CN111723595A - Personnel identity identification method and system - Google Patents
Personnel identity identification method and system Download PDFInfo
- Publication number
- CN111723595A CN111723595A CN201910201605.XA CN201910201605A CN111723595A CN 111723595 A CN111723595 A CN 111723595A CN 201910201605 A CN201910201605 A CN 201910201605A CN 111723595 A CN111723595 A CN 111723595A
- Authority
- CN
- China
- Prior art keywords
- finger vein
- feature information
- person
- recognition
- finger
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 210000003462 vein Anatomy 0.000 claims abstract description 180
- 230000001815 facial effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000011524 similarity measure Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 7
- 239000013598 vector Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000001727 in vivo Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 210000000554 iris Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
A personnel identification method and a system thereof, the method comprises: collecting face feature information of a recognized person; collecting finger vein characteristic information of the identified person; performing face recognition using the face feature information to obtain a set of persons meeting a predetermined condition; and performing finger vein recognition for the persons in the set using the finger vein feature information to obtain a recognition result.
Description
Technical Field
The invention relates to the field of identity recognition, in particular to a person identity recognition method and system combining face recognition and finger vein recognition.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The safe and reliable personnel identification is the premise and the basis for the development of all security and protection safety, financial payment business, travel clearance and the like. The biometric technology has the advantages of safety and reliability and user experience, which cannot be achieved by the traditional core segment, and is gaining favor of more and more financial institutions and high-tech companies, and is gradually applied to identification of various scenes of the society, such as: (1) the entrance and exit of the prison entrance guard of enterprises, colleges and universities and judicial prisons; (2) high-speed rail and airplane clearance; (3) ATM withdrawals and small financial consumption payments; (4) annual park card access, etc. However, at the same time, biometric identification as an emerging thing raises concerns about risks, and especially the application of biometric identification in the financial field presents challenges. On the premise of not depending on other identity documents or personal information, how to ensure the safety of identity verification and improve the comparison efficiency of biological characteristics determines whether the biological identification technology can become the key of mainstream application in a large-scale crowd application scene (such as million-level city crowd scale).
Biometric identification is a new identification technology. In real life, everyone is distinguished from other people's unique biological characteristics, such as fingerprints, veins, human faces, voiceprints, irises, etc. Although biometric identification techniques have been developed in great length, certain problems still remain. The fingerprint identification history is longest, the technology is the most mature, but the problems of difficult fingerprints, stained fingerprints, forged fingerprints and the like exist; the iris image has the advantages of high precision, high safety performance, non-contact acquisition and the like, but the acquisition hardware has high configuration requirement and huge configuration; the voiceprint recognition is good in uniqueness, but is easily influenced by physical conditions, age, emotion and the like, and the extraction and modeling difficulty is high.
Face recognition has the advantages of collecting non-contact and rapid recognition, is the most widely applied biological feature at present, but has changeability (such as illumination, angle, expression, shielding, age increase, face-lifting and the like all can change facial features), and when the scale of a personnel database is too large, the face recognition method comprises the following steps of 1: and the N identification error rate is higher.
The finger vein authentication technology is a second generation biometric technology with high precision, which performs personal identification by using vein line images obtained after near infrared rays penetrate fingers. The finger vein recognition technology is to obtain vein lines for recognition by the reaction of flowing blood in vivo to infrared light. The finger vein belongs to the internal characteristics of a human body and is difficult to forge and steal; the finger vein image can be acquired only under the condition of living body, so that the forgery and the falsification are extremely difficult. Therefore, the finger vein authentication technique 1: 1, highly accurate authentication, wherein FRR (false rejection) is less than 0.01%, FAR (false acceptance) is less than 0.0001%; the disadvantage is that the authentication speed is relatively slow.
In the prior art, various biological characteristics are adopted for identity recognition, but the schemes usually adopt parallel fusion, namely after the recognition result of each biological characteristic is calculated, the final recognition result is determined through weight or priority, but the scheme has the disadvantages of low authentication speed and high error rate.
Therefore, a scheme for efficiently and accurately identifying the identity of a person is needed.
Disclosure of Invention
The present invention provides more sufficient identification information by combining a plurality of biometric information to achieve high identification accuracy and at the same time has relatively high identification efficiency. Specifically, through comparison of advantages and disadvantages of various biological characteristics, the method disclosed by the invention integrates face recognition and finger vein recognition, firstly uses the face recognition to carry out rapid screening, and then carries out high-precision living body verification on the finger vein recognition, so that the recognition speed is ensured, and the recognition accuracy and safety are also ensured.
One aspect of the invention relates to a person identification method, which comprises the following steps: collecting face feature information of a recognized person; collecting finger vein characteristic information of the identified person; performing face recognition using the face feature information to obtain a set of persons meeting a predetermined condition; and performing finger vein recognition for the persons in the set using the finger vein feature information to obtain a recognition result.
Optionally, the finger vein feature information is finger vein feature information of one finger of the identified person.
Optionally, the method further includes: and if the recognition result shows that the finger vein characteristic information of at least two persons in the set is matched with the finger vein characteristic information of the recognized person, acquiring the finger vein characteristic information of another finger of the recognized person, and executing finger vein recognition on the at least two persons by using the finger vein characteristic information of the another finger to obtain a new recognition result.
Optionally, the finger vein feature information includes finger vein feature information of at least two fingers of the identified person.
Optionally, the performing, for the persons in the set, finger vein recognition using the finger vein feature information to obtain a recognition result includes: performing finger vein recognition on the persons in the set by using finger vein feature information of one finger of the recognized person to obtain a preliminary recognition result; if the preliminary identification result shows that the finger vein feature information of zero or one person in the set is matched with the finger vein feature information of the identified person, taking the preliminary identification result as a final identification result; and if the preliminary identification result shows that the finger vein characteristic information of at least two persons in the set is matched with the finger vein characteristic information of the identified person, performing finger vein identification on the at least two persons by using the finger vein characteristic information of the other finger of the identified person to obtain a final identification result.
Optionally, the performing face recognition using the face feature information to obtain a set of people meeting a predetermined condition includes: comparing the face feature information with stored face feature information of each of a plurality of persons to obtain similarity measurement; and if the similarity measure is larger than a preset similarity threshold value, taking the corresponding person as the person meeting the preset condition.
Optionally, the similarity threshold is set according to requirements on accuracy or efficiency of the identification of the identity of the person.
Optionally, the acquisition of the facial feature information and the finger vein feature information is triggered simultaneously when the finger placement of the identified person is detected.
Another aspect of the invention relates to a storage medium in which a computer program is stored which, when being executed by a processor, can be used for carrying out the above-mentioned method.
Yet another aspect of the invention relates to an electronic device comprising a processor and a memory, in which a computer program is stored which, when being executed by the processor, is operative to carry out the method as described above.
Yet another aspect of the present invention relates to a person identification system, comprising: the module is used for collecting the face feature information of the identified person; the module is used for collecting finger vein characteristic information of the identified person; a module for performing face recognition using the face feature information to obtain a set of persons meeting a predetermined condition; and means for performing finger vein recognition for the persons in the set using the finger vein feature information to obtain a recognition result.
