CN116305043B - Universal identity verification method based on multiple biological characteristics - Google Patents
Universal identity verification method based on multiple biological characteristics Download PDFInfo
- Publication number
- CN116305043B CN116305043B CN202211697075.0A CN202211697075A CN116305043B CN 116305043 B CN116305043 B CN 116305043B CN 202211697075 A CN202211697075 A CN 202211697075A CN 116305043 B CN116305043 B CN 116305043B
- Authority
- CN
- China
- Prior art keywords
- dynamic
- information
- static
- biological
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012795 verification Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000003068 static effect Effects 0.000 claims abstract description 99
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000012937 correction Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003672 processing method Methods 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a universal identity verification method based on various biological characteristics, which comprises the following steps: acquiring a dynamic biological characteristic of a current user, wherein the dynamic biological characteristic is a biological characteristic of the current user acquired in real time; acquiring static biological characteristics of a target user stored in a system; according to the dynamic biological characteristics and the static biological characteristics, calculating a first matching degree of the current user and the target user, and judging whether the first matching degree is larger than a preset first matching degree or not; when the first matching degree is determined to be larger than the preset first matching degree, passing the identity verification; otherwise, the identity verification fails, and information of failure in the identity verification is returned. The invention provides an identity verification mode based on the user biological characteristics, which can ensure the safety and improve the verification speed. Meanwhile, the invention provides a general biological feature processing method, which can ensure the universality of data processing and verification algorithms and reduce the consumption of computing power resources of a computer.
Description
Technical Field
The invention relates to the technical field of data processing and security verification, in particular to a universal identity verification method based on various biological characteristics.
Background
The development of internet technology and computer technology provides convenience for the production and life of human beings, and the human beings are more and more separated from computer equipment, so that the security of the computer equipment and data thereof is particularly important. The traditional unlocking means of the computer is to manually key in a password, and the method of actively unlocking the computer by a user is original, the unlocking speed is low, and the risk of password leakage exists, so that the password is gradually eliminated. Most of today's computer devices employ a passive unlocking mode for a user, specifically, when the user unlocks the device, the device detects a part of the biometric feature of the user and verifies the identity of the user through the part of the biometric feature. The verification method is high in safety, but has the advantages of low development speed, low unlocking speed, low precision, high misjudgment rate and poor universality due to the fact that the starting is late and the algorithm has a certain defect.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, the invention aims to provide a general identity verification method based on various biological characteristics, and aims to provide an identity verification algorithm which has higher precision and speed and is general to various biological characteristics.
In order to achieve the above objective, an embodiment of the present invention provides a general authentication method based on multiple biological characteristics, including:
acquiring the dynamic biological characteristics of the current user; the dynamic biological characteristics are biological characteristics of the current user acquired in real time;
acquiring static biological characteristics of a target user stored in a system;
according to the dynamic biological characteristics and the static biological characteristics, calculating a first matching degree of the current user and the target user, and judging whether the first matching degree is larger than a preset first matching degree or not;
when the first matching degree is determined to be larger than the preset first matching degree, passing the identity verification; otherwise, the identity verification fails, and information of failure in the identity verification is returned.
Preferably, calculating the first matching degree between the current user and the target user according to the dynamic biological feature and the static biological feature includes:
performing digital processing on the dynamic biological characteristics to obtain digital dynamic biological characteristics; dividing the digital dynamic biological characteristics to obtain a plurality of digital dynamic biological characteristic blocks;
performing digital processing on the static biological characteristics to obtain digital static biological characteristics; dividing the digital static biological characteristics to obtain a plurality of digital static biological characteristic blocks;
extracting a plurality of digital dynamic biological feature blocks and digital static biological feature blocks corresponding to each digital dynamic biological feature block;
acquiring dynamic characteristic information of the digital dynamic biological characteristic block;
acquiring static characteristic information of the digital static biological characteristic block;
calculating the feature matching degree of the dynamic feature information and the static feature information; the feature matching degree is a first matching degree of the current user and the target user.
Preferably, extracting a plurality of digitized dynamic biometric blocks and digitized static biometric blocks corresponding to each digitized dynamic biometric block includes:
numbering the digitized dynamic biological feature blocks and the digitized static biological feature blocks respectively;
acquiring basic data information of the digital dynamic biological feature block; the basic data information comprises the number of data types and the richness of each data;
extracting a plurality of digital dynamic biological feature blocks as target digital dynamic biological feature blocks according to the basic data information;
acquiring the number of the target digital dynamic biological feature block, and establishing a target number sequence;
and extracting the digital static biological feature block corresponding to the target digital dynamic biological feature block according to the target serial number sequence.
Preferably, extracting a plurality of digitized dynamic biometric blocks as target digitized dynamic biometric blocks according to the basic data information includes:
acquiring attribute information of the digital dynamic biological feature block; the attribute information is the type of the dynamic biological feature corresponding to the digital dynamic biological feature block;
analyzing the type of the data information included in the digital dynamic biological feature block and the weight of each data information according to the basic data information and the attribute information;
calculating according to the type of the data information of the digital dynamic biological feature block and the weight of each data information to obtain a type evaluation value of the digital dynamic biological feature block;
comparing the type evaluation value with a preset type evaluation value;
and marking the digital dynamic biological feature block as a target digital dynamic biological feature block when the type evaluation value is determined to be larger than the preset type evaluation value.
Preferably, acquiring the dynamic feature information of the digitized dynamic biometric block includes:
performing high-pass filtering correction on the target digital dynamic biological feature block to obtain primary dynamic feature information;
dividing the first-level dynamic characteristic information into first-class dynamic characteristic information, second-class dynamic characteristic information and third-class dynamic characteristic information; the first type of dynamic characteristic information is endpoint characteristic information; the second type of dynamic characteristic information is turning point characteristic information; the third type of dynamic characteristic information is closed point characteristic information;
establishing a rectangular coordinate system, and acquiring primary coordinate information corresponding to the primary dynamic characteristic information; the primary coordinate information comprises first-type dynamic coordinate information corresponding to the first-type dynamic feature information, second-type dynamic coordinate information corresponding to the second-type dynamic feature information and third-type dynamic coordinate information corresponding to the third-type dynamic feature information;
correcting the primary coordinate information to obtain secondary coordinate information;
and performing de-coordinated processing on the secondary coordinate information to obtain secondary dynamic characteristic information corresponding to the secondary coordinate information, and marking the secondary dynamic characteristic information as dynamic characteristic information.
Preferably, the correcting the primary coordinate information to obtain secondary coordinate information includes:
judging whether the first type of dynamic coordinate information, the second type of dynamic coordinate information and the third type of dynamic coordinate information in the primary coordinate information need correction processing according to the attribute information of the digital dynamic biological feature block, and acquiring a judging result;
when the determined result is that the i-th type dynamic coordinate information needs to be corrected, a corresponding i-th type coordinate information correction algorithm is obtained;
and carrying out correction processing on the ith dynamic coordinate information according to the ith coordinate information correction algorithm.
Preferably, calculating the feature matching degree of the dynamic feature information and the static feature information according to the dynamic feature information and the static feature information includes:
establishing a dynamic basic function and a dynamic characteristic function according to the dynamic characteristic information;
establishing a static basic function and a static characteristic function according to the static characteristic information;
randomly generating verification data points, substituting the verification data points into the dynamic basic function, the dynamic characteristic function, the static basic function and the static characteristic function to obtain a dynamic basic function value, a dynamic characteristic function value, a static basic function value and a static characteristic function value, and substituting the dynamic basic function value, the dynamic characteristic function value, the static basic function value and the static characteristic function value into a characteristic matching degree calculation formula to obtain the characteristic matching degree.
Preferably, after determining that the authentication is not passed, the method further comprises:
acquiring the working mode of the current equipment; the working mode comprises at least one of a normal mode, a strict mode, an auxiliary verification mode and an emergency mode;
when the working mode is determined not to be an emergency mode, determining a time judging section according to the working mode;
acquiring verification failure times of identity verification failing in the time judging interval, and comparing the verification failure times with preset verification failure times;
and when the verification failure times are determined to be larger than the preset verification failure times, locking the current equipment, and entering an emergency mode.
Preferably, the locking the current device, entering the emergency mode, includes:
acquiring an emergency unlocking password of an emergency mode stored in a system;
and taking the emergency unlocking password as an encryption key to encrypt the data in the current equipment.
Preferably, after locking the current device and entering the emergency mode, the method further comprises:
acquiring a real-time unlocking password input by the user;
comparing the real-time unlocking password with the emergency unlocking password;
and when the real-time unlocking password is determined to be the same as the emergency unlocking password, taking the real-time unlocking password as a decryption key, and performing decryption processing on the data in the current equipment.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention provides a general identity verification method based on various biological characteristics, and the processing and verification of the various biological characteristics are completed through a set of algorithm, so that the universality of the verification algorithm is ensured, and the loss of computational power resources of a computer is reduced.
2. The invention provides a method for acquiring and correcting characteristic information, which is based on a rectangular coordinate system and is used for carrying out data processing on the characteristic information.
3. The invention provides an evaluation method of a digital biological feature block, which is used for screening according to the type evaluation value of the digital biological feature block (namely the reference value of the block) in the verification process, reserving the block with high reference value, removing the block with low reference value and improving the verification speed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a generic authentication method based on multiple biological features according to one embodiment of the invention;
FIG. 2 is a schematic diagram of dynamic biometric processing according to one embodiment of the invention;
fig. 3 is a schematic diagram of an emergency mode operation principle according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
As shown in fig. 1, the present invention provides a general identity verification method based on multiple biological characteristics, which is characterized by comprising S1-S42:
s1, acquiring dynamic biological characteristics of a current user;
s2, acquiring static biological characteristics of a target user stored in a system;
s3, calculating a first matching degree of the current user and the target user according to the dynamic biological characteristics and the static biological characteristics, and judging whether the first matching degree is larger than a preset first matching degree or not;
s41, when the first matching degree is determined to be larger than the preset first matching degree, passing the authentication; s42, otherwise, the identity verification fails, and identity verification failure information is returned.
The working principle of the technical scheme is as follows: acquiring the biological characteristics of the current user, wherein the biological characteristics comprise unique biological characteristics such as fingerprints, pupil patterns, face and the like, acquiring static biological characteristics of a target user stored in a system after acquiring dynamic biological characteristics of the current user, analyzing and processing the characteristics, calculating a first matching degree, and when the first matching degree is larger than a preset value, indicating that the similarity between the current user and the target user is high, and passing the authentication; otherwise, the identity verification fails, and verification failure information is returned.
The beneficial effects of the technical scheme are that: because the biological characteristics of each person are different, the biological characteristics of different persons are quite different, and the identity of the user can be accurately judged according to the matching degree of the biological characteristics, so that the safety is extremely high.
According to some embodiments of the invention, calculating a first degree of matching between the current user and the target user based on the dynamic biometric and the static biometric comprises:
performing digital processing on the dynamic biological characteristics to obtain digital dynamic biological characteristics; dividing the digital dynamic biological characteristics to obtain a plurality of digital dynamic biological characteristic blocks;
performing digital processing on the static biological characteristics to obtain digital static biological characteristics; dividing the digital static biological characteristics to obtain a plurality of digital static biological characteristic blocks;
extracting a plurality of digital dynamic biological feature blocks and digital static biological feature blocks corresponding to each digital dynamic biological feature block;
acquiring dynamic characteristic information of the digital dynamic biological characteristic block;
acquiring static characteristic information of the digital static biological characteristic block;
calculating the feature matching degree of the dynamic feature information and the static feature information; the feature matching degree is a first matching degree of the current user and the target user.
The working principle of the technical scheme is as follows: because the computer cannot identify the biological characteristics, the biological characteristics need to be digitally processed to obtain the digital biological characteristics (including digital dynamic biological characteristics and digital static biological characteristics) which can be identified by the computer; because the data in the digital biological characteristics are unevenly distributed, a part of the digital biological characteristics are in a blank state or sparse in data quantity, the part of the digital biological characteristics have no reference significance, the digital biological characteristics need to be divided, only a significant part is extracted for processing, the characteristic information is obtained, and the characteristic matching degree of the characteristic information is the first matching degree.
The beneficial effects of the technical scheme are that: discarding the blocks with meaningless data content only retains the meaningful digitized biological feature blocks with higher data content, thereby being beneficial to reducing the calculated amount and accelerating the verification speed.
According to some embodiments of the present invention, extracting a plurality of digitized dynamic biometric blocks and digitized static biometric blocks corresponding to each digitized dynamic biometric block comprises:
numbering the digitized dynamic biological feature blocks and the digitized static biological feature blocks respectively;
acquiring basic data information of the digital dynamic biological feature block; the basic data information comprises the number of data types and the richness of each data;
extracting a plurality of digital dynamic biological feature blocks as target digital dynamic biological feature blocks according to the basic data information;
acquiring the number of the target digital dynamic biological feature block, and establishing a target number sequence;
and extracting the digital static biological feature block corresponding to the target digital dynamic biological feature block according to the target serial number sequence.
The working principle of the technical scheme is as follows: for example, when the digitized dynamic biological feature is segmented to obtain 9 digitized dynamic biological feature blocks, the digitized static biological feature is segmented according to the same algorithm to obtain 9 digitized static biological feature blocks, and the 18 blocks are corresponding to each other in pairs, and the corresponding blocks are marked with the same blocks due to the same segmentation algorithm; and extracting a plurality of digital dynamic biological characteristic blocks suitable for calculating the first matching degree according to the basic data information (the basic data information comprises the data information richness and the data information type quantity) of the blocks, and acquiring corresponding digital static biological characteristic blocks according to the serial numbers of the blocks.
The beneficial effects of the technical scheme are that: the digital static biological feature blocks are matched with the digital dynamic biological feature blocks in a numbering mode, and only the dynamic biological feature blocks and the corresponding static biological feature blocks are directly selected after the numbering of the dynamic biological feature blocks are extracted, so that the additional extraction of the static biological feature blocks is not needed, the operation steps are reduced, and the efficiency is improved.
According to some embodiments of the invention, extracting a plurality of digitized dynamic biometric blocks as target digitized dynamic biometric blocks from the base data information comprises:
acquiring attribute information of the digital dynamic biological feature block; the attribute information is the type of the dynamic biological feature corresponding to the digital dynamic biological feature block;
analyzing the type of the data information included in the digital dynamic biological feature block and the weight of each data information according to the basic data information and the attribute information;
calculating according to the type of the data information of the digital dynamic biological feature block and the weight of each data information to obtain a type evaluation value of the digital dynamic biological feature block;
comparing the type evaluation value with a preset type evaluation value;
and marking the digital dynamic biological feature block as a target digital dynamic biological feature block when the type evaluation value is determined to be larger than the preset type evaluation value.
The working principle of the technical scheme is as follows: for example, when the dynamic biometric feature is a fingerprint, the digitized dynamic biometric feature block (i.e., digitized fingerprint block) is a digitized image including a plurality of discrete points, and the fingerprint pattern can be divided into continuous lines, lines including turns and closed lines, and after image processing, the three lines become three discrete point sets, and the weights of the three discrete point sets are different, and for the fingerprint, the discrete point set weight of the turned line is the highest, and the weight of the closed line corresponding to the discrete point set is the lowest. And calculating the type evaluation value of the digital fingerprint block according to the number and the weight of the three types of scattered point sets. For example, when the number of turned line scatter sets is 3 and the weight thereof is 0.5, the type evaluation value of the contribution of the turned line scatter sets is 1.5, and according to the same manner, we can calculate the type evaluation values of the remaining two scatter sets, and sum the type evaluation values of the three scatter sets to obtain the type evaluation value of the digitized fingerprint block, wherein the type evaluation value is greater than the preset type evaluation value to indicate that the block has a very high reference meaning, and the block is used as the target digitized dynamic biological feature block (hereinafter, the working principle of the technical scheme is partially abbreviated as the target block).
The beneficial effects of the technical scheme are that: the target block is screened according to the reference value, so that the stability of the verification process and the reliability of the verification result can be ensured.
According to some embodiments of the invention, obtaining the dynamic feature information of the digitized dynamic biometric block comprises:
performing high-pass filtering correction on the target digital dynamic biological feature block to obtain primary dynamic feature information;
dividing the first-level dynamic characteristic information into first-class dynamic characteristic information, second-class dynamic characteristic information and third-class dynamic characteristic information; the first type of dynamic characteristic information is endpoint characteristic information; the second type of dynamic characteristic information is turning point characteristic information; the third type of dynamic characteristic information is closed point characteristic information;
establishing a rectangular coordinate system, and acquiring primary coordinate information corresponding to the primary dynamic characteristic information; the primary coordinate information comprises first-type dynamic coordinate information corresponding to the first-type dynamic feature information, second-type dynamic coordinate information corresponding to the second-type dynamic feature information and third-type dynamic coordinate information corresponding to the third-type dynamic feature information;
correcting the primary coordinate information to obtain secondary coordinate information; and performing de-coordinated processing on the secondary coordinate information to obtain secondary dynamic characteristic information corresponding to the secondary coordinate information, and marking the secondary dynamic characteristic information as dynamic characteristic information.
The working principle of the technical scheme is as follows: for example, filtering the target digitized biological feature block, discarding the unobtrusive feature points, only retaining the highlighted feature points as first-level dynamic feature information, establishing a coordinate system, converting the first-level dynamic feature information into first-level coordinate information, where the first-level dynamic feature information is already described in the previous scheme and is classified into three types, so that the first-level coordinate information includes three types of dynamic coordinate information (first-type dynamic coordinate information, second-type dynamic coordinate information and third-type dynamic coordinate information), and correcting one or more of the three types of dynamic coordinate information to obtain second-level coordinate information. The primary dynamic coordinate information is the result of converting the primary characteristic information into a coordinate system, and the corresponding secondary characteristic information can be obtained by carrying out opposite processing on the secondary dynamic coordinate information, wherein the secondary characteristic information is the characteristic information; the dynamic biological characteristic information and the static biological characteristic information are processed in the mode.
The beneficial effects of the technical scheme are that: filtering the target block, discarding the unobtrusive feature points, and only reserving the outstanding feature points, so that the calculated amount can be reduced, and the calculation speed can be increased; the characteristic information of the target block is converted into the coordinate system, so that the processing speed is high, and the accuracy is high.
According to some embodiments of the invention, correcting the primary coordinate information to obtain secondary coordinate information includes:
judging whether the first type of dynamic coordinate information, the second type of dynamic coordinate information and the third type of dynamic coordinate information in the primary coordinate information need correction processing according to the attribute information of the digital dynamic biological feature block, and acquiring a judging result;
when the determined result is that the i-th type dynamic coordinate information needs to be corrected, a corresponding i-th type coordinate information correction algorithm is obtained;
and carrying out correction processing on the ith dynamic coordinate information according to the ith coordinate information correction algorithm.
Further, the invention provides a coordinate correction algorithm corresponding to the second type of dynamic coordinate information, which comprises the following steps:
acquiring a plurality of data point sets included in the second type of dynamic coordinate information, and numbering the data point sets;
acquiring coordinates of each data point in the data point set, and respectively recording the coordinates as coordinate points A (x 1 ，y 1 ) Coordinate point B (x 2 ，y 2 ) Coordinate point C (x 3 ，y 3 ）；
Ordering the ordinate of the coordinate point A, B, C from small to large, and taking the coordinate point corresponding to the ordinate intermediate value as a characteristic coordinate base point;
shielding the characteristic coordinate base points, taking the first coordinate point of the remaining two coordinate points as a symmetry center, and obtaining the symmetry point of the second coordinate point; similarly, taking the second coordinate point as a symmetry center, and acquiring a symmetry point of the first coordinate point;
taking the coordinate point A, B, C as a basic data set and taking the characteristic coordinate basic point and two symmetrical points as a characteristic data set;
the processing modes of the rest data point sets are the same;
combining the basic data set and the characteristic data set of all data point sets into a target data set, wherein the target data set is the second type of dynamic coordinate information.
The working principle of the technical scheme is as follows: in the above technical solution, for different types of biological features, weights of three types of feature information are different, for example, the turning point feature information of the fingerprint has a higher weight, the closing point feature information has a lowest weight (because of fewer closing points in the fingerprint), and the closing point feature information of the face has a highest weight, so that we need to process the feature information with a higher weight according to the type of biological feature; the present invention provides a processing scheme of the second type of coordinate information (corresponding to turning point characteristic information), for example, when y 1 ＜y 2 ＜y 3 When y is 2 The corresponding coordinate point is the coordinate point B as the characteristic coordinate base point; when the coordinate point B is a feature coordinate base pointA symmetry point C1 (X) of the coordinate point C is obtained with the coordinate point a as a symmetry center 3 ，Y 3 ) In this process, according to the mathematical principle, we can know that,，we can obtain y3=2y 2 －y 3 ，X3=2x 2 －x 3 The method comprises the steps of carrying out a first treatment on the surface of the The coordinate point C is taken as a symmetry center to obtain a symmetry point C1 of the coordinate point A; a, B, C is taken as a basic data set, and A1 and B, C1 are taken as characteristic data sets. The dynamic characteristic coordinate information and the static characteristic coordinate information are obtained and processed in the above mode.
The beneficial effects of the technical scheme are that: and according to the type of the biological characteristics, correcting coordinate information of a certain type in a targeted manner, ensuring the reliability of a verification result, reducing the calculated amount and further improving the verification speed.
According to some embodiments of the invention, calculating the feature matching degree of the dynamic feature information and the static feature information includes:
establishing a dynamic basic function and a dynamic characteristic function according to the dynamic characteristic information;
establishing a static basic function and a static characteristic function according to the static characteristic information;
randomly generating verification data points, substituting the verification data points into the dynamic basic function, the dynamic characteristic function, the static basic function and the static characteristic function to obtain a dynamic basic function value, a dynamic characteristic function value, a static basic function value and a static characteristic function value, and substituting the dynamic basic function value, the dynamic characteristic function value, the static basic function value and the static characteristic function value into a first matching degree calculation formula to obtain the characteristic matching degree.
The method for establishing the basic function and the characteristic function comprises the following steps:
acquiring a target data set corresponding to the first type of dynamic characteristic information, the second type of dynamic characteristic information, the third type of dynamic characteristic information and each type of dynamic characteristic information in the dynamic characteristic information;
acquiring a basic data set and a characteristic data set in the target data set;
carrying out nonlinear fitting on data points in the basic data set by using a least square method to obtain a basic function; fitting the data points in the characteristic data set to obtain a characteristic function;
and establishing a basic function and a feature function according to the static feature information.
The calculation formula of the first matching degree comprises:
wherein P is the first matching degree, J is the verification data point substituted into the dynamic basic function value, K is the verification data point substituted into the dynamic feature function value, alpha is the weight of the dynamic basic function, beta is the weight of the dynamic feature function, and because the reference meaning of the feature function is larger, the values of 0 < alpha < beta, alpha and beta are determined by the types of the dynamic biological features corresponding to the dynamic feature information; n is an adjustable parameter, N is more than 0 and less than 1, S is a verification data point substituted into a static basis function value, T is a verification data point substituted into a static basis function value, epsilon is a weight value of the static basis function, zeta is a weight value of a static characteristic function, epsilon is more than 0 and less than zeta, and the values of epsilon and zeta are determined by the type of the static biological characteristic corresponding to the static characteristic information.
As shown in fig. 2, the present invention provides a dynamic biometric processing schematic diagram, comprising 2-1 to 2-6:
2-1, acquiring dynamic biological characteristic information of a current user, and performing digital processing on the dynamic biological characteristic information; as shown in the figure, after the user fingerprint image is read, the user fingerprint image is subjected to digital processing to obtain a digital image; the process for digitizing the fingerprint image of the user comprises the following steps: one or more of tone scale adjustment, image binarization and filtering;
2-2, after the dynamic biological feature information is digitally processed, a digital image containing a plurality of lines is obtained, and the digital image is processed to obtain end points of a plurality of nearly straight lines with different sizes, turning points of the turning lines and closing points (which do not exist in the embodiment illustrated in the figure) of the closing lines; the black solid dots in 2-2 in FIG. 2 represent the end points and turning points, and the size of the dots represents the degree of prominence;
2-3, processing the image containing the scattered points and the lines obtained in the step 2 to obtain primary dynamic characteristic information (in the embodiment, a set of the scattered points with different sizes);
2-4, carrying out high-pass filtering on the scattered point set image obtained in the step 2-3, and only retaining more prominent first-level dynamic characteristic information (namely black original points with larger radius);
2-5, establishing a rectangular coordinate system to obtain primary dynamic feature coordinate information corresponding to the primary dynamic feature information;
2-6, correcting the primary dynamic feature coordinate information in the rectangular coordinate system to obtain secondary dynamic feature coordinate information; the secondary dynamic feature coordinate information comprises dynamic basic data points (scattered point sets formed by dots) and dynamic feature data points (X marks in images), the dynamic basic data points and the dynamic feature data points are respectively grouped, a dynamic basic data set and a dynamic feature data set are established, and the dynamic basic data set and the dynamic feature data set are respectively fitted to obtain a dynamic basic function (shown by solid lines in 2-6 in fig. 2) and a dynamic feature function (shown by broken lines in 2-6 in fig. 2).
It should be noted that, the steps of some technologies in the embodiment shown in fig. 2 are slightly different from those in the technical solution before fig. 2, and the two embodiments are different, but are all embodiments formed according to the technical solution, and do not limit the present invention, and it should be noted that the exchange of specific steps in the technical solution shown in the two embodiments does not affect the beneficial effects of the present invention, and are also within the scope of the present invention.
The working principle of the technical scheme is as follows: fitting the basic data set and the characteristic data set by using a least square method to obtain a basic function and a characteristic function, randomly generating data points, substituting the data points into the basic function and the characteristic function respectively, and substituting the calculated basic function value and characteristic function value into a first matching degree calculation formula to calculate the first matching degree.
The beneficial effects of the technical scheme are that: the first matching degree is quantized, and the calculation result is more accurate; the existence of the adjustable parameter N in the first matching degree calculation formula enables a user to adjust verification accuracy according to own requirements, and user experience is improved.
As shown in fig. 3, the present invention provides a schematic diagram of an emergency mode operation principle, including S31-S38:
s31, acquiring a working mode of the current equipment;
s32, when the working mode is determined not to be an emergency mode, determining a time judging section according to the working mode;
s33, acquiring verification failure times of identity verification failing in the time judging interval, and comparing the verification failure times with preset verification failure times;
s34, locking the current equipment and entering an emergency mode when the verification failure times are determined to be larger than the preset verification failure times;
s35, acquiring an emergency unlocking password of an emergency mode stored in a system, and encrypting data in the current equipment by taking the emergency unlocking password as an encryption key;
s36, acquiring a real-time unlocking password input by the user;
s37, comparing the real-time unlocking password with the emergency unlocking password;
and S38, when the real-time unlocking password is determined to be the same as the emergency unlocking password, taking the real-time unlocking password as a decryption key, and performing decryption processing on the data in the current equipment.
The working principle of the technical scheme is as follows: and presetting a plurality of working modes for the equipment, locking the equipment when the equipment identity verification failure times exceed preset times within a fixed time, encrypting data according to an emergency unlocking password preset by a user, and decrypting the data according to the password input by the current user when the emergency unlocking password input by the current user is identical to the emergency unlocking password preset by the user.
The beneficial effects of the technical scheme are that: setting an emergency mode, and entering the emergency mode to seal and store the data of the user when the user encounters a special condition and the biological characteristics cannot be identified or the biological characteristics cannot be identified for a plurality of times, so that the data of the user is prevented from leaking, and the safety is improved; the data is encrypted by taking the emergency unlocking password preset by the user as an encryption key, and the emergency unlocking password input by the current user is used as a decryption key in decryption, so that the system can be prevented from judging the emergency unlocking password input by the current user by mistake as the preset emergency unlocking password, the secondary verification is performed, the safety is improved, and the verification system is prevented from being cracked to a certain extent.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. A universal authentication method based on multiple biological features, comprising:
acquiring the dynamic biological characteristics of the current user; the dynamic biological characteristics are biological characteristics of the current user acquired in real time;
acquiring static biological characteristics of a target user stored in a system;
according to the dynamic biological characteristics and the static biological characteristics, calculating a first matching degree of the current user and the target user, and judging whether the first matching degree is larger than a preset first matching degree or not;
when the first matching degree is determined to be larger than the preset first matching degree, passing the identity verification; otherwise, the identity verification fails, and information of failure in the identity verification is returned;
according to the dynamic biological characteristics and the static biological characteristics, calculating a first matching degree between the current user and the target user comprises the following steps:
performing digital processing on the dynamic biological characteristics to obtain digital dynamic biological characteristics; dividing the digital dynamic biological characteristics to obtain a plurality of digital dynamic biological characteristic blocks;
performing digital processing on the static biological characteristics to obtain digital static biological characteristics; dividing the digital static biological characteristics to obtain a plurality of digital static biological characteristic blocks;
extracting a plurality of digital dynamic biological feature blocks and digital static biological feature blocks corresponding to each digital dynamic biological feature block;
acquiring dynamic characteristic information of the digital dynamic biological characteristic block;
acquiring static characteristic information of the digital static biological characteristic block;
calculating the feature matching degree of the dynamic feature information and the static feature information; the feature matching degree is a first matching degree of the current user and the target user;
calculating the feature matching degree of the dynamic feature information and the static feature information according to the dynamic feature information and the static feature information, including:
establishing a dynamic basic function and a dynamic characteristic function according to the dynamic characteristic information;
establishing a static basic function and a static characteristic function according to the static characteristic information;
randomly generating verification data points, substituting the verification data points into the dynamic basic function, the dynamic characteristic function, the static basic function and the static characteristic function to obtain a dynamic basic function value, a dynamic characteristic function value, a static basic function value and a static characteristic function value, and substituting the dynamic basic function value, the dynamic characteristic function value, the static basic function value and the static characteristic function value into a characteristic matching degree calculation formula to obtain characteristic matching degree;
the method for establishing the basic function and the characteristic function comprises the following steps:
acquiring a target data set corresponding to the first type of dynamic characteristic information, the second type of dynamic characteristic information, the third type of dynamic characteristic information and each type of dynamic characteristic information in the dynamic characteristic information;
acquiring a basic data set and a characteristic data set in the target data set;
carrying out nonlinear fitting on data points in the basic data set by using a least square method to obtain a basic function; fitting the data points in the characteristic data set to obtain a characteristic function;
the calculation formula of the first matching degree comprises:
wherein P is the first matching degree, J is the verification data point substituted into the dynamic basic function value, K is the verification data point substituted into the dynamic feature function value, alpha is the weight of the dynamic basic function, beta is the weight of the dynamic feature function, and because the reference meaning of the feature function is larger, the values of 0 < alpha < beta, alpha and beta are determined by the types of the dynamic biological features corresponding to the dynamic feature information; n is an adjustable parameter, N is more than 0 and less than 1, S is a verification data point substituted into a static basis function value, T is a verification data point substituted into a static basis function value, epsilon is a weight value of the static basis function, zeta is a weight value of a static characteristic function, epsilon is more than 0 and less than zeta, and the values of epsilon and zeta are determined by the type of the static biological characteristic corresponding to the static characteristic information.
2. The method of claim 1, wherein extracting a plurality of digitized dynamic biometric blocks and digitized static biometric blocks corresponding to each digitized dynamic biometric block comprises:
numbering the digitized dynamic biological feature blocks and the digitized static biological feature blocks respectively;
acquiring basic data information of the digital dynamic biological feature block; the basic data information comprises the number of data types and the richness of each data;
extracting a plurality of digital dynamic biological feature blocks as target digital dynamic biological feature blocks according to the basic data information;
acquiring the number of the target digital dynamic biological feature block, and establishing a target number sequence;
and extracting the digital static biological feature block corresponding to the target digital dynamic biological feature block according to the target serial number sequence.
3. The universal authentication method based on multiple biological features of claim 2, wherein extracting a number of digitized dynamic biological feature blocks as target digitized dynamic biological feature blocks from the basic data information comprises:
acquiring attribute information of the digital dynamic biological feature block; the attribute information is the type of the dynamic biological feature corresponding to the digital dynamic biological feature block;
analyzing the type of the data information included in the digital dynamic biological feature block and the weight of each data information according to the basic data information and the attribute information;
calculating according to the type of the data information of the digital dynamic biological feature block and the weight of each data information to obtain a type evaluation value of the digital dynamic biological feature block;
comparing the type evaluation value with a preset type evaluation value;
and marking the digital dynamic biological feature block as a target digital dynamic biological feature block when the type evaluation value is determined to be larger than the preset type evaluation value.
4. The method of claim 1, wherein obtaining dynamic feature information of the digitized dynamic biometric block comprises:
performing high-pass filtering correction on the target digital dynamic biological feature block to obtain primary dynamic feature information;
dividing the first-level dynamic characteristic information into first-class dynamic characteristic information, second-class dynamic characteristic information and third-class dynamic characteristic information; the first type of dynamic characteristic information is endpoint characteristic information; the second type of dynamic characteristic information is turning point characteristic information; the third type of dynamic characteristic information is closed point characteristic information;
establishing a rectangular coordinate system, and acquiring primary coordinate information corresponding to the primary dynamic characteristic information; the primary coordinate information comprises first-type dynamic coordinate information corresponding to the first-type dynamic feature information, second-type dynamic coordinate information corresponding to the second-type dynamic feature information and third-type dynamic coordinate information corresponding to the third-type dynamic feature information;
correcting the primary coordinate information to obtain secondary coordinate information;
and performing de-coordinated processing on the secondary coordinate information to obtain secondary dynamic characteristic information corresponding to the secondary coordinate information, and marking the secondary dynamic characteristic information as dynamic characteristic information.
5. The method for universal authentication based on multiple biological features according to claim 4, wherein correcting the primary coordinate information to obtain secondary coordinate information comprises:
judging whether the first type of dynamic coordinate information, the second type of dynamic coordinate information and the third type of dynamic coordinate information in the primary coordinate information need correction processing according to the attribute information of the digital dynamic biological feature block, and acquiring a judging result;
when the determined result is that the i-th type dynamic coordinate information needs to be corrected, a corresponding i-th type coordinate information correction algorithm is obtained;
and carrying out correction processing on the ith dynamic coordinate information according to the ith coordinate information correction algorithm.
6. The multi-biometric based universal authentication method according to claim 1, further comprising, after determining that authentication is failed:
acquiring the working mode of the current equipment; the working mode comprises at least one of a normal mode, a strict mode, an auxiliary verification mode and an emergency mode;
when the working mode is determined not to be an emergency mode, determining a time judging section according to the working mode;
acquiring verification failure times of identity verification failing in the time judging interval, and comparing the verification failure times with preset verification failure times;
and when the verification failure times are determined to be larger than the preset verification failure times, locking the current equipment, and entering an emergency mode.
7. The multiple biometric based universal authentication method according to claim 6, wherein the locking the current device into emergency mode comprises:
acquiring an emergency unlocking password of an emergency mode stored in a system;
and taking the emergency unlocking password as an encryption key to encrypt the data in the current equipment.
8. The multiple biometric based universal authentication method according to claim 7, further comprising, after locking the current device into the emergency mode:
acquiring a real-time unlocking password input by the user;
comparing the real-time unlocking password with the emergency unlocking password;
and when the real-time unlocking password is determined to be the same as the emergency unlocking password, taking the real-time unlocking password as a decryption key, and performing decryption processing on the data in the current equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211697075.0A CN116305043B (en) | 2022-12-28 | 2022-12-28 | Universal identity verification method based on multiple biological characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211697075.0A CN116305043B (en) | 2022-12-28 | 2022-12-28 | Universal identity verification method based on multiple biological characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116305043A CN116305043A (en) | 2023-06-23 |
| CN116305043B true CN116305043B (en) | 2023-12-19 |
Family
ID=86836639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211697075.0A Active CN116305043B (en) | 2022-12-28 | 2022-12-28 | Universal identity verification method based on multiple biological characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116305043B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152318A (en) * | 2011-12-07 | 2013-06-12 | ***通信集团天津有限公司 | Identity authentication method, device and system thereof |
| CN103646199A (en) * | 2013-12-26 | 2014-03-19 | 中国电子科技集团公司第三研究所 | Sudoku password and facial image-based authentication method |
| CN104615992A (en) * | 2015-02-11 | 2015-05-13 | 浙江中烟工业有限责任公司 | Long-distance fingerprint dynamic authentication method |
| CN104809453A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Authentication method based on fingerprints |
| CN105046144A (en) * | 2015-07-02 | 2015-11-11 | 成都亿邻通科技有限公司 | Protection method for application program of mobile terminal |
| CN113688671A (en) * | 2021-07-14 | 2021-11-23 | 公安部物证鉴定中心 | Fingerprint similarity calculation method and device, storage medium and terminal |
| CN113986581A (en) * | 2021-10-29 | 2022-01-28 | 平安普惠企业管理有限公司 | Data aggregation processing method and device, computer equipment and storage medium |
| CN114268453A (en) * | 2021-11-17 | 2022-04-01 | 中国南方电网有限责任公司 | Power system unlocking method and device, computer equipment and storage medium |
-
2022
- 2022-12-28 CN CN202211697075.0A patent/CN116305043B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152318A (en) * | 2011-12-07 | 2013-06-12 | ***通信集团天津有限公司 | Identity authentication method, device and system thereof |
| CN103646199A (en) * | 2013-12-26 | 2014-03-19 | 中国电子科技集团公司第三研究所 | Sudoku password and facial image-based authentication method |
| CN104615992A (en) * | 2015-02-11 | 2015-05-13 | 浙江中烟工业有限责任公司 | Long-distance fingerprint dynamic authentication method |
| CN104809453A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Authentication method based on fingerprints |
| CN105046144A (en) * | 2015-07-02 | 2015-11-11 | 成都亿邻通科技有限公司 | Protection method for application program of mobile terminal |
| CN113688671A (en) * | 2021-07-14 | 2021-11-23 | 公安部物证鉴定中心 | Fingerprint similarity calculation method and device, storage medium and terminal |
| CN113986581A (en) * | 2021-10-29 | 2022-01-28 | 平安普惠企业管理有限公司 | Data aggregation processing method and device, computer equipment and storage medium |
| CN114268453A (en) * | 2021-11-17 | 2022-04-01 | 中国南方电网有限责任公司 | Power system unlocking method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 优化非线性回归目标函数的数值实验;毛在砂;;化工学报(第07期);第1659-1665页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116305043A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101057248B (en) | Fingerprint biomass machine | |
| Ren et al. | Finger vein recognition system with template protection based on convolutional neural network | |
| CN112420187B (en) | Medical disease analysis method based on migratory federal learning | |
| CN102306305A (en) | Method for authenticating safety identity based on organic characteristic watermark | |
| CN109886202B (en) | IoM-based revocable palm print competition code feature identification method | |
| CN111507206A (en) | Finger vein identification method based on multi-scale local feature fusion | |
| Cho et al. | Core-based fingerprint image classification | |
| Ayoup et al. | Cancellable Multi-Biometric Template Generation Based on Arnold Cat Map and Aliasing. | |
| CN116305043B (en) | Universal identity verification method based on multiple biological characteristics | |
| Lv et al. | An algorithm of Iris feature-extracting based on 2D Log-Gabor | |
| Shao et al. | Template protection based on chaotic map for finger vein recognition | |
| Choudhary et al. | Multimodal biometric-based authentication with secured templates | |
| Islam et al. | Technology review: image enhancement, feature extraction and template protection of a fingerprint authentication system | |
| Hachim et al. | Iris-based authentication model in cloud environment (iamce) | |
| CN111046363B (en) | Identity verification method based on iris feature alliance random matching voting mechanism | |
| Shehu et al. | Detecting an alteration in biometric fingerprint databases | |
| Wickramaarachchi et al. | An effective iris biometric privacy protection scheme with renewability | |
| Reddy et al. | Authentication using fuzzy vault based on iris textures | |
| Mishra et al. | A neoteric approach for ear biometrics using multilinear PCA | |
| Yuan et al. | A low-rank LBP with local differential polarisation for fingerprint liveness detection | |
| Ashraf et al. | THE FRAMEWORK DESIGN FOR INCREASING SECURITY OF MULTI-MODAL BIOMETRIC AUTHENTICATION SYSTEM WITH DNN. | |
| Fernandez et al. | Biometric watermarking: an application-based review | |
| Sushma et al. | Multi Biometric Template Protection using Random Projection and Adaptive Bloom Filter | |
| Roy et al. | Iris recognition using biometric techniques | |
| Kaur et al. | Real-time chaff generation for a biometric fuzzy vault |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |