CN108319887A - A kind of identity authentication method and system - Google Patents

Abstract

The embodiment of the present invention discloses a method and system for identity authentication; the method includes: processing the collected target finger vein image through a preset image processing strategy to obtain the topological structure of the target finger vein; extracting the target finger vein according to the preset feature The strategy is to obtain at least two characteristic parameters of the target finger vein topology that are both translation invariant and rotation invariant; and combine the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology Matching is performed according to a preset matching strategy; when the matching is successful, it is determined that the authentication of the target finger vein image is successful. It is possible to avoid identification and authentication errors caused by translation or rotation during the acquisition process.

Description

Method and system for identity authentication

technical field

The present invention relates to the technical field of information security, in particular to an identity authentication method and system.

Background technique

Currently, one of the commonly used identity authentication technologies in the industry is biometric authentication, which includes fingerprint recognition authentication and face recognition authentication. However, in the biometric authentication technology, fingerprint recognition authentication has relatively high requirements on the environment; face recognition authentication, due to a series of human behaviors such as plastic surgery and makeup, will cause face recognition to be very inaccurate, so it is also the easiest to falsify .

At present, the finger vein recognition technology uses the vein pattern image obtained after the near-infrared rays penetrate the finger for identity authentication and recognition. However, most of the current finger vein recognition technologies are implemented by fuzzy matching of the feature points of the finger vein pattern, so that when translation and rotation occur during the acquisition process, recognition and authentication errors are caused.

Contents of the invention

In order to solve the above technical problems, the embodiment of the present invention expects to provide an identity authentication method and system that can avoid identification and authentication errors caused by translation or rotation during the acquisition process.

Technical scheme of the present invention is realized like this:

In a first aspect, an embodiment of the present invention provides a method for identity authentication, the method comprising:

Process the collected target finger vein image through a preset image processing strategy to obtain the topological structure of the target finger vein;

Obtaining at least two feature parameters of the target finger vein topology that are both translation invariant and rotation invariant according to a preset feature extraction strategy;

matching the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology according to a preset matching strategy;

When the matching is successful, it is determined that the authentication of the target finger vein image is successful.

In the solution above, the method further includes: when the matching is unsuccessful, determining that the authentication of the target finger vein image fails.

In the above solution, the image of the target finger vein is collected by a light source emitter that adds near-infrared light in the camera.

In the above solution, the characteristic parameters corresponding to the topological structure of the finger vein include the distance between the intersection points of the curves in the topological structure of the finger vein and the angle generated between the lines connecting the intersection points; wherein, the The distance between intersections is characterized by the length of the line connecting the intersections.

In the above solution, the acquisition of at least two feature parameters in the target finger vein topology structure with both translation invariance and rotation invariance according to the preset feature extraction strategy includes:

Extracting all intersections in the target finger vein topology according to the value of each pixel and the statistical value of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel;

All intersections in the target finger vein topology are connected in pairs, and the lengths of all the connections and the angles formed between all the connections are obtained.

In the above solution, the characteristic parameters corresponding to the finger vein topology include the endpoints of the curves in the finger vein topology, the intersection points of the curves in the finger vein topology and other curve intersections within a preset range. The distance between the curve intersections in the finger vein topology and the angle between the lines between the intersections of the curves and other curve intersections within the preset range; wherein, the curve intersections in the finger vein topology and the preset range The distances between other curve intersections in the finger vein topology are characterized by the lengths of lines between the curve intersections in the finger vein topology and other curve intersections within a preset range.

In the above solution, the acquisition of at least two feature parameters in the target finger vein topology structure with both translation invariance and rotation invariance according to the preset feature extraction strategy includes:

Obtain the endpoints of each curve in the target finger vein topology;

Extracting all intersections in the target finger vein topology according to the value of each pixel and the statistical value of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel;

Selecting a preset number of adjacent intersections corresponding to each intersection in the target finger vein topology according to a preset distance threshold;

Connect each intersection point with the corresponding adjacent intersection point, and obtain the lengths of all the connection lines and the included angles between all the connection lines.

In the above solution, matching the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology according to a preset matching strategy includes:

When the number of lines between the intersections of the target finger vein topology and the existing finger vein topology is the same as the number of included angles generated between the lines of intersections, determine the target finger Whether the number of lines whose length meets the preset first error range between the vein topology and the existing finger vein topology exceeds a preset first threshold;

When the number of connections between the target finger vein topology and the existing finger vein topology whose length satisfies a preset first error range exceeds a preset first threshold, determine the target finger vein topology Whether the number of included angles generated between lines satisfying a preset error range in the existing finger vein topological structure and satisfying a preset second error range exceeds a preset second threshold;

When the number of angles generated between the target finger vein topological structure and the line meeting the preset error range in the existing finger vein topological structure meets the second preset error range, the number of included angles exceeds the preset When the second threshold is reached, it is determined that the matching is successful.

In the above scheme, the method also includes:

When the authentication of the target finger vein image fails, an early warning message is sent; wherein, the early warning message is used to prompt and prevent unauthorized intrusion.

In the above scheme, the method also includes:

Perform statistics on the number of times of successful authentication of the target finger vein image and the total number of times of authentication of the target finger vein image, and obtain the authentication recognition rate of the target finger vein image;

When the authentication recognition rate of the target finger vein image is lower than a preset recognition rate threshold, prompt information is sent; wherein the prompt information is used to request adjustment of the recognition rate threshold.

In the second aspect, an embodiment of the present invention provides an identity authentication system, the system includes: an acquisition module, an image processing module, a feature extraction module, a matching module, and a first determination module; wherein,

The collection module is used to collect target finger vein images;

The image processing module is used to process the collected image of the target finger vein through a preset image processing strategy to obtain the topological structure of the target finger vein;

The feature extraction module is configured to obtain at least two feature parameters of the target finger vein topology that are both translation invariant and rotation invariant according to a preset feature extraction strategy;

The matching module is configured to match the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology according to a preset matching strategy; and when the matching is successful, trigger the first - determine the module;

The first determining module is configured to determine that the authentication of the target finger vein image is successful.

In the above solution, the system further includes: a second determination module; correspondingly, the matching module is further configured to trigger the second determination module when the matching is unsuccessful;

The second determination module is configured to determine that the authentication of the target finger vein image fails.

In the above solution, the acquisition module is composed of a light source emitter that adds near-infrared light in the camera.

In the above solution, the characteristic parameters corresponding to the topological structure of the finger vein include the distance between the intersection points of the curves in the topological structure of the finger vein and the angle generated between the lines connecting the intersection points; wherein, the The distance between intersections is characterized by the length of the line connecting the intersections.

In the above scheme, the feature extraction module is used for:

Extracting all intersections in the target finger vein topology according to the value of each pixel and the statistical value of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel; and,

All intersections in the target finger vein topology are connected in pairs, and the lengths of all the connections and the angles formed between all the connections are obtained.

In the above solution, the characteristic parameters corresponding to the finger vein topology include the endpoints of the curves in the finger vein topology, the intersection points of the curves in the finger vein topology and other curve intersections within a preset range. The distance between the curve intersections in the finger vein topology and the angle between the lines between the intersections of the curves and other curve intersections within the preset range; wherein, the curve intersections in the finger vein topology and the preset range The distances between other curve intersections in the finger vein topology are characterized by the lengths of lines between the curve intersections in the finger vein topology and other curve intersections within a preset range.

In the above scheme, the feature extraction module is used for:

Obtain the endpoints of each curve in the target finger vein topology;

And, extracting all intersections in the target finger vein topology according to the value of each pixel and statistical values of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel;

And, selecting a preset number of adjacent intersections corresponding to each intersection in the target finger vein topology according to a preset distance threshold;

And, each intersection point is connected with corresponding adjacent intersection points, and the lengths of all the connection lines and the included angles between all the connection lines are obtained.

In the above solution, the matching module is used for:

When the number of lines between the intersections of the target finger vein topology and the existing finger vein topology is the same as the number of included angles generated between the lines of intersections, determine the target finger Whether the number of lines whose length meets the preset first error range between the vein topology and the existing finger vein topology exceeds a preset first threshold; and,

When the number of connections between the target finger vein topology and the existing finger vein topology whose length satisfies a preset first error range exceeds a preset first threshold, determine the target finger vein topology Whether the number of included angles generated between lines satisfying a preset error range in the existing finger vein topology and satisfying a preset second error range exceeds a preset second threshold; and,

When the number of angles generated between the target finger vein topological structure and the line meeting the preset error range in the existing finger vein topological structure meets the second preset error range, the number of included angles exceeds the preset When the second threshold is reached, it is determined that the matching is successful.

In the above solution, the system further includes: an early warning module, configured to send early warning information when the target finger vein image authentication fails; wherein, the early warning information is used to prompt and prevent unauthorized intrusion.

In the above solution, the system further includes: a statistical module and a prompt module; wherein,

The statistics module is used to count the number of successful authentications of the target finger vein image and the total number of authentications of the target finger vein image, and obtain the recognition rate of the target finger vein image authentication;

The prompt module is configured to send prompt information when the target finger vein image authentication recognition rate is lower than a preset recognition rate threshold; wherein the prompt message is used to request adjustment of the recognition rate threshold.

The embodiment of the present invention provides a method and system for identity authentication; identity authentication is realized by matching the translation-invariant and rotation-invariant features in the finger vein pattern, which can avoid the occurrence of translation or rotation in the collection process. The identification authentication error.

In some embodiments of the present invention, the characteristic parameters corresponding to the finger vein topology used include the endpoints of the curves in the finger vein topology, the intersection points of the curves in the finger vein topology and other curves within a preset range The distance between intersections. In some embodiments, the characteristic parameters corresponding to the finger vein topology that can also be used in the same way can also include the endpoints of the curves in the finger vein topology and/or the intersection points of the curves in the finger vein topology The distance from the endpoints of other curves within the preset range.

In some embodiments of the present invention, the used characteristic parameters corresponding to the topological structure of the finger vein include angles formed by lines between the intersection points of the curves in the topological structure of the finger veins and other intersection points of the curves within a preset range. In some embodiments, the characteristic parameters corresponding to the topological structure of finger veins that can also be used in the same way may also include the intersection points of curves in the topological structure of finger veins and/or the intersection points of the curves in the topological structure of finger veins The angle formed by the lines connecting other curve endpoints within the preset range.

Description of drawings

FIG. 1 is a schematic flow diagram of a method for identity authentication provided by an embodiment of the present invention;

Fig. 2 is a schematic diagram of a normalized finger vein image provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of a finger vein image after image segmentation provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of a topological structure of a finger vein provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of a feature extraction process provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of an 8-neighborhood of a pixel provided by an embodiment of the present invention;

Fig. 7 is a schematic diagram of intersection points corresponding to finger vein topology provided by an embodiment of the present invention;

FIG. 8 is a schematic diagram of a connection line at an intersection provided by an embodiment of the present invention;

FIG. 9 is a schematic diagram of a matching process provided by an embodiment of the present invention;

FIG. 10 is a schematic flowchart of a matching strategy matching provided by an embodiment of the present invention;

FIG. 11 is a schematic structural diagram of an identity authentication system provided by an embodiment of the present invention;

FIG. 12 is a schematic structural diagram of another identity authentication system provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

Embodiment one

Referring to Figure 1, it shows a method of identity authentication provided by an embodiment of the present invention, which can be applied to an identity authentication system, and the method can include:

S101: Process the collected image of the target finger vein through a preset image processing strategy to obtain the topological structure of the target finger vein;

S102: Obtain at least two feature parameters of the target finger vein topology that are both translation invariant and rotation invariant according to a preset feature extraction strategy;

S103: Match the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology according to a preset matching strategy;

S104: When the matching is successful, it is determined that the authentication of the target finger vein image is successful.

Understandably, when the matching is not successful, it is determined that the authentication of the target finger vein image fails.

Through the technical solution shown in Figure 1, identity authentication can be realized by matching the translation-invariant and rotation-invariant features in the finger vein pattern, and identification and authentication errors caused by translation or rotation during the acquisition process can be avoided.

For the technical solution shown in FIG. 1 , in step S101 , the image of the target finger vein can be collected by a video collection front-end device, such as a camera for video surveillance. Specifically, the camera can be a dome camera commonly used in the industry, referred to as a dome camera, a card camera, a bolt camera, a dome camera with a pan-tilt for home use, etc., which will not be described in this embodiment. When realizing the collection of finger vein images, a near-infrared light source emitter can be added to these traditional cameras to collect finger vein images.

In the specific implementation process of step S101, after the target finger vein image is collected, the collected target finger vein image can be normalized, and the normalized image can be sequentially image enhanced, image segmented, and The image is thinned and repaired, so that the corresponding topological structure of the target finger vein can be represented by the thinned target finger vein image. The specific implementation processes of image normalization, image enhancement, image segmentation, and image thinning and restoration are conventional technical means in the field of image processing, and this embodiment will not repeat them.

For the above specific implementation process of step S101, refer to the four normalized finger vein images shown in Figure 2 as examples, and the results of image segmentation are shown in Figure 3. The corresponding topological structure of finger vein obtained after refinement and repair is shown in Fig. 4 .

It should be noted that, from the finger vein topology example shown in FIG. 4 , it can be seen that the finger vein topology can be summed up as multiple curves and intersection points between multiple curves. Because the angle between two straight lines and the relative distance between two points have translation invariance and rotation invariance, that is to say, these two features will not change due to translation and rotation.

Therefore, in a preferred implementation manner, the characteristic parameters corresponding to the finger vein topology include the distance between the intersections of the curves in the finger vein topology and the angle formed between the lines connecting the intersections.

Through the above description, when the characteristic parameter corresponding to the topological structure of the finger vein is preferably the distance between the intersection points of the curves in the topological structure of the finger vein and the angle generated between the lines connecting the intersection points, for step S102, refer to FIG. 5 , which can include:

S1021A: Extract all intersections in the target finger vein topology according to the value of each pixel and the statistical value of all neighborhood pixel values in the preset neighborhood corresponding to each pixel;

Specifically, taking the 8-neighborhood of pixel P ₀ as an example, that is, the 3×3 pixel area centered on pixel P ₀ as shown in FIG. 6 as an example, the 8-neighborhood pixel of pixel P ₀ are: P ₁ , P ₂ , P ₃ , P ₄ , P ₅ , P ₆ , P ₇ and P ₈ . When the condition shown in formula 1 is satisfied, the pixel point _P0 is an intersection point;

in, That is to say, N represents the number of times P ₁ to P ₈ are 1, and when N≥3, the point P ₀ is considered to be an intersection point in the target finger vein topology.

When all the pixels in the target finger vein topology are screened according to the conditions shown in the above formula 1, all intersections in the target finger vein topology can be obtained, as shown in Figure 7, which is the finger vein shown in Figure 4 The intersection point corresponding to the topological structure, the coordinate point set of the intersection point corresponding to the topological structure of each finger vein is represented by a matrix as follows:

Let the matrix X _k be the coordinate point set of the intersection point corresponding to the kth finger vein topology, where the value of k is from 1 to 4. Therefore, the matrix corresponding to the intersection points of the four finger vein topological structures shown in Figure 7 is:

S1022A: Connect all intersections in the target finger vein topology two by two, and obtain the lengths of all the connections and the included angles between all the connections.

Specifically, assuming that there are d intersection points, after connecting the intersection points two by two, it will generate lines; and the number of included angles between all lines is indivual.

It should be noted that the length of the connecting line represents the relative distance between the intersection points at both ends of the connecting line, which can be calculated by using the distance formula between two points on the plane, which will not be described in detail in this embodiment. The angle generated between the connecting lines can be calculated according to the cosine law of the triangle by the distance between the three intersection points of the two connecting lines forming the angle, for example, the connecting line between the intersection points A and B and The angle A formed by the line connecting the intersection points A and C is: Among them, the distance between BC points is a, the distance between AC points is b, and the distance between AB points is c.

Set the feature parameter set corresponding to the target finger vein topology as R=(l _m ,θ _u ); where, l represents the length of the line between any two intersection points [l ₁ ,l ₂ ,..., l _m ], the unit is pixel; θ represents the angle [θ ₁ ,θ ₂ ,...,θ _u ] generated by connecting any two intersection points, the unit is degree; and m represents the distance between any two intersection points The number of connecting lines; u represents the number of angles formed by any two intersection connecting lines.

Taking the intersection point corresponding to the topological structure of the first finger vein in Figure 7 and the corresponding matrix _X1 as an example, it can be obtained: l=[56, 29.0172, 27.0185, 15.6525, 42.5793, 16.1555, 25.2982, 68.352, 43.566, 27.8029, 47.0106，34.6699，29.1204，31.8277，45.2769，43.0813，56.5685，41.1096，33.0606，28.8444，23.7065，60.208，41.4849，42.1545，45.2769，55.3624，13.6015，29]，其中，m＝28；而θ＝[2.1211，1.9749 , 26.5651, 69.4440, 42.8789, 65.5560, ...], where u=168.

Referring to FIG. 8 , it is an effect diagram after all finger vein topological structures shown in FIG. 7 are connected with corresponding intersection points. It can be seen from Figure 8 that the topological relationship of each image in Figure 8 reflects the integrity and characteristics of the veins. Since the intersection refers to the internal feature points generated by the interlacing of veins, it can reflect the direction and distribution of veins. ; Therefore, in order to avoid mistaking the breakpoints in the images in Figure 8 as endpoints and thus affecting the recognition results. In this embodiment, only reliable intersection points are used as feature points for feature parameter acquisition.

For the above preferred implementation, in order to improve the accuracy of data and reduce the calculation overhead of data processing, in another preferred implementation, the characteristic parameters corresponding to the finger vein topology include the The endpoints of each curve, the distance between the curve intersections in the finger vein topology and other curve intersections within a preset range, and the curve intersections in the finger vein topology and other curve intersections in a preset range The included angle generated by the connecting lines; wherein, the distance between the curve intersections in the finger vein topology and other curve intersections within the preset range passes through the curve intersections in the finger vein topology and the preset range Characterized by the length of the line between the intersection points of the other curves.

It should be noted that the endpoints of each curve can accurately identify each curve, so that different curves can be distinguished by the endpoints; and in order to reduce the amount of calculation, each curve intersection does not need to be connected to all other intersections line, but can select the intersection point for connection within the preset range of each curve intersection point. At this time, for step S102, referring to FIG. 9, the target index is obtained according to the preset feature extraction strategy. At least two characteristic parameters that have both translation invariance and rotation invariance in the vein topology, specifically may include:

S1021B: Obtain the endpoints of each curve in the target finger vein topology;

S1022B: Extract all intersections in the target finger vein topology according to the value of each pixel and statistical values of all neighborhood pixel values in the preset neighborhood corresponding to each pixel;

S1023B: Correspondingly select a preset number of adjacent intersections for each intersection in the target finger vein topology according to a preset distance threshold;

S1024B: Connect each intersection point with a corresponding adjacent intersection point, and obtain the lengths of all the connection lines and the angles formed between all the connection lines.

It should be noted that, for the solution shown in FIG. 9 , in the specific implementation process, the difference from the technical solution shown in FIG. 5 is that in the process of connecting the intersection points, all the intersection points are not connected. line, and connect the adjacent intersection points with the preset number of trees selected according to the preset distance threshold,

In this embodiment, selecting a preset tree number of adjacent intersections according to a preset distance threshold may be, for each intersection, selecting a total of n points for connection in the order of the closest and/or the farthest, where , n is preferably a natural number less than half of the total number of intersection points according to the requirement of data volume. Therefore, in the technical solution shown in Figure 9, the selected intersection line can be considered as a part extracted from all the intersection lines to characterize the characteristic parameters corresponding to the topological structure of the finger vein, so that Figure 9 Compared with the solution shown in FIG. 5 , the shown solution reduces the amount of repeated calculations without reducing the amount of information, thereby saving system overhead without compromising accuracy.

It can be understood that for the above two preferred implementation methods, the characteristic parameters corresponding to the existing finger vein topology can also be obtained according to the above scheme, for example, it is also applicable to using only the endpoints of the curve or the mixed use of intersections and endpoints case, this embodiment will not repeat it.

Corresponding to the above two preferred implementations of step S102, for step S103, see FIG. 10 , which may specifically include:

S1031: Determine whether the number of lines between the intersections of the target finger vein topology and the existing finger vein topology is the same as the number of included angles generated between the lines of the intersections; if they are the same, go to S1032 ; If not the same, go to S1034;

S1032: Determine whether the number of connections between the target finger vein topology and the existing finger vein topology whose length meets the preset first error range exceeds the preset first threshold; if so, go to S1033; if not If it exceeds, go to S1034;

S1033: Determine whether the number of angles generated between the target finger vein topology and the connection line satisfying the preset error range in the existing finger vein topology exceeds the preset second error range. Two thresholds; if exceeded, go to S1034; if not exceeded, go to S1035;

S1034: Determine that the matching is successful;

S1035: It is determined that the matching is not successful.

In the specific implementation process, let R1=(l _m ,θ _u ) and R2=(l _n ,θ _v ) be the feature parameter sets of the target finger vein topology structure and the existing finger vein topology structure respectively. For Figure 9, can include:

Step a: Determine whether m and n and u and v are equal; if they are not equal, determine that the matching fails; if they are equal, proceed to step b;

Step b: Determine whether the number of intersection lines in R1 and R2 with equal or approximately equal lengths is greater than the preset first threshold, if less than the first threshold, the matching fails; if not less than the first threshold, continue to execute the step c;

Step c: Obtain the included angles generated by lines with equal or approximately equal lengths, which are θ _z1 and θ _z2 respectively; count the number of equal or approximately equal θ _z1 and θ _z2 , and judge that it is greater than the preset second threshold; If it is less than the second threshold, the matching fails; if it is greater than the second threshold, the matching is successful.

It can be understood that approximately equal can be considered to be within a preset error range between the two values; for the length of the connection line, the error range is preferably ±0.0005; for the included angle, the error range is preferably ±0.006.

It should be noted that in step c, only the angle generated by the successfully matched intersection line is continued to match, which not only retains the effective features of the vein, but also reduces the redundant information and calculation amount of crossing between features , giving the information needed for decision analysis to the greatest extent, and improving the accuracy of recognition.

Exemplarily, when the target finger vein image authentication fails, the technical solution of this embodiment may further include:

Send early warning information; the early warning information is used to prompt and prevent unauthorized intrusion; for example, an early warning text message can be sent to the system administrator to inform him of the reason for checking and prevent illegal personnel from intruding into the system.

Exemplarily, the technical solution of this embodiment may also include:

Perform statistics on the number of successful target finger vein image authentications and the total number of target finger vein image authentications to obtain the target finger vein image authentication recognition rate;

When the authentication recognition rate of the target finger vein image is lower than the preset recognition rate threshold, a prompt message is sent; the prompt message is used to request adjustment of the recognition rate threshold. For example, when the target finger vein image authentication recognition rate is lower than the set threshold, a reminder text message can be automatically sent to the system administrator to inform him of the reason for checking and analyze whether to adjust the system threshold setting.

This embodiment provides a method for identity authentication; identity authentication is realized by matching the translation-invariant and rotation-invariant features in the finger vein pattern, which can avoid identification and authentication caused by translation or rotation during the acquisition process mistake.

Embodiment two

Based on the same technical idea of the foregoing embodiments, see FIG. 11 , which shows an identity authentication system 110 provided by an embodiment of the present invention. The system 110 includes: an acquisition module 1101 , an image processing module 1102 , and a feature extraction module 1103 , a matching module 1104 and a first determination module 1105; wherein,

The acquisition module 1101 is configured to acquire target finger vein images;

The image processing module 1102 is configured to process the collected image of the target finger vein through a preset image processing strategy to obtain the topological structure of the target finger vein;

The feature extraction module 1103 is configured to obtain at least two feature parameters of the target finger vein topology that are both translation invariant and rotation invariant according to a preset feature extraction strategy;

The matching module 1104 is configured to match the characteristic parameters corresponding to the target finger vein topology with the characteristic parameters corresponding to the existing finger vein topology according to a preset matching strategy; and when the matching is successful, trigger the The first determination module 1105;

The first determining module 1105 is configured to determine that the authentication of the target finger vein image is successful.

Exemplarily, referring to FIG. 12 , the system 110 further includes: a second determination module 1106; correspondingly, the matching module 1104 is also configured to trigger the second determination module 1106 when the matching is unsuccessful;

The second determination module 1106 is configured to determine that the authentication of the target finger vein image fails.

Exemplarily, the collection module 1101 is composed of a light source emitter that adds near-infrared light in the camera.

Exemplarily, the characteristic parameters corresponding to the topological structure of the finger vein include the distance between the intersection points of the curves in the topological structure of the finger vein and the angle generated between the lines connecting the intersection points; wherein, the intersection The distance between points is characterized by the length of the line connecting the intersection points.

Further, the feature extraction module 1103 is used for:

Extracting all intersections in the target finger vein topology according to the value of each pixel and the statistical value of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel; and,

All intersections in the target finger vein topology are connected in pairs, and the lengths of all the connections and the angles formed between all the connections are obtained.

Exemplarily, the characteristic parameters corresponding to the finger vein topology include the endpoints of the curves in the finger vein topology, the intersection points of the curves in the finger vein topology and other curve intersections within a preset range. and the angle between the lines between the intersection points of the curves in the topological structure of the finger vein and other intersections of the curves within the preset range; The distances between other curve intersections in are characterized by the lengths of lines between the curve intersections in the finger vein topology and other curve intersections within a preset range.

Further, the feature extraction module 1103 is used for:

Obtain the endpoints of each curve in the target finger vein topology;

And, extracting all intersections in the target finger vein topology according to the value of each pixel and statistical values of all neighborhood pixel values in the preset range neighborhood corresponding to each pixel;

And, selecting a preset number of adjacent intersections corresponding to each intersection in the target finger vein topology according to a preset distance threshold;

And, each intersection point is connected with corresponding adjacent intersection points, and the lengths of all the connection lines and the included angles between all the connection lines are obtained.

Preferably, the matching module 1104 is configured to:

When the number of lines between the intersections of the target finger vein topology and the existing finger vein topology is the same as the number of included angles generated between the lines of intersections, determine the target finger Whether the number of lines whose length meets the preset first error range between the vein topology and the existing finger vein topology exceeds a preset first threshold; and,

When the number of connections between the target finger vein topology and the existing finger vein topology whose length satisfies a preset first error range exceeds a preset first threshold, determine the target finger vein topology Whether the number of included angles generated between lines satisfying a preset error range in the existing finger vein topology and satisfying a preset second error range exceeds a preset second threshold; and,

When the number of angles generated between the target finger vein topological structure and the line meeting the preset error range in the existing finger vein topological structure meets the second preset error range, the number of included angles exceeds the preset When the second threshold is reached, it is determined that the matching is successful.

Exemplarily, on the basis of the identity authentication system shown in FIG. 11 , referring to FIG. 12 , the system 110 may further include: an early warning module 1107, configured to send early warning information when the target finger vein image authentication fails; wherein , the warning information is used to prompt and prevent unauthorized intrusion.

Exemplarily, referring to FIG. 12, the system 110 may further include: a statistics module 1108 and a prompt module 1109; wherein,

The statistical module 1108 is configured to count the number of successful authentications of the target finger vein image and the total number of authentications of the target finger vein image, and obtain the authentication recognition rate of the target finger vein image;

The prompt module 1109 is configured to send prompt information when the target finger vein image authentication recognition rate is lower than a preset recognition rate threshold; wherein, the prompt message is used to request adjustment of the recognition rate threshold.

Understandably, the statistical module 1108 may acquire the total number of authentications by adding the number of successful authentications and the number of failed authentications respectively corresponding to the first determining module 1105 and the second determining module 1106 .

This embodiment provides an identity authentication system; identity authentication is realized by matching the translation-invariant and rotation-invariant features in the finger vein pattern, which can avoid identification authentication caused by translation or rotation during the collection process mistake.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention.

Claims (20)

1. A method of identity authentication, the method comprising:

processing the collected target finger vein image through a preset image processing strategy to obtain a target finger vein topological structure;

acquiring at least two characteristic parameters which simultaneously have translational invariance and rotational invariance in the target finger vein topological structure according to a preset characteristic extraction strategy;

matching the characteristic parameters corresponding to the target finger vein topological structure with the characteristic parameters corresponding to the existing finger vein topological structure according to a preset matching strategy;

and when the matching is successful, determining that the target finger vein image is successfully authenticated.

2. The method of claim 1, further comprising: and when the matching is unsuccessful, determining that the target finger vein image authentication fails.

3. The method of claim 1, wherein the target finger vein image is acquired by a light source emitter in a camera that adds near infrared light.

4. The method according to claim 1, wherein the characteristic parameters corresponding to the finger vein topology include a distance between curve intersections in the finger vein topology and an included angle generated between lines connecting the intersections; wherein the distance between the intersections is characterized by the length of the intersection line.

5. The method according to claim 4, wherein the obtaining at least two feature parameters having both translation invariance and rotation invariance in the target finger vein topology according to a preset feature extraction strategy comprises:

extracting all cross points in the target finger vein topological structure according to the value of each pixel point and the statistical value of all neighborhood pixel point values in a preset range neighborhood corresponding to each pixel point;

and connecting every two intersection points in the target finger vein topological structure, and acquiring the lengths of all the connecting lines and included angles generated between all the connecting lines.

6. The method according to claim 1, wherein the characteristic parameters corresponding to the finger vein topology include end points of each curve in the finger vein topology, distances between curve intersections in the finger vein topology and other curve intersections within a preset range, and included angles generated by connecting lines between the curve intersections in the finger vein topology and other curve intersections within the preset range; and the distance between the curve intersection point in the finger vein topological structure and other curve intersection points in the preset range is represented by the length of a connecting line between the curve intersection point in the finger vein topological structure and other curve intersection points in the preset range.

7. The method according to claim 6, wherein the obtaining at least two feature parameters having both translation invariance and rotation invariance in the target finger vein topology according to a preset feature extraction strategy comprises:

acquiring endpoints of all curves in the target finger vein topological structure;

extracting all cross points in the target finger vein topological structure according to the value of each pixel point and the statistical value of all neighborhood pixel point values in a preset range neighborhood corresponding to each pixel point;

correspondingly selecting a preset number of adjacent cross points from each cross point in the target finger vein topological structure according to a preset distance threshold;

and connecting each intersection point with the corresponding adjacent intersection point to obtain the lengths of all the connecting lines and included angles generated among all the connecting lines.

8. The method according to claim 5 or 7, wherein the matching of the characteristic parameters corresponding to the target finger vein topological structure with the characteristic parameters corresponding to the existing finger vein topological structure according to a preset matching strategy comprises:

when the number of connecting lines between intersections in the target finger vein topological structure and the existing finger vein topological structure is the same as the number of included angles generated between the connecting lines of the intersections, determining whether the number of the connecting lines between the target finger vein topological structure and the existing finger vein topological structure, the length of which meets a preset first error range, exceeds a preset first threshold value;

when the number of connecting lines of which the lengths between the target finger vein topological structure and the existing finger vein topological structure meet a preset first error range exceeds a preset first threshold value, determining whether the number of included angles generated between the connecting lines of the target finger vein topological structure and the existing finger vein topological structure meeting the preset error range meets a preset second error range exceeds a preset second threshold value;

and when the number of included angles meeting a preset second error range and generated between the connecting lines meeting the preset error range in the target finger vein topological structure and the existing finger vein topological structure exceeds a preset second threshold, determining that the matching is successful.

9. The method of claim 1, further comprising:

when the target finger vein image authentication fails, sending early warning information; wherein, the early warning information is used for prompting and preventing unauthorized behavior invasion.

10. The method of claim 1, further comprising:

counting the successful authentication times of the target finger vein image and the total authentication times of the target finger vein image to obtain the authentication identification rate of the target finger vein image;

when the target finger vein image authentication identification rate is lower than a preset identification rate threshold value, sending prompt information; and the prompt information is used for requesting to adjust the identification rate threshold value.

11. A system for identity authentication, the system comprising: the device comprises an acquisition module, an image processing module, a feature extraction module, a matching module and a first determination module; wherein,

the acquisition module is used for acquiring a target finger vein image;

the image processing module is used for processing the acquired target finger vein image through a preset image processing strategy to acquire a target finger vein topological structure;

the characteristic extraction module is used for acquiring at least two characteristic parameters which have translational invariance and rotational invariance simultaneously in the target finger vein topological structure according to a preset characteristic extraction strategy;

the matching module is used for matching the characteristic parameters corresponding to the target finger vein topological structure with the characteristic parameters corresponding to the existing finger vein topological structure according to a preset matching strategy; and when the matching is successful, triggering the first determining module;

the first determining module is used for determining that the target finger vein image is successfully authenticated.

12. The system of claim 11, further comprising: a second determination module; correspondingly, the matching module is further configured to trigger the second determining module when the matching is unsuccessful;

the second determining module is used for determining that the target finger vein image fails to be authenticated.

13. The system of claim 11, wherein the collection module comprises a light source emitter in the camera that adds near infrared light.

14. The system according to claim 11, wherein the characteristic parameters corresponding to the finger vein topology include a distance between curve intersections in the finger vein topology and an included angle generated between lines connecting the intersections; wherein the distance between the intersections is characterized by the length of the intersection line.

15. The system of claim 14, wherein the feature extraction module is configured to:

extracting all cross points in the target finger vein topological structure according to the value of each pixel point and the statistical value of all neighborhood pixel point values in a preset range neighborhood corresponding to each pixel point; and the number of the first and second groups,

and connecting every two intersection points in the target finger vein topological structure, and acquiring the lengths of all the connecting lines and included angles generated between all the connecting lines.

16. The system according to claim 11, wherein the characteristic parameters corresponding to the finger vein topology include an end point of each curve in the finger vein topology, a distance between a curve intersection point in the finger vein topology and another curve intersection point in a preset range, and an included angle generated by a connecting line between the curve intersection point in the finger vein topology and another curve intersection point in the preset range; and the distance between the curve intersection point in the finger vein topological structure and other curve intersection points in the preset range is represented by the length of a connecting line between the curve intersection point in the finger vein topological structure and other curve intersection points in the preset range.

17. The system of claim 16, wherein the feature extraction module is configured to:

acquiring endpoints of all curves in the target finger vein topological structure;

extracting all cross points in the target finger vein topological structure according to the value of each pixel point and the statistical value of all neighborhood pixel point values in a preset range neighborhood corresponding to each pixel point;

correspondingly selecting a preset number of adjacent intersections from each intersection in the target finger vein topological structure according to a preset distance threshold;

and connecting each intersection point with the corresponding adjacent intersection point to obtain the lengths of all the connecting lines and included angles generated among all the connecting lines.

18. The system of claim 15 or 17, wherein the matching module is configured to:

when the number of connecting lines between intersections in the target finger vein topological structure and the existing finger vein topological structure is the same as the number of included angles generated between the connecting lines of the intersections, determining whether the number of the connecting lines between the target finger vein topological structure and the existing finger vein topological structure, the length of which meets a preset first error range, exceeds a preset first threshold value; and the number of the first and second groups,

when the number of connecting lines of which the lengths between the target finger vein topological structure and the existing finger vein topological structure meet a preset first error range exceeds a preset first threshold value, determining whether the number of included angles generated between the connecting lines of the target finger vein topological structure and the existing finger vein topological structure meeting the preset error range meets a preset second error range exceeds a preset second threshold value; and the number of the first and second groups,

and when the number of included angles meeting a preset second error range and generated between the connecting lines meeting the preset error range in the target finger vein topological structure and the existing finger vein topological structure exceeds a preset second threshold, determining that the matching is successful.

19. The system of claim 11, further comprising: the early warning module is used for sending early warning information when the target finger vein image authentication fails; wherein, the early warning information is used for prompting and preventing unauthorized behavior invasion.

20. The system of claim 11, further comprising: a counting module and a prompting module; wherein,

the counting module is used for counting the successful authentication times of the target finger vein image and the total authentication times of the target finger vein image to obtain the authentication identification rate of the target finger vein image;

the prompt module is used for sending prompt information when the target finger vein image authentication identification rate is lower than a preset identification rate threshold value; and the prompt information is used for requesting to adjust the identification rate threshold value.