CN117789278A - Face recognition temperature measurement method, device and system - Google Patents
Face recognition temperature measurement method, device and system Download PDFInfo
- Publication number
- CN117789278A CN117789278A CN202410210228.7A CN202410210228A CN117789278A CN 117789278 A CN117789278 A CN 117789278A CN 202410210228 A CN202410210228 A CN 202410210228A CN 117789278 A CN117789278 A CN 117789278A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- face image
- comparison
- facial
- 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 125
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 45
- 230000008569 process Effects 0.000 claims abstract description 86
- 230000001815 facial effect Effects 0.000 claims description 38
- 238000012545 processing Methods 0.000 claims description 33
- 238000012216 screening Methods 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 18
- 230000008921 facial expression Effects 0.000 claims description 15
- 210000000697 sensory organ Anatomy 0.000 claims description 15
- 210000000056 organ Anatomy 0.000 claims description 10
- 208000031636 Body Temperature Changes Diseases 0.000 claims description 9
- 238000004861 thermometry Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000000052 comparative effect Effects 0.000 claims 3
- 230000000875 corresponding effect Effects 0.000 description 65
- 238000004590 computer program Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 210000001508 eye Anatomy 0.000 description 5
- 238000005259 measurement Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241001156002 Anthonomus pomorum Species 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the field of computers, in particular to a face recognition temperature measurement method, a face recognition temperature measurement device and a face recognition temperature measurement system, wherein the face recognition temperature measurement method comprises face images of all angles of a person to be measured in a first process video, and the face images of all angles can be simulated to generate a plurality of types of simulated face images, namely, a face temperature database finally established comprises face conditions of the person to be measured in various different states, so that the identity of the person to be measured can be accurately recognized no matter what face state the person to be measured shows in the temperature measurement process of the person to be measured in the future; in this application, face temperature database covers widely, has guaranteed the accuracy to the people that is surveyed discernment to need not to arrange in addition that the staff carries out information entry to the people that is surveyed, promoted the efficiency of temperature measurement greatly.
Description
Technical Field
The present invention relates to the field of computers, and in particular, to a face recognition temperature measurement method, device and system.
Background
Human body temperature measurement refers to assessing health status and detecting whether there is a fever symptom by measuring the body temperature of a human body.
The existing human body temperature measurement process separates information acquisition from temperature measurement, personnel information and acquired temperature are required to be correlated manually or at the rear end, the same personnel need to repeat the same information acquisition operation each time when carrying out temperature acquisition, such as form filling, and the like, so that the time for actually carrying out temperature measurement acquisition is very inconvenient, most of time is consumed in information collection, and the overall efficiency of the temperature measurement process is reduced.
Therefore, the existing human body temperature measurement method is used for manually matching human body information with temperature measurement data, so that the problem of low overall temperature measurement efficiency is caused.
Disclosure of Invention
Accordingly, it is necessary to provide a face recognition temperature measurement method, device and system for solving the above problems.
The embodiment of the invention is realized in such a way that the face recognition temperature measurement method comprises the following steps:
s1: when a detected person enters a detection area for the first time, recording a first process video, and collecting a first infrared image corresponding to each video frame of the first process video;
s2: screening a plurality of first face images meeting a set standard from the first process video;
s3: for any one first face image, identifying face key points on the first face image;
s4: changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image;
s5: establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
s6: when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video;
s7: screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
s8: comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
s9: and comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
In one embodiment, the present invention provides a face recognition temperature measurement device, the device comprising:
the first acquisition module is used for recording a first process video when a detected person enters the detection area for the first time and acquiring a first infrared image corresponding to each video frame of the first process video;
the first processing module is used for screening a plurality of first face images meeting the set standard from the first process video;
the second processing module is used for identifying the facial key points on any one of the first face images;
the third processing module is used for changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model so as to obtain a corresponding simulated face image;
the fourth processing module is used for establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
the second acquisition module is used for starting recording a second process video when the detected person enters the detection area again and acquiring a second infrared image corresponding to each video frame of the second process video;
the fifth processing module is used for screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
the sixth processing module is used for comparing the first comparison face image with each face image in the face temperature database so as to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
and the seventh processing module is used for comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
In one embodiment, the present invention provides a face recognition thermometry system, the system comprising:
the acquisition device is used for recording video and acquiring infrared images; and
and the computer equipment is connected with the acquisition equipment and is used for executing the face recognition temperature measurement method.
The invention provides a face recognition temperature measurement method, a face recognition temperature measurement device and a face recognition temperature measurement system, wherein the method comprises the steps of recording a first process video when a detected person enters a detection area for the first time, and collecting a first infrared image corresponding to each video frame of the first process video; screening a plurality of first face images meeting a set standard from the first process video; for any one first face image, identifying face key points on the first face image; changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image; establishing a face temperature database aiming at the detected person; when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video; screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image; comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database; comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image to determine the body temperature change of the tested person; in the method, the face images of all angles of the detected person are included in the first process video, the face images of all angles can be simulated to generate a plurality of types of simulated face images, namely, the face conditions of the detected person in various different states are included in the finally established face temperature database, so that the identity of the detected person can be accurately identified no matter what face state the detected person shows in the temperature measurement process of the detected person in the future, no additional arrangement of staff is needed for inputting information to the detected person, and the temperature measurement efficiency is greatly improved.
Drawings
FIG. 1 is a first flowchart of a face recognition temperature measurement method provided in one embodiment;
FIG. 2 is a second flowchart of a face recognition thermometry method provided in one embodiment;
FIG. 3 is a block flow diagram of a face recognition temperature measurement device provided in one embodiment;
fig. 4 is a schematic diagram of a face recognition temperature measurement system according to an embodiment;
FIG. 5 is a block diagram of the internal architecture of a computer device in one embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of this disclosure.
As shown in fig. 1-2, in one embodiment, a face recognition thermometry method is provided, the method comprising:
s1: when a detected person enters a detection area for the first time, recording a first process video, and collecting a first infrared image corresponding to each video frame of the first process video;
s2: screening a plurality of first face images meeting a set standard from the first process video;
s3: for any one first face image, identifying face key points on the first face image;
s4: changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image;
s5: establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
s6: when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video;
s7: screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
s8: comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
s9: and comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
In this embodiment, the method is executed in a computer device, where the computer device may be an independent physical server or terminal, or may be a server cluster formed by multiple physical servers, or may be a cloud server that provides basic cloud computing services such as a cloud server, a cloud database, a cloud storage, a CDN, and the like; the method comprises the steps that a collecting device is adopted for data collection, wherein the collecting device comprises two cameras, one is a video camera and is used for collecting a first process video and a second process video, and the other is an infrared camera and is used for collecting a first infrared image and a second infrared image;
in this embodiment, the set criteria include the face area ratio of the person to be measured reaching a preset ratio, the facial features of the person to be measured being intact, and other preset criteria; facial keypoints refer to some specific locations or markers on the face that are used to describe and locate important features of the face, such as eye keypoints: the positions of the corners of the eyes, the centers of the eyes, the eyebrows and the like are used for positioning the positions and the shapes of the eyes and the key points of the nose: the nose tip, the upper edge of the nose bridge, the nose wings and other positions are used for describing the shape and the position of the nose, and the key points of the mouth are as follows: the mouth corner, the upper lip center, the lower lip center and the like are used for describing the shape and the opening and closing degree of the mouth, and the cheek key points are as follows: high and low points of the cheek to describe contours and protrusions of the cheek region;
in this embodiment, adjusting the relative positions of the facial key points may enable the skin area where the facial key points are located to change correspondingly, so that the first facial image presents different facial expressions, and thus each simulated facial image is obtained;
in the embodiment, the face image with the highest five sense organs definition is screened out from the second process video, so that the matching accuracy of the face image and the image in the face temperature database can be further ensured;
in this embodiment, the method for comparing the first infrared image and the second infrared image may be a hot spot contrast method: judging the temperature change by comparing the position and intensity change of the hot spots (namely hot spots on the surface of the object) in the same area; temperature profile comparison method: comparing and analyzing the temperature distribution graphs of the two infrared images, checking the temperature change condition of the same area, and if the color depth or the tone of a certain area is changed, possibly representing that the temperature is correspondingly changed; temperature measurement point comparison method: and selecting specific positions in the infrared image as measurement points, measuring at different times or under different conditions, and comparing measurement results to judge the change condition of the temperature.
In the application, as the detected person can move in front of the lens, the face images of all angles of the detected person are included in the first process video, and the face images of all angles can be simulated to generate a plurality of types of simulated face images, namely, the face condition of the detected person in various different states is included in the finally established face temperature database, namely, the face temperature database has a wide coverage range, and the identity of the detected person can be accurately identified no matter what face state the detected person shows in the temperature measurement process of the detected person in the future, so that the information input of the detected person is not required to be additionally arranged, and the temperature measurement efficiency is greatly improved.
As a preferred embodiment, the screening the first face images from the first process video, which meet the set criteria, includes:
s21: taking a first video frame image from a first process video as a first candidate image;
s22: identifying a face area in the first candidate image, and calculating a first proportion of the face area to the image area of the first candidate image;
s23: judging whether the first proportion exceeds a preset proportion, and if not, excluding the first candidate image;
s24: if yes, judging whether the five sense organs in the face area are complete, if not, excluding the first candidate image, and if so, taking the first candidate image as a first face image;
s25: and taking down one video frame image from the first process video as a first candidate image, and executing steps S22 to S25 until each video frame image in the first process video is judged.
In this embodiment, the preset ratio may be 50%, 60% or other ratios, which are not limited herein; the computer equipment can rapidly and accurately identify the detected person corresponding to the face image reaching the set standard, so that each first candidate image screened out reaches the set standard, and the computer equipment can accurately correspond each first candidate image to the detected person;
as a preferred embodiment, changing the relative positions of the facial key points on the first face image according to the relative positions of the facial key points in the preset face template model, so as to obtain a corresponding simulated face image includes:
s41: acquiring a face template model corresponding to one facial expression;
s42: the size and the angle of the face template model are adjusted so that the size and the angle of the face template model are consistent with those of the face in the first face image;
s43: identifying the relative position of the facial key point of the adjusted face template model as a first relative position;
s44: adjusting the relative positions of facial key points on the first facial image according to the first relative positions, so as to obtain a simulated facial image presenting the facial expression;
s45: and obtaining a face template model corresponding to another facial expression, and executing the steps S42 to S45 until a simulated face image corresponding to each facial expression is obtained.
In this embodiment, each face template model presents a facial expression, which is a standard facial expression, and the standard facial expression is a facial expression in which each facial key point is located at a preset relative position;
the facial states of various types corresponding to the first face image can be obtained by adjusting the first face image to the facial expressions of various face template models, so that the facial image data of the face temperature database can be enriched, and the matching accuracy is improved.
As a preferred embodiment, the screening out the face image with the highest definition of the five sense organs from the second process video includes:
s71: taking the first video frame image from the second process video as a second candidate image;
s72: identifying a face region in the second candidate image, and calculating a second proportion of the face region to the area of the second candidate image;
s73: judging whether the second proportion exceeds a preset proportion, and if not, excluding the second candidate image;
s74: if yes, judging whether the five sense organs in the face area are complete, if not, excluding the second candidate image, and if so, taking the second candidate image as a second face image;
s75: taking one video frame image from the second process video as a second candidate image, and executing steps S72 to S75 until each video frame image in the second process video is judged;
s76: and carrying out five-sense organ definition analysis on each second face image, and outputting the second face image with the highest five-sense organ definition.
The five-sense-organ definition analysis for any one of the second face images includes:
five facial organs in the second facial image are identified, and then a local image of the area where each facial organ is located is cut off;
calculating the definition of each partial image by adopting a definition gradient evaluation function;
and calculating the average definition of each local image, and taking the average definition as the definition of the second face image.
In this embodiment, the manner of screening the second face image is the same as the manner of screening the first face image; some facial organs have two, such as eyes, with corresponding partial images having two; the local image is an image comprising the complete corresponding organ; the sharpness gradient evaluation function may employ a Brenner gradient function, an energy gradient function, a gray variance function, or other types of evaluation functions;
as a preferred embodiment, comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database includes:
s81: taking a face image from the face temperature database as a second comparison face image;
s82: taking the facial key points of the first comparison face image as first key points, taking the facial key points of the second comparison face image as second key points, and overlapping the second comparison face image with the first comparison face image;
s83: determining the matching degree of the second comparison face image and the first comparison face image according to the coincidence degree of the first key point and the second key point;
s84: taking another face image from the face temperature database as a second comparison face image, and executing the steps S82 to S84 until the matching degree of each face image in the face temperature database and the second comparison face image is obtained;
s85: and outputting the face image with the highest matching degree with the second comparison face image.
Determining the matching degree of the second comparison face image and the first comparison face image through the following formula:
wherein M is the matching degree,adjusting the coefficient for the matching degree, < >>For the number of first key points, +.>Is the number of first keypoints that coincide with the second keypoints.
In this embodiment, the face image with the highest matching degree with the second face image is screened from the face temperature database, and if the matching degree of the two face images is high, it means that the two images are similar in both face angle and facial expression, and the temperatures corresponding to the two face images can be more comparable.
As a preferred embodiment, if the face image with the highest matching degree is the first face image, comparing the first infrared image corresponding to the first face image with the second infrared image corresponding to the first comparison face image;
if the face image with the highest matching degree is the simulated face image, determining a first face image corresponding to the simulated face image, and comparing the first infrared image corresponding to the first face image with a second infrared image corresponding to the first comparison face image.
In this embodiment, the simulated face images corresponding to any one of the first face images are generated according to the first face image, so that the first infrared images corresponding to the simulated face images, that is, the first infrared images corresponding to the first face image, can be further compared with the second infrared images corresponding to the second face image no matter whether the first face image or the simulated face image with the highest matching degree with the second face image is the first face image or the simulated face image;
in the present embodiment of the present invention, in the present embodiment,the value range of (2) is 10-20, and the coefficient value range can be other value ranges, which are not limited herein.
As shown in fig. 3, in one embodiment, there is provided a face recognition temperature measurement apparatus, the apparatus including:
the first acquisition module is used for recording a first process video when a detected person enters the detection area for the first time and acquiring a first infrared image corresponding to each video frame of the first process video;
the first processing module is used for screening a plurality of first face images meeting the set standard from the first process video;
the second processing module is used for identifying the facial key points on any one of the first face images;
the third processing module is used for changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model so as to obtain a corresponding simulated face image;
the fourth processing module is used for establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
the second acquisition module is used for starting recording a second process video when the detected person enters the detection area again and acquiring a second infrared image corresponding to each video frame of the second process video;
the fifth processing module is used for screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
the sixth processing module is used for comparing the first comparison face image with each face image in the face temperature database so as to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
and the seventh processing module is used for comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
The process of implementing the respective functions of each module in the face recognition temperature measurement device provided in this embodiment may refer to the description of the embodiment shown in fig. 1, which is not repeated here.
As shown in fig. 4, in one embodiment, a face recognition thermometry system is provided, the system comprising:
the acquisition device is used for recording video and acquiring infrared images; and
and the computer equipment is connected with the acquisition equipment and is used for executing the face recognition temperature measurement method.
In this embodiment, the acquisition device and the computer device cooperate to execute the face recognition temperature measurement method, because the measured person moves in front of the lens, the face images of all angles of the measured person are included in the first process video, and the face images of all angles can be simulated to generate a plurality of types of simulated face images, namely, the face condition of the measured person in various different states is included in the finally established face temperature database, namely, the coverage range of the face temperature database is wide, and further, the identity of the measured person can be accurately identified no matter what face state the measured person shows in the temperature measurement process of the measured person in the future, no additional arrangement of staff is needed to input information to the measured person, and the temperature measurement efficiency is greatly improved.
FIG. 5 illustrates an internal block diagram of a computer device in one embodiment. As shown in fig. 5, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, where the computer program when executed by the processor may cause the processor to implement the face recognition temperature measurement method provided by the embodiment of the present invention. The internal memory may also store a computer program, which when executed by the processor, causes the processor to execute the face recognition temperature measurement method provided by the embodiment of the invention. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, the face recognition temperature measurement device provided by the embodiment of the invention can be implemented in a form of a computer program, and the computer program can be run on a computer device as shown in fig. 5. The memory of the computer device may store various program modules constituting the face recognition temperature measuring device, for example, a first acquisition module, a first processing module, a second processing module, a third processing module, a fourth processing module, a second acquisition module, a fifth processing module, and a sixth processing module shown in fig. 3. The computer program constituted by the respective program modules causes the processor to execute the steps in the face recognition temperature measurement method of the respective embodiments of the present invention described in the present specification.
For example, the computer device shown in fig. 5 may execute step S1 through the first acquisition module in the face recognition temperature measurement device shown in fig. 3; the computer equipment can execute the step S2 through the first processing module; the computer equipment can execute the step S3 through the second processing module; the computer equipment can execute the step S4 through the third processing module; the computer equipment can execute the step S5 through a fourth processing module; the computer equipment can execute the step S6 through the second acquisition module; the computer equipment can execute the step S7 through a fifth processing module; the computer device may perform step S8 through a sixth processing module.
In one embodiment, a computer device is presented, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1: when a detected person enters a detection area for the first time, recording a first process video, and collecting a first infrared image corresponding to each video frame of the first process video;
s2: screening a plurality of first face images meeting a set standard from the first process video;
s3: for any one first face image, identifying face key points on the first face image;
s4: changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image;
s5: establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
s6: when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video;
s7: screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
s8: comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
s9: and comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of:
s1: when a detected person enters a detection area for the first time, recording a first process video, and collecting a first infrared image corresponding to each video frame of the first process video;
s2: screening a plurality of first face images meeting a set standard from the first process video;
s3: for any one first face image, identifying face key points on the first face image;
s4: changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image;
s5: establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
s6: when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video;
s7: screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
s8: comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
s9: and comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A face recognition temperature measurement method, the method comprising:
s1: when a detected person enters a detection area for the first time, recording a first process video, and collecting a first infrared image corresponding to each video frame of the first process video;
s2: screening a plurality of first face images meeting a set standard from the first process video;
s3: for any one first face image, identifying face key points on the first face image;
s4: changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model, so as to obtain a corresponding simulated face image;
s5: establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
s6: when the person to be detected enters the detection area again, recording a second process video, and collecting a second infrared image corresponding to each video frame of the second process video;
s7: screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
s8: comparing the first comparison face image with each face image in the face temperature database to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
s9: and comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
2. The method of claim 1, wherein the screening out a number of first face images from the first process video that meet a set criterion comprises:
s21: taking a first video frame image from a first process video as a first candidate image;
s22: identifying a face area in the first candidate image, and calculating a first proportion of the face area to the image area of the first candidate image;
s23: judging whether the first proportion exceeds a preset proportion, and if not, excluding the first candidate image;
s24: if yes, judging whether the five sense organs in the face area are complete, if not, excluding the first candidate image, and if so, taking the first candidate image as a first face image;
s25: and taking down one video frame image from the first process video as a first candidate image, and executing steps S22 to S25 until each video frame image in the first process video is judged.
3. The method of claim 1, wherein changing the relative positions of the facial key points on the first face image according to the relative positions of the facial key points in the preset face template model, and further obtaining the corresponding simulated face image comprises:
s41: acquiring a face template model corresponding to one facial expression;
s42: the size and the angle of the face template model are adjusted so that the size and the angle of the face template model are consistent with those of the face in the first face image;
s43: identifying the relative position of the facial key point of the adjusted face template model as a first relative position;
s44: adjusting the relative positions of facial key points on the first facial image according to the first relative positions, so as to obtain a simulated facial image presenting the facial expression;
s45: and obtaining a face template model corresponding to another facial expression, and executing the steps S42 to S45 until a simulated face image corresponding to each facial expression is obtained.
4. The method of claim 2, wherein screening out the facial image with the highest facial definition from the second process video comprises:
s71: taking the first video frame image from the second process video as a second candidate image;
s72: identifying a face region in the second candidate image, and calculating a second proportion of the face region to the area of the second candidate image;
s73: judging whether the second proportion exceeds a preset proportion, and if not, excluding the second candidate image;
s74: if yes, judging whether the five sense organs in the face area are complete, if not, excluding the second candidate image, and if so, taking the second candidate image as a second face image;
s75: taking one video frame image from the second process video as a second candidate image, and executing steps S72 to S75 until each video frame image in the second process video is judged;
s76: and carrying out five-sense organ definition analysis on each second face image, and outputting the second face image with the highest five-sense organ definition.
5. The method of claim 4, wherein performing the facial definition analysis on any one of the second face images comprises:
five facial organs in the second facial image are identified, and then a local image of the area where each facial organ is located is cut off;
calculating the definition of each partial image by adopting a definition gradient evaluation function;
and calculating the average definition of each local image, and taking the average definition as the definition of the second face image.
6. The method of claim 1, wherein comparing the first comparison face image with each face image in the face temperature database to determine the face image in the face temperature database that matches the first comparison face image most closely comprises:
s81: taking a face image from the face temperature database as a second comparison face image;
s82: taking the facial key points of the first comparison face image as first key points, taking the facial key points of the second comparison face image as second key points, and overlapping the second comparison face image with the first comparison face image;
s83: determining the matching degree of the second comparison face image and the first comparison face image according to the coincidence degree of the first key point and the second key point;
s84: taking another face image from the face temperature database as a second comparison face image, and executing the steps S82 to S84 until the matching degree of each face image in the face temperature database and the second comparison face image is obtained;
s85: and outputting the face image with the highest matching degree with the second comparison face image.
7. The method of claim 6, wherein the degree of matching of the second comparative face image to the first comparative face image is determined by the following formula:
，
wherein M is the matching degree,adjusting the coefficient for the matching degree, < >>For the number of first key points, +.>Is the number of first keypoints that coincide with the second keypoints.
8. The method of claim 6, wherein if the face image with the highest matching degree is a first face image, comparing the first infrared image corresponding to the first face image with the second infrared image corresponding to the first comparative face image;
if the face image with the highest matching degree is the simulated face image, determining a first face image corresponding to the simulated face image, and comparing the first infrared image corresponding to the first face image with a second infrared image corresponding to the first comparison face image.
9. A face recognition temperature measurement device, the device comprising:
the first acquisition module is used for recording a first process video when a detected person enters the detection area for the first time and acquiring a first infrared image corresponding to each video frame of the first process video;
the first processing module is used for screening a plurality of first face images meeting the set standard from the first process video;
the second processing module is used for identifying the facial key points on any one of the first face images;
the third processing module is used for changing the relative positions of the face key points on the first face image according to the relative positions of the face key points in the preset face template model so as to obtain a corresponding simulated face image;
the fourth processing module is used for establishing a face temperature database aiming at the detected person, wherein the face temperature database comprises all first face images of the detected person, a simulated face image corresponding to each first face image and a first infrared image corresponding to each first face image;
the second acquisition module is used for starting recording a second process video when the detected person enters the detection area again and acquiring a second infrared image corresponding to each video frame of the second process video;
the fifth processing module is used for screening out a face image with highest five sense organs definition from the second process video, and taking the face image as a first comparison face image;
the sixth processing module is used for comparing the first comparison face image with each face image in the face temperature database so as to determine the face image with the highest matching degree with the first comparison face image in the face temperature database;
and the seventh processing module is used for comparing the first infrared image corresponding to the face image with the highest matching degree with the second infrared image corresponding to the first comparison face image so as to determine the body temperature change of the tested person.
10. A face recognition thermometry system, the system comprising:
the acquisition device is used for recording video and acquiring infrared images; and
computer device, connected to the acquisition device, for performing the face recognition thermometry method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410210228.7A CN117789278A (en) | 2024-02-26 | 2024-02-26 | Face recognition temperature measurement method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410210228.7A CN117789278A (en) | 2024-02-26 | 2024-02-26 | Face recognition temperature measurement method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117789278A true CN117789278A (en) | 2024-03-29 |
Family
ID=90402131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410210228.7A Pending CN117789278A (en) | 2024-02-26 | 2024-02-26 | Face recognition temperature measurement method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117789278A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444555A (en) * | 2020-03-23 | 2020-07-24 | 深圳云天励飞技术有限公司 | Temperature measurement information display method and device and terminal equipment |
| CN111486962A (en) * | 2020-04-15 | 2020-08-04 | 易造机器人（深圳）有限公司 | Remote human face temperature measurement system based on infrared imaging and implementation method |
| CN111626125A (en) * | 2020-04-26 | 2020-09-04 | 浙江大华技术股份有限公司 | Face temperature detection method, system and device and computer equipment |
| CN111768511A (en) * | 2020-07-07 | 2020-10-13 | 湖北省电力装备有限公司 | Staff information recording method and device based on cloud temperature measurement equipment |
| CN113447128A (en) * | 2020-03-10 | 2021-09-28 | 百度在线网络技术（北京）有限公司 | Multi-person body temperature detection method and device, electronic equipment and storage medium |
| CN116110100A (en) * | 2023-01-14 | 2023-05-12 | 深圳市大数据研究院 | Face recognition method, device, computer equipment and storage medium |
-
2024
- 2024-02-26 CN CN202410210228.7A patent/CN117789278A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113447128A (en) * | 2020-03-10 | 2021-09-28 | 百度在线网络技术（北京）有限公司 | Multi-person body temperature detection method and device, electronic equipment and storage medium |
| CN111444555A (en) * | 2020-03-23 | 2020-07-24 | 深圳云天励飞技术有限公司 | Temperature measurement information display method and device and terminal equipment |
| CN111486962A (en) * | 2020-04-15 | 2020-08-04 | 易造机器人（深圳）有限公司 | Remote human face temperature measurement system based on infrared imaging and implementation method |
| CN111626125A (en) * | 2020-04-26 | 2020-09-04 | 浙江大华技术股份有限公司 | Face temperature detection method, system and device and computer equipment |
| CN111768511A (en) * | 2020-07-07 | 2020-10-13 | 湖北省电力装备有限公司 | Staff information recording method and device based on cloud temperature measurement equipment |
| CN116110100A (en) * | 2023-01-14 | 2023-05-12 | 深圳市大数据研究院 | Face recognition method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 中国人工智能学会: "《中国人工智能进展2009》", 31 December 2009, 北京邮电大学出版社, pages: 482 - 485 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667011B (en) | Damage detection model training and vehicle damage detection method, device, equipment and medium | |
| US10303982B2 (en) | Systems and methods for machine learning enhanced by human measurements | |
| US10410292B2 (en) | Method, system, apparatus, and storage medium for realizing antifraud in insurance claim based on consistency of multiple images | |
| WO2021000524A1 (en) | Hole protection cap detection method and apparatus, computer device and storage medium | |
| CN106897658B (en) | Method and device for identifying human face living body | |
| CN108985155A (en) | Mouth model training method, mouth recognition methods, device, equipment and medium | |
| Prince et al. | Tied factor analysis for face recognition across large pose differences | |
| US9092662B2 (en) | Pattern recognition method and pattern recognition apparatus | |
| WO2020248387A1 (en) | Face recognition method and apparatus based on multiple cameras, and terminal and storage medium | |
| CN108447061B (en) | Commodity information processing method and device, computer equipment and storage medium | |
| CN110852285A (en) | Object detection method and device, computer equipment and storage medium | |
| CN111191532B (en) | Face recognition method and device based on construction area and computer equipment | |
| KR20200100806A (en) | Analysis of captured images to determine test results | |
| CN110598687A (en) | Vehicle identification code detection method and device and computer equipment | |
| WO2021114612A1 (en) | Target re-identification method and apparatus, computer device, and storage medium | |
| CN109299658A (en) | Face area detecting method, face image rendering method, device and storage medium | |
| CN110660078B (en) | Object tracking method, device, computer equipment and storage medium | |
| US20240169518A1 (en) | Method and apparatus for identifying body constitution in traditional chinese medicine, electronic device, storage medium and program | |
| CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
| CN113706481A (en) | Sperm quality detection method, sperm quality detection device, computer equipment and storage medium | |
| Nambiar et al. | Shape context for soft biometrics in person re-identification and database retrieval | |
| CN113780145A (en) | Sperm morphology detection method, sperm morphology detection device, computer equipment and storage medium | |
| CN109448193A (en) | Identity information recognition methods and device | |
| CN112525355A (en) | Image processing method, device and equipment | |
| CN116824311A (en) | Performance detection method, device, equipment and storage medium of crowd analysis algorithm |
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 |