CN111814561A - Face recognition method, face recognition equipment and access control system - Google Patents
Face recognition method, face recognition equipment and access control system Download PDFInfo
- Publication number
- CN111814561A CN111814561A CN202010526043.9A CN202010526043A CN111814561A CN 111814561 A CN111814561 A CN 111814561A CN 202010526043 A CN202010526043 A CN 202010526043A CN 111814561 A CN111814561 A CN 111814561A
- Authority
- CN
- China
- Prior art keywords
- path
- face recognition
- camera
- visible light
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005286 illumination Methods 0.000 claims abstract description 32
- 239000013589 supplement Substances 0.000 claims description 58
- 238000004891 communication Methods 0.000 claims description 17
- 238000007689 inspection Methods 0.000 claims description 4
- 230000002045 lasting effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000001502 supplementing effect Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- 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
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
- G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
-
- 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
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Input (AREA)
- Studio Devices (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a face recognition method, a face recognition device, a storage device and an access control system, wherein the face recognition method comprises the following steps: acquiring the illumination brightness of the current environment, and calculating to obtain the required fill-in brightness value based on the illumination brightness; when the brightness value of the required supplementary lighting is determined to be not greater than a first threshold value, controlling a first path of visible light camera to perform face recognition and face anti-fake work; when the brightness value of the required supplementary lighting is determined to be not less than a second threshold value, controlling a second path of infrared camera to perform face recognition and face anti-fake work; wherein the first threshold is less than or equal to the second threshold; and when the brightness value of the required supplementary lighting is determined to be larger than a first threshold and smaller than a second threshold, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera. Through the mode, the problems of dazzling, light pollution and the like in the prior art are avoided.
Description
Technical Field
The invention relates to the technical field of security systems, in particular to a face recognition method, face recognition equipment, a face recognition storage device and an access control system.
Background
The face recognition technology in the prior art usually adopts a binocular camera to work together, wherein the first path of camera is responsible for face recognition, and the second path of camera is responsible for face anti-counterfeiting. The first camera is required to be supplemented with light by a white light supplement lamp when the ambient brightness is lower than a certain threshold value, so that the first camera can perform face recognition at night. The second path of cameras adopt an infrared light supplement lamp to carry out light supplement when being normally on so as to keep the face to have enough brightness, and therefore face anti-fake work is carried out. However, the white light supplement lamp is not only dazzling and causes light pollution, but also increases the complexity and cost of system hardware.
Therefore, in order to solve the above problems, it is necessary to provide a new face recognition method, device and access control system.
Disclosure of Invention
In order to achieve the above object, the present invention provides a face recognition method, comprising: acquiring the illumination brightness of the environment, and calculating to obtain the required fill-in brightness value based on the illumination brightness; when the required fill-in light brightness value is determined to exceed the preset fill-in light brightness value range, controlling the first path of visible light camera or the second path of infrared camera to perform face recognition and face anti-fake work; and when the required light supplement brightness value is determined to be within a preset light supplement brightness value range, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
As a further improvement of the present invention, the lower limit of the preset fill-in luminance value range is a first threshold, and the upper limit thereof is a second threshold, and the first threshold is equal to or lower than the second threshold; when the required fill light brightness value is determined to exceed the preset fill light brightness value range, the first path of visible light camera or the second path of visible light camera is controlled to perform face recognition and face anti-fake work, and the method comprises the following steps: when the required fill-in light brightness value is determined to be smaller than the first threshold value, controlling a first path of visible light camera to perform face recognition and face anti-fake work; when the brightness value of the required supplementary lighting is determined to be larger than the second threshold value, controlling a second path of infrared camera to perform face recognition and face anti-fake work; when the required fill light brightness value is determined to be within the preset fill light brightness value range, the first path of visible light camera and/or the second path of infrared camera are selectively controlled to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera, and the method comprises the following steps: and when the required fill light brightness value is determined to be larger than the first threshold value and smaller than the second threshold value, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
As a further improvement of the present invention, the face recognition method further comprises: when the first path of visible light camera is selected based on the identification result, updating the first threshold value to be a current required supplementary lighting brightness value; and updating the second threshold value to be the current required fill light brightness value when the second path of infrared camera is selected based on the identification result.
As a further improvement of the present invention, the selecting and controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera includes: controlling the first path of visible light camera and the second path of infrared camera to simultaneously perform face recognition and face anti-fake work and lasting for a T time period; counting the successful times of face recognition and face anti-fake work of the first path of visible light camera as a and the successful times of face recognition and face anti-fake work of the second path of infrared camera as b in the T time period; when a is confirmed to be larger than b, the recognition result of the first path of visible light camera is superior to that of the second path of infrared camera, and the first path of visible light camera is controlled to perform face recognition and face anti-fake work; when a is confirmed to be smaller than b, the recognition result of the second path of infrared camera is superior to that of the first path of visible light camera, and the second path of infrared camera is controlled to perform face recognition and face anti-fake work; and when a is confirmed to be equal to b, the recognition result of the first path of visible light camera is the same as that of the second path of infrared camera, and the first path of visible light camera and the second path of infrared camera are controlled to perform face recognition and face anti-fake work.
As a further improvement of the invention, the value range of T is more than or equal to 300s and less than or equal to 600 s.
As a further improvement of the present invention, the controlling the first path of visible light camera to perform face recognition and face anti-fake work includes: confirming that the first path of visible light camera triggers a dynamic examination event; the control second way infrared camera carries out face identification, face anti-fake work, includes before: confirming that the second path of infrared camera triggers a dynamic inspection event; the selection control the first path of visible light camera and/or the second path of infrared camera to carry out face recognition and face anti-fake work, and the method comprises the following steps: and confirming that the first path of visible light camera and/or the second path of infrared camera triggers a dynamic examination event.
As a further improvement of the present invention, the acquiring the illumination brightness of the environment and calculating the required fill-in luminance value based on the illumination brightness includes: and acquiring the illumination brightness of the environment according to the image brightness acquired by the first path of visible light camera, and calculating to obtain the required light supplement brightness value based on the illumination brightness through a Smart intelligent light supplement algorithm.
As a further improvement of the present invention, the controlling the second path of infrared camera to perform face recognition and face anti-fake work includes: and adjusting the brightness value of the infrared light supplement lamp of the second path of infrared camera according to a SmartIR intelligent light supplement algorithm.
The present invention also provides a face recognition apparatus, comprising: the human face recognition method comprises a first path of visible light camera, a second path of infrared camera, a processor, a memory and a communication circuit, wherein the first path of visible light camera, the second path of infrared camera, the memory and the communication circuit are coupled to the processor, and the processor, the memory and the communication circuit can realize the human face recognition method when working.
The present invention also provides an access control system, comprising: the face recognition equipment and the access control switch device which is in communication connection with the face recognition equipment are arranged; the entrance guard switch device is used for selecting whether to open an entrance guard according to the working result of the face recognition equipment.
Compared with the prior art, the invention has the beneficial effects that:
different from the prior art, the first path of visible light camera and the second path of infrared camera in the face recognition method provided by the invention can perform both face recognition work and face anti-fake work, so that the first path of visible light camera and the second path of infrared camera do not need to work simultaneously all the time, but selectively work according to the relation between the required fill-in light brightness value and the preset fill-in light brightness value range, and the problems of overheating and service life reduction caused by long-time opening of an infrared fill-in light in the prior art are solved; and under the condition that the required light supplement brightness value is within the range of the preset light supplement brightness value, the first path of visible light camera or the second path of infrared camera or the first path of visible light camera and the second path of infrared camera work simultaneously can be selected and controlled according to the recognition results of the first path of visible light camera and the second path of infrared camera, and on the premise of considering the rapid face recognition, one path of camera is selected as much as possible to work so as to reduce the condition that the two paths of cameras work simultaneously.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart of an embodiment of a face recognition method according to the present invention;
FIG. 2 is a schematic flow chart of another embodiment of a face recognition method according to the present invention;
FIG. 3 is a schematic flow chart of an application scenario of the face recognition method of the present invention;
FIG. 4 is a schematic flow chart illustrating dynamic adjustment of the first threshold and the second threshold in FIG. 3 according to the face recognition method of the present invention;
FIG. 5 is a schematic structural diagram of an embodiment of a face recognition device according to the present invention;
FIG. 6 is a schematic structural diagram of a memory device according to an embodiment of the present invention;
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
Referring to fig. 1, the present invention provides a face recognition method, including:
s101: acquiring the illumination brightness of the environment, and calculating to obtain the required fill-in brightness value based on the illumination brightness;
s102: when the required fill-in light brightness value is determined to exceed the preset fill-in light brightness value range, controlling the first path of visible light camera or the second path of infrared camera to perform face recognition and face anti-fake work;
s103: and when the required light supplement brightness value is determined to be within the preset light supplement brightness value range, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
Through the mode, the first path of visible light camera and the second path of infrared camera in the face recognition method can perform both face recognition work and face anti-fake work, so that the first path of visible light camera and the second path of infrared camera do not need to work simultaneously all the time, but selectively work according to the relation between the required fill-in light brightness value and the preset fill-in light brightness value range, and the problems of overheating and service life reduction caused by long-time opening of an infrared fill-in light in the prior art are solved; and under the condition that the required light supplement brightness value is within the range of the preset light supplement brightness value, the first path of visible light camera or the second path of infrared camera or the first path of visible light camera and the second path of infrared camera work simultaneously can be selected and controlled according to the recognition results of the first path of visible light camera and the second path of infrared camera, and on the premise of considering the rapid face recognition, one path of camera is selected as much as possible to work so as to reduce the condition that the two paths of cameras work simultaneously.
Specifically, referring to fig. 2, fig. 2 is a schematic flow chart of another embodiment of the face recognition method of the present invention, and the face recognition method includes:
s201: and acquiring the illumination brightness of the environment, and calculating to obtain the required fill-in brightness value based on the illumination brightness.
Specifically, the face recognition device provided by the invention comprises a first path of visible light camera and a second path of infrared camera.
In one embodiment, the step S201 includes: and acquiring the illumination brightness of the current environment according to the image brightness acquired by the first path of visible light camera, and calculating to obtain the required light supplement brightness value based on the illumination brightness through a Smart intelligent light supplement algorithm.
It should be noted that, due to the working conditions of the first path of visible light camera, white light fill-in lamp hardware is not required to be set, and the required fill-in light brightness value is only a virtual value calculated according to the brightness of the image acquired by the first path of visible light camera. Therefore, different from the prior art, the first path of visible light camera provided by the invention avoids the problems of dazzling and light pollution, reduces the hardware cost and improves the user experience.
Of course, in other embodiments of the present invention, other manners may be used to obtain the illumination brightness value of the current environment, which are within the scope of the present invention and are not limited herein.
S202: and when the brightness value of the required supplementary lighting is determined to be smaller than the first threshold value, controlling the first path of visible light camera to perform face recognition and face anti-fake work.
Specifically, the first path of visible light camera is set to perform face recognition and face anti-fake. When the required supplementary lighting brightness value is smaller than the first threshold value, namely the required supplementary lighting brightness calculated by the first path of visible light camera is smaller, the illumination brightness of the current environment is relatively brighter, and at the moment, the face recognition equipment controls the first path of visible light camera to start a face algorithm to perform face recognition and face anti-fake work. Meanwhile, face recognition and face anti-fake work of the second path of infrared camera are turned off, so that the problem that the infrared light supplement lamp is overheated or the service life of the infrared light supplement lamp is shortened due to the fact that the infrared light supplement lamp is turned on for a long time is solved.
The face recognition work of the first path of visible light camera is as follows: the method comprises the steps that a face collected by a video is subjected to frame taking according to a specific frame rate, then feature extraction is carried out, comparison with an authorized face stored in a database in advance is carried out, and when the similarity is larger than a set threshold value, the comparison is successful; on the contrary, when the similarity is smaller than the set threshold, the comparison fails. The face anti-fake work of the first path of visible light camera is as follows: the non-living bodies in front of the first path of visible light camera, such as human face photos or human faces played by videos, are filtered, so that the non-living body attack is effectively prevented, and the reliability and the safety are improved.
In one embodiment, the human face anti-counterfeiting task may be motion liveness detection, such as blink detection, and the human face recognition device may request the user to blink twice and distinguish whether the human face is a live body according to the collected change of the opening and closing state of the eyes. Or, in another embodiment, the face anti-fake work can also be 3D detection, and by verifying whether the acquired portrait is a stereo portrait, attacks of non-living bodies such as plane photos and photos with different degrees of curvature can be prevented.
Of course, in other embodiments of the present invention, other manners may be adopted to perform face recognition and face anti-fake operations, and the effects of face recognition and face anti-fake are within the protection scope of the present invention, which is not limited herein.
Further, before the first path of visible light camera is controlled to perform face recognition and face anti-fake work in step S202, it is further determined that the first path of visible light camera triggers a motion detection event. When the dynamic inspection event is triggered, the face algorithm is really started to perform face recognition and face anti-fake work. By the mode, the first path of visible light camera is not started to carry out face recognition and face anti-fake work when no person passes, so that the consumption of the CPU (Central processing Unit) use load of the embedded system is reduced.
S203: when the brightness value of the required supplementary lighting is determined to be larger than a second threshold value, controlling a second path of infrared camera to perform face recognition and face anti-fake work; wherein the first threshold is less than or equal to the second threshold.
Specifically, similar to the step S202, the second infrared camera is set to perform both face recognition and face anti-fake. When the required light supplement brightness value is determined to be not smaller than the second threshold value, namely the required light supplement brightness calculated by the first path of visible light camera is very large, the illumination brightness of the current environment is relatively dark, and at the moment, the face recognition equipment controls the second path of infrared camera to start a face algorithm to perform face recognition and face anti-fake work. Meanwhile, the face recognition and face anti-fake work of the first path of visible light camera is closed, and the use of an embedded system CPU is reduced.
The human face recognition and human face anti-fake work of the second path of infrared camera is the same as the principle of the first path of visible light camera, and the details are not repeated here.
Further, before controlling the second channel of infrared cameras to perform face recognition and face anti-fake work in step S203, it is further determined that the second channel of infrared cameras triggers a motion detection event. When the dynamic inspection event is triggered, the face algorithm is really started to perform face recognition and face anti-fake work. Similarly, by the mode, the second path of infrared cameras are not started to perform face recognition and face anti-fake work when no person passes through the embedded system, so that the consumption of the CPU (central processing unit) of the embedded system is reduced.
In addition, in this embodiment, before controlling the second infrared camera to perform face recognition and face anti-fake operation in step S203, the method further includes adjusting a brightness value of an infrared light supplement lamp of the second infrared camera according to a SmartIR intelligent light supplement algorithm, so as to achieve an effect of adjusting brightness of a video image acquired by the second infrared camera, so that the second infrared camera performs face recognition and face anti-fake operation according to the face algorithm in an optimal working environment.
When the brightness value of the infrared light supplement lamp calculated according to the SmartIR intelligent light supplement algorithm is infinitely close to 0, the infrared light supplement lamp can be turned off; and when the brightness value of the infrared light supplement lamp calculated according to the SmartIR intelligent light supplement algorithm is greater than 0, the infrared light supplement lamp can be turned on. Therefore, the second path of infrared camera not only can adjust the brightness value of the infrared light supplement lamp through the SmartIR intelligent light supplement algorithm, but also can control the on and off of the infrared light supplement lamp.
Therefore, through the mode, the infrared light supplement lamp of the second path of infrared camera does not need to be kept normally on for a long time as in the prior art, and the problem that equipment is overheated or the service life of the infrared light supplement lamp is shortened is further avoided.
S204: and when the brightness value of the required supplementary lighting is determined to be larger than a first threshold and smaller than a second threshold, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
Specifically, when it is determined that the required fill-in light brightness value is greater than a first threshold and smaller than a second threshold, if the first path of visible light camera is directly selected, the recognition result may be poor because the first path of visible light camera does not have a white light fill-in light; if the second path of infrared camera is directly selected, the second path of infrared camera is influenced by the illumination brightness of the current environment, and the brightness value of the infrared light supplement lamp calculated through the SmartIR intelligent light supplement algorithm is insufficient, so that the face recognition result is poor. Therefore, in order to achieve better recognition speed and recognition rate, the invention selects the first path of visible light camera to work, or the second path of infrared camera to work, or the first path of visible light camera and the second path of infrared camera to work simultaneously by the following modes:
and in the T time period, the successful face recognition times of the first path of visible light camera is a, and the successful face recognition times of the second path of infrared camera is b. The value range of T is more than or equal to 300s and less than or equal to 600s, so that the problems that two paths work simultaneously for a long time and increase the CPU load of an embedded system due to the fact that the time for judging the identification result is too long are avoided, and the judgment result is inaccurate due to the fact that the time for judging the identification result is too short are solved. Of course, in other embodiments, the value range of T may also be adjusted according to actual use requirements.
When a is confirmed to be larger than b, namely the number of times of successful face recognition of the first path of visible light camera is larger than that of times of successful face recognition of the second path of infrared camera, the recognition result of the first path of visible light camera is superior to that of the second path of infrared camera, and at the moment, the first path of visible light camera is controlled to perform face recognition and face anti-fake work;
when a is confirmed to be smaller than b, namely the number of times of successful face recognition of the first path of visible light camera is smaller than that of times of successful face recognition of the second path of infrared camera, which shows that the recognition result of the second path of infrared camera is superior to that of the first path of visible light camera, the second path of infrared camera is controlled to perform face recognition and face anti-fake work at the moment;
when a is confirmed to be equal to b, namely the number of times of successful face recognition of the first path of visible light camera is equal to the number of times of successful face recognition of the second path of infrared camera, and the recognition result of the first path of visible light camera is the same as the recognition result of the second path of infrared camera, the first path of visible light camera and the second path of infrared camera are controlled to simultaneously perform face recognition and face anti-fake work, and if any path of visible light camera is successfully recognized, the face recognition is successful, and the recognition speed is increased.
Of course, in other embodiments, the recognition result may be determined in other manners, which are within the scope of the present invention and are not limited herein.
In a scene, such as an underground garage, where the time is in a critical illumination brightness, in order to reduce the time for the first path of visible light camera and the second path of infrared camera to work simultaneously, so as to reduce the load of the CPU of the embedded system, the step S104 further includes: when the first path of visible light camera is selected based on the identification result, updating a first threshold value to be a current required fill-in light brightness value; and when the second path of infrared camera is selected based on the identification result, updating the second threshold value to be the current required fill light brightness value. Through the mode, the first threshold value and the second threshold value are dynamically updated and adjusted according to the actual recognition result, so that smooth switching transition of work of different cameras is realized on the premise of ensuring quick face recognition.
In an application scenario, referring to fig. 3, assuming that the illumination brightness of the environment gradually changes from bright to dark, the dynamic adjustment process can be roughly divided into three stages as shown in fig. 3: the first phase is day, the second phase is a critical time period of day and night, and the third phase is night. In the first stage, the required light supplement brightness value is smaller than a first threshold value, only the first path of visible light camera carries out face recognition and face anti-fake work, after the program starts, the first path of visible light camera obtains the required light supplement brightness value through a video acquisition mode according to a Smart intelligent light supplement algorithm, when the required light supplement brightness value is smaller than the first threshold value, the face recognition equipment judges whether a dynamic detection event is triggered, if yes, the first path of visible light camera is controlled to carry out face recognition and face anti-fake work through a white light face algorithm, and meanwhile, the second path of infrared camera and an infrared light supplement lamp thereof are turned off; in the third stage, the brightness value of the required supplementary lighting is larger than the second threshold value, only the second path of infrared camera carries out face recognition and face anti-fake work, the second path of infrared camera adjusts the brightness value of the infrared supplementary lighting lamp through a SmartIR intelligent supplementary lighting algorithm, and controls the second path of infrared camera to carry out face recognition and face anti-fake work through the infrared face algorithm according to whether the detection event is triggered. In the third stage, the brightness value of the required supplementary lighting is greater than the first threshold and less than the second threshold, and at this time, the face recognition device controls the first path of visible light camera and the second path of infrared camera to work simultaneously, and the process can be finished as long as one path of visible light camera and the second path of infrared camera is successfully recognized.
Further, referring to fig. 4, the dynamic update process of the first threshold and the second threshold is as follows: after the program starts, initializing a first threshold value to be 0, and initializing a second threshold value to be 100; and then judging whether the brightness value of the required supplementary lighting changes or not, and judging the size relation between the brightness value of the required supplementary lighting and the first threshold and the second threshold. Specifically, when the required fill-in light brightness value is judged to be smaller than a first threshold value or larger than a second threshold value, the first threshold value and the second threshold value are kept unchanged; when the required fill light brightness value is judged to be larger than the first threshold value and smaller than the second threshold value, the identification success times of the first path of visible light camera and the second path of infrared camera in 300S are counted to be a and b respectively. If a is larger than b, the first path of visible light camera identification result is superior to the second path of infrared camera identification result, and at the moment, the first threshold value is updated to be the light supplement brightness value required currently; if a is less than b, the recognition result of the second path of infrared cameras is superior to that of the first path of visible light cameras, and at the moment, the second threshold value is updated to be the brightness value of the light supplement required currently; and if a is equal to b, namely the first path of visible light camera identification result is the same as the second path of infrared camera identification result, the first threshold value and the second threshold value are not changed.
Therefore, with reference to fig. 3 and 4, the above-mentioned face recognition process specifically includes: when the illumination brightness of the environment is bright enough, the first path of visible light camera obtains the required light supplement brightness value through a Smart intelligent light supplement algorithm, and maps the light supplement brightness value to the range of 0-100. The brightness value of the light supplement required currently is 0, the initial value of the first threshold is 0, and the initial value of the second threshold is 100, at this time, the face recognition device controls the first visible light camera to perform face recognition and face anti-fake work. Then, when the illumination brightness of the environment is gradually reduced, the brightness value of the required supplementary lighting obtained by the second path of visible light camera through a Smart intelligent supplementary lighting algorithm is larger than 0, and the condition that the brightness value is larger than a first threshold and smaller than a second threshold is met, so that the number of successful face recognition times of the first path of visible light camera in 300s is counted as a, and the number of successful face recognition times of the second path of infrared camera is counted as b; with the change of illumination brightness, firstly, when a is larger than b, namely a first path of visible light camera identification result is superior to a second path of infrared camera identification result, updating a first threshold value to be a current required light supplement brightness value, namely, when the required light supplement brightness value is in a range from 0 to the current required light supplement brightness value, selecting the first path of visible light camera to work; when a is equal to b, namely the first path of visible light camera recognition result is the same as the second path of infrared camera recognition result, the first threshold and the second threshold are not changed, two paths of simultaneous recognition are continuously carried out, and if any path of recognition is successful, the face recognition is successful, so that the recognition speed is increased; and then when a is less than b, namely the identification result of the second path of infrared cameras is superior to the identification result of the first path of visible light cameras, updating the second threshold value to be the current required light supplementing brightness value, namely selecting the second path of infrared cameras to work when the required light supplementing brightness value is in the range from the current required light supplementing brightness value to 100. And finally, when the illumination brightness of the environment is the lowest, namely the brightness value of the currently required supplementary lighting is not less than a second threshold value, the second path of infrared camera is directly selected to carry out face recognition and face anti-fake work. After the dynamic adjustment, the first threshold value and the second threshold value tend to be stable, and the situation that the first path of visible light camera and the second path of infrared camera work simultaneously is reduced. Moreover, the above process includes the following steps no matter before the first path of visible light camera and/or the second path of infrared camera are selectively controlled to perform face recognition and face anti-fake work: and confirming that the first path of visible light camera and/or the second path of infrared camera triggers the dynamic examination event, which is not described herein again.
Referring to fig. 5, the present invention further provides a face recognition device 50, which includes a first path of visible light camera 51, a second path of infrared camera 52, a processor 53, a memory 54, and a communication circuit 55, wherein the first path of visible light camera 51, the second path of infrared camera 52, the memory 54, and the communication circuit 55 are coupled to the processor 53, and when the processor 53, the memory 54, and the communication circuit 55 operate, the face recognition method in any of the above embodiments can be implemented. Specifically, the communication circuit 55 may include at least one of: wifi communication circuit, bluetooth communication circuit, cellular mobile communication circuit, etc. The processor 53 may also be referred to as a CPU (Central Processing Unit). The processor 53 may be an integrated circuit chip having signal processing capabilities. The processor 53 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 53 may be commonly implemented by a plurality of integrated circuit chips.
In an application scene, the invention also provides an access control system, which comprises the face recognition equipment and an access control switch device in communication connection with the face recognition equipment; the access control switch device is used for selecting whether to open the access control according to the working result of the face recognition equipment.
The invention also provides a face recognition device, which is applied to face recognition equipment and can execute the face recognition method in any embodiment, and the face recognition device comprises the following steps: a calculation module and a control module. Specifically, the calculation module is configured to obtain illumination brightness of a current environment, and calculate a required fill-in luminance value based on the illumination brightness; the control module is used for controlling the first path of visible light camera to perform face recognition and face anti-fake work when the required fill light brightness value is determined to be not greater than the first threshold value; the control module is further used for controlling a second path of infrared camera to perform face recognition and face anti-fake work when the required fill light brightness value is determined to be not smaller than a second threshold value; the control module is further used for selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera when the required light supplementing brightness value is determined to be larger than the first threshold and smaller than the second threshold.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a memory device according to an embodiment of the invention. The storage device 60 stores program instructions 600 that can be executed by a processor, and the program instructions 600 are used for implementing the face recognition method in any of the above embodiments. That is, when the face recognition method is implemented in software and sold or used as an independent product, the face recognition method may be stored in a storage device 60 readable by an electronic device, and the storage device 60 may be a usb disk, an optical disk, a server, or the like.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A face recognition method, comprising:
acquiring the illumination brightness of the environment, and calculating to obtain the required fill-in brightness value based on the illumination brightness; when the required fill-in light brightness value is determined to exceed the preset fill-in light brightness value range, controlling the first path of visible light camera or the second path of infrared camera to perform face recognition and face anti-fake work;
and when the required light supplement brightness value is determined to be within the preset light supplement brightness value range, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
2. The face recognition method according to claim 1, wherein a lower limit of the preset fill-in luminance value range is a first threshold, an upper limit thereof is a second threshold, and the first threshold is smaller than or equal to the second threshold;
when the required fill light brightness value is determined to exceed the preset fill light brightness value range, the first path of visible light camera or the second path of visible light camera is controlled to perform face recognition and face anti-fake work, and the method comprises the following steps:
when the required fill-in light brightness value is determined to be smaller than the first threshold value, controlling a first path of visible light camera to perform face recognition and face anti-fake work;
and when the brightness value of the required supplementary lighting is determined to be larger than the second threshold value, controlling a second path of infrared camera to perform face recognition and face anti-fake work.
When the required fill light brightness value is determined to be within the preset fill light brightness value range, the first path of visible light camera and/or the second path of infrared camera are selectively controlled to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera, and the method comprises the following steps:
and when the required fill light brightness value is determined to be larger than the first threshold value and smaller than the second threshold value, selectively controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera.
3. The face recognition method of claim 1, further comprising:
when the first path of visible light camera is selected based on the identification result, updating the first threshold value to be a current required supplementary lighting brightness value;
and updating the second threshold value to be the current required fill light brightness value when the second path of infrared camera is selected based on the identification result.
4. The face recognition method according to claim 1, wherein the selecting and controlling the first path of visible light camera and/or the second path of infrared camera to perform face recognition and face anti-fake work based on the recognition results of the first path of visible light camera and the second path of infrared camera comprises:
controlling the first path of visible light camera and the second path of infrared camera to simultaneously perform face recognition and face anti-fake work and lasting for a T time period;
counting the successful times of face recognition and face anti-fake work of the first path of visible light camera as a and the successful times of face recognition and face anti-fake work of the second path of infrared camera as b in the T time period;
when a is confirmed to be larger than b, the recognition result of the first path of visible light camera is superior to that of the second path of infrared camera, and the first path of visible light camera is controlled to perform face recognition and face anti-fake work;
when a is confirmed to be smaller than b, the recognition result of the second path of infrared camera is superior to that of the first path of visible light camera, and the second path of infrared camera is controlled to perform face recognition and face anti-fake work;
and when a is confirmed to be equal to b, the recognition result of the first path of visible light camera is the same as that of the second path of infrared camera, and the first path of visible light camera and the second path of infrared camera are controlled to perform face recognition and face anti-fake work.
5. The face recognition method according to claim 4, wherein T is in a range of 300s ≦ T ≦ 600 s.
6. The face recognition method of claim 2,
the control first way visible light camera carries out face identification, face anti-fake work, includes before: confirming that the first path of visible light camera triggers a dynamic examination event;
the control second way infrared camera carries out face identification, face anti-fake work, includes before: confirming that the second path of infrared camera triggers a dynamic inspection event;
the selection control the first path of visible light camera and/or the second path of infrared camera to carry out face recognition and face anti-fake work, and the method comprises the following steps: and confirming that the first path of visible light camera and/or the second path of infrared camera triggers a dynamic examination event.
7. The face recognition method of claim 1, wherein the obtaining of the illumination brightness of the environment and the calculating of the required fill-in luminance value based on the illumination brightness comprise: and acquiring the illumination brightness of the environment according to the image brightness acquired by the first path of visible light camera, and calculating to obtain the required light supplement brightness value based on the illumination brightness through a Smart intelligent light supplement algorithm.
8. The face recognition method according to claim 2, wherein the controlling of the second path of infrared camera to perform face recognition and face anti-fake comprises:
and adjusting the brightness value of the infrared light supplement lamp of the second path of infrared camera according to a SmartIR intelligent light supplement algorithm.
9. A face recognition device, comprising:
the human face recognition system comprises a first path of visible light camera, a second path of infrared camera, a processor, a memory and a communication circuit, wherein the first path of visible light camera, the second path of infrared camera, the memory and the communication circuit are coupled to the processor, and the processor, the memory and the communication circuit can realize the human face recognition method as claimed in any one of claims 1 to 8 when in work.
10. An access control system, comprising:
the face recognition device of claim 9 and an access control switch device in communication with the face recognition device; the entrance guard switch device is used for selecting whether to open an entrance guard according to the working result of the face recognition equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010526043.9A CN111814561A (en) | 2020-06-11 | 2020-06-11 | Face recognition method, face recognition equipment and access control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010526043.9A CN111814561A (en) | 2020-06-11 | 2020-06-11 | Face recognition method, face recognition equipment and access control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814561A true CN111814561A (en) | 2020-10-23 |
Family
ID=72845739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010526043.9A Pending CN111814561A (en) | 2020-06-11 | 2020-06-11 | Face recognition method, face recognition equipment and access control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814561A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112650379A (en) * | 2020-12-29 | 2021-04-13 | 深圳市商汤科技有限公司 | Activation method and device, electronic equipment and computer readable storage medium |
| CN113221774A (en) * | 2021-05-19 | 2021-08-06 | 重庆幸尚付科技有限责任公司 | Face recognition system and attendance device |
| WO2021208789A1 (en) * | 2020-04-14 | 2021-10-21 | 华为技术有限公司 | Photographing method and electronic device |
| CN117854194A (en) * | 2024-03-07 | 2024-04-09 | 深圳市开拓者安防科技有限公司 | Visual access control method and system based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203416333U (en) * | 2013-07-17 | 2014-01-29 | 广东安居宝数码科技股份有限公司 | PWM infrared fill-in light switching device |
| CN106897716A (en) * | 2017-04-27 | 2017-06-27 | 广东工业大学 | A kind of dormitory safety monitoring system and method |
| CN107679481A (en) * | 2017-09-27 | 2018-02-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN108776799A (en) * | 2018-08-17 | 2018-11-09 | 勿识（深圳）智能硬件有限公司 | Face identification device, the method and system for starting recognition of face |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
| CN109857238A (en) * | 2019-02-25 | 2019-06-07 | 深圳传音通讯有限公司 | Terminal unlock method and terminal |
| CN110008878A (en) * | 2019-03-27 | 2019-07-12 | 中控智慧科技股份有限公司 | A kind of anti-false method of Face datection and the face identification device for having anti-false function |
| CN110458062A (en) * | 2019-07-30 | 2019-11-15 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment and storage medium |
-
2020
- 2020-06-11 CN CN202010526043.9A patent/CN111814561A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203416333U (en) * | 2013-07-17 | 2014-01-29 | 广东安居宝数码科技股份有限公司 | PWM infrared fill-in light switching device |
| CN106897716A (en) * | 2017-04-27 | 2017-06-27 | 广东工业大学 | A kind of dormitory safety monitoring system and method |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
| CN107679481A (en) * | 2017-09-27 | 2018-02-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN108776799A (en) * | 2018-08-17 | 2018-11-09 | 勿识（深圳）智能硬件有限公司 | Face identification device, the method and system for starting recognition of face |
| CN109857238A (en) * | 2019-02-25 | 2019-06-07 | 深圳传音通讯有限公司 | Terminal unlock method and terminal |
| CN110008878A (en) * | 2019-03-27 | 2019-07-12 | 中控智慧科技股份有限公司 | A kind of anti-false method of Face datection and the face identification device for having anti-false function |
| CN110458062A (en) * | 2019-07-30 | 2019-11-15 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 方圆圆: "《人脸识别与美颜算法实战基于Python、机器学习与深度学习》", 30 April 2020, 机械工业出版社, pages: 129 * |
| 马库斯•杜•索托伊: "《天才与算法人脑与AI的数学思维》", 31 March 2020, 机械工业出版社, pages: 69 - 70 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021208789A1 (en) * | 2020-04-14 | 2021-10-21 | 华为技术有限公司 | Photographing method and electronic device |
| CN112650379A (en) * | 2020-12-29 | 2021-04-13 | 深圳市商汤科技有限公司 | Activation method and device, electronic equipment and computer readable storage medium |
| CN113221774A (en) * | 2021-05-19 | 2021-08-06 | 重庆幸尚付科技有限责任公司 | Face recognition system and attendance device |
| CN117854194A (en) * | 2024-03-07 | 2024-04-09 | 深圳市开拓者安防科技有限公司 | Visual access control method and system based on artificial intelligence |
| CN117854194B (en) * | 2024-03-07 | 2024-06-07 | 深圳市开拓者安防科技有限公司 | Visual access control method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814561A (en) | Face recognition method, face recognition equipment and access control system | |
| EP3180784B1 (en) | Management for wearable display | |
| JP2022118730A (en) | Vehicle door lock release method and device, system, vehicle, electronic apparatus and storage medium | |
| US20170150025A1 (en) | Image exposure method for mobile terminal based on eyeprint recognition and image exposure system | |
| CN111614892B (en) | Face image acquisition method, shooting device and computer-readable storage medium | |
| CN114596620B (en) | Light supplement control method, device and equipment for face recognition equipment and storage medium | |
| US11138429B2 (en) | Iris recognition using eye-tracking system | |
| CN102917159A (en) | Mode removal for improved multi-modal background subtraction | |
| CN106941588B (en) | Data processing method and electronic equipment | |
| CN113747008B (en) | Camera and light supplementing method | |
| CN112861011A (en) | Scene recommendation method and device and terminal equipment | |
| WO2016025614A1 (en) | Power management for wearable display | |
| CN106022283A (en) | Biometric identification method, biometric identification device and identification equipment | |
| CN112055961B (en) | Shooting method, shooting device and terminal equipment | |
| CN108174088A (en) | A kind of brightness adjusting method, device, terminal and computer readable storage medium | |
| CN107508965B (en) | Image acquisition method and related product | |
| CN113297880A (en) | Fingerprint acquisition method, fingerprint acquisition device, fingerprint acquisition terminal and storage medium | |
| CN116580493A (en) | Access control system, control method, equipment and medium for face recognition | |
| CN113627263B (en) | Exposure method, device and equipment based on face detection | |
| CN112966575B (en) | Target face recognition method and device applied to smart community | |
| CN116055895A (en) | Image processing method and related device | |
| CN114286004A (en) | Focusing method, shooting device, electronic equipment and medium | |
| CN116939358A (en) | Image processing method and related device | |
| CN111219940A (en) | Method and device for controlling light in refrigerator and refrigerator | |
| CN102413296B (en) | Remote control method for double-channel television and double-channel television 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 |