CN112686148B - Face recognition system suitable for crowds with various heights - Google Patents
Face recognition system suitable for crowds with various heights Download PDFInfo
- Publication number
- CN112686148B CN112686148B CN202011604068.2A CN202011604068A CN112686148B CN 112686148 B CN112686148 B CN 112686148B CN 202011604068 A CN202011604068 A CN 202011604068A CN 112686148 B CN112686148 B CN 112686148B
- Authority
- CN
- China
- Prior art keywords
- walking
- module
- user
- processing module
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 claims abstract description 84
- 230000009467 reduction Effects 0.000 claims abstract description 9
- 238000003331 infrared imaging Methods 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 6
- 230000001815 facial effect Effects 0.000 claims 2
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000037237 body shape Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000000034 method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image recognition, in particular to a face recognition system suitable for people with various heights, which comprises an acquisition module, an adjustment module, a control module, a gate module, a mobile trigger module and a processing module, wherein the acquisition module is used for acquiring face images of users and sending the face images to the control module, the control module is used for matching the face images with pre-stored face information, the gate module is controlled to be opened when the control module is successfully matched, the mobile trigger module is used for acquiring walking images within a preset range of the users, the processing module is used for judging whether the shapes of the users on the walking images are completely located on the walking images, the processing module is used for sending a reduction adjustment signal to the control module when the shapes of the users are completely located on the walking images, and the control module is used for controlling the adjustment module to adjust the positions of the acquisition module according to the reduction adjustment signal. The mobile trigger module and the processing module can be arranged independently of the related modules of the gate, and the related modules of the gate do not need to be improved or replaced greatly, so that the cost is reduced.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a face recognition system suitable for crowds with various heights.
Background
Along with the improvement of the intelligent degree of the home, more and more living communities introduce an access control system based on face recognition. Currently, an access control system based on face recognition generally fixes a camera device for face recognition at an access control position to ensure a certain recognition range of the camera device. However, for the crowd entering the living community, the individual personnel has higher or shorter height, the access control system still cannot recognize the face, and the use is inconvenient.
Aiming at the problem of face recognition of the access control system, the patent with publication number CN206179043U discloses a face recognition system, which consists of a server and a plurality of face recognition devices connected with the server in a communication way, and each face recognition device comprises: tripod, electronic rotary device and electronic every single move device etc. adopt among the above-mentioned technical scheme, because face identification camera is installed in the backup pad, and the backup pad is under the cooperation of tripod, electronic rotary device, devices such as electronic every single move device, its height, direction and angle of adjustment that can be convenient, therefore can satisfy different height users 'operation requirement, improved user's experience degree, make face identification device have characteristics that the reliability of use is high, operation is comfortable.
When the system is used for face recognition, when a user is a child entering the access control, the child cannot trigger the system to perform face recognition due to the short height, the existing access control system needs to be updated to adapt to the face recognition of the child, and the improvement cost of the access control system is high.
Disclosure of Invention
The invention aims to provide a face recognition system suitable for crowds with various heights, so as to solve the problem that shorter children cannot trigger the existing access control system to perform face recognition.
The face recognition system suitable for the crowds with various heights comprises an acquisition module, an adjustment module, a control module and a gate module, wherein the acquisition module is used for acquiring face images of users and sending the face images to the control module, the adjustment module drives the acquisition module to adjust positions, the control module matches the face images with pre-stored face information, and when the face images and the face information which are the same are matched, the control module controls the gate module to be opened for the users to pass through;
The mobile trigger device comprises a ground, a collection module, a processing module, a control module and a reduction regulation signal, wherein the distance between the mobile trigger module and the ground is one half of the height of the collection module from the ground, the mobile trigger module collects walking images of a user in a preset height and preset distance range above the ground, the processing module obtains the walking images, the processing module judges whether the user figure is completely located on the walking images, the processing module sends the reduction regulation signal to the control module when the user figure is completely located on the walking images, and the control module controls the start of the regulation module according to the reduction regulation signal.
The beneficial effect of this scheme is:
When a user enters a social area, the adjusting module drives the acquisition module to adjust the position, so that the acquisition module acquires the face image and sends the face image to the control module for matching, and when matching is successful, the control module controls the gate module to be opened for the user to enter; meanwhile, a mobile triggering module collects a walking image of a user in a preset range above the ground, namely a walking image of the lower body of the user, a processing module is enabled to identify the user figure according to the walking image, namely the lower body figure of the user on the walking image is judged, whether the user figure is completely located on the walking image is judged, namely whether the user is a child is judged, when the user figure is completely located on the walking image is judged, a lowering adjusting signal is sent to a control module by the processing module, so that the control module is triggered to control the adjusting module to start the position of the adjusting module, and face information of the user is accurately collected; and the movable trigger module and the processing module can be arranged independently of the related modules of the gate, can be directly attached to the existing gate without greatly improving or replacing the related modules of the gate, and is more flexible and convenient to use and reduces the cost.
Further, the processing module compares the top edge of the user figure on the walking image with the top edge of the walking image, and when the top edge of the figure is lower than the top edge of the image, the processing module judges that the user figure is completely located on the walking image.
The beneficial effects are that: when the child user approaches the gate module, according to whether the top edge of the figure of the child user on the walking image is lower than the top edge of the walking image, the top edge of the figure is not contacted with the top edge of the walking image, so that whether the figure of the user is completely positioned on the walking image is judged, the accuracy of child user identification is improved, and the position of the acquisition module is adjusted by triggering the adjustment module in time.
Further, when the top edge of the figure contacts the top edge, the processing module identifies the leg walking profile of the user walking from the walking image, when the leg walking profile is an independent bar column, the processing module judges that the user figure is completely located on the walking image, when the leg walking profile is two independent bar columns, the processing module judges that the user figure is located outside the acquisition range of the mobile trigger module, the processing module sends a lifting adjusting signal to the control module, and the control module controls the starting of the adjusting module according to the lifting adjusting signal.
The beneficial effects are that: for face image acquisition of floodgate machine, the normal height that collection module was predetermine can satisfy most user's demand, and the setting of removal trigger module can gather the whole of body shape to the user of part height for the user of part height is shorter, can only gather the shank to the user of part height is higher, so, when user's body shape top edge is located the top border of walking image, through the leg walking profile when discernment walking to judge walking profile is an independent bar post or two independent bar posts, thereby judge that the user's body shape is the user of height is shorter or the user of body shape is higher, improve the accuracy of adjusting collection module position.
Further, the mobile trigger module continuously collects a plurality of walking images, the processing module identifies the walking angle of the leg of the same user from the plurality of walking images when the user figure is completely located in the walking images, when the walking angle is smaller than a preset angle, the processing module confirms and judges that the walking profile of the leg on the walking images is an independent bar column, and the processing module sends a reduction adjusting signal to the control module.
The beneficial effects are that: because child user's height is less, and the leg is also short, and the angle that the leg portion was opened when child user walked is less, so, through many walking images, the walking angle of the leg portion when being convenient for gather user's walking, the angle that both legs were opened when walking, then judge the size of walking angle, judge leg walking profile and be an independent bar post when walking angle is less, send reduction adjusting signal to control module, let collection module's position reduce, improve and judge child user's accuracy, and trigger in time and carry out face identification.
Further, the processing module recognizes the user shape at the same position on the plurality of walking images as a user, wherein the same position is a position obtained by adding a preset deviation to the coordinates of the pixel points on the walking images.
The beneficial effects are that: the user shapes at the same position on the plurality of walking images are used as a user for identification, so that the judgment accuracy is improved.
Further, the infrared imaging module is further included, when the leg walking profile is an independent bar column, the processing module obtains and sends imaging signals to the infrared imaging module, the infrared imaging module images an infrared image of a user walking according to the imaging signals, the processing module obtains the infrared image and identifies the infrared walking profile to judge, and when the top of the infrared walking profile contacts with the top edge and the infrared walking profile is two independent bar columns, the processing module changes the user figure to be completely located on the walking image and the user figure is located outside the acquisition range of the mobile triggering module.
