CN108376434A - A kind of intelligent home control system based on Internet of Things - Google Patents
A kind of intelligent home control system based on Internet of Things Download PDFInfo
- Publication number
- CN108376434A CN108376434A CN201810154287.1A CN201810154287A CN108376434A CN 108376434 A CN108376434 A CN 108376434A CN 201810154287 A CN201810154287 A CN 201810154287A CN 108376434 A CN108376434 A CN 108376434A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- user
- recognition
- facial image
- 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.)
- Granted
Links
- 230000001815 facial effect Effects 0.000 claims description 147
- 230000005055 memory storage Effects 0.000 claims description 24
- 230000006698 induction Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 abstract description 26
- 230000008569 process Effects 0.000 abstract description 7
- 238000012795 verification Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005201 scrubbing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of intelligent home control system and device based on Internet of Things, the system is by being arranged double face image recognition mode, and then the identity information of the different user in single image is identified, realize the high discrimination in the case of lower similarity, to improve safety and the efficiency of recognition of face, the low problem of recognition efficiency that single recognition of face is brought is avoided, the influence to environment-identification is reduced；In addition, the present invention is provided with the second user of multiple cooperation personal identification verifications, the flexibility in identification process is improved, the entrance guard management of user is further ensured.
Description
Technical field
The present invention relates to the technical fields more particularly to a kind of smart home based on Internet of Things of Internet of Things and smart home
Control system.
Background technology
Recognition of face belongs to field of biological recognition, is applied to intelligent door lock field, thus it is possible to vary the traditional need of people
The custom for wanting carrying keys that could open the door, by recognition of face control door unlatching, largely avoided people leave behind key cannot
The inconvenience of enabling.In addition, mechanical key, which exists, loses stolen risk, recognition of face has higher peace as authentication
Quan Xing.And recognition of face is relative to fingerprint recognition, has non-contact, more easily advantage, it is easier to be easily accepted by a user, still
Recognition of face is come with some shortcomings on door lock.For example, door lock is generally seated on door, height has been fixed when mounted,
For facial image may be caused to capture for the user of different heights, difficult, recognition accuracy is low, recognition speed is not fast enough
Classes are over individually registers one's residence with greater need for convenient and efficient scrubbing brush face when going home for problem, especially children.In addition, at present to the adjusting of camera
Mostly adjusting manually, use is more inconvenient, and also more difficult that camera is accurately adjusted to required angle, user experience is poor, and
The accuracy of recognition of face is impacted.
In view of the above-mentioned problems, document CN107146305A is used to judge whether that someone enters induction by human body induction module
Region, image capture module are used to acquire the face image into the people of induction region；Image capture module, transmission mechanism and master
The cooperation of processor is realized when not including complete facial image in the image information of acquisition, and primary processor can pass through transmission
Mechanism carries out automatic adjusument to the angle position of image capture module automatically, to expand the effective range of recognition of face,
The accuracy of recognition of face is improved, and has the advantages that high degree of intelligence, simple operation and recognition speed are fast.Mobile terminal and nothing
The cooperation of line communication module realizes the remote control and the long-range identification function of guest of door lock.Light compensating lamp is used to be Image Acquisition
Module light filling ensures that image capture module can collect enough clearly images.
However, there is also many defects for the above method, first, although the above method can be by adjusting image capture module
Improve image recognition efficiency, but single biological information recognition method inevitable requirement has higher want to the collecting efficiency of image
It asks, and its identification is affected by environmental factor, therefore, there are significant limitations for single biological information recognition method；
Secondly, the above method is a kind of only external adjusting method in image recognition processes, is not carried out to image recognition itself
It is effective to improve, therefore, need to be proposed a kind of method that the living things feature recognition efficiency for intelligent door lock is improved, to
Efficiency, flexibility and the accuracy of biological information identification are improved, and then meets the diversification of user, individualized experience.
Invention content
The present invention provides a kind of intelligent home control system based on Internet of Things, and the system comprises following modules：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described first
User confirms into after the double face image recognition mode, is associated with to first facial image that the memory stores
Second user mobile terminal client terminal send recognition of face checking request；Agree to the recognition of face in the second user
After checking request, reopen described image acquisition module with obtain and meanwhile comprising first user the first facial image and
The double face image of second facial image of the second user；
Face quantity identification module, the face quantity in the double face image for identification, if in the double face image
Face quantity be 2, then execute comprehensive similarity judgment module；If the face quantity in the double face image is not 2,
It prompts first user and the second user to resurvey double face image, and returns and re-execute the face quantity knowledge
Other module；
Comprehensive similarity judgment module, the processor for the intelligent door lock obtain the double face image, and described in identification
The first face in double face image and the second face；Respectively by the image of first face, the image of second face
Characteristic Contrast is carried out with the first facial image, the second facial image of memory storage, obtains the double face image
Comprehensive similarity；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock opening module is executed；
When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts described the
One user changes the opening ways of the intelligent door lock；
Door lock opening module opens the intelligent door lock for being judged as successful match.
As a preferred embodiment, further including：
First similarity threshold is more than the comprehensive similarity threshold value.
As a preferred embodiment, further including：
The double face image recognition mode of the intelligent door lock is arranged in the administrator of the smart home, with setting with
The associated second user of recognition of face of first user；First user has single recognition of face of the intelligent door lock
Permission, the second user have single recognition of face permission of the intelligent door lock or do not have the intelligent door lock one
Face identifies permission.
As a preferred embodiment, described reopen described image acquisition module to obtain while include described
The double face image of the first facial image of first user and the second facial image of the second user, specifically includes：
Described image acquisition module is reopened, described image acquisition module obtains double face image, and the double face image is same
When the first facial image comprising first user and the second user the second facial image, and the double face image
Described in the second facial image part be covered in non-the first face part or the double face in first facial image
First facial image part described in image is covered in the non-second face part in second facial image.
As a preferred embodiment, the face quantity in the identification double face image, specifically includes：
The double face image is obtained, identifies first facial image and second facial image region, and divide
Go out the first image-region where first facial image and the second image-region where second facial image, it is described
First image-region and second image-region form the double face image；Respectively to described first image region and described
The image of second image-region is pre-processed, and carries out Face detection to pretreated image, by the successful people of positioning
Face quantity is as the face quantity identified.
As a preferred embodiment, described respectively by the image of first face, the figure of second face
As the first facial image, the second facial image progress Characteristic Contrast with memory storage, the double face image is obtained
Comprehensive similarity, specifically include：
First facial image of the image of first face and memory storage is subjected to Characteristic Contrast, is obtained the first
Face image similarity a1；Second facial image of the image of second face and memory storage is subjected to feature pair
Than obtaining the second facial image similarity a2；
Comprehensive similarity a12=a1*c1+a2*c2 of the double face image；Wherein, c1 is the first facial image similarity
The weight coefficient of a1, c2 are the weight coefficient of the second facial image similarity a2.
As a preferred embodiment, prompt first user changes the opening square of the intelligent door lock
Formula specifically includes：
The image capture module for closing the intelligent door lock forbids first user to use the unlocking mode of recognition of face；
Prompt first user using any one following unlocking mode：Key unlocking, unlocking of swiping the card, fingerprint unlocking, bluetooth
It unlocks, infrared ray is unlocked.
As a preferred embodiment, described associated to first facial image stored with the memory
The mobile terminal client terminal of second user sends recognition of face checking request, further includes：
The second user have it is multiple, when first user enter double face image recognition mode when, the intelligent door lock
Processor obtains all and associated second user of first facial image mobile terminal position information, and base
Judge the air line distance of the second user and the intelligent door lock in the location information, is only less than to the air line distance
Described in several nearest described second users of the second user or the air line distance of preset distance threshold are sent
The recognition of face checking request of first user.
In addition, the present invention provides a kind of intelligent home control device based on Internet of Things, described device includes following module：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described first
User confirms into after the double face image recognition mode, is associated with to first facial image that the memory stores
Second user mobile terminal client terminal send recognition of face checking request；Agree to the recognition of face in the second user
After checking request, reopen described image acquisition module with obtain and meanwhile comprising first user the first facial image and
The double face image of second facial image of the second user；
Face quantity identification module, the face quantity in the double face image for identification, if in the double face image
Face quantity be 2, then execute comprehensive similarity judgment module；If the face quantity in the double face image is not 2,
It prompts first user and the second user to resurvey double face image, and returns and re-execute the face quantity knowledge
Other module；
Comprehensive similarity judgment module, the processor for the intelligent door lock obtain the double face image, and described in identification
The first face in double face image and the second face；Respectively by the image of first face, the image of second face
Characteristic Contrast is carried out with the first facial image, the second facial image of memory storage, obtains the double face image
Comprehensive similarity；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock opening module is executed；
When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts described the
One user changes the opening ways of the intelligent door lock；
Door lock opening module opens the intelligent door lock for being judged as successful match.
The present invention provides a kind of intelligent home control system and device based on Internet of Things, and the system is by being arranged double face
Image recognition pattern, and then the identity information of the different user in single image is identified, realize lower similarity
In the case of high discrimination avoid the identification that single recognition of face is brought to improve safety and the efficiency of recognition of face
The low problem of efficiency, reduces the influence to environment-identification；In addition, the present invention is provided with the of multiple cooperation personal identifications verifications
Two users improve the flexibility in identification process, further ensure the entrance guard management of user.
Description of the drawings
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to institute in embodiment and description of the prior art
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of a kind of schematic diagram of embodiment of intelligent home control system based on Internet of Things of the present invention.
Specific implementation mode
The embodiment further illustrated the present invention below in conjunction with attached drawing.
Embodiment one：
As shown in Figure 1, the present invention provides a kind of intelligent home control system based on Internet of Things, the system comprises such as lower dies
Block：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；It should be noted that the reality
The face characteristic comparison applied in mode is not different from the recognition of face mode of this field routine, and therefore, this will not be repeated here.Show
Example property, first similarity threshold is 0.9.
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described
First user confirms into after the double face image recognition mode, to first facial image stored with the memory
The mobile terminal client terminal of associated second user sends recognition of face checking request；Agree to the face in the second user
After identifying checking request, described image acquisition module is reopened to obtain while include the first face figure of first user
The double face image of picture and the second facial image of the second user；It should be noted that the double face in the embodiment
Recognition mode is different with recognition of face pattern above-mentioned, that is, single face recognition mode, and only in single recognition of face mould
Formula does not carry out successfully just automatically turning on the double face image recognition mode in the case of recognition of face, that is, under default situations
The priority of the double face image recognition mode is less than the single face recognition mode, and the purpose being arranged in this way is because double
It needs to carry out double recognitions of face in face recognition mode, the complexity and difficulty of identification want higher, therefore, under regular situation for example
Preferentially known using above-mentioned single face when light in environment-identification is preferably or the head portrait position of the first user is more satisfactory
Other pattern, to improve the speed of identification.Illustratively, it with the associated second user of the first facial image can be management
Member user is preset, for example, second user can be the kinsfolk of the first user, can also be that the first subscriber household is attached
The good friend closely to live, it might even be possible to be the neighbours etc. of the first user, not limit herein.The purpose being arranged in this way is second user
Image can be not only acquired on its mobile terminal so that the first user uses in facial image recognition process, it can also be to
The intelligent door lock position of one user helps the first user to carry out image recognition to unlock；It not only can ensure the first use
The safety of the gate inhibition at family may also help in the safety management that the crowd that the needs including such as children are guarded carries out gate inhibition；From
And improve the safety during access control system use.
Face quantity identification module, the face quantity in the double face image for identification, if the double face figure
Face quantity as in is 2, then executes comprehensive similarity judgment module；If the face quantity in the double face image is not
2, then prompt first user and the second user to resurvey double face image, and return and re-execute the face number
Measure identification module；It should be noted that it is only a kind of example that above-mentioned face quantity, which is 2, further, it is also possible to be used multiple second
Recognition of face is opened in family simultaneously after agreeing to above-mentioned request, and obtains the plurality of human faces image of corresponding multiple second users, and then improves
The accuracy of image recognition and safety.In addition, first user and the second user is prompted to resurvey double face figure
Picture can only prompt the first user of no successful acquisition full facial image or second user to carry out image again and adopt
Collection, can also prompt whole users to acquire image again, not be limited herein.
Comprehensive similarity judgment module, the processor for the intelligent door lock obtains the double face image, and identifies
The first face in the double face image and the second face；Respectively by the image of first face, second face
Image and the first facial image, the second facial image of memory storage carry out Characteristic Contrast, obtain the double face figure
The comprehensive similarity of picture；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock unlatching is executed
Module；When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts institute
State the opening ways that the first user changes the intelligent door lock；It should be noted that illustrative, the comprehensive similarity threshold value
It is 0.7.
Door lock opening module opens the intelligent door lock for being judged as successful match.
As a preferred embodiment, further including：
First similarity threshold is more than the comprehensive similarity threshold value.It should be noted that the first similarity is arranged here
Threshold value be more than the comprehensive similarity threshold value be the reason is that, since Characteristic Contrast is related to a variety of environmental factors, Duo Getu
Its matching degree can be then reduced together as being integrated into after independent progress Characteristic Contrast, therefore, in order to avoid similarity threshold is arranged
The influence of the excessively high accuracy to recognition result is arranged comprehensive similarity threshold value and is less than the first similarity threshold here；So not
Only ensure that the accuracy of image recognition, also avoid threshold value be arranged it is excessively high caused by recognition result inaccuracy problem.
As a preferred embodiment, further including：
The double face image recognition mode of the intelligent door lock is arranged in the administrator of the smart home, with setting with
The associated second user of recognition of face of first user；First user has single recognition of face of the intelligent door lock
Permission, the second user have single recognition of face permission of the intelligent door lock or do not have the intelligent door lock one
Face identifies permission.It should be noted that be provided with the user right of second user here is less than the user right of the first user
Because there is the first user higher operation grade, second user to carry out recognition of face as just the first user of auxiliary；Certainly,
Second user can also have user gradation identical with the first user.
As a preferred embodiment, described reopen described image acquisition module to obtain while include described
The double face image of the first facial image of first user and the second facial image of the second user, specifically includes：
Described image acquisition module is reopened, described image acquisition module obtains double face image, and the double face image is same
When the first facial image comprising first user and the second user the second facial image, and the double face image
Described in the second facial image part be covered in non-the first face part or the double face in first facial image
First facial image part described in image is covered in the non-second face part in second facial image.It needs to illustrate
It is, when the second user unlocks scene near intelligent door lock, not done to the position of the first user and second user bright
True division, common left and right position, described image acquisition module scene obtain double face image；In the second user
When unlocking live not near intelligent door lock, the graphic interface of upper left bottom right can be presented, so that the first user refers to.
As a preferred embodiment, the face quantity in the identification double face image, specifically includes：
The double face image is obtained, identifies first facial image and second facial image region, and divide
Go out the first image-region where first facial image and the second image-region where second facial image, it is described
First image-region and second image-region form the double face image；Respectively to described first image region and described
The image of second image-region is pre-processed, and carries out Face detection to pretreated image, by the successful people of positioning
Face quantity is as the face quantity identified.It should be noted that passing through any one in two dotted lines in double face image
By the image segmentation be the first facial image where the first image-region, that is, left area and second facial image where
The second image-region, that is, right area；Then the image of left area and right area is pre-processed respectively, and then right
Pretreated image carries out Face detection, i.e., orients the face quantity in left-side images and image right and face place respectively
Position；It is achieved in the identification of face quantity and position.When determining for the facial image that double face image is upper left and lower right area
The identification of position and quantity, is identified and is positioned using method similar to the above, this will not be repeated here.Illustratively, above-mentioned
The division principle in region can be placement rule of the image capture module to different acquisition image, i.e. image capture module acquiescence will
The image of acquisition is then split with left and right region based on dotted line by two image left-right situs, and the split position of dotted line can
It is identified with the edge detection method based on image, this will not be repeated here.
As a preferred embodiment, described respectively by the image of first face, the figure of second face
As the first facial image, the second facial image progress Characteristic Contrast with memory storage, the double face image is obtained
Comprehensive similarity, specifically include：
First facial image of the image of first face and memory storage is subjected to Characteristic Contrast, is obtained the first
Face image similarity a1；Second facial image of the image of second face and memory storage is subjected to feature pair
Than obtaining the second facial image similarity a2；
Comprehensive similarity a12=a1*c1+a2*c2 of the double face image；Wherein, c1 is the first facial image similarity
The weight coefficient of a1, c2 are the weight coefficient of the second facial image similarity a2.
It should be noted that the computational methods of above-mentioned first facial image similarity a1 and the second facial image similarity a2
Using the matching algorithm of this field routine, this will not be repeated here.Illustratively, the assignment of above-mentioned weight coefficient c1 and c2 can root
It is configured according to the role of the first user and second user in administrator family, for example, if user is householder, for
Its weight coefficient c1 assigns larger weighted value 0.9；If family is to need to be guarded user such as old man, minor, for
Its weight coefficient c1 assigns smaller weighted value 0.7；If user is the personnel such as friend, neighbours other than kinsfolk, for
Its weight coefficient c1 assigns minimum weighted value 0.5；The user of above-mentioned hypothesis can be the first user, can also be the second use
Family does not limit herein.By above-mentioned calculating, due to introducing weight coefficient c1 and c2, the comprehensive similarity a12 of gained can be small
In the similarity of individual human face image；But its recognition efficiency increased.Therefore, it is carried out using above-mentioned comprehensive similarity double
Face identification can reduce the dependence to single recognition of face, avoid causing due to the systematic error in single face recognition process
Identification mistake problem, and then the Stability and veracity of recognition of face is improved, in the case of realizing lower similarity
It is low to avoid the recognition efficiency that single recognition of face is brought to improve safety and the efficiency of recognition of face for high discrimination
Problem reduces the influence to environment-identification factor.
As a preferred embodiment, prompt first user changes the opening square of the intelligent door lock
Formula specifically includes：
The image capture module for closing the intelligent door lock forbids first user to use the unlocking mode of recognition of face；
Prompt first user using any one following unlocking mode：Key unlocking, unlocking of swiping the card, fingerprint unlocking, bluetooth
It unlocks, infrared ray is unlocked.It should be noted that the above-mentioned unlocking mode enumerated is only a kind of example, however it is not limited to above several
Kind unlocking mode.
As a preferred embodiment, described associated to first facial image stored with the memory
The mobile terminal client terminal of second user sends recognition of face checking request, further includes：
The second user have it is multiple, when first user enter double face image recognition mode when, the intelligent door lock
Processor obtains all and associated second user of first facial image mobile terminal position information, and base
Judge the air line distance of the second user and the intelligent door lock in the location information, is only less than to the air line distance
Described in several nearest described second users of the second user or the air line distance of preset distance threshold are sent
The recognition of face checking request of first user.
It should be noted that the image recognition of any one second user, which is provided to the first user of cooperation, carries out face knowledge
, do not obtain the mobile terminal position information of second user also for convenient for second user with most fast speed responsive
The identification of one user operates, to improve recognition speed；For example, second user is the neighbours of the first user, then in the straight line of the two
Apart from it is nearest when, response speed be typically it is most fast, the neighbours coordinate the first user carry out recognition of face to unlock as early as possible
It is that efficiency is highest.It is above-mentioned using air line distance rather than plan range be also consider same level it is upper downstairs
Influence of the layer to this method.In addition, the setting of above-mentioned distance threshold can be adjusted according to actual needs, obtained with flexible setting
The quantity of the second user of auth response is taken, can also be 5 kilometers, or even without setting, acquiescence for example, can be 50 meters
For infinity, so that the verification that the first user obtains most second users is supported.
Embodiment two：
The present invention provides a kind of intelligent home control device based on Internet of Things, and described device includes following module：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described first
User confirms into after the double face image recognition mode, is associated with to first facial image that the memory stores
Second user mobile terminal client terminal send recognition of face checking request；Agree to the recognition of face in the second user
After checking request, reopen described image acquisition module with obtain and meanwhile comprising first user the first facial image and
The double face image of second facial image of the second user；
Face quantity identification module, the face quantity in the double face image for identification, if in the double face image
Face quantity be 2, then execute comprehensive similarity judgment module；If the face quantity in the double face image is not 2,
It prompts first user and the second user to resurvey double face image, and returns and re-execute the face quantity knowledge
Other module；
Comprehensive similarity judgment module, the processor for the intelligent door lock obtain the double face image, and described in identification
The first face in double face image and the second face；Respectively by the image of first face, the image of second face
Characteristic Contrast is carried out with the first facial image, the second facial image of memory storage, obtains the double face image
Comprehensive similarity；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock opening module is executed；
When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts described the
One user changes the opening ways of the intelligent door lock；
Door lock opening module opens the intelligent door lock for being judged as successful match.
As a preferred embodiment, further including：
First similarity threshold is more than the comprehensive similarity threshold value.It should be noted that the first similarity is arranged here
Threshold value be more than the comprehensive similarity threshold value be the reason is that, since Characteristic Contrast is related to a variety of environmental factors, Duo Getu
Its matching degree can be then reduced together as being integrated into after independent progress Characteristic Contrast, therefore, in order to avoid similarity threshold is arranged
The influence of the excessively high accuracy to recognition result is arranged comprehensive similarity threshold value and is less than the first similarity threshold here；So not
Only ensure that the accuracy of image recognition, also avoid threshold value be arranged it is excessively high caused by recognition result inaccuracy problem.
As a preferred embodiment, further including：
The double face image recognition mode of the intelligent door lock is arranged in the administrator of the smart home, with setting with
The associated second user of recognition of face of first user；First user has single recognition of face of the intelligent door lock
Permission, the second user have single recognition of face permission of the intelligent door lock or do not have the intelligent door lock one
Face identifies permission.It should be noted that be provided with the user right of second user here is less than the user right of the first user
Because there is the first user higher operation grade, second user to carry out recognition of face as just the first user of auxiliary；Certainly,
Second user can also have user gradation identical with the first user.
As a preferred embodiment, described reopen described image acquisition module to obtain while include described
The double face image of the first facial image of first user and the second facial image of the second user, specifically includes：
Described image acquisition module is reopened, described image acquisition module obtains double face image, and the double face image is same
When the first facial image comprising first user and the second user the second facial image, and the double face image
Described in the second facial image part be covered in non-the first face part or the double face in first facial image
First facial image part described in image is covered in the non-second face part in second facial image.It needs to illustrate
It is, when the second user unlocks scene near intelligent door lock, not done to the position of the first user and second user bright
True division, common left and right position, described image acquisition module scene obtain double face image；In the second user
When unlocking live not near intelligent door lock, the graphic interface of upper left bottom right can be presented, so that the first user refers to.
As a preferred embodiment, the face quantity in the identification double face image, specifically includes：
The double face image is obtained, identifies first facial image and second facial image region, and divide
Go out the first image-region where first facial image and the second image-region where second facial image, it is described
First image-region and second image-region form the double face image；Respectively to described first image region and described
The image of second image-region is pre-processed, and carries out Face detection to pretreated image, by the successful people of positioning
Face quantity is as the face quantity identified.It should be noted that passing through any one in two dotted lines in double face image
By the image segmentation be the first facial image where the first image-region, that is, left area and second facial image where
The second image-region, that is, right area；Then the image of left area and right area is pre-processed respectively, and then right
Pretreated image carries out Face detection, i.e., orients the face quantity in left-side images and image right and face place respectively
Position；It is achieved in the identification of face quantity and position.When determining for the facial image that double face image is upper left and lower right area
The identification of position and quantity, is identified and is positioned using method similar to the above, this will not be repeated here.Illustratively, above-mentioned
The division principle in region can be placement rule of the image capture module to different acquisition image, i.e. image capture module acquiescence will
The image of acquisition is then split with left and right region based on dotted line by two image left-right situs, and the split position of dotted line can
It is identified with the edge detection method based on image, this will not be repeated here.
As a preferred embodiment, described respectively by the image of first face, the figure of second face
As the first facial image, the second facial image progress Characteristic Contrast with memory storage, the double face image is obtained
Comprehensive similarity, specifically include：
First facial image of the image of first face and memory storage is subjected to Characteristic Contrast, is obtained the first
Face image similarity a1；Second facial image of the image of second face and memory storage is subjected to feature pair
Than obtaining the second facial image similarity a2；
Comprehensive similarity a12=a1*c1+a2*c2 of the double face image；Wherein, c1 is the first facial image similarity
The weight coefficient of a1, c2 are the weight coefficient of the second facial image similarity a2.
It should be noted that the computational methods of above-mentioned first facial image similarity a1 and the second facial image similarity a2
Using the matching algorithm of this field routine, this will not be repeated here.Illustratively, the assignment of above-mentioned weight coefficient c1 and c2 can root
It is configured according to the role of the first user and second user in administrator family, for example, if user is householder, for
Its weight coefficient c1 assigns larger weighted value 0.9；If family is to need to be guarded user such as old man, minor, for
Its weight coefficient c1 assigns smaller weighted value 0.7；If user is the personnel such as friend, neighbours other than kinsfolk, for
Its weight coefficient c1 assigns minimum weighted value 0.5；The user of above-mentioned hypothesis can be the first user, can also be the second use
Family does not limit herein.By above-mentioned calculating, due to introducing weight coefficient c1 and c2, the comprehensive similarity a12 of gained can be small
In the similarity of individual human face image；But its recognition efficiency increased.Therefore, it is carried out using above-mentioned comprehensive similarity double
Face identification can reduce the dependence to single recognition of face, avoid causing due to the systematic error in single face recognition process
Identification mistake problem, and then the Stability and veracity of recognition of face is improved, in the case of realizing lower similarity
It is low to avoid the recognition efficiency that single recognition of face is brought to improve safety and the efficiency of recognition of face for high discrimination
Problem reduces the influence to environment-identification factor.
As a preferred embodiment, prompt first user changes the opening square of the intelligent door lock
Formula specifically includes：
The image capture module for closing the intelligent door lock forbids first user to use the unlocking mode of recognition of face；
Prompt first user using any one following unlocking mode：Key unlocking, unlocking of swiping the card, fingerprint unlocking, bluetooth
It unlocks, infrared ray is unlocked.It should be noted that the above-mentioned unlocking mode enumerated is only a kind of example, however it is not limited to above several
Kind unlocking mode.
As a preferred embodiment, described associated to first facial image stored with the memory
The mobile terminal client terminal of second user sends recognition of face checking request, further includes：
The second user have it is multiple, when first user enter double face image recognition mode when, the intelligent door lock
Processor obtains all and associated second user of first facial image mobile terminal position information, and base
Judge the air line distance of the second user and the intelligent door lock in the location information, is only less than to the air line distance
Described in several nearest described second users of the second user or the air line distance of preset distance threshold are sent
The recognition of face checking request of first user.
It should be noted that the image recognition of any one second user, which is provided to the first user of cooperation, carries out face knowledge
, do not obtain the mobile terminal position information of second user also for convenient for second user with most fast speed responsive
The identification of one user operates, to improve recognition speed；For example, second user is the neighbours of the first user, then in the straight line of the two
Apart from it is nearest when, response speed be typically it is most fast, the neighbours coordinate the first user carry out recognition of face to unlock as early as possible
It is that efficiency is highest.It is above-mentioned using air line distance rather than plan range be also consider same level it is upper downstairs
Influence of the layer to this method.In addition, the setting of above-mentioned distance threshold can be adjusted according to actual needs, obtained with flexible setting
The quantity of the second user of auth response is taken, can also be 5 kilometers, or even without setting, acquiescence for example, can be 50 meters
For infinity, so that the verification that the first user obtains most second users is supported.
The present invention provides a kind of intelligent home control system and device based on Internet of Things, and the system is by being arranged double face
Image recognition pattern, and then the identity information of the different user in single image is identified, realize lower similarity
In the case of high discrimination avoid the identification that single recognition of face is brought to improve safety and the efficiency of recognition of face
The low problem of efficiency, reduces the influence to environment-identification；In addition, the present invention is provided with the of multiple cooperation personal identifications verifications
Two users improve the flexibility in identification process, further ensure the entrance guard management of user.
Those skilled in the art of the present technique be appreciated that can with computer program instructions come realize these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.It can be by this
A little computer program instructions are supplied to the processor of all-purpose computer, special purpose computer or other programmable data processing methods
Machine is generated, is used for be performed instruction by the processor of computer or other programmable data processing methods and create
Realize the method specified in the frame or multiple frames of structure chart and/or block diagram and/or flow graph.
Those skilled in the art of the present technique are appreciated that in the various operations crossed by discussion in the present invention, method, flow
Steps, measures, and schemes can be replaced, changed, combined or be deleted.Further, each with having been crossed by discussion in the present invention
Other steps, measures, and schemes in kind operation, method, flow may also be alternated, changed, rearranged, decomposed, combined or deleted.
Further, in the prior art to have and step, measure, the scheme in various operations, method, flow disclosed in the present invention
It may also be alternated, changed, rearranged, decomposed, combined or deleted.
Example the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (9)
1. a kind of intelligent home control system based on Internet of Things, which is characterized in that the system comprises following modules：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described first
User confirms into after the double face image recognition mode, is associated with to first facial image that the memory stores
Second user mobile terminal client terminal send recognition of face checking request；Agree to the recognition of face in the second user
After checking request, reopen described image acquisition module with obtain and meanwhile comprising first user the first facial image and
The double face image of second facial image of the second user；
Face quantity identification module, the face quantity in the double face image for identification, if in the double face image
Face quantity be 2, then execute comprehensive similarity judgment module；If the face quantity in the double face image is not 2,
It prompts first user and the second user to resurvey double face image, and returns and re-execute the face quantity knowledge
Other module；
Comprehensive similarity judgment module, the processor for the intelligent door lock obtain the double face image, and described in identification
The first face in double face image and the second face；Respectively by the image of first face, the image of second face
Characteristic Contrast is carried out with the first facial image, the second facial image of memory storage, obtains the double face image
Comprehensive similarity；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock opening module is executed；
When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts described the
One user changes the opening ways of the intelligent door lock；
Door lock opening module opens the intelligent door lock for being judged as successful match.
2. intelligent home control system according to claim 1, which is characterized in that further include：
First similarity threshold is more than the comprehensive similarity threshold value.
3. intelligent home control system according to claim 1, which is characterized in that further include：
The double face image recognition mode of the intelligent door lock is arranged in the administrator of the smart home, with setting with
The associated second user of recognition of face of first user；First user has single recognition of face of the intelligent door lock
Permission, the second user have single recognition of face permission of the intelligent door lock or do not have the intelligent door lock one
Face identifies permission.
4. intelligent home control system according to claim 1, which is characterized in that described to reopen described image acquisition
Module with obtain and meanwhile the second facial image of the first facial image and the second user comprising first user it is double
Facial image specifically includes：
Described image acquisition module is reopened, described image acquisition module obtains double face image, and the double face image is same
When the first facial image comprising first user and the second user the second facial image, and the double face image
Described in the second facial image part be covered in non-the first face part or the double face in first facial image
First facial image part described in image is covered in the non-second face part in second facial image.
5. intelligent home control system according to claim 4, which is characterized in that in the identification double face image
Face quantity, specifically include：
The double face image is obtained, identifies first facial image and second facial image region, and divide
Go out the first image-region where first facial image and the second image-region where second facial image, it is described
First image-region and second image-region form the double face image；Respectively to described first image region and described
The image of second image-region is pre-processed, and carries out Face detection to pretreated image, by the successful people of positioning
Face quantity is as the face quantity identified.
6. intelligent home control system according to claim 1, which is characterized in that described respectively by first face
Image, the image of second face and the first facial image, the second facial image of memory storage carry out feature pair
Than obtaining the comprehensive similarity of the double face image, specifically including：
First facial image of the image of first face and memory storage is subjected to Characteristic Contrast, is obtained the first
Face image similarity a1；Second facial image of the image of second face and memory storage is subjected to feature pair
Than obtaining the second facial image similarity a2；
Comprehensive similarity a12=a1*c1+a2*c2 of the double face image；Wherein, c1 is the first facial image similarity
The weight coefficient of a1, c2 are the weight coefficient of the second facial image similarity a2.
7. intelligent home control system according to claim 1, which is characterized in that prompt first user changes
The opening ways of the intelligent door lock, specifically include：
The image capture module for closing the intelligent door lock forbids first user to use the unlocking mode of recognition of face；
Prompt first user using any one following unlocking mode：Key unlocking, unlocking of swiping the card, fingerprint unlocking, bluetooth
It unlocks, infrared ray is unlocked.
8. according to claim 1-6 any one of them intelligent home control systems, which is characterized in that it is described to the storage
The mobile terminal client terminal of the associated second user of the first facial image of device storage sends recognition of face checking request, also
Including：
The second user have it is multiple, when first user enter double face image recognition mode when, the intelligent door lock
Processor obtains all and associated second user of first facial image mobile terminal position information, and base
Judge the air line distance of the second user and the intelligent door lock in the location information, is only less than to the air line distance
Described in several nearest described second users of the second user or the air line distance of preset distance threshold are sent
The recognition of face checking request of first user.
9. a kind of intelligent home control device based on Internet of Things, which is characterized in that described device includes following module：
First similarity judgment module senses the first use for the human body induction module in the intelligent door lock of the smart home
When the human body at family enters preset induction region, the intelligent door lock opens image capture module to obtain the first facial image；
Characteristic Contrast is carried out to the first facial image of the memory storage of first facial image and the smart home, when described
When the result of Characteristic Contrast is more than or equal to preset first similarity threshold, then door lock opening module is executed；When the feature pair
When the result of ratio is less than preset first similarity threshold, then double recognition of face starting modules are executed；
Double recognition of face starting modules, for prompting first user to enter double face image recognition mode, described first
User confirms into after the double face image recognition mode, is associated with to first facial image that the memory stores
Second user mobile terminal client terminal send recognition of face checking request；Agree to the recognition of face in the second user
After checking request, reopen described image acquisition module with obtain and meanwhile comprising first user the first facial image and
The double face image of second facial image of the second user；
Face quantity identification module, the face quantity in the double face image for identification, if in the double face image
Face quantity be 2, then execute comprehensive similarity judgment module；If the face quantity in the double face image is not 2,
It prompts first user and the second user to resurvey double face image, and returns and re-execute the face quantity knowledge
Other module；
Comprehensive similarity judgment module, the processor for the intelligent door lock obtain the double face image, and described in identification
The first face in double face image and the second face；Respectively by the image of first face, the image of second face
Characteristic Contrast is carried out with the first facial image, the second facial image of memory storage, obtains the double face image
Comprehensive similarity；When the comprehensive similarity is more than or equal to preset comprehensive similarity threshold value, then door lock opening module is executed；
When the comprehensive similarity is less than preset comprehensive similarity threshold value, then judge that it fails to match for recognition of face, prompts described the
One user changes the opening ways of the intelligent door lock；
Door lock opening module opens the intelligent door lock for being judged as successful match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810154287.1A CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810154287.1A CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108376434A true CN108376434A (en) | 2018-08-07 |
| CN108376434B CN108376434B (en) | 2020-12-25 |
Family
ID=63017824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810154287.1A Active CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108376434B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409249A (en) * | 2018-09-30 | 2019-03-01 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN109447597A (en) * | 2018-12-27 | 2019-03-08 | 深圳市沃特沃德股份有限公司 | More people carry out the method, apparatus and face identification system of attendance jointly |
| CN110021101A (en) * | 2019-03-29 | 2019-07-16 | 深圳市九洲电器有限公司 | A kind of intelligent entrance guard control method and intelligent access control system |
| CN112070954A (en) * | 2020-09-14 | 2020-12-11 | 上海商汤智能科技有限公司 | Living body identification method, living body identification device, living body identification equipment and storage medium |
| CN113516814A (en) * | 2021-04-19 | 2021-10-19 | 新疆爱华盈通信息技术有限公司 | Intelligent supply method and terminal based on face recognition |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101142586A (en) * | 2005-03-18 | 2008-03-12 | 皇家飞利浦电子股份有限公司 | Method of performing face recognition |
| WO2011039040A1 (en) * | 2009-10-02 | 2011-04-07 | Tessera Technologies Ireland Limited | Improving face recognition performance using additional image features |
| CN202662026U (en) * | 2012-06-05 | 2013-01-09 | 上海锦江电子技术工程有限公司 | Multi-face recognition system |
| CN102945366A (en) * | 2012-11-23 | 2013-02-27 | 海信集团有限公司 | Method and device for face recognition |
| CN103236103A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Anti-follow access control system based on face recognition |
| CN103440691A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Bank exchequer long-distance defense management system |
| CN103714347A (en) * | 2013-12-30 | 2014-04-09 | 汉王科技股份有限公司 | Facial recognition method and facial recognition device |
| CN104599367A (en) * | 2014-12-31 | 2015-05-06 | 苏州福丰科技有限公司 | Multi-user parallel access control recognition method based on three-dimensional face image recognition |
| CN106250851A (en) * | 2016-08-01 | 2016-12-21 | 徐鹤菲 | A kind of identity identifying method, equipment and mobile terminal |
| CN107077615A (en) * | 2017-01-12 | 2017-08-18 | 厦门中控生物识别信息技术有限公司 | Fingerprint method for anti-counterfeit and equipment |
| CN107195045A (en) * | 2017-05-18 | 2017-09-22 | 盐城工学院 | Gate inhibition's door bell and button system and safety-protection system |
| US20180047230A1 (en) * | 2014-04-25 | 2018-02-15 | Vivint, Inc. | Automatic system access using facial recognition |
-
2018
- 2018-02-22 CN CN201810154287.1A patent/CN108376434B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101142586A (en) * | 2005-03-18 | 2008-03-12 | 皇家飞利浦电子股份有限公司 | Method of performing face recognition |
| WO2011039040A1 (en) * | 2009-10-02 | 2011-04-07 | Tessera Technologies Ireland Limited | Improving face recognition performance using additional image features |
| CN202662026U (en) * | 2012-06-05 | 2013-01-09 | 上海锦江电子技术工程有限公司 | Multi-face recognition system |
| CN102945366A (en) * | 2012-11-23 | 2013-02-27 | 海信集团有限公司 | Method and device for face recognition |
| CN103236103A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Anti-follow access control system based on face recognition |
| CN103440691A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Bank exchequer long-distance defense management system |
| CN103714347A (en) * | 2013-12-30 | 2014-04-09 | 汉王科技股份有限公司 | Facial recognition method and facial recognition device |
| US20180047230A1 (en) * | 2014-04-25 | 2018-02-15 | Vivint, Inc. | Automatic system access using facial recognition |
| CN104599367A (en) * | 2014-12-31 | 2015-05-06 | 苏州福丰科技有限公司 | Multi-user parallel access control recognition method based on three-dimensional face image recognition |
| CN106250851A (en) * | 2016-08-01 | 2016-12-21 | 徐鹤菲 | A kind of identity identifying method, equipment and mobile terminal |
| CN107077615A (en) * | 2017-01-12 | 2017-08-18 | 厦门中控生物识别信息技术有限公司 | Fingerprint method for anti-counterfeit and equipment |
| CN107195045A (en) * | 2017-05-18 | 2017-09-22 | 盐城工学院 | Gate inhibition's door bell and button system and safety-protection system |
Non-Patent Citations (3)
| Title |
|---|
| JIANCHUN XIE, JIAN YANG, JIANJUN QIANA, LEI LUO: "Bi-weighted robust matrix regression for face recognition", 《NEUROCOMPUTING》 * |
| 李硕豪，张军: "基于OMAP3530数字图像处理的多人脸识别系统设计", 《微型机与应用》 * |
| 黄智，罗永: "从专利角度看人脸识别技术的发展", 《电视技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409249A (en) * | 2018-09-30 | 2019-03-01 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN109447597A (en) * | 2018-12-27 | 2019-03-08 | 深圳市沃特沃德股份有限公司 | More people carry out the method, apparatus and face identification system of attendance jointly |
| CN109447597B (en) * | 2018-12-27 | 2022-04-12 | 深圳市沃特沃德信息有限公司 | Method and device for attendance checking by multiple persons and face recognition system |
| CN110021101A (en) * | 2019-03-29 | 2019-07-16 | 深圳市九洲电器有限公司 | A kind of intelligent entrance guard control method and intelligent access control system |
| CN112070954A (en) * | 2020-09-14 | 2020-12-11 | 上海商汤智能科技有限公司 | Living body identification method, living body identification device, living body identification equipment and storage medium |
| CN113516814A (en) * | 2021-04-19 | 2021-10-19 | 新疆爱华盈通信息技术有限公司 | Intelligent supply method and terminal based on face recognition |
| CN113516814B (en) * | 2021-04-19 | 2023-04-18 | 新疆爱华盈通信息技术有限公司 | Intelligent supply method and terminal based on face recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108376434B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108376434A (en) | A kind of intelligent home control system based on Internet of Things | |
| US10679443B2 (en) | System and method for controlling access to a building with facial recognition | |
| US10032327B1 (en) | Access control system with facial recognition and unlocking method thereof | |
| KR20200062284A (en) | Vehicle and vehicle door unlock control method, device and vehicle door unlock system | |
| US11205312B2 (en) | Applying image analytics and machine learning to lock systems in hotels | |
| CN109727344A (en) | 3D Intelligent door lock capable of recognizing face and 3D face unlocking method | |
| CN110313008A (en) | Method and smart card suitable for the registration of gradually fingerprint | |
| JP2009527804A (en) | Distributed standoff ID verification compatible with multiple face recognition systems (FRS) | |
| US20130163833A1 (en) | Security device with security image update capability | |
| KR102093858B1 (en) | Biometrics-based vehicle control device and vehicle control method using same | |
| CN206431724U (en) | A kind of gate control system based on face recognition technology | |
| CN109255219A (en) | A kind of temperature sense unlocking method and system based on bio-identification terminal | |
| CN109809262B (en) | Elevator permission safety control system | |
| KR101634943B1 (en) | Car Parking Management System for Disabled Person Using Biometrics and Mobile Communication Terminal Authentication | |
| CN113003330A (en) | Intelligent elevator control method and system based on face recognition | |
| CN108389290A (en) | A kind of intelligent home furnishing control method based on Internet of Things | |
| CN118334758B (en) | Image recognition method and system applied to building access control system | |
| CN109285260A (en) | A kind of gate control method and device | |
| JP4434560B2 (en) | Entrance / exit management system | |
| KR101926709B1 (en) | Control apparatus for biometric and method thereof | |
| CN113112664A (en) | Vertical entrance guard's equipment of face identification | |
| CN111932758A (en) | Intelligent access control system based on face recognition technology | |
| AU2022435296B2 (en) | Trusted seamless authentication method for access control | |
| CN214359584U (en) | Elevator man-machine interaction system | |
| KR20140060081A (en) | Apparatus and method for speed gate based on face recognition at a distance |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201209 Address after: 506, Zhongxin science and technology building, Bagualing Industrial Zone, No. 31, Bagua Road, Hualin community, Yuanling street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Huake Intelligent Information Co.,Ltd. Address before: East house, 11th floor, building 6, yujingwan community, beiyihuan, Biyang County, Zhumadian City, Henan Province 463700 Applicant before: Chen Chong |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |