. In the present embodiment, the edge of the fingerprint in the fingerprint image can be detected in accordance with the following steps.

S21: Perform grayscale processing on the fingerprint image to obtain a fingerprint grayscale image.

In this embodiment, if the fingerprint image collected from the fingerprint detection area is a color image, the color image may be subjected to gradation processing to meet the needs of subsequent processing. The color image is usually displayed by the color change of three channels of R (Red, Red), G (Green, Green), B (Blue, Blue), and the superposition between them. In this embodiment, each can be The pixel values of the channels are weighted averaged to convert the pixel values of the three channels of RGB into grayscale values. Optionally, in the embodiment, the fingerprint image may be grayed out according to any one of the following formulas:

Formula 1: Gray=(R+G+B)/3;

Formula 2: Gray = 0.299R + 0.587G + 0.114B;

Where R, G, and B represent the pixel values of the R channel, the G channel, and the B channel, respectively, and Gray represents the gray value after the graying process.

In the present embodiment, if the fingerprint image is not an image in the RGB format, the format of the fingerprint image may be first converted into an RGB format, and then the gradation processing is performed.

S22: Perform filtering processing on the fingerprint grayscale image by using a preset Gaussian function to obtain a filtered image that filters out noise.

In the present embodiment, it is considered that in the fingerprint grayscale image, there is often more noise, and the noise may seriously affect the accuracy of the processing result in the subsequent processing. Therefore, in the present embodiment, the fingerprint grayscale image may be subjected to filtering processing to obtain a filtered image that filters out noise. Optionally, a preset Gaussian function may be used as the filter function in this embodiment. The preset Gaussian function can be, for example:

In this embodiment, the pixel matrix of the fingerprint grayscale image may be subjected to a convolution operation with the Gaussian function described above, so that noise in the fingerprint grayscale image may be filtered out to obtain the fingerprint grayscale. The filtered image corresponding to the image.

S23: Calculate a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image.

In this embodiment, the edge of the fingerprint in the filtered image may be determined by calculating a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image. In the present embodiment, the gradient magnitude and the gradient direction corresponding to each pixel point can be calculated by the first-order partial derivative matrix. Optionally, in the embodiment, the first-order partial derivative matrix may be divided into a lateral partial derivative matrix (x-axis direction) and a longitudinal partial derivative matrix (y-axis direction). Therefore, a lateral convolution operator (x-axis direction) and a longitudinal convolution operator (y-axis direction) can be specified in advance, and each pixel point in the filtered image is separately convoluted by the two convolution operators Thus, a corresponding first-order partial derivative matrix can be obtained.

In this embodiment, the lateral convolution operator and the vertical convolution operator can be as follows:

Where s _x is the lateral convolution operator and s _y is the longitudinal convolution operator.

The first-order partial derivative matrix obtained by processing each pixel in the filtered image by using the lateral convolution operator and the vertical convolution operator may be as follows:

P[i,j]=(f[i,j+1]-f[i,j]+f[i+1,j+1]-f[i+1,j])/2;

Q[i,j]=(f[i,j]-f[i+1,j]+f[i,j+1]-f[i+1,j+1])/2;

Where P[i,j] represents the first-order lateral partial derivative corresponding to the pixel of the i-th row and the j-th column, and Q[i,j] represents the first-order longitudinal partial derivative corresponding to the pixel of the i-th row and the j-th column, f[i,j] represents the pixel value corresponding to the pixel of the i-th row and the j-th column.

After the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix are calculated, the gradient magnitude and the gradient direction corresponding to each pixel point can be calculated according to the first equation.

The first equation includes:

Q[i,j]=arctan(Q[i,j]/P[i,j])

Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.

S24: Determine a maximum value pixel point in the filtered image according to the calculated gradient magnitude and the gradient direction.

In this embodiment, the gray value of the pixel in the filtered image changes along the gradient direction of the pixel, and the point where the gray value is the largest in the local area adjacent to the pixel often falls in the The pixel points correspond to the gradient direction. In the present embodiment, the pixel point whose gradation value is the largest in the adjacent partial region may be referred to as a maximum value pixel point. Since the pixel point on the edge of the fingerprint is in the local area adjacent thereto, the gray value is often the largest, and therefore, in the present embodiment, the maximum value pixel point can be determined in the filtered image. Optionally, a preset pixel point may be selected in a preset area in the filtered image, and a preset number of pixel points adjacent to the preset pixel point are selected along a gradient direction of the preset pixel point. . In the implementation process, it is often possible to select 8 pixel points adjacent to the preset pixel point. Determining, according to the calculated gradient magnitude, a magnitude relationship between a grayscale value of the preset pixel point and a gray value of each of the selected preset number of pixel points; when the preset The gray value of the pixel is greater than or equal to each of the preset number of pixels When the gray value is used, the preset pixel point may be determined as a maximum value pixel point.

It should be noted that, since the pixel points in the gradient direction corresponding to the preset pixel points may not be in the selected 8 pixel points, in this case, the gradient direction needs to be according to the 8 pixel points. Interpolating the pixel points to determine a gray value of the pixel in the gradient direction, so that the preset pixel point can be compared with the pixel point in the gradient direction to determine the preset pixel point Whether it is a maximum value pixel.

S25: Select, from the maximum value pixel, a pixel point whose gray value is greater than or equal to a preset threshold, and determine the selected pixel point as an edge pixel point of the fingerprint.

In the present embodiment, due to the calculation error or the influence of the interference pixel point, there may be pixel points not on the edge among the maximum value pixel points determined in step S24. In this case, it is necessary to judge the gradation value of the determined maximum value pixel again to remove the pixel having a lower gradation value. Optionally, in the embodiment, a pixel point whose gray value is greater than or equal to a preset threshold may be selected from the maximum value pixel points, and the selected pixel point is determined as an edge pixel point of the fingerprint. .

Thus, by the above processing steps, the first fingerprint having the first edge and the second fingerprint having the second edge in the fingerprint image can be obtained. The first edge and the second edge may be rectangular dashed boxes as shown in FIG.

S3: Calculate a distance between the first fingerprint and the second fingerprint.

In this embodiment, after the first fingerprint and the second fingerprint are recognized from the fingerprint image, the distance between the first fingerprint and the second fingerprint may be calculated to represent the first fingerprint and the second fingerprint. Positional relationship. Optionally, the distance between the first fingerprint and the second fingerprint may be represented by a distance between two fingerprint center points. The center point of the first fingerprint and the second fingerprint may be determined by coordinate values of four vertices on the first edge and the second edge. Optionally, in the embodiment, the first fingerprint may be determined according to coordinate values of pixel points of the uppermost, lowermost, leftmost, and rightmost sides on the first edge and the second edge. The first center point and the second center point of the second fingerprint.

Optionally, the calculating a distance between the first fingerprint and the second fingerprint includes:

Determining the center point of the fingerprint according to the first expression;

Determining a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint;

The first expression includes:

among them,

Is the abscissa of the center point of the fingerprint,

Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint.

In this way, after determining the first center point and the second center point, the distance between the first center point and the second center point may be determined as being between the first fingerprint and the second fingerprint the distance. The distance determining sub-module determines a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint, including: according to the second expression Calculating a relative distance between a center point of the first fingerprint and the second fingerprint.

The second expression includes:

Where (Xa, Ya) is the center point coordinate of the first fingerprint, (Xb, Yb) is the center point coordinate of the second fingerprint, and L is between the first center point and the second center point a distance, x _a is the abscissa of the center point of the first fingerprint, y _{a is} the ordinate of the center point of the first fingerprint, and x _b is the abscissa of the center point of the second fingerprint, y _b The ordinate of the center point of the second fingerprint.

S4: Calculate an angle between the first fingerprint and the second fingerprint.

In this embodiment, the positional relationship between the first fingerprint and the second fingerprint may include an angle between the two, in addition to the distance between the two. Optionally, in this embodiment, a direction perpendicular to a texture of the first fingerprint may be determined as a first direction of the first fingerprint, and a direction perpendicular to a texture of the second fingerprint may be determined. a second direction of the second fingerprint, and determining an angle between the first direction and the second direction as an angle between the first fingerprint and the second fingerprint. As shown in FIG. 3, the direction of the oblique line corresponding to the left fingerprint may be the first direction, and the direction of the vertical line corresponding to the right fingerprint may be the second direction, then this The angle between the two straight lines may be an angle between the first fingerprint and the second fingerprint.

S5: when both the first fingerprint and the second fingerprint match the pre-stored fingerprint template, and the calculated distance between the distance and the angle and the pre-stored distance and angle is less than or equal to When the error value is preset, the terminal device is unlocked.

In this embodiment, after determining the positional relationship between the first fingerprint and the second fingerprint, the first fingerprint and the second fingerprint may be recognized while identifying the first fingerprint and the second fingerprint. The positional relationship between the two is determined to determine that the first fingerprint and the second fingerprint in the current positional relationship can unlock the terminal device. Optionally, in the embodiment, the first fingerprint and the second fingerprint may be matched first, and the user may input multiple fingerprints in the terminal device that can unlock the terminal device to form a fingerprint template. Then, after the first fingerprint and the second fingerprint are recognized from the fingerprint image, the first fingerprint and the second fingerprint may be compared with the fingerprint template, when the first fingerprint and the second fingerprint are both present in the fingerprint When the template is in the template, it is determined that the first fingerprint and the second fingerprint match the fingerprint template.

In this embodiment, the condition that the first fingerprint and the second fingerprint match the fingerprint template cannot be used to unlock the terminal device, and the first fingerprint and the second fingerprint are required to be The positional relationship is judged. Similarly, the distance and the angle between the first fingerprint and the second fingerprint can also be pre-recorded into the terminal device by the user, and then the distance and angle between the first fingerprint and the second fingerprint in the fingerprint image are calculated. Thereafter, the calculated distance and the included angle may be compared with a pre-stored distance and angle, when the calculated distance and the angle between the angle and the pre-stored distance and angle are less than or When it is equal to the preset error value, it indicates that the positional relationship between the current first fingerprint and the second fingerprint matches the preset positional relationship. Then, in the case where the fingerprint matching and the positional relationship between the fingerprints also match, the terminal device can be unlocked.

It can be seen from the above that the multi-fingerprint identification method provided by the embodiment of the present invention can obtain multiple fingerprints in the fingerprint image by identifying the collected fingerprint image. By calculating the distance and angle relationship between the plurality of fingerprints, the calculated distance and angle can be compared with the pre-stored distance and angle. In this way, when a plurality of fingerprints are present in the preset fingerprint database, and the positional relationship between the plurality of fingerprints also satisfies the preset positional relationship, the terminal device can be unlocked. It can be seen that the multi-fingerprint identification method provided by the embodiment of the present invention adds a process of matching the positional relationship between the fingerprints on the basis of fingerprint matching. It not only enhances the security of encryption, but also enhances the user's interest in designing fingerprint positional relationships.

An embodiment of the present invention further provides a multi-fingerprint identification device. FIG. 4 is a functional block diagram of a multi-fingerprint identification device according to an embodiment of the present invention. As shown in FIG. 4, the apparatus may include: a fingerprint collection unit 100, a fingerprint recognition unit 200, a distance calculation unit 300, an angle calculation unit 400, and an unlocking unit 500.

The fingerprint collection unit 100 is configured to collect a fingerprint image from a fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprints;

The fingerprint identification unit 200 is configured to identify the fingerprint in the fingerprint image, and acquire the first fingerprint and the second fingerprint;

The distance calculating unit 300 is configured to calculate a distance between the first fingerprint and the second fingerprint;

The angle calculation unit 400 is configured to calculate an angle between the first fingerprint and the second fingerprint;

The unlocking unit 500 is configured to match the first fingerprint and the second fingerprint with a pre-stored fingerprint template, and calculate the distance between the distance and the angle and the pre-stored distance and angle When the error is less than or equal to the preset error value, the terminal device is unlocked.

In an optional implementation manner of the embodiment of the present invention, the fingerprint identification unit 200 specifically includes: an edge detection module.

The fingerprint identification unit identifies the fingerprint in the fingerprint image, and acquiring the first fingerprint and having the second fingerprint includes:

The edge detection module is configured to detect an edge of the fingerprint in the fingerprint image, and acquire a first fingerprint having a first edge and a second fingerprint having a second edge.

Optionally, the edge detection module 200 includes a grayscale processing sub-module 201, a filtering sub-module 202, a gradient calculation sub-module 203, a maximum-value pixel determination sub-module 204, and a screening sub-module 205.

The detecting, by the edge detecting module 200, the edge of the fingerprint in the fingerprint image includes:

The grayscale processing sub-module 201 is configured to perform grayscale processing on the fingerprint image to obtain a fingerprint grayscale image.

The filtering sub-module 202 is configured to perform filtering processing on the fingerprint grayscale image by using a preset Gaussian function to obtain a filtered image that filters out noise.

The gradient calculation sub-module 203 is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel point in the filtered image.

The maximum value pixel determination sub-module 204 is configured to determine a maximum value pixel point in the filtered image based on the calculated gradient magnitude and the gradient direction.

The filtering sub-module 205 is configured to filter, from the maximum-value pixel, a pixel point whose gray value is greater than or equal to a preset threshold, and determine the selected pixel point as an edge pixel of the fingerprint.

In an optional implementation manner of the embodiment of the present invention, the gradient calculation sub-module 203 includes: a partial derivative matrix calculation sub-module and an amplitude direction calculation sub-module.

The gradient calculation sub-module 203 calculates a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image, including:

The partial derivative matrix calculation submodule is configured to calculate a first-order lateral partial derivative matrix and a first-order vertical partial derivative matrix corresponding to each pixel in the filtered image according to a preset lateral convolution operator and a longitudinal convolution operator .

The amplitude direction calculation submodule is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel according to the first equation according to the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix.

The first equation includes:

Q[i,j]=arctan(Q[i,j]/P[i,j])

Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.

In an optional implementation manner of the embodiment of the present invention, the maximum value pixel point determining sub-module 204 includes: a gray value comparison sub-module.

The maximum value pixel determination sub-module 204 determines the maximum value pixel in the filtered image according to the calculated gradient magnitude and the gradient direction, including:

a gray value comparison sub-module, configured to select a preset pixel point in the filtered image, and select a preset number of pixel points adjacent to the preset pixel point along a gradient direction of the preset pixel point And determining, according to the calculated gradient amplitude, a magnitude relationship between the gray value of the preset pixel point and the gray value of each pixel point in the selected preset number of pixel points; When the gray value of the pixel is greater than or equal to the gray value of each of the selected preset number of pixels, the preset pixel is determined as the maximum pixel.

In an optional implementation manner of the embodiment of the present invention, the distance calculation unit 300 includes a center point determination sub-module 301 and a distance determination sub-module 302.

The calculating, by the distance calculating unit 300, the distance between the first fingerprint and the second fingerprint includes:

The central point determining submodule 301 is configured to determine a center point of the fingerprint according to the first expression.

The distance determining sub-module 302 is configured to determine a relative distance between a center point of the first fingerprint and the second fingerprint as a distance between the first fingerprint and the second fingerprint.

The first expression includes:

among them,

Is the abscissa of the center point of the fingerprint,

Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint.

The determining, by the distance determining sub-module 302, the relative distance between the center point of the first fingerprint and the second fingerprint as the distance between the first fingerprint and the second fingerprint includes:

Calculating a relative distance between a center point of the first fingerprint and the second fingerprint according to a second expression.

The second expression includes:

Where (Xa, Ya) is the center point coordinate of the first fingerprint, and (Xb, Yb) is the center point coordinate of the second fingerprint.

In an optional implementation manner of the embodiment of the present invention, the included angle calculation unit 400 includes a first direction determining module 401, a second direction determining module 402, and an angle determining module 403.

The angle calculation unit 400 calculates an angle between the first fingerprint and the second fingerprint, including:

The first direction determining module 401 is configured to determine a direction perpendicular to the texture of the first fingerprint as the first direction θA of the first fingerprint.

The second direction determining module 402 is configured to determine a direction perpendicular to the texture of the second fingerprint as the second direction θB of the second fingerprint.

The angle determining module 403 is configured to determine an angle θ=|θA−θB| between the first direction and the second direction as an angle between the first fingerprint and the second fingerprint .

It should be noted that the implementation manner of each of the foregoing functional modules is consistent with the description in steps S1 to S5, and details are not described herein again.

It can be seen from the above that the multi-fingerprint identification device provided by the embodiment of the present invention can obtain multiple fingerprints in the fingerprint image by identifying the collected fingerprint image. By calculating the distance and angle relationship between the plurality of fingerprints, the calculated distance and angle can be compared with the pre-stored distance and angle. In this way, when a plurality of fingerprints are present in the preset fingerprint database, and the positional relationship between the plurality of fingerprints also satisfies the preset positional relationship, the terminal device can be unlocked. It can be seen that the multi-fingerprint identification device provided by the embodiment of the present invention adds a process of matching the positional relationship between the fingerprints on the basis of fingerprint matching, which not only enhances the security of encryption. And also enhances the user's interest in designing fingerprint positional relationships.

A computer readable storage medium storing computer executable instructions that, when executed by a processor, implement the multi-fingerprint identification method.

One of ordinary skill in the art will appreciate that all or a portion of the steps of the above-described embodiments can be implemented using a computer program flow, which can be stored in a computer readable storage medium, such as on a corresponding hardware platform (eg, The system, device, device, device, etc. are executed, and when executed, include one or a combination of the steps of the method embodiments.

Alternatively, all or part of the steps of the above embodiments may also be implemented using an integrated circuit. The steps may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps may be fabricated into a single integrated circuit module.

The devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.

When the device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. The above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Industrial applicability

The method and device for identifying multiple fingerprints provided by the embodiments of the present invention can obtain multiple fingerprints in the fingerprint image by identifying the collected fingerprint image. By calculating the distance and angle relationship between the plurality of fingerprints, the calculated distance and angle can be compared with the pre-stored distance and angle. In this way, when a plurality of fingerprints are present in the preset fingerprint database, and the positional relationship between the plurality of fingerprints also satisfies the preset positional relationship, the terminal device can be unlocked. The solution of the embodiment of the present invention adds a process of matching the positional relationship between fingerprints on the basis of fingerprint matching, which not only enhances the security of encryption, but also enhances the interest of the user in designing the positional relationship of the fingerprint.

Claims (15)

1. A method for identifying multiple fingerprints, comprising:

   Collecting a fingerprint image from a fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprints;

   Identifying a fingerprint in the fingerprint image to obtain a first fingerprint and a second fingerprint;

   Calculating a distance between the first fingerprint and the second fingerprint;

   Calculating an angle between the first fingerprint and the second fingerprint;

   When the first fingerprint and the second fingerprint are both matched with the pre-stored fingerprint template, and the calculated distance between the distance and the angle and the pre-stored distance and angle is less than or equal to the preset When the error value is used, the terminal device is unlocked.
2. The method for identifying a multi-fingerprint according to claim 1, wherein the identifying the fingerprint in the fingerprint image, obtaining the first fingerprint and having the second fingerprint comprises:

   Detecting an edge of the fingerprint in the fingerprint image, acquiring a first fingerprint having a first edge and a second fingerprint having a second edge.
3. The method for identifying a multi-fingerprint according to claim 2, wherein the detecting the edge of the fingerprint in the fingerprint image comprises:

   Performing grayscale processing on the fingerprint image to obtain a fingerprint grayscale image;

   Filtering the fingerprint grayscale image by using a preset Gaussian function to obtain a filtered image that filters out noise;

   Calculating a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image;

   Determining a maximum value pixel point in the filtered image according to the calculated gradient magnitude and the gradient direction;

   A pixel point whose gray value is greater than or equal to a preset threshold is selected from the maximum value pixel points, and the selected pixel point is determined as an edge pixel point of the fingerprint.
4. The method for identifying a multi-fingerprint according to claim 3, wherein the calculating a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image comprises:

   Calculating each image in the filtered image according to a preset lateral convolution operator and a longitudinal convolution operator a first-order lateral partial derivative matrix corresponding to the prime point and a first-order longitudinal partial derivative matrix;

   Calculating a gradient magnitude and a gradient direction corresponding to each pixel according to the first equation according to the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix;

   The first equation includes:

   

   Q[i,j]=arctan(Q[i,j]/P[i,j]);

   Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.
5. The multi-fingerprint recognition method according to claim 3, wherein determining the maximum value pixel points in the filtered image according to the calculated gradient magnitude and the gradient direction comprises:

   Selecting a preset pixel point in the filtered image, and selecting a preset number of pixel points adjacent to the preset pixel point along a gradient direction of the preset pixel point, according to the calculated gradient amplitude Determining a relationship between a gray value of the preset pixel point and a gray value of each of the selected preset number of pixel points; when the gray value of the preset pixel point is greater than or equal to When the gray value of each of the preset number of pixels is selected, the preset pixel is determined as a maximum pixel.
6. The method for identifying a multi-fingerprint according to claim 2, wherein the calculating a distance between the first fingerprint and the second fingerprint comprises:

   Determining the center point of the fingerprint according to the first expression;

   Determining a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint;

   The first expression includes:

   

   among them,

   

   Is the abscissa of the center point of the fingerprint,

   

   Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint;

   Determining a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint includes:

   Calculating a relative distance between a center point of the first fingerprint and the second fingerprint according to a second expression;

   The second expression includes:

   

   Where (Xa, Ya) is the center point coordinate of the first fingerprint, and (Xb, Yb) is the center point coordinate of the second fingerprint.
7. The method for identifying a multi-fingerprint according to claim 2, wherein the calculating an angle between the first fingerprint and the second fingerprint comprises:

   Determining an angle of a texture of the first fingerprint and the second fingerprint with a vertical direction as a direction angle of the first fingerprint and the second fingerprint;

   If the direction angles of the first fingerprint and the second fingerprint are θA and θB, respectively, the relative angle between the first fingerprint and the second fingerprint is θ=|θA-θB| The relative angle between the first fingerprint and the second fingerprint is determined as an angle between the fingerprints.
8. A multi-fingerprint identification device includes: a fingerprint collection unit, a fingerprint recognition unit, a distance calculation unit, an angle calculation unit, and an unlocking unit;

   The fingerprint collection unit is configured to collect a fingerprint image from a fingerprint detection area of the terminal device, where the fingerprint image includes at least two fingerprints;

   The fingerprint identification unit is configured to identify a fingerprint in the fingerprint image, and acquire a first fingerprint and a second fingerprint;

   The distance calculation unit is configured to calculate a distance between the first fingerprint and the second fingerprint;

   The angle calculation unit is configured to calculate an angle between the first fingerprint and the second fingerprint;

   The unlocking unit is configured to match the first fingerprint and the second fingerprint with a pre-stored fingerprint template, and calculate the distance and the angle between the angle and the pre-stored distance and angle The terminal device is unlocked when the error between the errors is less than or equal to the preset error value.
9. The multi-fingerprint identification device according to claim 8, wherein the fingerprint recognition unit comprises an edge detection module;

   The fingerprint identification unit identifies the fingerprint in the fingerprint image, and acquiring the first fingerprint and having the second fingerprint includes:

   The edge detection module is configured to detect an edge of the fingerprint in the fingerprint image, and acquire a first fingerprint having a first edge and a second fingerprint having a second edge.
10. The apparatus for identifying multiple fingerprints according to claim 9, wherein the edge detection module comprises a grayscale processing sub-module, a filtering sub-module, a gradient calculation sub-module, a maximum-value pixel determination sub-module, and a screening sub-module;

    The detecting, by the edge detecting module, the edge of the fingerprint in the fingerprint image comprises:

    The grayscale processing sub-module is configured to perform grayscale processing on the fingerprint image to obtain a fingerprint grayscale image;

    The filtering sub-module is configured to filter the fingerprint grayscale image by using a preset Gaussian function to obtain a filtered image that filters out noise;

    The gradient calculation sub-module is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image;

    The maximum value pixel point determining submodule is configured to determine a maximum value pixel point in the filtered image according to the calculated gradient magnitude and the gradient direction;

    The screening sub-module is configured to filter, from the maximum-value pixel, a pixel point whose gray value is greater than or equal to a preset threshold, and determine the selected pixel point as an edge pixel of the fingerprint.
11. The apparatus for identifying multiple fingerprints according to claim 10, wherein the gradient calculation sub-module comprises: a partial derivative matrix calculation sub-module and an amplitude direction calculation sub-module;

    The gradient calculation sub-module calculates a gradient magnitude and a gradient direction corresponding to each pixel in the filtered image, including:

    The partial derivative matrix calculation submodule is configured to calculate a first-order lateral partial derivative matrix and a first order corresponding to each pixel point in the filtered image according to a preset lateral convolution operator and a longitudinal convolution operator Longitudinal partial derivative matrix;

    The amplitude direction calculation submodule is configured to calculate a gradient magnitude and a gradient direction corresponding to each pixel according to the first equation according to the first-order lateral partial derivative matrix and the first-order longitudinal partial derivative matrix;

    The first equation includes:

    

    Q[i,j]=arctan(Q[i,j]/P[i,j]);

    Where M[i,j] is the gradient magnitude corresponding to the pixel point of the i-th row and the j-th column, and P[i,j] is the first-order lateral partial derivative matrix corresponding to the pixel point of the i-th row and the j-th column, Q [i, j] is a first-order longitudinal partial derivative matrix corresponding to the pixel points of the i-th row and the j-th column, and Q[i, j] is a gradient direction corresponding to the pixel points of the i-th row and the j-th column.
12. The multi-fingerprint identification device according to claim 10, wherein the maximum value pixel point determination sub-module comprises: a gray value comparison sub-module;

    The maxima pixel determination sub-module determines the maximum value pixel in the filtered image according to the calculated gradient magnitude and the gradient direction, including:

    The gray value comparison sub-module is configured to select a preset pixel point in the filtered image, and select a preset number of pixels adjacent to the preset pixel point along a gradient direction of the preset pixel point Point, determining, according to the calculated gradient magnitude, a magnitude relationship between a grayscale value of the preset pixel point and a gray value of each of the selected preset number of pixel points; When the gray value of the preset pixel is greater than or equal to the gray value of each of the selected preset number of pixels, the preset pixel is determined as the maximum pixel.
13. The multi-fingerprint identification device according to claim 9, wherein the distance calculation unit comprises: a center point determination sub-module and a distance determination sub-module;

    The calculating, by the distance calculation unit, the distance between the first fingerprint and the second fingerprint includes:

    The center point determining submodule is configured to determine a center point of the fingerprint according to the first expression;

    The distance determining submodule is configured to determine a relative distance between a center point of the first fingerprint and the second fingerprint as a distance between the first fingerprint and the second fingerprint;

    The first expression includes:

    

    among them,

    

    Is the abscissa of the center point of the fingerprint,

    

    Is the ordinate of the center point of the fingerprint, X ₃ is the minimum abscissa in the coordinates corresponding to the edge pixel of the fingerprint, X ₄ is the largest abscissa in the coordinates corresponding to the edge pixel of the fingerprint, and Y ₁ is the edge pixel of the fingerprint The maximum ordinate in the coordinates corresponding to the point, Y ₂ is the minimum ordinate in the coordinates corresponding to the edge pixel of the fingerprint;

    The distance determining sub-module determines a relative distance between the first fingerprint and a center point of the second fingerprint as a distance between the first fingerprint and the second fingerprint, including:

    Calculating a relative distance between a center point of the first fingerprint and the second fingerprint according to a second expression;

    The second expression includes:

    

    Where (Xa, Ya) is the center point coordinate of the first fingerprint, and (Xb, Yb) is the center point coordinate of the second fingerprint.
14. The multi-fingerprint identification device according to claim 9, wherein the angle calculation unit calculates an angle between the first fingerprint and the second fingerprint, including:

    Determining an angle of a texture of the first fingerprint and the second fingerprint with a vertical direction as a direction angle of the first fingerprint and the second fingerprint;

    If the direction angles of the first fingerprint and the second fingerprint are θA and θB, respectively, the relative angle between the first fingerprint and the second fingerprint is θ=|θA-θB| The relative angle between the first fingerprint and the second fingerprint is determined as an angle between the fingerprints.
15. A computer readable storage medium storing computer executable instructions that, when executed by a processor, implement the multi-fingerprint identification method of any one of claims 1 to 7.

Images