CN117727122B - Access control gate based on face recognition and identity recognition method - Google Patents
Access control gate based on face recognition and identity recognition method Download PDFInfo
- Publication number
- CN117727122B CN117727122B CN202410104779.5A CN202410104779A CN117727122B CN 117727122 B CN117727122 B CN 117727122B CN 202410104779 A CN202410104779 A CN 202410104779A CN 117727122 B CN117727122 B CN 117727122B
- Authority
- CN
- China
- Prior art keywords
- gate
- pressure sensor
- gate body
- image
- entrance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000000926 separation method Methods 0.000 claims abstract description 78
- 230000005764 inhibitory process Effects 0.000 claims description 24
- 230000000670 limiting effect Effects 0.000 claims description 5
- 241000287107 Passer Species 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006698 induction Effects 0.000 description 5
- 238000005192 partition Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention discloses an access gate based on face recognition and an identity recognition method, comprising an access gate body arranged on the ground, wherein first shooting equipment and face recognition components are respectively arranged on two sides of an inlet end of the access gate body; the first shooting device is used for shooting image data of the entrance ground area; the face recognition component comprises a second shooting device for acquiring face image data and a display component for displaying the face image data; the entrance ground area in front of the entrance end of the gate body is longitudinally provided with a marking which divides the entrance ground area into a plurality of separation areas, and a plurality of first pressure sensors are transversely arranged in each separation area; the invention only compares and identifies the image blocks corresponding to the separation area where the target person is located, improves the speed of face recognition, effectively avoids identifying the face images of people in areas (such as sides) outside the target person, improves the reliability of identity recognition, and has higher recognition precision.
Description
Technical Field
The invention relates to the technical field of gate machines, in particular to a gate machine of an access control based on face recognition and an identity recognition method.
Background
In the existing face recognition gate entrance guard machine, the situation that a plurality of people exist in front of the gate entrance guard machine is often caused in the face information collection process, and when the plurality of people exist, the face information is often input into a system to carry out face recognition, so that the workload of face recognition feature comparison is increased;
On the other hand, because the gate can not judge the concrete personnel who need pass through the gate at this moment, and once face recognition system compares the face information of rear personnel successfully, gate opening will lead to the inconsistent condition of personnel and the personnel that actually pass through of face recognition to take place, reduced gate's identification reliability.
Disclosure of Invention
The invention aims to overcome the defects and provide an access control gate based on face recognition and an identity recognition method.
In order to achieve the above object, the present invention is specifically as follows:
The invention provides an access gate based on face recognition, which comprises an access gate body arranged on the ground, wherein first shooting equipment and face recognition components are respectively arranged on two sides of an inlet end of the access gate body; the first shooting device is used for shooting image data of the entrance ground area; the face recognition component comprises a second shooting device for acquiring face image data and a display component for displaying the face image data;
the entrance ground area in front of the entrance end of the gate body is longitudinally provided with a marking which divides the entrance ground area into a plurality of separation areas, and a plurality of first pressure sensors are transversely arranged in each separation area.
In the invention, a plurality of second pressure sensors are transversely arranged in the ground area of the gate below the gate body, and a plurality of third pressure sensors are transversely arranged in the ground area of the outlet behind the outlet end of the gate body;
the gate inhibition machine further comprises a control unit for controlling the gate inhibition machine to work.
The gate body of the gate control machine comprises a gate body which is arranged oppositely, an arc-shaped baffle plate and a power component which is used for driving the arc-shaped baffle plate to move are movably arranged on the inner side of the gate body, and the arc-shaped baffle plate is driven to move by the power component so as to realize opening and closing of an inlet end and an outlet end of the gate body of the gate control machine.
The power assembly comprises a motor arranged on a gate body, a driving roller rotatably connected to the gate body and two supporting rollers, wherein the two supporting rollers are symmetrically distributed on two sides of the driving roller, and the output end of the motor is connected with the driving roller so that the driving roller drives the arc-shaped baffle plate to slide under the guiding limiting action of the two supporting rollers.
According to the invention, the inner side of the gate body is concavely provided with the accommodating groove, the driving roller and the supporting roller are both arranged in the accommodating groove, and one end of the arc-shaped baffle plate can be accommodated in the accommodating groove.
The second aspect of the invention also provides an identity recognition method based on the gate inhibition machine, which comprises the following steps:
S1: numbering each separation area in sequence, and numbering each first pressure sensor in each separation area in sequence;
s2: acquiring first weight data output by each first pressure sensor; collecting a first image of an entrance ground area of an entrance gate body; collecting a second image of the face image of the person to be passed;
S3: determining a first pressure sensor closest to the gate body of the gate and a separation area where the first pressure sensor is positioned according to the number of the first pressure sensor outputting first weight data, and determining a target person to pass through the gate body according to the determined separation area and a first image;
S4: dividing the second image into image blocks corresponding to the separation areas one by one according to the separation areas where the target persons are located, reserving the image blocks corresponding to the separation areas where the target persons are located, and shielding the rest image blocks;
S5: and carrying out image recognition on the reserved image blocks to obtain current face image data of the target personnel, comparing the current face image data with pre-stored face image data, if the comparison result is true, opening the entrance end of the gate body, otherwise, keeping the entrance end of the gate body closed.
The method comprises the steps of obtaining second weight data of each second pressure sensor after an entrance end of an entrance gate body is opened, and comparing the second weight data of each second pressure sensor with the sum of first weight data output by a first pressure sensor corresponding to a stepping position of a target person;
if the comparison result is true, the determined target person passes through, the outlet end of the gate inhibition machine body is opened, otherwise, the outlet end of the gate inhibition machine body is kept closed.
In the invention, after the target person passes through the outlet end of the gate body, third weight data of the third pressure sensor is obtained, and the end of the target person identification process is judged according to the third weight data.
The beneficial effects of the invention are as follows: the invention only compares and identifies the image blocks corresponding to the separation area where the target person is located, thereby reducing the number of noise characteristics of image processing, reducing the occupancy rate of hardware resources and improving the speed of face recognition, and meanwhile, the invention can effectively avoid the situation that the door gate body is opened by mistake due to the fact that the face images of people in the area (such as the side) beyond the target person are identified, thereby improving the reliability of identity recognition and having higher recognition precision.
Drawings
FIG. 1 is a schematic diagram of an access gate according to the present invention;
FIG. 2 is an exploded view of the gate body of the present invention;
FIG. 3 is a flow chart of the identification method of the present invention;
Reference numerals illustrate: 101. a gate body; 1011. a receiving groove; 102. an arc baffle; 103. a motor; 104. a driving roller; 105. a support roller; 200. a first photographing device; 301. a second photographing device; 302. a display assembly; 400. marking lines; 500. a first pressure sensor; 600. a second pressure sensor; 700. and a third pressure sensor.
Detailed Description
The invention will now be described in further detail with reference to the drawings and the specific embodiments, without limiting the scope of the invention.
As shown in fig. 1 to 3, the door lock gate based on face recognition according to the present embodiment includes a door lock gate body 101 disposed on the ground, and a first photographing device 200 and a face recognition component are disposed on two sides of an inlet end of the door lock gate body 101, respectively; the first photographing apparatus 200 is used to photograph image data of an entrance ground area; the face recognition component comprises a second shooting device 301 for acquiring face image data and a display component 302 for displaying the face image data; preferably, the first photographing apparatus 200 is a first camera, and photographs a ground area in front of an inlet end of the gate main body 101 through the first camera, so as to obtain a first image; the second photographing apparatus 301 is a second camera; the face of the person to be passed is subjected to image shooting identification through the second camera, so that a second image can be obtained; then, the recognized face image is displayed through the display component 302 so that passers-by can observe the recognition result;
A reticle 400 dividing the entrance ground area into a plurality of divided areas is longitudinally provided at the entrance ground area located in front of the entrance end of the entrance gate body 101, and a plurality of first pressure sensors 500 are transversely arranged in each divided area.
Specifically, in actual use, the gate inhibition machine of the embodiment performs image acquisition on the ground area of the entrance of the gate inhibition machine body 101 through the first camera to obtain a first image; the face of the person to be passed is subjected to image shooting identification through a second camera to obtain a second image, and the second image is displayed through a display component 302; through setting the marking 400, the entrance ground area is divided into a plurality of separation areas, the width of each separation area can only accommodate one passer to stand, the plurality of separation areas can be sequentially set into a separation area 1, a separation area 2 and a separation area 3 from left to right, when the person to be passed steps on the first pressure sensor 500, each person to be passed steps on at least one first pressure sensor 500 and at most three first pressure sensors 500, the pressed first pressure sensors 500 can generate induction signals, and therefore first weight data are obtained; because the distance value of each first pressure sensor 500 from the gate body 101 is unique and determined, the first pressure sensors 500 are numbered sequentially, and according to the number of the first pressure sensor 500 outputting the first weight data and the separation area where the distance value is located for the nearest personnel to be passed; then, determining target personnel to pass through the gate body 101 according to the determined separation area and the first image;
Then the second image is divided into image blocks corresponding to the separation areas one by one according to the separation areas where the target persons are located, so that only the image blocks corresponding to the separation areas where the target persons are located are compared and identified, the number of noise characteristics of image processing is reduced, the occupancy rate of hardware resources is reduced, the face recognition speed is improved, meanwhile, face images of persons in areas (such as sides) beyond the target persons can be effectively prevented from being identified, the situation that the gate body 101 is opened by mistake is caused, the reliability of identity recognition is improved, and the recognition accuracy is higher.
As shown in fig. 1, in an access gate based on face recognition according to the present embodiment, in some embodiments, a plurality of second pressure sensors 600 are transversely arranged in a gate ground area below the gate body 101, and a plurality of third pressure sensors 700 are transversely arranged in an exit ground area behind an exit end of the gate body 101; the gate also includes a control unit (not shown) for controlling the operation of the gate. The control unit stores the number of the separation zone and the face information of the entered passers, and also stores the number of each first pressure sensor 500 and the distance value between each first pressure sensor 500 and the gate main body 101, so that the separation zone is determined according to the number and the distance value of the first pressure sensor 500.
Specifically, after the identification of the target person is successful, the entrance end of the gate entrance guard body 101 is opened, the target person enters the channel of the gate entrance guard body 101, at this time, the target person steps on the second pressure sensor 600, the second pressure sensor 600 generates an induction signal, so as to obtain second weight data, the second weight data is compared with corresponding first weight data, so as to determine whether the passing person in the channel of the gate entrance guard body 101 is the target person identified by the face recognition component, if the comparison result of the second weight data and the corresponding first weight data is true, the exit end of the gate entrance guard body 101 is opened, the target person steps on the third pressure sensor 700 on the ground through the exit end of the gate entrance guard body 101, the third pressure sensor 700 generates an induction signal, so as to obtain third weight data, at this time, the identity identification process of the target person is completed; the arrangement avoids the phenomenon that the actual passing personnel are inconsistent with the identified target personnel, and can avoid the trailing personnel to enter the device at the same time, thereby further improving the reliability of the identification.
As shown in fig. 1 and fig. 2, in an access gate based on face recognition according to this embodiment, in some embodiments, the access gate body 101 includes a gate body 101 disposed opposite to each other, an arc-shaped baffle 102 and a power assembly for driving the arc-shaped baffle 102 to move are movably disposed on the inner side of the gate body 101, and the arc-shaped baffle 102 is driven to move by the power assembly, so as to realize opening and closing of an inlet end and an outlet end of the access gate body 101.
Specifically, a channel for a person to pass through the gate body 101 is formed between the two gate bodies 101, and when in actual use, the first pressure sensor 500 uploads first weight data to the control unit, and the face recognition component uploads the identified second image to the control unit;
The first camera uploads a first image to the control unit; the control unit prestores the numbers of the first pressure sensors 500 and the numbers of the separation areas, such as the numbers of the separation areas are sequentially 1, 2 and 3 from left to right, the numbers of the first pressure sensors 500 positioned in the separation area 1 are 11, 12 and 13 … … n, the numbers of the first pressure sensors 500 positioned in the separation area 2 are 21, 22 and 23 … … n, the numbers of the first pressure sensors 500 positioned in the separation area 3 are 31, 32 and 33 … … n, face information of a passing person and a distance value Y between each first pressure sensor 500 and the gate body 101 are recorded, and the numbers of the first pressure sensors 500 and the distance value Y between the first pressure sensors 500 and the gate body 101 have a mapping relation, namely the numbers of the first pressure sensors 500 and the distance value Y have a one-to-one correspondence; the first weight data uploaded by the first pressure sensor 500 can be used for screening the first pressure sensor 500 closest to the gate inhibition machine body 101 according to the number of the first pressure sensor 500 outputting the first weight data, obtaining the distance value Y of the first pressure sensor 500 from the gate inhibition machine body 101 according to the number of the first pressure sensor 500, determining the separation area where the first pressure sensor 500 closest to the gate inhibition machine body 101 is located according to the number of the screened first pressure sensor 500 and the first weight data output by the screened first pressure sensor 500, and determining the personnel to be passed closest to the gate inhibition machine body 101 according to the determined separation area in combination with the first image, namely determining the target personnel so as to split the second image;
The first image can be identified through the control unit, if the marking 400 image appears on the right side of the target person image, the target person is judged to be in the separation area No. 1, if the marking 400 image appears on the left side of the target person image, the target person is judged to be in the separation area No. 3, and if the marking 400 images appear on the left side and the right side of the target person image, the target person is judged to be in the separation area No. 2; thereby being capable of reconfirming the separation area where the target personnel are located;
then the control unit performs segmentation processing on the second image, so that the second image is segmented into image blocks corresponding to the separation area No. 1, the separation area No. 2 and the separation area No. 3, namely the image block No. 1, the image block No. 2 and the image block No. 3; if the target person is located in the separation area No. 2, the corresponding image block No. 2 is reserved, the image block No. 1 and the image block No. 3 are shielded, then the control unit identifies the face image in the image block No. 2 and compares the face characteristics with the stored recorded face information, if the face characteristics are compared and pass, the control unit controls the power assembly to drive the arc baffle 102 to move, so that the arc baffle 102 opens the inlet end of the gate body 101 and closes the outlet end of the gate body 101 until the second weight data and the corresponding first weight data are compared and pass, the control unit controls the power assembly to drive the arc baffle 102 to reversely move, so that the arc baffle 102 opens the outlet end of the gate body 101 and closes the inlet end of the gate body 101, and the entry of the following person is prevented.
In this embodiment, by setting the arc-shaped baffle plate 102, the opening and closing control of the inlet and outlet ends of the gate body 101 can be realized, and compared with the independent control of two groups of baffle plates, the structure is simplified.
As shown in fig. 2, in the door control gate based on face recognition according to the present embodiment, in some embodiments, the power assembly includes a motor 103 mounted on the gate body 101, a driving roller 104 rotatably connected to the gate body 101, and two supporting rollers 105, the two supporting rollers 105 are symmetrically distributed on two sides of the driving roller 104, and an output end of the motor 103 is connected with the driving roller 104, so that the driving roller 104 drives the arc baffle 102 to slide under the guiding and limiting effects of the two supporting rollers 105.
In actual use, the motor 103 drives the driving roller 104 to rotate, and the driving roller 104 drives the arc baffle 102 to move under the guiding and limiting actions of the two supporting rollers 105, so that the opening and closing control of the inlet and outlet ends of the gate body 101 is realized.
As shown in fig. 1 and 2, in the door lock gate based on face recognition according to the present embodiment, in some embodiments, a receiving slot 1011 is concavely formed in the inner side of the gate body 101, the driving roller 104 and the supporting roller 105 are both disposed in the receiving slot 1011, and one end of the arc-shaped baffle 102 can be accommodated in the receiving slot 1011. In this embodiment, the accommodating groove 1011 is provided to facilitate accommodating the arc-shaped baffle 102, so that the structure is more compact.
In some embodiments, the gate access machine based on face recognition further includes a speaker (not shown) in communication with the control unit. According to the embodiment, the loudspeaker is arranged, so that after the target person is successfully identified, the control unit can generate a voice signal of 'please pass' through the loudspeaker, can also generate a voice signal of 'failed identification' through the loudspeaker after the identification fails, and can also generate a voice signal of 'mismatch and please exit' through the loudspeaker after the passing person enters the channel and the comparison result of the second weight data and the corresponding first weight data fails, so as to prompt the person in the channel to exit the channel of the gate control body 101;
when the person in the channel exits the channel of the gate inhibition machine body 101, the first pressure sensor 500 close to the gate inhibition machine body 101 outputs fourth weight data and uploads the fourth weight data to the control unit, and the control unit judges that the identity recognition process is finished according to the fourth weight data and then performs the next round of identity recognition process.
As shown in fig. 1 to 3, the present embodiment further provides an identification method based on the gate inhibition machine described above, including the following steps:
step S1: numbering each of the divided regions in turn, and numbering each of the first pressure sensors 500 in each of the divided regions in turn;
for example, the numbers of the separation areas are 1,2 and 3 in sequence from left to right, the numbers of the first pressure sensors 500 positioned in the separation area 1 are 11, 12 and 13 … … n, the numbers of the first pressure sensors 500 positioned in the separation area 2 are 21, 22 and 23 … … n, and the numbers of the first pressure sensors 500 positioned in the separation area 3 are 31, 32 and 33 … … n.
Step S2: acquiring first weight data output by each first pressure sensor 500; collecting a first image of an entrance ground area of the gate body 101; collecting a second image of the face image of the person to be passed;
Specifically, a first image of the ground area of the entrance of the gate body 101 is collected by a first camera and uploaded to a control unit, a second image of the face of the person to be passed is collected by a second camera and uploaded to the control unit, when the person to be passed is located in the ground area of the entrance of the gate body 101, the first pressure sensor 500 which is stepped on by the person to be passed generates an induction signal, first weight data is obtained, and the first pressure sensor 500 which is not stepped on does not generate an induction signal;
When d persons to be passed exist in the ground area of the entrance gate body 101, each person to be passed steps on at least one first pressure sensor 500 and at most three first pressure sensors 500, at this time, the first weight data are data sets X (i) = { X1 (i), X2 (i), X3 (i) … … Xn (i) }, wherein 1.ltoreq.i.ltoreq. 3,i represent numbers of the separation areas, the first pressure sensors 500 between each separation area are arranged independently of each other, for example, n first pressure sensors 500 are arranged in the longitudinal direction of the separation area 1, the data set X (i) represents first weight data sets output by all the first pressure sensors 500 in the separation area with the i number, for example, X3 (1) is the first weight data output by the first pressure sensor 500 with the number 3 in the separation area 1;
A mapping relationship of y=f (n) exists between the distance value Y between each first pressure sensor 500 and the gate main body 101 and the number n of the corresponding first pressure sensor 500.
Step S3: determining a first pressure sensor 500 nearest to the gate body 101 and a partition area where the first pressure sensor 500 is located according to the number of the first pressure sensor 500 outputting first weight data, and determining a target person to pass through the gate body 101 according to the determined partition area and a first image;
Specifically, the control unit obtains a distance value Y (i) = { Y1 (i), Y2 (i), Y3 (i) … … Yn (i) } between the first pressure sensor 500 and the gate main body 101 according to the number of the first pressure sensor 500 outputting the first weight data, and simultaneously screens out first weight data Xn (i) output by the first pressure sensor 500 closest to the gate main body 101 from the data sets Y (i) = { Y1 (i), Y2 (i), Y3 (i) … … Yn (i) } by recursively comparing 1.ltoreq.i.ltoreq.3, and screens out the smallest distance value Yn (i) from the data sets Y (i) = { Y1 (i), Y2 (i), Y3 (i) … … Yn (i) } according to the determined separation area, thereby determining the nearest target person to the gate main body 101;
The control unit identifies the first image according to the determined separation area as follows: the control unit determines a target person by identifying the nearest stepping position of each separation area from the gate body 101 and according to the number of the first pressure sensors 500 between the stepping position and the gate body 101;
If the number of the first pressure sensors 500 between the stepping positions of the two separation areas and the gate body 101 is the same, the target person in the middle separation area has priority; if the number of the first pressure sensors 500 between the pressing positions of the separation areas on the two sides is the same as that of the first pressure sensors 500 between the gate main body 101, the target person located in the separation area on the left side has priority;
Further, the control unit judges the separation area where the target person is located again in the process of identifying the first image according to the determined separation area and the target person; the method comprises the following steps: if the marking 400 image appears on the right side of the target person image, the target person is judged to be in the partition area No.1, if the marking 400 image appears on the left side of the target person image, the target person is judged to be in the partition area No. 3, and if the marking 400 images appear on the left side and the right side of the target person image, the target person is judged to be in the partition area No. 2; therefore, the separation area where the target person is further confirmed, and error processing during subsequent processing of the second image is avoided.
Step S4: dividing the second image into image blocks corresponding to the separation areas one by one according to the separation areas where the target persons are located, reserving the image blocks corresponding to the separation areas where the target persons are located, and shielding the rest image blocks;
Specifically, the control unit segments the second image according to the separation areas to form image blocks corresponding to the separation areas one by one, namely an image block No.1, an image block No. 2 and an image block No. 3, and after the second image is segmented, the image blocks except the image block where the target person is located are shielded, and the image block where the target person is located is reserved.
Step S5: performing image recognition on the reserved image blocks to obtain current face image data of a target person, comparing the current face image data with pre-stored face image data, if the comparison result is true, opening the entrance end of the gate body 101, otherwise, keeping the entrance end of the gate body 101 closed;
Specifically, the control unit performs face image recognition on the reserved image blocks to obtain current face image data of a target person, then compares the current face image data with pre-stored face image data, if the comparison result is passed, namely the comparison result is true, the control unit controls the power component to drive the arc-shaped baffle plate 102 to move, the inlet end of the gate body 101 is opened, and meanwhile, the outlet end of the gate body 101 is closed, so that the target person enters a channel of the gate body 101;
if the comparison result fails, the control unit controls the power component to be disabled, and the inlet end of the gate body 101 is in a closed state.
Therefore, before face feature comparison, the separation area where the target person is located is identified through the first image, other separation areas are shielded, and only the separation area where the target person is located is compared and identified, so that on one hand, the number of noise features of image processing can be greatly reduced, the occupancy rate of hardware resources is reduced, the face recognition speed is improved, on the other hand, face images of people in areas (such as sides) beyond the target person can be effectively prevented from being identified, the situation that the gate body 101 is opened by mistake is caused, and the reliability of identity recognition is improved.
As shown in fig. 1 to 3, in the identification method according to the present embodiment, in some embodiments, after the entrance end of the gate main body 101 is opened, second weight data of each second pressure sensor 600 is obtained, and the second weight data of each second pressure sensor 600 is compared with the sum of the first weight data output by the first pressure sensor 500 corresponding to the position where the target person steps on;
if the comparison result is true, the determined target person passes through, the exit end of the gate inhibition machine body 101 is opened, otherwise, the exit end of the gate inhibition machine body 101 is kept closed.
Specifically, after the entrance end of the gate body 101 is opened, a target person enters the channel of the gate body 101, when the target person steps on the second pressure sensor 600, the second pressure sensor 600 generates a sensing signal, so as to obtain second weight data Xm, the second weight data Xm is transmitted to the control unit, the control unit can determine a first pressure sensor 500 corresponding to the stepping position of the target person according to the first image, and if the stepping position of the target person corresponds to one first pressure sensor 500, the first weight data Xn (i) output by the first pressure sensor 500 is compared with the sum of the second weight data Xm output by the second pressure sensor 600;
if the target person steps on the two first pressure sensors 500, comparing the first weight data Xn (i) output by the first pressure sensor 500 which is determined to be closest to the gate body 101 and the first weight data xn+1 (i) output by the first pressure sensor 500 whose number is arranged behind the first pressure sensor 500 with the sum of the second weight data Xm output by the second pressure sensor 600;
If the target person steps on the position corresponding to the three first pressure sensors 500, adding the first weight data Xn (i) output by the first pressure sensor 500 closest to the gate body 101, the first weight data xn+1 (i) output by the first pressure sensor 500 with the serial number arranged behind the first pressure sensor 500, and the first weight data xn+2 (i) to obtain a first result, if the first pressure sensor 500 with the serial number 24 is closest to the gate body 101 and located in the separation area 2, adding the first weight data X4 (2) output by the first pressure sensor 500 with the serial number 24, the first weight data X5 (2) output by the first pressure sensor 500 with the serial number 25, and the first weight data X6 (2) output by the first pressure sensor 500 with the serial number 26 to obtain a first result; adding the second weight data Xm output by each second pressure sensor 600 to obtain a second result, comparing the first result with the second result by the control unit, judging that the first result is a target person if the error is within a set threshold range, controlling the power component by the control unit to drive the arc-shaped baffle plate 102 to move, opening the outlet end of the gate body 101, and closing the inlet end of the gate body 101 so that the target person passes through the gate body 101;
if the error exceeds the set threshold range, it is determined that the passer in the channel of the gate body 101 is a non-target person, the control unit may control the speaker to play a prompt voice to prompt the passer in the channel of the gate body 101 to exit the channel, after the passer exits the channel, the passer presses the first pressure sensor 500 with the front code, the first pressure sensor 500 with the front code outputs fourth weight data to the control unit, after receiving the fourth weight data, it is determined that the identification process is ended, and the identification of the next round is waited.
So pass personnel in entering the passageway through face identification are rechecked by the weight through the second pressure sensor 600, the trailing personnel can be prevented from entering, and the reliability of the identification is further improved.
As shown in fig. 1 to 3, in the identification method according to the present embodiment, in some embodiments, after the target person passes through the exit end of the gate body 101, third weight data of the third pressure sensor 700 is obtained, and it is determined that the identification process of the target person is finished according to the third weight data.
Specifically, after the target person walks out of the range of the gate body 101, tramples on the third pressure sensor 700, the third pressure sensor 700 outputs third weight data to the control unit, and after the control unit receives the third weight data, the control unit determines that the target person passes normally, determines that the identity recognition process of the target person is finished, and performs the identity recognition process of the next passing person.
The foregoing description is only one preferred embodiment of the invention, and therefore all changes and modifications that come within the meaning and range of equivalency of the structures, features and principles of the invention are intended to be embraced therein.
Claims (7)
1. The identification method of the gate inhibition machine based on the face recognition is characterized in that the gate inhibition machine comprises a gate inhibition machine body arranged on the ground, and first shooting equipment and face recognition components are respectively arranged on two sides of an inlet end of the gate inhibition machine body; the first shooting device is used for shooting image data of the entrance ground area; the face recognition component comprises a second shooting device for acquiring face image data and a display component for displaying the face image data;
the entrance ground area in front of the entrance end of the gate body is longitudinally provided with a marking which divides the entrance ground area into a plurality of separation areas, and a plurality of first pressure sensors are transversely arranged in each separation area;
The identity recognition method is realized by the following steps:
Numbering each separation area in sequence, and numbering each first pressure sensor in each separation area in sequence;
Acquiring first weight data output by each first pressure sensor; collecting a first image of an entrance ground area of an entrance gate body; collecting a second image of the face image of the person to be passed;
Determining a first pressure sensor closest to the gate body of the gate and a separation area where the first pressure sensor is positioned according to the number of the first pressure sensor outputting first weight data, and determining a target person to pass through the gate body according to the determined separation area and a first image;
Dividing the second image into image blocks corresponding to the separation areas one by one according to the separation areas where the target persons are located, reserving the image blocks corresponding to the separation areas where the target persons are located, and shielding the rest image blocks;
And carrying out image recognition on the reserved image blocks to obtain current face image data of the target personnel, comparing the current face image data with pre-stored face image data, if the comparison result is true, opening the entrance end of the gate body, otherwise, keeping the entrance end of the gate body closed.
2. The identification method according to claim 1, wherein a plurality of second pressure sensors are transversely arranged in a gate ground area below the gate body of the gate access, and a plurality of third pressure sensors are transversely arranged in an exit ground area behind an exit end of the gate body of the gate access;
the gate inhibition machine further comprises a control unit for controlling the gate inhibition machine to work.
3. The identification method according to claim 2, wherein the gate body comprises gate bodies which are arranged oppositely, an arc-shaped baffle plate and a power component for driving the arc-shaped baffle plate to move are movably arranged on the inner sides of the gate bodies, and the arc-shaped baffle plate is driven to move by the power component so as to realize opening and closing of an inlet end and an outlet end of the gate body.
4. The identification method according to claim 3, wherein the power assembly comprises a motor installed on the gate body, a driving roller rotatably connected to the gate body, and two supporting rollers symmetrically distributed on two sides of the driving roller, and an output end of the motor is connected with the driving roller, so that the driving roller drives the arc baffle to slide under the guiding and limiting actions of the two supporting rollers.
5. The method according to claim 4, wherein the inner side of the gate body is concavely provided with a receiving groove, the driving roller and the supporting roller are both disposed in the receiving groove, and one end of the arc-shaped baffle can be accommodated in the receiving groove.
6. The identification method according to claim 2, wherein after the entrance end of the gate body is opened, second weight data of each second pressure sensor is obtained, and the second weight data of each second pressure sensor is compared with the sum of the first weight data output by the first pressure sensor corresponding to the pressing position of the target person;
if the comparison result is true, the determined target person passes through, the outlet end of the gate inhibition machine body is opened, otherwise, the outlet end of the gate inhibition machine body is kept closed.
7. The identification method according to claim 2, wherein after the target person passes through the exit end of the gate body, third weight data of the third pressure sensor is obtained, and the end of the identification process of the target person is determined according to the third weight data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410104779.5A CN117727122B (en) | 2024-01-25 | 2024-01-25 | Access control gate based on face recognition and identity recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410104779.5A CN117727122B (en) | 2024-01-25 | 2024-01-25 | Access control gate based on face recognition and identity recognition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117727122A CN117727122A (en) | 2024-03-19 |
| CN117727122B true CN117727122B (en) | 2024-06-11 |
Family
ID=90203646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410104779.5A Active CN117727122B (en) | 2024-01-25 | 2024-01-25 | Access control gate based on face recognition and identity recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117727122B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013020366A (en) * | 2011-07-08 | 2013-01-31 | Namco Bandai Games Inc | Game system, program, and information storage medium |
| WO2018209531A1 (en) * | 2017-05-15 | 2018-11-22 | 深圳市永恒丰科技有限公司 | Train taking control system based on face recognition |
| CN209625380U (en) * | 2019-04-18 | 2019-11-12 | 深圳南亿科技股份有限公司 | A kind of access control system with Initiative Defense illegal invasion |
| CN112016482A (en) * | 2020-08-31 | 2020-12-01 | 成都新潮传媒集团有限公司 | Method and device for distinguishing false face and computer equipment |
| CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
| CN113228034A (en) * | 2018-12-26 | 2021-08-06 | 浙江大华技术股份有限公司 | Gate equipment system and control method thereof |
| CN116281480A (en) * | 2023-04-10 | 2023-06-23 | 成都睿瞳科技有限责任公司 | Visual detection system, method and storage medium based on intelligent camera |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9019237B2 (en) * | 2008-04-06 | 2015-04-28 | Lester F. Ludwig | Multitouch parameter and gesture user interface employing an LED-array tactile sensor that can also operate as a display |
| US9609385B2 (en) * | 2014-08-28 | 2017-03-28 | The Nielsen Company (Us), Llc | Methods and apparatus to detect people |
| CN105117695B (en) * | 2015-08-18 | 2017-11-24 | 北京旷视科技有限公司 | In vivo detection equipment and biopsy method |
| CN107123081A (en) * | 2017-04-01 | 2017-09-01 | 北京小米移动软件有限公司 | image processing method, device and terminal |
-
2024
- 2024-01-25 CN CN202410104779.5A patent/CN117727122B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013020366A (en) * | 2011-07-08 | 2013-01-31 | Namco Bandai Games Inc | Game system, program, and information storage medium |
| WO2018209531A1 (en) * | 2017-05-15 | 2018-11-22 | 深圳市永恒丰科技有限公司 | Train taking control system based on face recognition |
| CN113228034A (en) * | 2018-12-26 | 2021-08-06 | 浙江大华技术股份有限公司 | Gate equipment system and control method thereof |
| CN209625380U (en) * | 2019-04-18 | 2019-11-12 | 深圳南亿科技股份有限公司 | A kind of access control system with Initiative Defense illegal invasion |
| CN112016482A (en) * | 2020-08-31 | 2020-12-01 | 成都新潮传媒集团有限公司 | Method and device for distinguishing false face and computer equipment |
| CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
| CN116281480A (en) * | 2023-04-10 | 2023-06-23 | 成都睿瞳科技有限责任公司 | Visual detection system, method and storage medium based on intelligent camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117727122A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20070122011A1 (en) | Face authentication system and gate management system | |
| KR100682906B1 (en) | Apparatus and method for detecting face in image using boost algorithm | |
| EP0082304B1 (en) | Method of identifying a person by speech and face recognition, and device for carrying out the method | |
| KR20070109712A (en) | Parking management system using lpr and method thereof | |
| KR20120119724A (en) | Management system for entrance and method thereof | |
| CN112037405A (en) | Gate control method, device, equipment and medium | |
| CN112507315B (en) | Personnel passing detection system based on intelligent brain | |
| CN117727122B (en) | Access control gate based on face recognition and identity recognition method | |
| CN108171985A (en) | Vehicle identification method and device | |
| JP2599701B2 (en) | Elevator Standby Passenger Number Detection Method | |
| CN112087603A (en) | Intelligent examination room supervision method | |
| CN107000960A (en) | Evacuate controller | |
| CN110276617A (en) | Unmanned convenience store enters recognition methods, device, equipment and storage medium | |
| EP2505540A1 (en) | Access monitoring device with at least one video unit | |
| EP1680769A1 (en) | Method and device for passage control and/or isolation of persons | |
| US11837018B1 (en) | System and method for access control using a plurality of images | |
| JPH11185087A (en) | Entering/leaving person control system | |
| CN110930432A (en) | Video analysis method, device and system | |
| CN113936345B (en) | Method and system for processing check ticket information of fast-passing asynchronous video in scenic spot | |
| CN113313014B (en) | Customs detection system based on facial feature analysis emotion intensity | |
| JPH0460880A (en) | Moving body discrimination and analysis controlling system | |
| CN113052100A (en) | Traffic identification method and related device | |
| EP2422324B1 (en) | Automated teller machine comprising camera arrangement to detect manipulation attempts | |
| JP2020063659A (en) | Information processing system | |
| CN216412235U (en) | Rail transit security inspection passing device |
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 |