The beneficial effects are that: because the user's clothing influence, for example, when an adult user wears longer overcoat or longuette, because the misleading of clothing parcel easily judges the leg walking profile as an independent bar column, the walking angle of the user is not easy to accurately collect, when the leg walking profile is identified as an independent bar column, infrared imaging is carried out again, and the walking profile is judged again, namely, the infrared walking profile on the infrared image is judged, so that two independent bar columns on the walking image are accurately identified, and the interference of the clothing on whether the user figure is completely located on the walking image is reduced; not every person carries out infrared imaging and judges walking profile again, so that judging programs are saved.
Further, the control module sends a counting signal to the processing module when the same face image and face information are matched, the processing module counts the number of people passing through in a preset time period according to the counting signal to obtain a counting value, and the processing module obtains a walking image when the counting value is smaller than a preset threshold value.
The beneficial effects are that: because when the users who get into the community through the gate are more, even if children need to get into, children can follow behind adult and get into, for example children follow guardian and get into when entering, judge how much of entering user through the count, and only when getting into the user less and children only can oneself get into the community, just acquire walking image and carry out discernment judgement, need not to discern children alone and then open the gate module, reduce the operation handling capacity of system in the people stream peak period of getting into the community, facilitate the use.
Drawings
FIG. 1 is a schematic block diagram of a face recognition system suitable for people of various heights according to a first embodiment of the present invention.
Detailed Description
Further details are provided below with reference to the specific embodiments.
Example 1
Face recognition system suitable for people with various heights, as shown in fig. 1: the system comprises an acquisition module, an adjustment module, a control module, a gate module, a mobile trigger module and a processing module; the acquisition module can use the existing camera, the acquisition module signal is connected with the control module, the adjustment module can use the existing hydraulic cylinder to adjust the height, the adjustment module signal is connected with the control module, the gate module can use the existing gate control equipment, the gate module signal is connected with the control module, and the control module can use the existing gate controller; the control module can be connected with the processing module through a signal in a wired communication or wireless communication mode, the processing module can use an existing sea SOC chip, the mobile trigger module can use an existing high-definition camera, the mobile trigger module can be fixed to an inlet and outlet of the gate module through a gasket and a screw, and the mobile trigger module is located at the lower position of the acquisition module.
The acquisition module is used for acquiring a face image of a user and sending the face image to the control module, the control module matches the face image with pre-stored face information, when the face image is matched with the pre-stored face information, the pre-stored face information can be the face information of a business owner allowed to pass through a cell, and the control module controls the gate module to be opened for the user to pass through; the control module sends a counting signal to the processing module when the face image is matched with the face information, namely, a user counts each time the face image passes through the gate module, the processing module counts the number of people passing through the gate module in a preset time period according to the counting signal to obtain a count value, the preset time period can be set according to a people flow peak time period of entering communities, for example, the preset time period can be set to fifteen minutes, the processing module obtains a walking image when the count value is smaller than a preset threshold, the preset threshold can be set according to the requirement of each community, for example, the preset threshold can be set to five.
The distance from the ground when the mobile trigger module is installed is one half of the height of the acquisition module from the ground, namely the height of the mobile trigger module is smaller than the height of the acquisition module, the mobile trigger module acquires a walking image of a user in a preset height and preset distance range above the ground, the preset height and the preset distance are set according to the visual angle range of the high-definition camera after the installation, the processing module acquires the walking image and recognizes the user figure, the processing module extracts the outline as the user figure by using an image gradient algorithm after gray processing of the image, the processing module judges whether the user figure is completely located on the walking image or not, and the specific judging method is that the processing module compares the top edge of the user figure on the walking image with the top edge of the walking image, namely the top edge of the walking image, the top edge is the edge of the walking image, and when the top edge of the figure is located below the top edge, the processing module judges that the user figure is completely located on the walking image.
The processing module sends a lowering adjusting signal to the control module when the user figure is completely located on the walking image, the control module controls the adjusting module to start according to the lowering adjusting signal, and the adjusting module starts to drive the collecting module to adjust the position in a lowering mode.
When the top edge of the figure contacts the top edge, namely the top edge of the figure reaches the position of the top edge, the processing module identifies the leg walking profile of the user walking from the walking image, the leg walking profile is a more specific profile of the user figure, when the leg walking profile is an independent bar column, the processing module judges that the user figure is completely positioned on the walking image, when the leg walking profile is two independent bar columns, the processing module judges that the user figure is positioned outside the acquisition range of the mobile triggering module, namely the user is higher and can only shoot two legs, the processing module sends a lifting adjusting signal to the control module, and the control module controls the adjusting module to start according to the lifting adjusting signal, and the adjusting module drives the acquisition module to ascend.
The mobile trigger module continuously collects a plurality of walking images, the processing module identifies the walking angle of the legs of the same user from the plurality of walking images when the user figure is completely located in the walking images, the walking angle is the included angle of the two legs during walking, when the walking angle is smaller than a preset angle, the preset angle can be set according to the actual situation of a child user, the child user can set according to the actual situation, for example, the child user can set a child under five years old, for example, the preset angle is 20 degrees, the processing module confirms and judges the walking profile of the legs on the walking images to be an independent bar column, and the processing module sends a reduction adjusting signal to the control module; the processing module recognizes the user shape at the same position on the plurality of walking images as a user, wherein the same position is a position obtained by adding preset deviation to pixel point coordinates on the walking images.
The specific implementation process is as follows:
When the intelligent walking system is used, face images are acquired through the acquisition module, then the control module is used for matching the face images with face information, the gate module is opened for passing when the matching is successful, meanwhile, the control module is used for sending counting signals to the processing module, the mobile triggering module is used for continuously acquiring a plurality of walking images, the walking images are images of a user walking within a preset height and a preset distance range above the ground, the processing module is used for recognizing the shape of the user at the same position on the plurality of walking images as a user, the processing module is also used for counting in a preset time period to obtain a count value, and when the count value is smaller than a preset threshold, the processing module acquires the walking images from the mobile triggering module.
The processing module is used for identifying the shape of the user from the walking image, the processing module is used for comparing the top edge of the shape of the user on the walking image with the top edge of the walking image so as to judge whether the shape of the user is completely positioned on the walking image, and when the top edge of the shape is positioned below the top edge, the processing module is used for judging that the shape of the user is completely positioned on the walking image; when the user figure is completely positioned on the walking image, the processing module sends a lowering adjusting signal to the control module, so that the control module controls the adjusting module to drive the acquisition module to descend to acquire the face image of the child user; when the top edge of the figure contacts the top edge, the processing module judges that the figure of the user is not completely positioned on the walking image, at the moment, the processing module recognizes the leg walking outline of the user when walking from the walking image, when the leg walking outline is an independent bar column, the processing module judges that the figure of the user is completely positioned on the walking image, the processing module sends a lowering adjusting signal, when the leg walking outline is two independent bar columns, namely, only two legs of a owner are shot, the processing module judges that the figure of the user is positioned outside the acquisition range of the mobile triggering module, the processing module sends a lifting adjusting signal to the control module, the control module controls the adjusting module to start according to the lifting adjusting signal, the adjusting module drives the acquisition module to ascend, and when the leg walking outline is completely positioned on the walking image, the processing module recognizes the walking angle of the same user leg from a plurality of walking images, and judges that the walking outline is an independent bar column, namely, the child user with a short target is judged.
The child user with shorter height can also independently use the face recognition system to pass through the gate module, so that the user with shorter height can also use the gate module, the user range capable of being used is enlarged, the misjudgment is reduced by the multiple judgment mode, and the action of adjusting the height of the acquisition module is more accurate.
Example two
The difference between the first embodiment and the second embodiment is that the infrared imaging module is further included, when the leg walking profile is an independent bar column, the processing module obtains an imaging signal sent to the infrared imaging module, the infrared imaging module images an infrared image of the user walking according to the imaging signal, the processing module obtains the infrared image and identifies the infrared walking profile to judge, and when the top of the infrared walking profile contacts the top edge and the infrared walking profile is two independent bar columns, the processing module changes the user figure to be completely located on the walking image and the user figure is located outside the acquisition range of the mobile triggering module.
When the leg walking profile is identified as an independent bar column, infrared imaging is performed again, and the walking profile is judged again, namely, the infrared walking profile on the infrared image is judged, so that two independent bar columns on the walking image are accurately identified, and the interference of clothing on whether the user figure is completely located on the walking image is reduced; not every person carries out infrared imaging and judges walking profile again, so that judging programs are saved.
Example III
The difference from the first embodiment is that the processing module calculates the height value of the central angle from the ground when the walking angle is smaller than the preset angle, for example, by setting a coordinate axis on the walking image, obtaining the first point coordinate of the central angle of the walking angle and the second point coordinate of the vertical point of the walking angle on the ground, calculating the height value by using the first point coordinate and the second point coordinate, comparing the height value with the height threshold, and when the height value is smaller than the height threshold, judging the walking profile as an independent bar column by the processing module, wherein 'one' refers to 'one' in number, namely, judging the target as a child user with shorter height.
Because the walking angles of people with different heights are probably the same, when the walking angle is obtained, the height value of the central angle of the walking angle and the ground is judged, and then whether the walking angle is an independent bar column is judged according to the height value, so that a child user with a shorter height is accurately judged, the situation that the corresponding face information cannot be acquired by the acquisition module due to the fact that the height of the user is misjudged is reduced, and the speed of the user entering a community in a face recognition mode is improved.
The foregoing is merely exemplary embodiments of the present application, and specific structures and features that are well known in the art are not described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (5)
1. Be suitable for multiple height crowd's face identification system, including collection module, adjustment module, control module and floodgate machine module, collection module is used for gathering user's face image and sends to control module, adjustment module drives collection module adjustment position, control module matches face image and the facial information that prestores, when matching same face image and facial information, control module control floodgate machine module opens and supplies the user to pass through, its characterized in that:
The mobile trigger module is used for acquiring walking images of a user in a preset height and preset distance range above the ground, the processing module is used for acquiring the walking images, judging whether the user figure is completely located on the walking images or not, sending a lowering adjusting signal to the control module when the user figure is completely located on the walking images, and controlling the control module to start according to the lowering adjusting signal;
The processing module compares the top edge of the figure of the user on the walking image with the top edge of the walking image, when the top edge of the figure is lower than the top edge of the image, the processing module judges that the figure of the user is completely located on the walking image, when the top edge of the figure is contacted with the top edge, the processing module identifies the leg walking profile of the user during walking from the walking image, when the leg walking profile is an independent bar column, the processing module judges that the figure of the user is completely located on the walking image, when the leg walking profile is two independent bar columns, the processing module judges that the figure of the user is located outside the acquisition range of the mobile trigger module, the processing module sends a lifting adjusting signal to the control module, and the control module controls the starting of the adjusting module according to the lifting adjusting signal.
2. The face recognition system for multiple height people according to claim 1, wherein: the mobile trigger module continuously collects a plurality of walking images, the processing module identifies the walking angle of the leg of the same user from the plurality of walking images when the user figure is completely located in the walking images, and when the walking angle is smaller than a preset angle, the processing module confirms and judges that the walking profile of the leg on the walking image is an independent bar column, and the processing module sends a reduction adjusting signal to the control module.
3. The face recognition system for multiple height people according to claim 2, wherein: the processing module recognizes the user shape at the same position on the plurality of walking images as a user, wherein the same position is a position obtained by adding preset deviation to pixel point coordinates on the walking images.
4. The face recognition system for multiple height people according to claim 2, wherein: the infrared imaging module is used for imaging an infrared image of the walking of the user according to the imaging signals, the processing module is used for acquiring the infrared image and identifying the infrared walking profile to judge, and when the top of the infrared walking profile contacts with the top edge and the infrared walking profile is two independent bar columns, the processing module is used for changing the shape of the user from being completely positioned on the walking image to be outside the acquisition range of the mobile triggering module.
5. The face recognition system for multiple height people according to any one of claims 1-4, wherein: the control module sends a counting signal to the processing module when the same face image and face information are matched, the processing module counts the number of people passing through in a preset time period according to the counting signal to obtain a counting value, and the processing module acquires a walking image when the counting value is smaller than a preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604068.2A CN112686148B (en) | 2020-12-30 | 2020-12-30 | Face recognition system suitable for crowds with various heights |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604068.2A CN112686148B (en) | 2020-12-30 | 2020-12-30 | Face recognition system suitable for crowds with various heights |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686148A CN112686148A (en) | 2021-04-20 |
| CN112686148B true CN112686148B (en) | 2024-06-21 |
Family
ID=75454619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011604068.2A Active CN112686148B (en) | 2020-12-30 | 2020-12-30 | Face recognition system suitable for crowds with various heights |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686148B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229629B (en) * | 2023-05-09 | 2023-07-25 | 山东力拓智能科技有限公司 | Access control calling device control method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533805A (en) * | 2019-07-29 | 2019-12-03 | 深圳绿米联创科技有限公司 | Method, apparatus, intelligent door lock and the electronic equipment of intelligent door lock control |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169874A (en) * | 2006-10-23 | 2008-04-30 | 上海阿艾依智控系统有限公司 | Biological identification access control device |
| KR101037116B1 (en) * | 2009-09-28 | 2011-05-26 | 주식회사 레드코어 | The face recognition system where the photographing bringing up for discussion angle control is possible |
| KR101795701B1 (en) * | 2015-11-02 | 2017-11-09 | 주식회사 파이브지티 | Face recognition system and method of multiple identification |
| CN206431724U (en) * | 2017-01-25 | 2017-08-22 | 辛明江 | A kind of gate control system based on face recognition technology |
| CN107423714A (en) * | 2017-07-28 | 2017-12-01 | 中控智慧科技股份有限公司 | Image acquisition equipment and method |
| CN107978051B (en) * | 2017-12-15 | 2020-10-30 | 湖北联城通科技股份有限公司 | Access control system and method based on face recognition |
| CN108447159B (en) * | 2018-03-28 | 2020-12-18 | 百度在线网络技术（北京）有限公司 | Face image acquisition method and device and entrance and exit management system |
| CN111104873A (en) * | 2019-12-02 | 2020-05-05 | 广州极泽科技有限公司 | Face recognition method, system, equipment and medium with cooperation of multiple image processing devices |
-
2020
- 2020-12-30 CN CN202011604068.2A patent/CN112686148B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533805A (en) * | 2019-07-29 | 2019-12-03 | 深圳绿米联创科技有限公司 | Method, apparatus, intelligent door lock and the electronic equipment of intelligent door lock control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686148A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919132B (en) | Pedestrian falling identification method based on skeleton detection | |
| CN106127148B (en) | A kind of escalator passenger's anomaly detection method based on machine vision | |
| CN106875629B (en) | Home-based endowment system based on somatosensory network and control method thereof | |
| US8170295B2 (en) | Personal authentication system and personal authentication method | |
| EP1134691B1 (en) | Image processing apparatus and method for extracting feature of faces | |
| BenAbdelkader et al. | Person identification using automatic height and stride estimation | |
| CN108764058B (en) | Double-camera face in-vivo detection method based on thermal imaging effect | |
| CN101499129B (en) | Distant range iris recognition system and method | |
| CN101465033B (en) | Automatic tracking recognition system and method | |
| CN101847206B (en) | Pedestrian traffic statistical method and system based on traffic monitoring facilities | |
| CN107992797A (en) | Face identification method and relevant apparatus | |
| CN102262727A (en) | Method for monitoring face image quality at client acquisition terminal in real time | |
| CN107480658A (en) | Face identification device and method based on multi-angle video | |
| CN105844128A (en) | Method and device for identity identification | |
| CN105868694A (en) | Dual-mode emotion identification method and system based on facial expression and eyeball movement | |
| CN107392112A (en) | A kind of facial expression recognizing method and its intelligent lock system of application | |
| CN101526997A (en) | Embedded infrared face image identifying method and identifying device | |
| CN202130312U (en) | Driver fatigue driving monitoring device | |
| CN111739248B (en) | Artificial intelligent Internet of things security system and control method | |
| CN112686148B (en) | Face recognition system suitable for crowds with various heights | |
| CN105138967B (en) | Biopsy method and device based on human eye area active state | |
| CN112002044B (en) | Face recognition unlocking system of intelligent door lock and judgment method thereof | |
| CN109754478A (en) | A kind of face intelligent Checking on Work Attendance method of low user's fitness | |
| JP5766096B2 (en) | Face image authentication device | |
| CN112232110A (en) | Intelligent face temperature control recognition device and epidemic prevention 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 | ||
| GR01 | Patent grant |