CN110796125A - Face authentication method and system - Google Patents
Face authentication method and system Download PDFInfo
- Publication number
- CN110796125A CN110796125A CN201911236014.2A CN201911236014A CN110796125A CN 110796125 A CN110796125 A CN 110796125A CN 201911236014 A CN201911236014 A CN 201911236014A CN 110796125 A CN110796125 A CN 110796125A
- Authority
- CN
- China
- Prior art keywords
- feature
- face
- storage
- source
- detection
- 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
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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a face authentication method, which comprises the following steps of registering face storage characteristics; setting a storage feature mark and a storage feature source of the face storage feature; acquiring human face detection characteristics; setting a detection feature mark and a detection feature source of the face detection feature; comparing the stored characteristic source with the detected characteristic source, and comparing the stored characteristic mark with the detected characteristic mark; if the comparison is successful, comparing the face storage feature with the face detection feature; and if the comparison between the face storage characteristics and the face detection characteristics is successful, the face authentication is passed. The face authentication method disclosed by the invention can improve the compatibility of face recognition products and is suitable for various occasions with different environments.
Description
Technical Field
The present invention relates to the field of face recognition technology, and more particularly, to a face authentication method and system.
Background
The face recognition technology is one of biological recognition technologies, is a biological feature recognition technology for automatically identifying identities according to unique physiological features of faces, and has the advantages of non-contact data acquisition, convenience, quickness, strong interactivity, convenience for retrospective tracing and the like.
The existing face recognition application field is very wide, for example, a common access control system can also adopt a face recognition system, namely, face data is collected through a camera, the collected face data is compared with pre-stored authentication data, and if the comparison is successful, the face recognition is successful. And if the comparison fails, the face recognition fails.
The camera that adopts at present generally is two kinds for visible light camera and near-infrared camera, but the identification equipment that the visible light camera corresponds has following problem: 1. the identification is carried out by adopting a visible light source, the device cannot be used in a dark environment, and light is supplemented at night. 2. Plane photos or other non-real human faces are easy to be adopted for false authentication, and effective anti-counterfeiting cannot be achieved. The identification device corresponding to the near-infrared camera also has the following problems: 1. short-wave light sources in near-infrared bands are used, imaging is performed by a reflection light source, and the device cannot be used in a direct solar radiation environment; 2. although effective anti-counterfeiting can be performed, the face features must be registered on the terminal equipment, and convenience is not sufficient.
Therefore, the face authentication method and the face authentication system are designed, the compatibility of face recognition products is improved, the face authentication system is suitable for various occasions with different environments, and a more convenient and accurate face recognition technology is provided for the industry.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a face authentication method, which improves the compatibility of face recognition products and is suitable for various occasions with different environments.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a face authentication method comprises the following steps,
registering face storage features;
setting a storage feature mark and a storage feature source of the face storage feature;
acquiring human face detection characteristics;
setting a detection feature mark and a detection feature source of the face detection feature;
comparing the stored feature source with the detected feature source, and comparing the stored feature tag with the detected feature tag;
if the comparison is successful, comparing the face storage feature with the face detection feature;
if the face storage feature and the face detection feature are successfully compared, passing face authentication;
wherein the storage feature indicia and the detection feature indicia comprise visible light indicia and near infrared indicia, and the storage feature sources and the detection feature sources comprise device sources and photo sources.
Preferably, the setting of the storage feature tag and the storage feature source of the face storage feature specifically includes:
setting the source of the storage characteristics;
if the storage characteristic source is the equipment source, setting the storage characteristic mark as the visible light mark and the near infrared mark;
and if the storage feature source is the photo source, setting the storage feature mark as the visible light mark.
Preferably, the comparing the stored signature source with the detected signature source, and the comparing the stored signature with the detected signature; if the comparison is successful, the comparison between the face storage feature and the face detection feature specifically comprises:
comparing the stored characteristic source with the detected characteristic source;
if the comparison is successful, comparing the storage characteristic mark with the detection characteristic mark;
and if the storage feature mark and the detection feature mark are successfully compared, comparing the face storage feature with the face detection feature.
Preferably, the comparing the stored signature source with the detected signature source, and the comparing the stored signature with the detected signature; if the comparison is successful, the comparison between the face storage feature and the face detection feature specifically comprises:
comparing the storage feature tag with the detection feature tag;
if the comparison is successful, comparing the storage feature source with the detection feature source;
and if the storage feature source is successfully compared with the detection feature source, comparing the face storage feature with the face detection feature.
Preferably, before the comparing the stored signature source with the detected signature source and the comparing the stored signature with the detected signature, the method further comprises:
judging the detection feature marks;
and if the face detection feature is a visible light mark, performing near-infrared supplementary lighting, re-acquiring the face detection feature, and updating the detection feature mark and the detection feature source of the face detection feature.
Preferably, before the comparing the stored signature source with the detected signature source and the comparing the stored signature with the detected signature, the method further comprises:
judging the detection feature marks;
and if the detected features are the near-infrared marks, performing visible light supplementary lighting, re-acquiring the face detection features, and updating the detection feature marks and the detection feature sources of the face detection features.
A face authentication system comprising:
the registration module is used for registering the face storage characteristics;
the setting module is connected with the registration module and is used for setting a storage feature mark and a storage feature source of the face storage feature;
the acquisition module is connected with the setting module and is used for acquiring the face detection features, and the setting module is also used for setting the detection feature marks and the detection feature sources of the face detection features;
the comparison module is connected with the setting module and is used for comparing the storage feature source with the detection feature source and comparing the storage feature mark with the detection feature mark;
the comparison module is also used for comparing the face storage feature with the face detection feature;
and the authentication module is connected with the comparison module and is used for passing the face authentication.
Preferably, the method further comprises the following steps:
the registration storage module is connected between the registration module and the setting module and is used for storing the face storage features;
and the acquisition and storage module is connected between the acquisition module and the setting module and is used for storing the face detection characteristics.
Preferably, the acquisition module includes a visible light camera module and a near-infrared camera module.
Preferably, the method further comprises the following steps:
the judging module connected with the acquiring module is used for judging the source of the detection characteristic;
the visible light compensating module is connected with the visible light camera module;
the near-infrared light supplementing module is connected with the near-infrared camera module;
if the judgment module judges that the visible light mark is the visible light mark, the near-infrared light supplement module is started, the acquisition module acquires the face detection feature again, and the setting module updates the detection feature mark and the detection feature source of the face detection feature;
if the judgment module judges that the near-infrared mark is the near-infrared mark, the visible light compensation module is started, the acquisition module acquires the face detection feature again, and the setting module updates the detection feature mark and the detection feature source of the face detection feature.
A face authentication device comprises a visible light camera, a near infrared camera, a central controller and a case with a hollow cavity,
the case comprises a case main body and a case independent chamber positioned at the top of the case main body;
the visible light camera and the near infrared camera are both arranged in the independent chamber of the chassis;
the central controller is arranged in the case main body and is electrically connected with the visible light camera and the near infrared camera.
Preferably, the chassis further comprises a chassis door panel movably connected with the chassis main body.
Preferably, the independent chamber of the chassis is rotatable.
Furthermore, a visible light supplement lamp and a near-infrared light supplement lamp which are electrically connected with the central controller are arranged in the independent chamber of the case.
Preferably, the rear of the cabinet main body is provided with a louver for exhausting and dissipating heat.
Preferably, a voice player electrically connected with the central controller is arranged on the chassis door panel.
According to the face authentication method provided by the invention, the feature marks and the feature sources are respectively set for the registered face storage features and the detected face detection features, namely the feature marks and the feature sources are used as identification bits, and when specific face features are compared, the identification bits can be compared firstly, so that the face feature data with more quantity and larger size can be prevented from being directly compared, and the processing speed is increased. Moreover, because the feature marks and the feature sources are respectively arranged, the light source is used as the main attribute of the feature marks, and the equipment source is used as the main attribute of the feature sources, so that more distinguishing attributes are given to the human face features, and the interference of various abnormal human face feature data can be effectively avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of one implementation of a face authentication method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of one embodiment of a face authentication system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of one implementation of the face authentication device in the embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments.
All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As shown in fig. 1, a face authentication method includes the following steps,
s1, registering face storage characteristics;
there are two ways to register the face storage features: in the first mode, an administrator enters a user management menu after face authentication, and acquires face storage characteristics of a current user by using acquisition equipment, wherein the face storage characteristics are directly and correspondingly bound with corresponding users, and registration is completed. In the second mode, the administrator uploads the user photos, the system collects the face storage characteristics in the user photos, the face storage characteristics are directly and correspondingly bound with corresponding users, and the registration is completed.
The two modes can be used for carrying out face storage feature registration on the user, adopting a photo to carry out face storage feature registration under the condition that the user cannot arrive at the place, and simultaneously supporting a mode of uploading the photo remotely, so that the requirement that the user and the face storage feature of the user can be correspondingly bound to finish the registration of the face storage feature to form the face data of the user under various conditions whether the user is present or not and whether the acquisition equipment is online or not can be met.
In the embodiment, a user ID is set for each user, and the face storage features of each user are corresponding to the respective user ID number to complete a one-to-one binding effect, and specific steps are not described in detail.
S2, setting storage feature marks and storage feature sources of the face storage features;
the storage characteristic marks comprise visible light marks and near infrared marks, namely the storage characteristic marks are mark bits, and the attributes of the mark bits comprise two attributes of the visible light marks and the near infrared marks, namely the storage characteristic marks of the same face storage characteristic can be only the visible light marks, only the near infrared marks or both the visible light marks and the near infrared marks.
Similarly, the source of the storage feature of the same face storage feature may be only a device source, may be only a photo source, or may be both a device source and a photo source.
S3, obtaining face detection characteristics;
the acquisition ways are various, including that a visible light camera and a near infrared camera which are arranged on the equipment are acquired by shooting, and the visible light camera is acquired by pictures.
The specific method for acquiring the face detection features after the face or the photo is shot can adopt the known technology in the field, for example, the face image data is collected, the face vector features are acquired through calculation, and the face detection features are formed, which will not be described in detail herein.
S4, setting a detection feature mark and a detection feature source of the face detection feature;
setting a detection feature mark and a detection feature source according to the acquisition equipment and the acquisition source of the face detection features, wherein the detection feature mark of the same face detection feature can be only a visible light mark, only a near-infrared mark or both the visible light mark and the near-infrared mark as the feature mark set in the step S2.
Similarly, the source of the detected feature of the same face detection feature may be only a device source, may be only a photo source, or may be both a device source and a photo source.
S5, comparing the stored feature source with the detected feature source, and comparing the stored feature mark with the detected feature mark;
s6, if the comparison is successful, comparing the face storage feature with the face detection feature;
the feature sources and the feature marks are respectively and correspondingly compared, the data volume of the feature sources and the feature marks is much smaller than that of the face storage features and the face detection features, namely, the storage feature marks and the storage feature sources are arranged in the prior art to divide all the face storage features into a plurality of subclasses, the subclasses are searched and compared during comparison, and then the specific face storage features are compared, so that the workload of calculation or comparison is reduced compared with the direct comparison of the face storage features and the face detection features, and the comparison efficiency is improved.
If the comparison is unsuccessful, for example, the acquisition device is in normal operation or does not meet the environmental requirements, for example, dark cloudy days cause insufficient visible light intensity, so that the face data acquired by the visible light camera is not clear enough, and further face detection feature acquisition is invalid, or the definition of the photo itself is insufficient, and face detection feature acquisition is also invalid. In actual application, various accidents or special conditions can cause invalid face detection feature acquisition or the stored feature mark and the stored feature source do not accord with the comparison rule, at the moment, prompt or warning information can be sent out to remind an operator to check, and the whole authentication step is stopped.
And S7, if the comparison between the face storage characteristics and the face detection characteristics is successful, passing the face authentication.
When the face storage characteristics and the face detection characteristics meet the comparison requirements through calculation and comparison, for example, the similarity between the face detection characteristics and the face storage characteristics reaches a comparison threshold, the comparison is considered to be successful, and at the moment, the whole authentication process is completed through face authentication.
If the comparison between the face storage features and the face detection features is unsuccessful, the two cases are basically divided into two cases, one is that the user is the same user, but the user cannot reach a comparison threshold value due to the fact that the user wears glasses, a hat and other objects which can cause redundant feature detection; the other is to detect that the user does not have the above situation, but the face storage feature of the user is not registered before, or the corresponding data after registration is damaged, which also causes that the comparison threshold value between the two is not reached.
No matter why the comparison is unsuccessful, corresponding prompt or warning information can be performed, and the specific method and information content can be selected according to requirements, which is not described again here.
Preferably, step S2 specifically includes:
s21, setting a storage characteristic source;
s22, if the storage feature source is an equipment source, setting the storage feature marks as a visible light mark and a near infrared mark;
and S23, if the storage feature source is a photo source, setting the storage feature mark as a visible light mark.
If the device is from the photo source, the human face storage characteristics are registered through photo data, the near-infrared camera cannot directly acquire the human face data from the photo, and only the visible-light camera can directly acquire the human face data from the photo, and if the device is from the device source, the human face storage characteristics are registered through data acquired by the camera, and the near-infrared mark and the visible-light mark are both set values which can be matched.
Preferably, the steps S5 and S6 are specifically:
s51, comparing and storing the feature source with the detection feature source;
s52, if the comparison is successful, comparing the storage characteristic mark with the detection characteristic mark;
and S61, if the comparison between the storage feature marks and the detection feature marks is successful, comparing the face storage features with the face detection features.
That is, in the step S5, the stored feature source and the detected feature source may be compared first, the stored feature tag and the detected feature tag may be compared after the comparison is successful, the comparison is successful again, and finally the stored face feature and the detected face feature are compared.
Similarly, step S5 and step S6 specifically include:
s53, comparing and storing the feature marks and the detection feature marks;
s54, if the comparison is successful, comparing the stored feature source with the detected feature source;
s62, if the stored feature source is successfully compared with the detected feature source, comparing the face storage feature with the face detection feature.
Preferably, before step S5, the method further includes:
s41, judging a detection feature mark;
and S42, if the human face detection feature is a visible light mark, performing near-infrared light supplement, re-acquiring the human face detection feature, and updating the detection feature mark and the detection feature source of the human face detection feature.
In some demand places with strict security requirements or authentication requirements, the authentication strength needs to be improved on the premise of not improving the comparison threshold, then visible light and near infrared are adopted to be carried out simultaneously, if only a visible light mark exists, the visible light mark indicates that the visible light strength is enough, at the moment, near infrared light supplement is carried out, the face detection features are obtained again according to the obtained near infrared data and the previous visible light data, and meanwhile, the detection feature mark and the detection feature source are updated.
By means of the near-infrared supplementary lighting reacquiring mode, the types of the face detection features participating in comparison can be increased, the authentication strength is improved, and relatively strict authentication requirements are met.
Similarly, before step S5, the method further includes:
s43, judging a detection feature source;
and S44, if the detected face is the near-infrared mark, performing visible light supplementary lighting, re-acquiring the face detection feature, and updating the detection feature mark and the detection feature source of the face detection feature.
If only the near-infrared mark exists, the fact that the detection is performed before the intensity of visible light is insufficient is indicated, visible light supplementary lighting is performed at the moment, the face detection feature is obtained again according to the obtained visible light data and the previous near-infrared data, meanwhile, the detection feature mark and the detection feature source are updated, the effect is similar to that of the above, and the description is omitted.
The invention also provides a face authentication system, comprising:
the registration module 01 is used for registering the face storage characteristics;
the setting module 02 is connected with the registration module 01 and is used for setting a storage feature mark and a storage feature source of the face storage feature;
the acquisition module 03 connected with the setting module 02 is used for acquiring the face detection features, and the setting module 02 is also used for setting the detection feature labels and the detection feature sources of the face detection features;
the comparison module 04 is connected with the setting module 02 and is used for comparing the stored feature source with the detected feature source and comparing the stored feature mark with the detected feature mark;
the comparison module 04 is further configured to compare the face storage feature with the face detection feature;
and the authentication module 05 is connected with the comparison module 04 and is used for passing the face authentication.
In practical application, a computer or a mobile phone or other terminal equipment can be used as input equipment, and existing processed face storage features are correspondingly bound with a user through the registration module 01.
The setting module 02, the comparing module and the authenticating module 05 can be installed on a chip or a PLC with an arithmetic function, and it should be noted that the connection in this embodiment is not limited to a specific connection manner, and may be a physical hard connection or a logical software connection, that is, an entity electrical connection or a wireless communication connection, for example, a bluetooth, an infrared, or a wire, a cable, and the like, which will not be described herein again.
Preferably, the method further comprises the following steps:
the registration storage module is connected between the registration module 01 and the setting module 02 and is used for storing the face storage characteristics;
and the acquisition and storage module is connected between the acquisition module 03 and the setting module 02 and is used for storing the face detection characteristics.
The registering storage module and the obtaining storage module can select different storage devices according to actual requirements, and because the data volume required to be stored by the registering storage module is large, and after one-time batch initialization registration, the number of times of subsequent data supplement is relatively small, a traditional hard disk with large capacity can be adopted, and certainly if the cost is not considered, a solid state disk with higher reading speed and higher cost can also be adopted.
The amount of data acquired by the storage module each time is small, but the number of times of data supplement is large, or the frequency of data update is high, so that a small-capacity solid state disk is generally adopted, and on the premise of meeting the reading speed and improving the effect efficiency, excessive cost waste is avoided.
Preferably, the acquisition module 03 includes a visible light camera and a near-infrared camera, and a visible light camera and a near-infrared camera are generally adopted, that is, the acquisition module 03 adopts a dual-camera mode of visible light and near-infrared in order to adapt to more time and weather.
Further, the method also comprises the following steps:
the judging module 06 connected to the obtaining module 03 is used for judging the detection feature mark;
a visible light compensating part connected to the visible light photographing part;
the near-infrared light supplementing component is connected with the near-infrared camera shooting component;
if the judgment module 06 judges that the human face detection feature is a visible light mark, the near-infrared light supplement component is started, the acquisition module 03 acquires the human face detection feature again, and the setting module 02 updates a detection feature mark and a detection feature source of the human face detection feature;
if the judgment module 06 judges that the detection feature is the near-infrared mark, the visible light compensation component is started, the acquisition module 03 acquires the face detection feature again, and the setting module 02 updates the detection feature mark and the detection feature source of the face detection feature.
The visible light supplementing component is a visible light supplementing lamp, the near-infrared light supplementing component is a near-infrared light supplementing lamp, the number of the specific light supplementing lamps can be selected according to actual needs, and the adjustable light supplementing intensity can be set.
The invention also discloses a face authentication device, which comprises a visible light camera 1, a near infrared camera 2, a central controller 7 and a case with a hollow cavity,
the case comprises a case body 6 and a case independent chamber positioned at the top of the case body 6;
the visible light camera 1 and the near infrared camera 2 are both arranged in the independent chamber of the chassis;
the central controller 7 is disposed in the housing main body 6 and electrically connected to the visible light camera 1 and the near-infrared camera 2.
This equipment adopts two camera modes of visible light and near-infrared, when registering and acquireing the face detection characteristic face storage characteristic promptly, utilizes visible light camera 1 and near-infrared camera 2 of setting on equipment to acquire through making a video recording to and acquire through visible light camera 1 discernment photo, adapt to more demand environment.
And visible light camera 1 and near-infrared camera 2 can be selected according to actual need, and owing to all install in quick-witted case independent cavity, can be under the prerequisite that does not influence other equipment in the quick-witted case main part 6, swift individual change or maintain visible light camera 1 and near-infrared camera 2.
The central controller 7 is configured to log in the received face storage features to the system, or store the face storage features in a memory, such as a hard disk or a mobile hard disk, and correspondingly set storage feature sources of the face storage features, specifically, a photo source and an equipment source, and correspondingly set storage feature marks of the face storage features, specifically, a near-infrared mark and a visible light mark.
After the steps are processed, the feature sources and the feature labels are respectively and correspondingly compared, the data volume of the feature sources and the feature labels is much smaller than that of the face storage features and the face detection features, namely, the storage feature labels and the storage feature sources are arranged in the prior art to divide all the face storage features into several subclasses, the subclasses are searched and compared during comparison, and then the specific face storage features are compared, so that the workload of calculation or comparison is reduced compared with the direct comparison of the face storage features and the face detection features, and the comparison efficiency is improved.
If the comparison is unsuccessful, for example, the acquisition device is in normal operation or does not meet the environmental requirements, for example, the visible light intensity is insufficient in dark cloudy days, so that the face data acquired by the visible light camera 1 is not clear enough, and further face detection feature acquisition is invalid, or the definition of the picture itself is insufficient, and face detection feature acquisition is also invalid. In actual application, various accidents or special conditions can cause invalid face detection feature acquisition or the stored feature mark and the stored feature source do not accord with the comparison rule, at the moment, prompt or warning information can be sent out to remind an operator to check, and the whole authentication step is stopped.
When the central controller 7 performs calculation and comparison, the face storage feature and the face detection feature meet the comparison requirement, for example, the similarity between the face detection feature and the face storage feature reaches the comparison threshold, the comparison is considered to be successful, and at this time, the whole authentication process is completed through face authentication.
In practical application, the case body 6 may be further provided with a liquid crystal display 5 for human-computer interaction by an administrator, or for displaying information on whether authentication is successful or not, or for displaying information on current date and time, and details thereof are not described.
Preferably, the chassis further comprises a chassis door panel movably connected with the chassis main body 6.
Adopt the quick-witted case door plant with quick-witted case main part 6 swing joint, can open quick-witted case door plant when needing, convenient maintenance or the change to interior equipment. Can utilize the tool to lock of different grade type to realize the swing joint between chassis main part 6 and the chassis door plant according to the user demand of difference, for example this embodiment adopts the triangulation chain to fix.
Preferably, the independent chamber of the case is rotatable, is used for adjusting the angles of the visible light camera 1 and the near infrared camera 2, can adapt to various installation environments, and achieves a good recognition effect. In addition, still including setting up the quick-witted case upper cover on the independent cavity upper portion of quick-witted case, when needs, can be through opening quick-witted case upper cover, convenient maintain or change visible light camera 1 and near infrared camera 2.
Further, a visible light supplementary lighting lamp 3 and a near infrared supplementary lighting lamp 4 which are electrically connected with a central controller 7 are arranged in the independent chamber of the case.
If the central processing unit judges that the detection feature mark is a visible light mark, the near-infrared light supplement lamp 4 is started, the face detection feature is obtained again, and the detection feature mark and the detection feature source of the face detection feature are updated;
and if the detection feature mark is judged to be the near-infrared mark, the visible light supplementary lighting lamp 3 is started, the face detection feature is obtained again, and the detection feature mark and the detection feature source of the face detection feature are updated.
The visible light fill light 3 and the near-infrared fill light 4 can both select specific quantity according to actual demand to and set up the fill light intensity that can adjust.
And the specific position that sets up of visible light filling lamp 3 and near-infrared light filling lamp 4 can be selected according to actual conditions, for example, in this embodiment, visible light filling lamp 3 is on the left side that is close to visible light camera 1, and near-infrared light filling lamp 4 is on the right that is close to near-infrared camera 2.
Preferably, the rear portion of the cabinet main body 6 is provided with a louver for exhausting and dissipating heat, so as to ensure good heat dissipation inside the cabinet and stable operation of the equipment.
Preferably, a voice player electrically connected to the central controller 7 is disposed on the chassis door panel, and is used for collecting the notification voice of success or failure, and of course, other types of information may also be played, such as time broadcast and weather broadcast.
The above describes a face authentication method and system provided by the present invention in detail. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A face authentication method is characterized by comprising the following steps,
registering face storage features;
setting a storage feature mark and a storage feature source of the face storage feature;
acquiring human face detection characteristics;
setting a detection feature mark and a detection feature source of the face detection feature;
comparing the stored feature source with the detected feature source, and comparing the stored feature tag with the detected feature tag;
if the comparison is successful, comparing the face storage feature with the face detection feature;
if the face storage feature and the face detection feature are successfully compared, passing face authentication;
wherein the storage feature indicia and the detection feature indicia comprise visible light indicia and near infrared indicia, and the storage feature sources and the detection feature sources comprise device sources and photo sources.
2. The face authentication method according to claim 1, wherein the setting of the storage feature tag and the storage feature source of the face storage feature specifically comprises:
setting the source of the storage characteristics;
if the storage characteristic source is the equipment source, setting the storage characteristic mark as the visible light mark and the near infrared mark;
and if the storage feature source is the photo source, setting the storage feature mark as the visible light mark.
3. The face authentication method of claim 1, wherein the comparing the stored feature source with the detected feature source, and the comparing the stored feature tag with the detected feature tag; if the comparison is successful, the comparison between the face storage feature and the face detection feature specifically comprises:
comparing the stored characteristic source with the detected characteristic source;
if the comparison is successful, comparing the storage characteristic mark with the detection characteristic mark;
and if the storage feature mark and the detection feature mark are successfully compared, comparing the face storage feature with the face detection feature.
4. The face authentication method of claim 1, wherein the comparing the stored feature source with the detected feature source, and the comparing the stored feature tag with the detected feature tag; if the comparison is successful, the comparison between the face storage feature and the face detection feature specifically comprises:
comparing the storage feature tag with the detection feature tag;
if the comparison is successful, comparing the storage feature source with the detection feature source;
and if the storage feature source is successfully compared with the detection feature source, comparing the face storage feature with the face detection feature.
5. The method of claim 1, wherein prior to comparing the stored feature source with the detected feature source and comparing the stored feature tag with the detected feature tag, further comprising:
judging the detection feature marks;
and if the face detection feature is a visible light mark, performing near-infrared supplementary lighting, re-acquiring the face detection feature, and updating the detection feature mark and the detection feature source of the face detection feature.
6. The method of claim 1, wherein prior to comparing the stored feature source with the detected feature source and comparing the stored feature tag with the detected feature tag, further comprising:
judging the detection feature marks;
and if the detected features are the near-infrared marks, performing visible light supplementary lighting, re-acquiring the face detection features, and updating the detection feature marks and the detection feature sources of the face detection features.
7. A face authentication system, comprising:
the registration module is used for registering the face storage characteristics;
the setting module is connected with the registration module and is used for setting a storage feature mark and a storage feature source of the face storage feature;
the acquisition module is connected with the setting module and is used for acquiring the face detection features, and the setting module is also used for setting the detection feature marks and the detection feature sources of the face detection features;
the comparison module is connected with the setting module and is used for comparing the storage feature source with the detection feature source and comparing the storage feature mark with the detection feature mark;
the comparison module is also used for comparing the face storage feature with the face detection feature;
and the authentication module is connected with the comparison module and is used for passing the face authentication.
8. The face authentication system of claim 7, further comprising:
the registration storage module is connected between the registration module and the setting module and is used for storing the face storage features;
and the acquisition and storage module is connected between the acquisition module and the setting module and is used for storing the face detection characteristics.
9. The face authentication system of claim 7, wherein the acquisition module comprises a visible light camera module and a near infrared camera module.
10. The face authentication system of claim 9, further comprising:
the judging module connected with the acquiring module is used for judging the source of the detection characteristic;
the visible light compensating module is connected with the visible light camera module;
the near-infrared light supplementing module is connected with the near-infrared camera module;
if the judgment module judges that the visible light mark is the visible light mark, the near-infrared light supplement module is started, the acquisition module acquires the face detection feature again, and the setting module updates the detection feature mark and the detection feature source of the face detection feature;
if the judgment module judges that the near-infrared mark is the near-infrared mark, the visible light compensation module is started, the acquisition module acquires the face detection feature again, and the setting module updates the detection feature mark and the detection feature source of the face detection feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911236014.2A CN110796125A (en) | 2019-12-05 | 2019-12-05 | Face authentication method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911236014.2A CN110796125A (en) | 2019-12-05 | 2019-12-05 | Face authentication method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796125A true CN110796125A (en) | 2020-02-14 |
Family
ID=69447552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911236014.2A Pending CN110796125A (en) | 2019-12-05 | 2019-12-05 | Face authentication method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796125A (en) |
-
2019
- 2019-12-05 CN CN201911236014.2A patent/CN110796125A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016072714A1 (en) | Electronic device and method for providing filter in electronic device | |
| CN208046746U (en) | A kind of safety-protection system based on face tracking | |
| CN109068116B (en) | Image processing method and device based on supplementary lighting, mobile terminal and storage medium | |
| CN207665104U (en) | Security monitoring device based on recognition of face | |
| CN106663187A (en) | Method and device for recognizing biometric information | |
| CN110175445B (en) | Fingerprint verification method and device, electronic equipment and storage medium | |
| US20210394636A1 (en) | Systems and methods for identifying characteristics of electric vehicles | |
| CN202352075U (en) | Five-in-one electronic police system | |
| CN105453418A (en) | Method and apparatus for identifying locations of solar panels | |
| CN103136551B (en) | Second generation citizen ID certificate Information Authentication instrument and I.D. and fingerprint verification system | |
| CN112435368A (en) | Intelligent storage cabinet for police equipment and police personnel equipment management method | |
| CN208903322U (en) | Self-help type multifunctional intellectual gate inhibition's all-in-one machine | |
| CN112163515A (en) | Iris image acquisition method and related product | |
| CN212433777U (en) | Face authentication equipment | |
| EP3929804A1 (en) | Method and device for identifying face, computer program, and computer-readable storage medium | |
| CN106851135B (en) | The method and apparatus being replaced for determining sensor | |
| CN110796125A (en) | Face authentication method and system | |
| CN208722285U (en) | A kind of entrance guard security system based on face intravenous sensor | |
| CN106845370A (en) | A kind of electronic peephole viewer accessory system, terminal device and electronic peephole viewer | |
| CN212724128U (en) | Face recognition processing circuit and access control system | |
| CN206741505U (en) | Identify management equipment and device | |
| CN115880213A (en) | Display abnormity detection method, device and system | |
| CN208873174U (en) | A kind of testimony of a witness veritification device | |
| CN213024429U (en) | Face recognition equipment | |
| CN107545211A (en) | High in the clouds data handling system |
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 |