The embodiment of the invention selects the face recognition and the finger vein recognition to be fused, avoids the difficulty of in vivo detection of the face recognition by utilizing the in vivo safety of the finger vein recognition, compensates the high false recognition rate of the face recognition by utilizing the high accuracy of the finger vein recognition, and compensates the problem of low speed of the finger vein recognition by utilizing the rapid recognition capability of the face recognition. Through the combination of the two biological characteristics, the advantages are made and the disadvantages are made up, so that the aim of quickly and accurately identifying the identity of the large-scale crowd can be fulfilled. Specifically, the embodiment of the invention adopts a strategy of decision-level sequence fusion for face and finger vein recognition, namely, firstly face recognition is used for carrying out suspected set rapid screening, and then finger vein technology is used for carrying out high-accuracy and high-anti-counterfeiting identity recognition, so that the method is particularly suitable for application scenes of large-scale crowd identity recognition. In an application scene of large-scale crowd identification, the time is saved when large-scale crowd data is screened by utilizing the advantage of high face identification speed, the defect that the speed of finger vein identification is low in large-scale data processing is overcome by using finger vein identification in a screened suspected set, and the accuracy and the efficiency of large-scale crowd identification are ensured. Meanwhile, the living body safety and stability of the finger vein recognition technology ensure the reliability of identity recognition, so the method is particularly suitable for mobile payment scenes needing extremely high safety. Under the condition of not needing to input partial or complete identity information of the identified personnel, the scheme of the invention can efficiently realize million-level personnel identity identification and achieve the aims of high accuracy and high anti-counterfeiting. According to the test, the face and finger vein feature library recognition is carried out in million-level people, the authentication speed is less than 2 seconds, meanwhile, the authentication precision reaches that the FRR (false rejection rate) is less than 5 percent, and the FAR (false acceptance rate) is less than 0.0001 percent. In addition, in some embodiments of the present invention, conditions (for example, similarity threshold) that need to be met by the similarity metric of face recognition may be set as needed according to different requirements on recognition accuracy, recognition efficiency, and the like in various different scenarios, so that great flexibility and applicability may be provided for an identity recognition scheme to adapt to various different application scenarios. In some embodiments of the invention, by adopting a finger vein identification successive authentication technology, the accuracy of personnel identification can be further improved, and the situation that a plurality of matched personnel exist in the identification result can be avoided to a great extent.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings, in which:
FIG. 1 illustrates a person identification system according to one embodiment of the invention;
FIG. 2 illustrates a person identification method according to one embodiment of the invention;
FIG. 3 illustrates a person identification method using finger vein recognition progressive authentication techniques according to one embodiment of the invention; and
fig. 4 illustrates a person identification method using a finger vein recognition successive authentication technique according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail by embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 shows a person identification system according to an embodiment of the present invention, which includes a front-end system 110 and a back-end system 120, where the front-end system 110 is mainly used to implement the acquisition of face feature information and finger vein feature information of a person to be identified, and the back-end system 120 is mainly used to perform face recognition and finger vein recognition using the feature information acquired by the front-end system 110, and finally generate a recognition result. A face feature information acquisition module 111 and a finger vein feature information acquisition module 112 may be included in the front-end system 110, the face feature information acquisition module 111 is configured to acquire face feature information (for example, a face image) of the identified person, and the finger vein feature information acquisition module 112 is configured to acquire finger vein feature information (for example, a finger vein image) of the identified person. Some other components may also be included in the front-end system 110, such as a microcontroller 114, memory 115, communication device 113, and the like. The back-end system 120 is communicatively coupled to the front-end system 110 via a wired or wireless communication link and may include a back-end system platform 121, a face recognition module 122, and a finger vein recognition module 123. The face recognition module 122 is configured to perform face recognition using the face feature information acquired by the face feature information acquisition module 111. When performing face recognition, the face recognition module 122 may compare the collected face feature information of the person currently being recognized with the face feature information of the person pre-stored in the background system 120 to obtain a comparison result. The finger vein recognition module 123 is configured to perform finger vein recognition using the finger vein feature information acquired by the finger vein feature information acquisition module 112. When performing finger vein recognition, the finger vein recognition module 123 may compare the collected finger vein feature information of a certain finger of the person currently being recognized with the finger vein feature information of corresponding fingers of some persons stored in the background system 120 in advance to obtain a comparison result. The face feature information or finger vein feature information pre-stored in the back-end system 120 may be previously acquired by the front-end system 110, but may also be acquired by other means, for example, by other information acquisition devices. In one embodiment, the pre-stored facial feature information or finger vein feature information may not be located in the background system 120, but may be located in another system capable of communicating with the background system 120.
The face feature information may be any information that can be used to represent face features (e.g., face images, face feature vectors, face feature templates, etc.); similarly, the finger vein feature information may be any information that can be used to represent the finger vein features (e.g., finger vein images, finger vein feature vectors, finger vein feature templates, etc.). Moreover, the face feature information collected by the face feature information collection module 111 may not belong to the same type as the face feature information pre-stored in the background system 120, as long as they can compare the similarity with each other. For example, the face feature information collected by the face feature information collection module 111 may be a face image, and the face feature information pre-stored in the background system 120 may be a face feature template of each person. Although the face image and the face feature template are different, the similarity between the two can be determined. Similarly, the finger vein feature information collected by the finger vein feature information collection module 112 may not belong to the same type as the finger vein feature information pre-stored in the background system 120, as long as they can compare the similarity with each other.
Since a human has multiple fingers, the finger vein feature information collection module 112 can collect vein feature information of one or more fingers of the same human. Similarly, the vein feature information of one or more fingers of the person may also be included in the pre-stored finger vein feature information in the background system. When the finger vein feature information collection module 112 collects information, it may send a corresponding prompt or instruction to the person to be collected to inform the person to collect the vein feature information of which finger. In the case that successive authentication using the finger vein feature information is required (which will be described in detail later), the finger vein feature information collection module 112 may also issue a corresponding prompt or instruction to the person to whom the information is collected (for example, "please reach out other registered fingers for information collection"), so as to inform the person to collect the vein feature information of other fingers for successive authentication.
The front-end system 110 and the back-end system 120 are shown in fig. 1 as two separate systems connected by communication, but it will be understood by those skilled in the art that they may also be integrated to be implemented as one single system, e.g., as a unitary machine. In addition, the face feature information acquisition module 111 and the finger vein feature information acquisition module 112 may be implemented in one device (for example, a face and finger vein acquisition all-in-one machine), but may also be implemented in different devices. Similarly, the face recognition module 122 and the finger vein recognition module 123 may be implemented in one device, but may also be implemented in different devices.
Fig. 2 shows a person identification method according to an embodiment of the present invention, which may be implemented by using the person identification system shown in fig. 1, but may be implemented by other forms of systems as long as the systems can implement the corresponding steps of the method. The method comprises the following steps:
step 201: and collecting the face feature information of the identified person.
In one embodiment, for example, in the case of using a human face and finger vein collection all-in-one machine, when a person places a finger at a corresponding position to collect finger vein feature information, the placement of the finger is sensed by the static induction module, so as to trigger the human face feature information collection module 111 to collect information. By the method, the face characteristic information acquisition and the finger vein characteristic information acquisition can be carried out simultaneously, which is beneficial to improving the personnel identification efficiency. Moreover, when the identified person places a finger at a position where finger vein feature information is collected, the face of the identified person is usually in a relatively fixed area, which is very beneficial to collecting face feature information (for example, is beneficial to quickly collecting a high-quality face image), and the face feature information and the finger vein feature information of the identified person can be collected for the same person, so that a possible confusion phenomenon when the face feature information and the finger vein feature information are collected at different times is avoided. Therefore, the method can effectively improve the efficiency and the accuracy of personnel identification.
In one embodiment, the people recognition system may detect whether a person is near the head-end system 110 during operation, which may be accomplished using various techniques known in the art, such as capacitive proximity sensors, inductive proximity sensors, photoelectric proximity sensors, and the like. If a person is detected to be close to the front-end system 110, the facial feature information acquisition module 111 therein may be triggered to acquire facial feature information of the person, for example, to take a facial image.
Of course, it will be understood by those skilled in the art that any other feasible manner may be used to trigger the information acquisition of the face feature information acquisition module 111, for example, by manual operation.
The collected face feature information of the identified person may be sent to the back-end system 120 via a network to facilitate face recognition by the face recognition module 122 therein using the face feature information.
Step 202: collecting finger vein characteristic information of the identified person.
When the identified person places a finger at a corresponding position on the front-end system 110 for collecting the finger vein feature information, the placement of the finger is sensed by the static induction module, so as to trigger the finger vein feature information collection module 112 in the front-end system 110 to collect the information. Of course, it will be understood by those skilled in the art that any other feasible manner may be used to trigger the information collection of the finger vein feature information collection module 112, for example, manually after the identified person places the finger.
The collected finger vein feature information of the identified person may be sent to the background system 120 through a network so as to perform finger vein identification by the finger vein identification module 123 therein using the finger vein feature information.
Step 203: and performing face recognition by using the face feature information to obtain a set of persons meeting a preset condition.
After the face recognition module 122 in the background system 120 receives the collected face feature information of the recognized person, it may perform face recognition using the face feature information. Specifically, the face recognition module 122 may compare the received face feature information with face feature information of a large number of pre-stored persons one by one to determine a corresponding similarity measure. The similarity measure may be used to evaluate a degree of similarity between the received face feature information and face feature information of a certain person stored in advance. The pre-stored facial feature information that is the subject of the comparison may be stored in the background system 120 or may be stored at a remote location, such as a remote server, accessible by the face recognition module 122.
In one embodiment, the face feature information collected by the face feature information collection module 111 in the front-end system 110 is a face image, and after the face recognition module 122 receives the face image, it may perform face detection, face localization, face feature extraction, and other operations on the face image to obtain a feature vector of the face, and compare the feature vector with the face feature information (e.g., face feature templates) of all the people stored in the back-end system 120 to obtain the similarity measure.
If the similarity measure between the acquired face feature information and the face feature information of a certain person stored in advance meets a preset condition (for example, is greater than a preset similarity threshold), the person can be regarded as a qualified person. Finally, a set of all qualified persons, more precisely, identification Information (IDs) of these persons, can be obtained by face recognition.
The conditions that need to be met by the similarity measure can be flexibly set according to actual conditions. For example, if the face recognition module 122 itself has a relatively high recognition accuracy, a relatively high similarity threshold may be set, so as to reduce the number of people in the above set as much as possible without omission, so as to save the time to be spent on subsequent finger vein recognition; accordingly, if the recognition accuracy of the face recognition module 122 itself is poor, a relatively low similarity threshold may be set to avoid the occurrence of omission. In a similar manner, the conditions (e.g., similarity threshold) required to be met by the similarity measurement of face recognition can be set as required according to different requirements on recognition accuracy, recognition efficiency and the like in various different scenes, so that great flexibility and applicability can be provided for the identity recognition scheme.
Step 204: and performing finger vein identification for the persons in the set by using the finger vein characteristic information to obtain an identification result.
The finger vein recognition module 123 may receive the finger vein feature information acquired by the finger vein feature information acquisition module 112, and may receive a set of qualified persons obtained after the face recognition module 122 performs face recognition. Thereafter, the finger vein recognition module 123 may perform finger vein recognition on the persons in the set using the collected finger vein feature information to obtain a recognition result. For example, the finger vein recognition module 123 may compare the collected finger vein feature information with the finger vein feature information of each person in the set to determine whether they match.
If the result of the finger vein recognition in step 204 shows that the finger vein feature information of any one person in the set can not be matched with the collected finger vein feature information, it indicates that the identification process or the authentication process for the person currently being recognized fails. According to different scenes, the system can perform different operations, such as displaying a prompt of identification failure, refusing to perform subsequent corresponding operations (e.g., opening a door, making financial payment, etc.), prompting to perform identification again, and the like.
If the finger vein identification result shows that the finger vein characteristic information of exactly one person in the set can be matched with the collected finger vein characteristic information, the identification process or the authentication process of the person currently being identified is successful, and therefore the system can perform subsequent corresponding operations, such as opening a door, making financial payment and the like.
If the finger vein recognition result shows that the finger vein feature information of at least two persons in the set can be matched with the collected finger vein feature information, the system can consider the recognition result to be invalid and prompt the person currently being recognized to re-recognize. The re-identification process may repeat the various steps shown in fig. 2. In some cases, for security reasons, the system may also consider the identification process or the authentication process to fail directly for the above-described case.
It should be noted that the steps shown in fig. 2 do not necessarily have to be executed in the above-mentioned order, but may be executed in a different order without affecting the functional implementation thereof, or some of the steps may be executed concurrently. For example, in one embodiment, the acquisition of the facial feature information and the finger vein feature information may be performed in a different order, or may be performed concurrently. In another embodiment, the finger vein feature information may be collected after performing face recognition.
In one embodiment of the invention, in order to improve the identification accuracy and avoid the situation that the final result of the finger vein identification shows that at least two persons are matched, a successive authentication technology can be adopted for the finger vein identification.
Fig. 3 shows a person identification method using a successive finger vein recognition authentication technique according to an embodiment of the present invention, which includes the following steps (some steps in fig. 3 are similar to those in fig. 2, and are not described in detail here):
step 301: and collecting the face feature information of the identified person.
Step 302: collecting finger vein characteristic information of one finger of the identified person.
Step 303: and performing face recognition by using the face feature information to obtain a set of persons meeting a preset condition.
Step 304: and performing finger vein recognition on the persons in the set by using the finger vein characteristic information of the finger to obtain a recognition result.
Step 305: and analyzing the finger vein recognition result to judge whether the finger vein characteristic information of at least two persons is matched with the finger vein characteristic information of the recognized person.
Step 306: if the judgment result is yes, the finger vein feature information of another finger of the identified person can be further collected, and finger vein identification is carried out on the at least two persons by using the finger vein feature information of the another finger to obtain a new identification result.
There may still be at least two people matching the identified person in the new recognition result, but the probability is greatly reduced compared to the case of using only one finger. In one embodiment, in the case that there are still at least two people matching the identified person in the new identification result, the identification result may be considered invalid, the identification process may be stopped, and subsequent corresponding operations (e.g., opening doors, making financial payments, etc.) may be denied.
If the new recognition result shows that the finger vein feature information of any one person can not be matched with the finger vein feature information of the other finger of the person to be recognized, the recognition process or the authentication process for the person currently being recognized is considered to fail.
If the new recognition result shows that the finger vein characteristic information of exactly one person can be matched with the finger vein characteristic information of the other finger of the recognized person, the recognition process or the authentication process of the person currently being recognized is considered to be successful, and therefore the system can perform the subsequent corresponding operation.
Fig. 4 shows a person identification method using successive finger vein recognition authentication according to another embodiment of the present invention, which includes the following steps (some steps in fig. 4 are similar to those in fig. 2, and will not be described in detail here):
step 401: and collecting the face feature information of the identified person.
Step 402: collecting finger vein characteristic information of at least two fingers of the identified person.
Step 403: and performing face recognition by using the face feature information to obtain a set of persons meeting a preset condition.
Step 404: and performing finger vein recognition on the persons in the set by using the finger vein feature information of one finger of the recognized person to obtain a preliminary recognition result.
Step 405: and analyzing the preliminary identification result to judge whether the finger vein characteristic information of at least two persons is matched with the finger vein characteristic information of the identified person.
Step 406: and if the judgment result is 'no', taking the preliminary identification result as a final identification result.
Step 407: and if the judgment result is yes, performing finger vein identification on the at least two persons by using the finger vein characteristic information of the other finger of the identified person to obtain a final identification result. Similarly, the final recognition result may still have at least two persons matching the recognized person, in which case the recognition result may be considered invalid, the recognition process may be stopped, and subsequent corresponding operations (e.g., opening a door, making financial payments, etc.) may be rejected.
In one embodiment of the invention, the invention may be implemented in the form of a computer program. The computer program may be stored in various storage media (e.g., hard disk, optical disk, flash memory, etc.), which when executed by a processor, can be used to implement the methods of the present invention.
In another embodiment of the invention, the invention may be implemented in the form of an electronic device. The electronic device comprises a processor and a memory in which a computer program is stored which, when being executed by the processor, can be used for carrying out the method of the invention.
References herein to "various embodiments," "some embodiments," "one embodiment," or "an embodiment," etc., indicate that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases "in various embodiments," "in some embodiments," "in one embodiment," or "in an embodiment," or the like, in various places throughout this document are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Thus, a particular feature, structure, or characteristic illustrated or described in connection with one embodiment may be combined, in whole or in part, with a feature, structure, or characteristic of one or more other embodiments without limitation, as long as the combination is not logical or operational. Expressions like "according to a" or "based on a" appearing herein are meant to be non-exclusive, i.e. "according to a" may cover "according to a only", and also "according to a and B", unless specifically stated or clearly known from the context, the meaning is "according to a only". The various steps described in the method flow in a certain order do not have to be performed in that order, rather the order of execution of some of the steps may be changed and some steps may be performed concurrently, as long as implementation of the scheme is not affected. For example, the present invention may collect the face feature information of the identified person first, may collect the vein feature information of the identified person first, or may perform both concurrently. The invention can collect the vein characteristic information of the identified person before executing the face identification, can also collect the vein characteristic information of the identified person after executing the face identification, or the two can be executed concurrently. Additionally, the various elements of the drawings of the present application are merely schematic illustrations and are not drawn to scale.
Having thus described several aspects of at least one embodiment of this invention, it is to be appreciated various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be within the spirit and scope of the invention.
Claims (11)
1. A person identification method comprises the following steps:
collecting face feature information of a recognized person;
collecting finger vein characteristic information of the identified person;
performing face recognition using the face feature information to obtain a set of persons meeting a predetermined condition; and
and performing finger vein identification for the persons in the set by using the finger vein characteristic information to obtain an identification result.
2. The method according to claim 1, wherein the finger vein feature information is finger vein feature information of one finger of the identified person.
3. The method of claim 2, further comprising:
and if the recognition result shows that the finger vein characteristic information of at least two persons in the set is matched with the finger vein characteristic information of the recognized person, acquiring the finger vein characteristic information of another finger of the recognized person, and executing finger vein recognition on the at least two persons by using the finger vein characteristic information of the another finger to obtain a new recognition result.
4. The method of claim 1, wherein the finger vein feature information comprises finger vein feature information of at least two fingers of the identified person.
5. The method of claim 4, the performing finger vein recognition using the finger vein feature information for the persons in the set to obtain recognition results comprising:
performing finger vein recognition on the persons in the set by using finger vein feature information of one finger of the recognized person to obtain a preliminary recognition result;
if the preliminary identification result shows that the finger vein feature information of zero or one person in the set is matched with the finger vein feature information of the identified person, taking the preliminary identification result as a final identification result;
and if the preliminary identification result shows that the finger vein characteristic information of at least two persons in the set is matched with the finger vein characteristic information of the identified person, performing finger vein identification on the at least two persons by using the finger vein characteristic information of the other finger of the identified person to obtain a final identification result.
6. The method of claim 1, wherein the performing face recognition using the facial feature information to derive a set of people meeting a predetermined condition comprises:
comparing the face feature information with stored face feature information of each of a plurality of persons to obtain similarity measurement; and
and if the similarity measure is larger than a preset similarity threshold value, taking the corresponding person as the person meeting the preset condition.
7. The method of claim 6, wherein the similarity threshold is set according to requirements for accuracy or efficiency of person identification.
8. The method of claim 1, wherein the acquisition of the facial feature information and the finger vein feature information is triggered simultaneously when the finger placement of the identified person is detected.
9. A storage medium in which a computer program is stored which, when being executed by a processor, is operative to carry out the method of any one of claims 1-8.
10. An electronic device comprising a processor and a memory, the memory having stored therein a computer program which, when executed by the processor, is operable to carry out the method of any one of claims 1-8.
11. A person identification system comprising:
the module is used for collecting the face feature information of the identified person;
the module is used for collecting finger vein characteristic information of the identified person;
a module for performing face recognition using the face feature information to obtain a set of persons meeting a predetermined condition; and
means for performing finger vein recognition using the finger vein feature information for the persons in the set to obtain recognition results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201605.XA CN111723595A (en) | 2019-03-18 | 2019-03-18 | Personnel identity identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201605.XA CN111723595A (en) | 2019-03-18 | 2019-03-18 | Personnel identity identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111723595A true CN111723595A (en) | 2020-09-29 |
Family
ID=72562091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910201605.XA Pending CN111723595A (en) | 2019-03-18 | 2019-03-18 | Personnel identity identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723595A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112668511A (en) * | 2020-12-31 | 2021-04-16 | 深兰盛视科技（苏州）有限公司 | Identity recognition method and device, electronic equipment and storage medium |
| CN112862983A (en) * | 2021-01-21 | 2021-05-28 | 广州广电运通智能科技有限公司 | Automatic ticketing method, system, device and medium |
| CN113888780A (en) * | 2021-10-08 | 2022-01-04 | 深兰盛视科技（苏州）有限公司 | Strong security and protection place management method based on vein recognition and related device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040133582A1 (en) * | 2002-10-11 | 2004-07-08 | Howard James V. | Systems and methods for recognition of individuals using multiple biometric searches |
| CN101097596A (en) * | 2006-06-29 | 2008-01-02 | 富士通株式会社 | Biometric authentication method and system |
| CN105260643A (en) * | 2015-10-30 | 2016-01-20 | 南昌欧菲生物识别技术有限公司 | Multi-fingerprint cross-unlocking method and system |
| CN106372482A (en) * | 2016-08-27 | 2017-02-01 | 广州同略信息科技有限公司 | Finger vein encryption communication terminal for confidential file |
| CN106709417A (en) * | 2016-11-11 | 2017-05-24 | 识益生物科技(北京）有限公司 | Multimodal biological recognition system and use method thereof |
| CN107305625A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method based on multi-mode biometric information |
| CN107305624A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method and device based on multi-mode biometric information |
| CN107437074A (en) * | 2017-07-27 | 2017-12-05 | 深圳市斑点猫信息技术有限公司 | A kind of identity identifying method and device |
-
2019
- 2019-03-18 CN CN201910201605.XA patent/CN111723595A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040133582A1 (en) * | 2002-10-11 | 2004-07-08 | Howard James V. | Systems and methods for recognition of individuals using multiple biometric searches |
| CN101097596A (en) * | 2006-06-29 | 2008-01-02 | 富士通株式会社 | Biometric authentication method and system |
| CN105260643A (en) * | 2015-10-30 | 2016-01-20 | 南昌欧菲生物识别技术有限公司 | Multi-fingerprint cross-unlocking method and system |
| CN107305625A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method based on multi-mode biometric information |
| CN107305624A (en) * | 2016-04-20 | 2017-10-31 | 厦门中控智慧信息技术有限公司 | A kind of person recognition method and device based on multi-mode biometric information |
| CN106372482A (en) * | 2016-08-27 | 2017-02-01 | 广州同略信息科技有限公司 | Finger vein encryption communication terminal for confidential file |
| CN106709417A (en) * | 2016-11-11 | 2017-05-24 | 识益生物科技(北京）有限公司 | Multimodal biological recognition system and use method thereof |
| CN107437074A (en) * | 2017-07-27 | 2017-12-05 | 深圳市斑点猫信息技术有限公司 | A kind of identity identifying method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112668511A (en) * | 2020-12-31 | 2021-04-16 | 深兰盛视科技（苏州）有限公司 | Identity recognition method and device, electronic equipment and storage medium |
| CN112862983A (en) * | 2021-01-21 | 2021-05-28 | 广州广电运通智能科技有限公司 | Automatic ticketing method, system, device and medium |
| CN113888780A (en) * | 2021-10-08 | 2022-01-04 | 深兰盛视科技（苏州）有限公司 | Strong security and protection place management method based on vein recognition and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bolle et al. | Guide to biometrics | |
| Delac et al. | A survey of biometric recognition methods | |
| Tripathi | A comparative study of biometric technologies with reference to human interface | |
| JP3356144B2 (en) | User authentication device using biometrics and user authentication method used therefor | |
| TWI599964B (en) | Finger vein recognition system and method | |
| CN104200146A (en) | Identity verifying method with video human face and digital lip movement password combined | |
| CN101661557A (en) | Face recognition system and face recognition method based on intelligent card | |
| Charity et al. | A bimodal biometrie student attendance system | |
| CN111723595A (en) | Personnel identity identification method and system | |
| Kaur | A study of biometric identification and verification system | |
| Gale et al. | Evolution of performance analysis of iris recognition system by using hybrid methods of feature extraction and matching by hybrid classifier for iris recognition system | |
| CN103646236B (en) | The coding encrypting and application process of a kind of palmprint information | |
| CN105184571A (en) | Payment authentication system based on combination of hand veins and multiple fingerprints | |
| JP2014518579A (en) | Demographic analysis method and system based on multimodal information | |
| TWI325568B (en) | A method for face varification | |
| Ibrahim et al. | Trends in Biometric Authentication: A review | |
| Choudhary | Survey of different biometrics techniques | |
| Okokpujie et al. | An enhanced voters registration and authentication application using Iris recognition technology | |
| Wang et al. | Multi-modal biometric authentication fusing iris and palmprint based on GMM | |
| Sharma et al. | Role of biometric technology over advanced security and protection in auto teller machine transaction | |
| Manjunath et al. | Analysis of unimodal and multimodal biometric system using iris and fingerprint | |
| Kubanek et al. | Intelligent Identity Authentication, Using Face and Behavior Analysis | |
| CN114120509A (en) | Regional access authorization device based on fusion identification technology | |
| Singh et al. | Hand geometry verification system: A review | |
| Ozkaya et al. | Intelligent face border generation system from fingerprints |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |