CN116030960A - System and method for analyzing physiological and psychological indexes based on face recognition technology - Google Patents
System and method for analyzing physiological and psychological indexes based on face recognition technology Download PDFInfo
- Publication number
- CN116030960A CN116030960A CN202211657245.2A CN202211657245A CN116030960A CN 116030960 A CN116030960 A CN 116030960A CN 202211657245 A CN202211657245 A CN 202211657245A CN 116030960 A CN116030960 A CN 116030960A
- Authority
- CN
- China
- Prior art keywords
- value
- physiological
- face
- camera
- psychological
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention discloses a physiological and psychological index analysis system and a physiological and psychological index analysis method based on a face recognition technology, wherein the physiological and psychological index analysis method comprises the following steps: when the pressure value of any pressure sensor is not zero, starting the illumination intensity sensor and the camera; whether the illumination intensity value is lower than a set illumination intensity threshold value or not, and if so, starting a light supplementing lamp for supplementing light; the electric push rod moves up and down to drive the camera to move up and down until the image shot by the camera is the front image of the face; the camera shoots face images of the person to be detected with odd frames per second and takes the face images as a group of face images, and shooting is stopped after M seconds are shot; acquiring gray value information of N regions of interest in each frame of face image; calculating to obtain the gray average value of each interested region in each group of face images; the gray average value of each interested region in the M groups of face images related to the physiological/psychological index is input into the corresponding physiological/psychological index neural network model, and the corresponding physiological/psychological index value is output; the right display screen displays the physiological/psychological index value.
Description
Technical Field
The invention relates to the technical field of physiological index/psychological index analysis, in particular to a physiological and psychological index analysis system and method based on a face recognition technology.
Background
In the prior art, the physiological index and psychological index of the person to be tested are generally obtained through measurement in a contact mode, or the psychological index of the person to be tested is obtained through a questionnaire form, so that the physiological and psychological conditions of the person to be tested are estimated. The technology for acquiring the physiological index and the psychological index in a contact manner is inconvenient, the technology for acquiring the psychological index in a questionnaire manner is troublesome in operation and high in subjectivity, and the physiological index and the psychological index of the person to be tested cannot be acquired rapidly, so that the design of a system capable of acquiring the physiological index and the psychological index of the person to be tested in a non-contact manner is particularly important.
Disclosure of Invention
Aiming at the problems and the defects existing in the prior art, the invention provides a physiological and psychological index analysis system and method based on a face recognition technology.
The invention solves the technical problems by the following technical proposal:
the invention provides a physiological and psychological index analysis system based on a face recognition technology, which is characterized by comprising a physiological and psychological index analysis machine and a standing area of a person to be detected, wherein the physiological and psychological index analysis machine comprises a shell, a vertical strip hole is formed in the middle position of the upper part of the shell, a vertical electric push rod is fixed at the lower part of the inner part of the shell, a moving block is fixed at the top of the vertical electric push rod, a camera facing the vertical strip hole is arranged on the moving block, a left display screen and a right display screen are respectively embedded at the upper part of the shell and positioned at the two sides of the vertical strip hole, a light supplementing lamp is respectively embedded at the upper part of the shell and the upper part and the lower part of the vertical strip hole, an illumination intensity sensor is arranged on the shell, a control module is arranged in the shell, the control module comprises a pressure judging module, a camera positioning module, a face recognition module, a blood spectrum analysis module and a model prediction module, and a plurality of pressure sensors are arranged in the standing area of the person to be detected;
any pressure sensor is used for sensing pressure, and the pressure judging module is used for starting the illumination intensity sensor, the camera positioning module and the camera when the pressure value transmitted by any pressure sensor is not zero;
the illumination intensity sensor is used for detecting illumination intensity of the environment where the physiological and psychological index analyzer is located, the camera positioning module is used for judging whether the illumination intensity value is lower than a set illumination intensity threshold value, and if yes, the light supplementing lamp is started to supplement light for the camera, and if no, the light supplementing lamp is not required to be started;
the camera is used for shooting images of a person to be detected, the camera positioning module is used for controlling the push rod end of the electric push rod to move up and down based on the images of the person to be detected so as to drive the camera on the moving block to move up and down, and the electric push rod is controlled to be suspended until the images shot by the camera are images of the front face of the person;
the camera is used for shooting face front images of a person to be detected with the set odd number of frames L per second, transmitting the face images with the set odd number of frames L per second as a group of face images to the face recognition module, and stopping shooting after shooting the set acquisition seconds M, wherein L, M is a positive integer;
the face recognition module is used for positioning a plurality of key points of facial features and outlines of each frame of face image in each group of face images by using a blood spectrum optical imaging technology, extracting gray value information of N interesting regions ROI in the face images according to coordinate information of each key point in the face images, transmitting the gray value information of the N interesting regions ROI in each frame of face images in each group of face images to the blood spectrum analysis module, and the left display screen is used for displaying the N interesting regions ROI in the face images;
the blood spectrum analysis module is used for sequentially receiving gray value information of N interested areas ROI in each frame of face image in each group of face image according to the acquisition time sequence relation, finding out the median value of gray values of the ith interested area ROIi in the L frame of face image in each group of face image, selecting the front j gray values and the rear j gray values corresponding to the median value, calculating the gray average value of the median value, the corresponding front j gray values and the corresponding rear j gray values to be used as the gray average value of the ith interested area ROIi in the group of face image, and further calculating and obtaining the gray average value of the ith interested area ROI in each group of face image, wherein i is a positive integer and is more than or equal to 1 and less than or equal to N, j is a positive integer and 2j+1 is less than L-10;
the model prediction module is used for inputting the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value;
the right display screen is used for displaying the output physiological index value/psychological index value.
Preferably, the upper cover of the vertical long strip hole is provided with a transparent ash blocking cover.
Preferably, the control module further comprises an alarm module, wherein the alarm module is used for judging whether the physiological index value/psychological index value is in the corresponding set physiological index value range/set psychological index value range, if yes, no alarm information is sent out, and if no, the right display screen is controlled to display the alarm information that the physiological index value/psychological index value exceeds the standard.
The invention also provides a physiological and psychological index analysis method based on the face recognition technology, which is characterized by being realized by the physiological and psychological index analysis system, and the physiological and psychological index analysis method comprises the following steps:
s1, any pressure sensor senses pressure, and when the pressure value transmitted by any pressure sensor is received by the pressure judging module and is not zero, the illumination intensity sensor, the camera positioning module and the camera are started;
s2, the illumination intensity sensor detects illumination intensity of the environment where the physiological and psychological index analyzer is located, the camera positioning module judges whether the illumination intensity value is lower than a set illumination intensity threshold value, if yes, a light supplementing lamp is started to supplement light for a camera, and if no, the light supplementing lamp is not required to be started;
s3, the camera shoots an image of the person to be detected, the camera positioning module controls the push rod end of the electric push rod to move up and down based on the image of the person to be detected so as to drive the camera on the moving block to move up and down, and the electric push rod is controlled to be suspended until the image shot by the camera is a face front image;
s4, the camera shoots the face front image of the person to be detected by setting an odd number of frames L per second, the face image with the odd number of frames L per second is used as a group of face images to be transmitted to the face recognition module, shooting is stopped after the shooting is performed by setting the acquisition seconds M, and L, M is a positive integer;
s5, the face recognition module utilizes a blood spectrum optical imaging technology to position a plurality of key points of facial five sense organs and outlines of each frame of face image in each group of face images, extracts gray value information of N interesting areas ROI in the face images according to coordinate information of each key point in the face images, transmits the gray value information of the N interesting areas ROI in each frame of face images in each group of face images to the blood spectrum analysis module, and the left display screen displays the N interesting areas ROI in the face images;
s6, the blood spectrum analysis module sequentially receives gray value information of N interested areas ROI in each frame of face image in each group of face image according to the acquisition time sequence relation, finds out the median value of gray values of the ith interested area ROIi in the L frame of face image in each group of face image, selects the first j gray values and the last j gray values corresponding to the median value, calculates gray average values of the median value, the first j gray values and the last j gray values as gray average values of the ith interested area ROIi in the group of face image, and further calculates and obtains gray average values of the ROI of each interested area in each group of face image, wherein i is a positive integer which is not less than 1 and not more than N, j is a positive integer which is 2j+1 and less than L-10;
s7, the model prediction module inputs the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value;
and S8, displaying the output physiological index value/psychological index value on the right display screen.
On the basis of conforming to the common knowledge in the field, the above preferred conditions can be arbitrarily combined to obtain the preferred examples of the invention.
The invention has the positive progress effects that:
according to the invention, by means of non-contact and continuous measurement through the camera, physiological indexes such as Heart Rate (HRV), respiratory rate, blood pressure (systolic pressure and diastolic pressure) and psychological indexes such as psychological pressure of a person to be measured are rapidly measured in real time by utilizing a face recognition technology, a blood spectrum analysis technology and a model prediction technology, so that the physiological and psychological conditions of the person can be estimated. The system can be applied to a plurality of situations and has the characteristics of portability, portability and quick acquisition.
Drawings
Fig. 1 is a schematic structural diagram of a physiological index analysis system based on face recognition technology according to a preferred embodiment of the present invention.
Fig. 2 is a schematic diagram of a face image according to a preferred embodiment of the present invention.
Fig. 3 is a flowchart of a physiological index analysis method based on face recognition technology according to a preferred embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the present embodiment provides a physiological and psychological index analysis system based on the face recognition technology, which includes a physiological and psychological index analyzer and a standing area 20 of a person to be tested positioned on the ground in front of the physiological and psychological index analyzer.
The physiological and psychological index analyzer comprises a shell 10, a vertical strip hole 11 is formed in the middle position of the upper portion of the shell 10, a transparent ash blocking cover is arranged on the upper cover of the vertical strip hole 11, a vertical electric push rod 12 is fixed to the lower portion in the shell 10, a moving block 13 is fixed to the top of the vertical electric push rod 12, a camera 14 facing the vertical strip hole 11 is fixed to the top of the moving block 13, a left display screen 15 and a right display screen 16 are respectively embedded in the upper portion of the shell 10 and located on two sides of the vertical strip hole 11, a light supplementing lamp 17 is respectively embedded in the upper portion of the shell 10 and located on the upper portion and the lower portion of the vertical strip hole 11, an illumination intensity sensor 18 is arranged on the shell 10, and a control module is arranged in the shell 10 and comprises a pressure judging module, a camera positioning module, a face recognition module, a blood spectrum analysis module, a model prediction module and an alarm module.
The region 20 on which the person to be tested stands is provided with a plurality of pressure sensors 21.
Any of the pressure sensors 21 is used for sensing pressure and transmitting the sensed pressure value to a pressure judging module, and the pressure judging module is used for indicating that a person to be tested stands on the standing area 20 of the person to be tested when the pressure value transmitted by any of the pressure sensors 21 is not zero, and then the illumination intensity sensor 18, the camera positioning module and the camera 14 can be started.
The illumination intensity sensor 18 is used for detecting illumination intensity of the environment where the physiological and psychological index analyzer is located, and transmitting the detected illumination intensity value to the camera positioning module, and the camera positioning module is used for judging whether the illumination intensity value is lower than a set illumination intensity threshold, if yes, the illumination intensity sensor is used for indicating that the ambient light is darker, in order to ensure that the camera can shoot clear images, the light supplementing lamp 17 is turned on to supplement light for the camera 14, and if no, the illumination intensity value is indicated that the ambient light is brighter, and the light supplementing lamp is not required to be turned on for supplementing light.
The camera 14 is used for shooting an image of a person to be detected, the camera positioning module is used for controlling the push rod end of the electric push rod 12 to move up and down based on the image of the person to be detected, so that the camera 14 on the moving block 13 is driven to move up and down along with the image, until the image shot by the camera 14 is a face front image, which indicates that the camera 14 is right on the face of the person to be detected at the moment, and the camera 14 is positioned on the face of the person to be detected, so that the electric push rod 12 is controlled to stop running.
The camera 14 is configured to capture a front face image of a face of a person under test with an odd number of frames L per second (e.g., 35 frames per second), transmit the face image with the odd number of frames L per second as a set of face images to the face recognition module, and stop capturing after capturing an acquisition number of seconds M (e.g., 60 seconds), where L, M is a positive integer.
For example: in this embodiment, the camera 14 shoots 35 frames per second of face frontal images of the person to be detected, so that 35 frames of face images form a group of face images, and the camera 14 stops shooting after shooting for 60 seconds, so as to obtain 60 groups of face images.
The face recognition module is configured to locate a plurality of key points of facial features and contours of each frame of face image in each group of face images by using a blood spectrum optical imaging technology, extract gray value information of N (e.g. 8) interesting regions ROI in the face images according to coordinate information of each key point in the face images, and transmit the gray value information of the N interesting regions ROI in each frame of face images in each group of face images to the blood spectrum analysis module, where the left display screen 15 is configured to display the N interesting regions ROI in the face images (see fig. 2).
The blood spectrum optical imaging Technology (TOI) is based on the semitransparent characteristic of human epidermis, light with different wavelengths penetrates the epidermis to form reflected light at different cortex, the spectral change of the reflected light is caused by the change of hemoglobin content generated by heart pulsation, and the high-definition digital camera can remotely capture the above spectral change of the face, so that the camera in the embodiment is a high-definition digital camera.
The blood spectrum analysis module is used for sequentially receiving gray value information of N interested regions ROI in each frame of face image in each group of face image according to the acquisition time sequence relation, finding out the median value of gray values of the ith interested region ROIi in the L frame of face image in each group of face image, selecting the first j gray values and the last j gray values corresponding to the median value, calculating the gray average value of the median value, the corresponding first j gray values and the corresponding last j gray values to be used as the gray average value of the ith interested region ROIi in the group of face image, and further calculating and obtaining the gray average value of the ith interested region ROI in each group of face image, wherein i is a positive integer, i is not more than 1 and not more than N, j is a positive integer, and 2j+1 is not more than L-10.
For example: in this embodiment, the gray value information of 8 interesting regions ROI in each of 35 frame face images in 60 group face images is sequentially received, the median value of the gray value of the 1 st interesting region ROI1 of 35 frame face images in 1 st group face images is found out from the information (the gray value of the 1 st interesting region ROI1 of 35 frame face images is sorted from small to large, the gray value at 18 th bit is the median value of the gray value of the 1 st interesting region ROI 1), the median value of the gray value of the 2 nd interesting region ROI1 of 35 frame face images, … …, the median value of the gray value of the 8 th interesting region ROI1 of 35 frame face images, and the median value of the gray value of the 1 st interesting region ROI1 of 35 frame face images is found out from the information, and then the median value of the gray value of the 2 nd interesting region ROI1 of 35 frame face images, the median value of the gray value of the 8 th interesting region ROI1 of 35 frame face images, and the median value of the gray value of the 8 th interesting region ROI1 of 35 frame face images can be found out from the median value of 35 th group face images, and the average value of the gray value of 1 of 35 frame face images can be found out from the rest of the 2 group face images.
Selecting the first 10 gray values and the last 10 gray values corresponding to the median of the gray values of the 1 st region of interest ROI1 in the 1 st group of face images, and calculating the gray average value of the median, the first 10 gray values and the last 10 gray values of the median as the gray average value of the 1 st region of interest ROI1 in the 1 st group of face images; … … selecting the first 10 gray values and the last 10 gray values corresponding to the median of the gray values of the 8 th region of interest ROI8 in the 1 st group of face images, and calculating the gray average value of the median, the first 10 gray values and the last 10 gray values of the median as the gray average value of the 8 th region of interest ROI8 in the 1 st group of face images; and by analogy, the gray average value of each region of interest (ROI) in each group of face images can be calculated and obtained.
The model prediction module is used for inputting the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value.
For example: in this embodiment, two regions of interest ROI related to heart rate are ROI1 and ROI2, respectively, the gray average value of 60 regions of interest ROI1 and the gray average value of 60 regions of interest ROI2 corresponding to 60 groups of face images are input into a trained heart rate neural network model, and heart rate values corresponding to the to-be-detected person are output. The heart rate neural network model is trained using pre-prepared samples. Other physiological indicators such as respiratory rate and blood pressure and so on.
In this embodiment, 3 regions of interest ROI related to psychological stress are ROI1, ROI3 and ROI4, respectively, the gray average value of 60 regions of interest ROI1, the gray average value of 60 regions of interest ROI3 and the gray average value of 60 regions of interest ROI4 corresponding to 60 groups of face images are input into the trained psychological stress neural network model, and psychological stress values corresponding to the testee are output. The psychological stress neural network model is trained by using a pre-prepared sample. Other psychological indicators such as fatigue status, etc. are analogized.
The right display screen 16 is used for displaying the output physiological/psychological index value.
The alarm module is used for judging whether the physiological index value/psychological index value is in the corresponding set physiological index value range/psychological index value range, if yes, no alarm information is sent out, and if no, the right display screen is controlled to display the alarm information that the physiological index value/psychological index value exceeds the standard.
As shown in fig. 3, the present embodiment further provides a physiological and psychological index analysis method based on a face recognition technology, which is implemented by using the physiological and psychological index analysis system, and the physiological and psychological index analysis method includes the following steps:
in step 1, any pressure sensor 21 senses pressure, and the pressure judging module starts the illumination intensity sensor 18, the camera positioning module and the camera 14 when the pressure value transmitted by any pressure sensor 21 is not zero.
And 2, the illumination intensity sensor 18 detects the illumination intensity of the environment where the physiological and psychological index analyzer is located, the camera positioning module judges whether the illumination intensity value is lower than a set illumination intensity threshold value, if yes, the light supplementing lamp 17 is started to supplement light for the camera, and if no, the light supplementing lamp 17 is not required to be started.
And 3, the camera 14 shoots images of the person to be detected, and the camera positioning module controls the push rod end of the electric push rod 12 to move up and down based on the images of the person to be detected so as to drive the camera 14 on the moving block 13 to move up and down, and controls the electric push rod 12 to pause until the images shot by the camera 14 are images of the front face of the person.
And 4, the camera 14 shoots the face front image of the person to be detected with the set odd number of frames L per second, and transmits the face image with the set odd number of frames L per second as a group of face images to the face recognition module, and stops shooting after shooting the set acquisition seconds M, wherein L, M is a positive integer.
And 5, the face recognition module performs positioning of a plurality of key points of facial features and outlines on each frame of face image in each group of face images by using a blood spectrum optical imaging technology, extracts gray value information of N interesting regions ROI in the face images according to coordinate information of each key point in the face images, transmits the gray value information of the N interesting regions ROI in each frame of face images in each group of face images to the blood spectrum analysis module, and the left display screen 15 displays the N interesting regions ROI in the face images.
And 6, sequentially receiving gray value information of N interested regions ROI in each frame of face image in each group of face image by the blood spectrum analysis module according to the acquisition time sequence relation, finding out the median value of gray values of the ith interested region ROIi in the L frame of face image in each group of face image, selecting the first j gray values and the last j gray values corresponding to the median value, calculating the gray average value of the median value, the corresponding first j gray values and the corresponding last j gray values to be used as the gray average value of the ith interested region ROIi in the group of face image, and further calculating and obtaining the gray average value of the ROI of each interested region in each group of face image, wherein i is a positive integer which is not less than 1 and not more than N, j is a positive integer which is 2j+1 and less than L-10.
And 7, the model prediction module inputs the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value.
And 8, displaying the output physiological index value/psychological index value on the right display screen 16.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.
Claims (4)
1. The physiological and psychological index analysis system based on the face recognition technology is characterized by comprising a physiological and psychological index analysis machine and a standing area of a person to be detected, wherein the physiological and psychological index analysis machine comprises a shell, a vertical strip hole is formed in the middle position of the upper portion of the shell, a vertical electric push rod is fixed at the lower portion of the interior of the shell, a moving block is fixed at the top of the vertical electric push rod, a camera facing the vertical strip hole is arranged on the moving block, a left display screen and a right display screen are respectively embedded in the upper portion of the shell and positioned on two sides of the vertical strip hole, light supplementing lamps are respectively embedded in the upper portion of the shell and positioned above and below the vertical strip hole, an illumination intensity sensor is arranged on the shell, a control module is arranged in the shell, and comprises a pressure judging module, a camera positioning module, a face recognition module, a blood spectrum analysis module and a model prediction module, and a plurality of pressure sensors are distributed in the standing area of the person to be detected;
any pressure sensor is used for sensing pressure, and the pressure judging module is used for starting the illumination intensity sensor, the camera positioning module and the camera when the pressure value transmitted by any pressure sensor is not zero;
the illumination intensity sensor is used for detecting illumination intensity of the environment where the physiological and psychological index analyzer is located, the camera positioning module is used for judging whether the illumination intensity value is lower than a set illumination intensity threshold value, and if yes, the light supplementing lamp is started to supplement light for the camera, and if no, the light supplementing lamp is not required to be started;
the camera is used for shooting images of a person to be detected, the camera positioning module is used for controlling the push rod end of the electric push rod to move up and down based on the images of the person to be detected so as to drive the camera on the moving block to move up and down, and the electric push rod is controlled to be suspended until the images shot by the camera are images of the front face of the person;
the camera is used for shooting face front images of a person to be detected with the set odd number of frames L per second, transmitting the face images with the set odd number of frames L per second as a group of face images to the face recognition module, and stopping shooting after shooting the set acquisition seconds M, wherein L, M is a positive integer;
the face recognition module is used for positioning a plurality of key points of facial features and outlines of each frame of face image in each group of face images by using a blood spectrum optical imaging technology, extracting gray value information of N interesting regions ROI in the face images according to coordinate information of each key point in the face images, transmitting the gray value information of the N interesting regions ROI in each frame of face images in each group of face images to the blood spectrum analysis module, and the left display screen is used for displaying the N interesting regions ROI in the face images;
the blood spectrum analysis module is used for sequentially receiving gray value information of N interested areas ROI in each frame of face image in each group of face image according to the acquisition time sequence relation, finding out the median value of gray values of the ith interested area ROIi in the L frame of face image in each group of face image, selecting the front j gray values and the rear j gray values corresponding to the median value, calculating the gray average value of the median value, the corresponding front j gray values and the corresponding rear j gray values to be used as the gray average value of the ith interested area ROIi in the group of face image, and further calculating and obtaining the gray average value of the ith interested area ROI in each group of face image, wherein i is a positive integer and is more than or equal to 1 and less than or equal to N, j is a positive integer and 2j+1 is less than L-10;
the model prediction module is used for inputting the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value;
the right display screen is used for displaying the output physiological index value/psychological index value.
2. The system for analyzing physiological and psychological indexes based on the face recognition technology according to claim 1, wherein the upper cover of the vertical long strip hole is provided with a transparent ash blocking cover.
3. The system for analyzing physiological and psychological indexes based on the face recognition technology according to claim 1, wherein the control module further comprises an alarm module, the alarm module is used for judging whether the physiological index value/psychological index value is in the corresponding set physiological index value range/psychological index value range, if yes, no alarm information is sent out, and if no, the right display screen is controlled to display the alarm information that the physiological index value/psychological index value exceeds the standard.
4. A physiological and psychological index analysis method based on face recognition technology, which is characterized in that the method is realized by the physiological and psychological index analysis system according to claim 1, and the physiological and psychological index analysis method comprises the following steps:
s1, any pressure sensor senses pressure, and when the pressure value transmitted by any pressure sensor is received by the pressure judging module and is not zero, the illumination intensity sensor, the camera positioning module and the camera are started;
s2, the illumination intensity sensor detects illumination intensity of the environment where the physiological and psychological index analyzer is located, the camera positioning module judges whether the illumination intensity value is lower than a set illumination intensity threshold value, if yes, a light supplementing lamp is started to supplement light for a camera, and if no, the light supplementing lamp is not required to be started;
s3, the camera shoots an image of the person to be detected, the camera positioning module controls the push rod end of the electric push rod to move up and down based on the image of the person to be detected so as to drive the camera on the moving block to move up and down, and the electric push rod is controlled to be suspended until the image shot by the camera is a face front image;
s4, the camera shoots the face front image of the person to be detected by setting an odd number of frames L per second, the face image with the odd number of frames L per second is used as a group of face images to be transmitted to the face recognition module, shooting is stopped after the shooting is performed by setting the acquisition seconds M, and L, M is a positive integer;
s5, the face recognition module utilizes a blood spectrum optical imaging technology to position a plurality of key points of facial five sense organs and outlines of each frame of face image in each group of face images, extracts gray value information of N interesting areas ROI in the face images according to coordinate information of each key point in the face images, transmits the gray value information of the N interesting areas ROI in each frame of face images in each group of face images to the blood spectrum analysis module, and the left display screen displays the N interesting areas ROI in the face images;
s6, the blood spectrum analysis module sequentially receives gray value information of N interested areas ROI in each frame of face image in each group of face image according to the acquisition time sequence relation, finds out the median value of gray values of the ith interested area ROIi in the L frame of face image in each group of face image, selects the first j gray values and the last j gray values corresponding to the median value, calculates gray average values of the median value, the first j gray values and the last j gray values as gray average values of the ith interested area ROIi in the group of face image, and further calculates and obtains gray average values of the ROI of each interested area in each group of face image, wherein i is a positive integer which is not less than 1 and not more than N, j is a positive integer which is 2j+1 and less than L-10;
s7, the model prediction module inputs the gray average value of each region of interest ROI in the M groups of face images related to the physiological index/psychological index into the correspondingly trained physiological index neural network model/psychological index neural network model based on the correlation relation between the physiological index/psychological index and the region of interest ROI so as to output the corresponding physiological index value/psychological index value;
and S8, displaying the output physiological index value/psychological index value on the right display screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657245.2A CN116030960A (en) | 2022-12-22 | 2022-12-22 | System and method for analyzing physiological and psychological indexes based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657245.2A CN116030960A (en) | 2022-12-22 | 2022-12-22 | System and method for analyzing physiological and psychological indexes based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116030960A true CN116030960A (en) | 2023-04-28 |
Family
ID=86072462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211657245.2A Pending CN116030960A (en) | 2022-12-22 | 2022-12-22 | System and method for analyzing physiological and psychological indexes based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030960A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019115561A (en) * | 2017-12-27 | 2019-07-18 | 国立大学法人滋賀医科大学 | Psychological state determination method, determination device, determination system, and determination program |
| CN110620879A (en) * | 2019-10-10 | 2019-12-27 | 武汉普利商用机器有限公司 | Dynamic light supplementing device and method for face recognition |
| CN110693508A (en) * | 2019-09-02 | 2020-01-17 | 中国航天员科研训练中心 | Multi-channel cooperative psychophysiological active sensing method and service robot |
| CN110729047A (en) * | 2019-09-06 | 2020-01-24 | 杭州中威电子股份有限公司 | Device and method for combining psychophysiological analysis and scale test based on face video |
| CN111166302A (en) * | 2019-12-25 | 2020-05-19 | 杭州中威电子股份有限公司 | Device and method for monitoring physiological indexes in real time in non-contact manner |
| CN111212203A (en) * | 2019-12-26 | 2020-05-29 | 中国科学院自动化研究所 | Self-adaptive face detection and recognition device |
| CN111839489A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact physiological and psychological health detection system |
| WO2021022599A1 (en) * | 2019-08-07 | 2021-02-11 | 杭州泽铭睿股权投资有限公司 | Infant monitoring camera capable of detecting heartbeat and respiration of infant |
| CN115317304A (en) * | 2022-07-28 | 2022-11-11 | 瑞多（上海）智能科技有限公司 | Intelligent massage method and system based on physiological characteristic detection |
-
2022
- 2022-12-22 CN CN202211657245.2A patent/CN116030960A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019115561A (en) * | 2017-12-27 | 2019-07-18 | 国立大学法人滋賀医科大学 | Psychological state determination method, determination device, determination system, and determination program |
| WO2021022599A1 (en) * | 2019-08-07 | 2021-02-11 | 杭州泽铭睿股权投资有限公司 | Infant monitoring camera capable of detecting heartbeat and respiration of infant |
| CN110693508A (en) * | 2019-09-02 | 2020-01-17 | 中国航天员科研训练中心 | Multi-channel cooperative psychophysiological active sensing method and service robot |
| CN110729047A (en) * | 2019-09-06 | 2020-01-24 | 杭州中威电子股份有限公司 | Device and method for combining psychophysiological analysis and scale test based on face video |
| CN110620879A (en) * | 2019-10-10 | 2019-12-27 | 武汉普利商用机器有限公司 | Dynamic light supplementing device and method for face recognition |
| CN111166302A (en) * | 2019-12-25 | 2020-05-19 | 杭州中威电子股份有限公司 | Device and method for monitoring physiological indexes in real time in non-contact manner |
| CN111212203A (en) * | 2019-12-26 | 2020-05-29 | 中国科学院自动化研究所 | Self-adaptive face detection and recognition device |
| CN111839489A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact physiological and psychological health detection system |
| CN115317304A (en) * | 2022-07-28 | 2022-11-11 | 瑞多（上海）智能科技有限公司 | Intelligent massage method and system based on physiological characteristic detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105050492B (en) | For determining the device and method of the vital sign of object | |
| CN106580294B (en) | Physiological signal remote monitoring system based on multi-mode imaging technology and application | |
| CN102499664B (en) | Video-image-based method and system for detecting non-contact vital sign | |
| US10004410B2 (en) | System and methods for measuring physiological parameters | |
| JP6521845B2 (en) | Device and method for measuring periodic fluctuation linked to heart beat | |
| CN109890274A (en) | For determining the equipment, system and method for the core temperature of object | |
| CN108701357A (en) | Equipment, system and method for skin detection | |
| CN106999116A (en) | Apparatus and method for skin detection | |
| EP1587414B1 (en) | A pupilometer | |
| CN105979861A (en) | Device, system and method for determining vital signs of a subject based on reflected and transmitted light | |
| CN111128382A (en) | Artificial intelligence multimode imaging analytical equipment | |
| Jeanne et al. | Camera-based heart rate monitoring in highly dynamic light conditions | |
| CN106821324A (en) | A kind of lingual diagnosis auxiliary medical system based on lingual surface and sublingual comprehensive analysis | |
| Przybyło | A deep learning approach for remote heart rate estimation | |
| CN116030960A (en) | System and method for analyzing physiological and psychological indexes based on face recognition technology | |
| JP5399777B2 (en) | Blink measurement device and blink measurement method | |
| US20240138692A1 (en) | Method and system for heart rate extraction from rgb images | |
| US20160210746A1 (en) | Organ imaging device | |
| CN114494299A (en) | Temperature detection device | |
| Khurshid et al. | Image processing to quantitate hemoglobin level for diagnostic support | |
| US20160242678A1 (en) | Organ image photographing apparatus | |
| WO2017154477A1 (en) | Pulse estimating device, pulse estimating system, and pulse estimating method | |
| Lewis et al. | Novel algorithms to monitor continuous cardiac activity with a video camera | |
| CN108939409A (en) | Cloud computing type speed modification method | |
| CN114209299B (en) | IPPG technology-based human physiological parameter detection channel selection method |
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 |