CN111445591A - Conference sign-in method, system, computer equipment and computer readable storage medium - Google Patents
Conference sign-in method, system, computer equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111445591A CN111445591A CN202010174883.3A CN202010174883A CN111445591A CN 111445591 A CN111445591 A CN 111445591A CN 202010174883 A CN202010174883 A CN 202010174883A CN 111445591 A CN111445591 A CN 111445591A
- Authority
- CN
- China
- Prior art keywords
- participants
- conference
- face recognition
- attributes
- information
- 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
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention provides a conference sign-in method, a system, computer equipment and a computer readable storage medium, wherein the conference sign-in method comprises the following steps: acquiring meeting information and declaration information of participants; taking a scene photo of the participant; extracting the face recognition characteristic value in the scene photo, and acquiring the scene photo and the face recognition characteristic value of the matched participant; performing face recognition characteristic value decomposition on the matched face recognition characteristic values of the participants and analyzing to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants; and carrying out statistics on the dimension information, and judging the conference participation degree according to the dimension information and the number of participants. The invention can count the participants who successfully check in through the portrait attribute analysis so as to obtain real and readable data.
Description
Technical Field
The invention relates to the technical field of conference sign-in, in particular to a conference sign-in method, a conference sign-in system, computer equipment and a computer readable storage medium.
Background
In order to count the attendance of the conference, the participants are signed before the general conference starts; in the existing conference sign-in method, the conference staff mostly adopts a mode of swiping a card or signing. If the user swipes the card to sign in, the user can be mixed into a meeting place as long as the card exists no matter what person exists, and the situation of impersonation can occur; if the personnel who need to participate in the conference forget to take the card, the personnel can not enter the conference place; and if the card is lost and a loss of the card is also required, the user experience is very poor. If the signature is adopted for signing, the situation that a person pretends to be the signature can also occur, or the participator can sign on behalf of the person, and the time required for signing is long, so the signing efficiency is very low.
Although conference check-in methods capable of automatically completing check-in and improving check-in efficiency have appeared, for example, chinese patent application, application No. CN201811409191.1 discloses a conference check-in method, apparatus and check-in device, which obtains declaration information of participants; the list information comprises the corresponding relation between the names of the participants and the characteristic images; collecting face images of the participants; matching the face image with the feature image; and if the matching is successful, marking the check-in state of the participant corresponding to the characteristic image as the check-in success. The attendance registration is completed by acquiring declaration information of the participants before the conference begins and screening the identities of the participants who sign in by adopting a face recognition technology. However, the conference check-in method of application No. CN201811409191.1 lacks scientificity and data, and the image analysis of the participants is not possible, so that the value conversion of the conference is low, and a powerful data support cannot be provided.
Disclosure of Invention
The invention aims to provide a conference sign-in method, a conference sign-in system, computer equipment and a computer readable storage medium, which can count participants who sign in successfully through portrait attribute analysis so as to obtain real and readable data.
In order to achieve the purpose, the invention provides a conference sign-in method, which comprises the following steps:
step S10: acquiring meeting information and declaration information of participants;
step S20: taking a scene photo of the participant;
step S30: extracting face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
step S40: performing face recognition characteristic value decomposition on the matched face recognition characteristic values of the participants and analyzing to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants;
step S50: and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
Specifically, the step S10 further includes:
step S110: a preset conference database is established in advance, and conference information is loaded in the preset conference database, wherein the conference information comprises conference subjects, conference time, conference places and conference people;
step S120: loading declaration information of the participants in a preset conference database;
step S130: and detecting the declaration information of the participants to screen the participants meeting the requirements.
Specifically, in step S120, the declaration information of the participant can be loaded in a single addition, a batch addition or a two-dimensional code addition manner, where the declaration information of the participant includes names of the participants, certificate numbers of the participants, mobile phone numbers of the participants, and photos of the participants.
In particular, the detection of step S130 includes photo quality detection and certificate number detection.
Particularly, the photo quality detection comprises detecting whether the background in the photo of the participant meets the face recognition requirement, detecting whether the face direction in the photo of the participant meets the face recognition requirement, detecting whether the light brightness in the photo of the participant meets the face recognition requirement, detecting whether the proportion of the face in the photo of the participant meets the face recognition requirement, and obtaining the primary screening photo through photo quality detection.
Particularly, the certificate numbers of the primary screening photo and the primary screening photo are further subjected to witness comparison, so that the declaration information of the participants meeting the meeting requirements is screened as declaration information of the participants.
Specifically, the step S20 may be to take live photos of the participant at multiple times in the meeting, which are random sampling points or timing sampling points, respectively, for analyzing and obtaining the emotional attribute of the participant.
The invention also provides a conference check-in system, which comprises:
the face input module is used for storing meeting information and declaration information of participants;
the face recognition module is used for taking the scene photos of the participants, extracting the face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
the user attribute analysis module is used for carrying out face recognition characteristic value decomposition on the face recognition characteristic values of the matched participants and analyzing to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants; and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
The invention also provides computer equipment which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the conference check-in method.
The invention further provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the conference check-in method.
The invention can count the participants who successfully check in through the portrait attribute analysis so as to obtain real and readable data, thereby not only providing a powerful data support, but also greatly improving the value conversion of the conference. The scene photos of the participants and the declaration information of the participants are matched and compared to obtain real check-in data, and the user attribute analysis module is used for carrying out portrait analysis on the matched participants to obtain portrait attributes of the participants, so that dimension information can be counted conveniently to obtain readable data. The associated information obtained by the image attribute analysis is obtained by the field photo analysis without being loaded in advance by the registration participant, thereby saving the registration program. In addition, the invention provides a plurality of modes for loading the declaration information of the participants, thereby increasing the convenience of information loading. And detecting the declaration information of the participants so as to automatically screen the participants.
Drawings
FIG. 1 is a flow chart of one embodiment of a conference check-in method of the present invention;
FIG. 2 is a detailed flowchart of step S10 in FIG. 1;
FIG. 3 is a flow chart of another embodiment of a conference check-in method of the present invention;
FIG. 4 is a block diagram of a conference check-in system of the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computer device of the conference check-in method of the present invention.
Reference numerals:
1. conference sign-in system 10, face input module 20 and face recognition module
30. User attribute analysis module 2, computer device 21, memory 22, processor
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a conference sign-in method, which includes the following steps:
step S10: acquiring meeting information and declaration information of participants;
step S20: taking a scene photo of the participant;
step S30: extracting face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
step S40: performing face recognition characteristic value decomposition on the matched face recognition characteristic values of the participants and analyzing to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants;
wherein the analysis process of the gender attribute comprises: reducing the face recognition characteristic value of the participant from a high-dimensional space to a low-dimensional space, calculating to obtain a gender sample of the most similar low-dimensional space, and obtaining gender according to the gender sample;
the analysis process of the emotion attribute comprises the following steps: the face recognition characteristic value is obtained by analyzing and judging the position of the mouth of the face, the opening degree of the mouth and the angle of the mouth in the face recognition characteristic value; the emotional attributes comprise joy, anger, sadness, startle, disgust;
the analysis process of the age attribute is as follows: extracting characteristic values of forehead, canthus and cheek regions from the face recognition characteristic values of the participants, and combining the shape and wrinkles of the face by using a flexible model to obtain the age;
the analysis process of the skin color attribute comprises the following steps: applying image segmentation preprocessing based on skin color information and front face identification verification from the face identification characteristic value of the participant, performing cluster analysis on skin color by using color space characteristics, mapping the skin color to generate a binary image, and then obtaining the skin color according to the shape characteristic of the face;
step S50: and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
Referring to fig. 2, step S10 in fig. 1 further includes:
step S110: a preset conference database is established in advance, and conference information is loaded in the preset conference database, wherein the conference information comprises conference subjects, conference time, conference places and conference people;
step S120: loading declaration information of the participants in a preset conference database;
step S130: and detecting the declaration information of the participants to screen the participants meeting the requirements.
The declaration information of the participant loaded in step S120 includes a plurality of mandatory items, the mandatory items may also form part of dimension information in the portrait attribute of the participant, and in order to save the registration procedure, the mandatory items only set dimension information that cannot be obtained from the live photograph.
In the step S120, the declaration information of the participant can be loaded in a single addition, batch addition or two-dimensional code addition manner, and the declaration information of the participant includes the name of the participant, the certificate number of the participant, the mobile phone number of the participant, and the photo of the participant. The names of the participants, the certificate numbers of the participants and the mobile phone numbers of the participants are the necessary items.
a. Single new mode: inputting names of the participants, certificate numbers of the participants, mobile phone numbers of the participants and photos of the participants;
b. a batch new adding mode: downloading a newly added excel template in batch, and inputting and uploading names of the participants, certificate numbers of the participants, mobile phone numbers of the participants and photos of the participants in batch;
c. two-dimensional code newly increases the mode: the conference participants obtain and recognize the conference participants two-dimensional code, and input personal names, certificate numbers of the conference participants, mobile phone numbers of the conference participants and photos of the conference participants;
the detection of the step S130 includes photo quality detection and certificate number detection.
And (3) photo quality detection: judging whether the quality of the photos of the participants meets the requirement of face recognition by using a living body detection technology, for example, whether the background in the photos of the participants meets the requirement of face recognition, whether the face direction in the photos of the participants meets the requirement of face recognition, whether the light brightness in the photos of the participants meets the requirement of face recognition, and whether the proportion of the faces in the photos of the participants meets the requirement of face recognition; primary screening photographs were obtained by photograph quality testing.
And (3) certificate number detection: and further carrying out witness comparison on the primary screening photo and the certificate number associated with the primary screening photo by using a public security V3 system so as to screen declaration information of the meeting personnel meeting the meeting requirements as declaration information of the meeting personnel.
The analysis process of step S40 includes:
image attribute analysis of gender attribute: reducing the face recognition characteristic value of the participant from a high-dimensional space to a low-dimensional space, calculating to obtain a gender sample of the most similar low-dimensional space, and obtaining gender according to the gender sample; the purpose of determining the gender is that the conference sign-in method can support various conferences, such as product release/marketing and the like, and can directionally analyze the gender characteristics of participants, so that accurate advertisement putting and popularization can be performed during and after the conference, and ineffective popularization is reduced. In step S10, the conference sign-in method of the present invention reduces the number of mandatory items, for example, the gender is not mandatory item, and further obtains the live photos of the participants through step S20, and identifies the gender of the participants through step S40 to complement and improve the portrait attributes of the participants.
Portrait attribute analysis of emotional attributes: analyzing a face characteristic value algorithm, and obtaining whether the mood of the user is happy or sad for the extracted features of the position of the face of the user, the opening degree of the mouth, the angle of the mouth and the like; the traditional conference analysis cannot accurately know the participation degree of participants, the participation degree is mainly analyzed and judged through the emotion attributes, and the emotion attributes can calculate the emotional characteristics such as joy, anger, sadness, startle, disgust and the like. The user attribute analysis module increases the collection of the dimension information of the emotion attribute, so that the host knows the user participation degree from data analysis.
Age attribute profile analysis: when a face characteristic value algorithm is extracted, the shape and wrinkles of a face are organically combined by using a flexible model, characteristic values of the forehead, the canthus, the cheek and other regions are fully extracted, and the age is estimated;
when obtaining the declaration information of the participant in step S10, the age of the participant is not an indispensable item, and the perfect information is further supplemented by face recognition to provide a more definite portrait attribute of the participant. Meanwhile, the statistics of the dimension information of the age characteristics can provide the age distribution of the participants more clearly.
And (3) analyzing the image attribute of the skin color attribute: and when extracting the face characteristic value, performing image segmentation preprocessing and front face identification verification based on skin color information, performing cluster analysis on skin colors by using the color space characteristics, performing skin color mapping in a YCbCr space to generate a binary image, and then confirming the skin colors according to the shape characteristics of the face. And for images under different light rays, distinguishing and distinguishing skin colors through classification optimization of an algorithm neural network.
Image attribute analysis of clothing attributes: and performing feature extraction on the photo by using a trained convolutional neural network for image retrieval, and retrieving clothes with high similarity value so as to distinguish the clothes types of the photo people. The invention can also provide interesting experience matched with the clothing type according to the clothing type, so that the participants can feel better when signing in.
After the analysis of the various attributes is completed, the system automatically carries out data statistics and realizes data readability.
The conference sign-in system carries out data association based on sex, age, emotion, clothing, skin color attribute, combination field, appearance time and associated participants, and finally carries out statistics and outputs the complete portrait of a user, so that a user can accurately judge the multi-dimensional information of the participants based on the information.
The method comprises the steps of obtaining associated information by classifying portrait attributes of participants who successfully check in, wherein the associated information comprises age group distribution conditions and Chinese and western person distribution conditions, and analyzing person personalities and the like according to clothing attributes.
In addition, the declaration information of the successful attendee is compared with the declaration information of the attendee, so that the occupation ratio of the on-site attendee and the attendee can be counted, and the real participation degree of the attendee can be referred by the host.
Referring to fig. 3, the present invention provides a conference sign-in method, which includes the following steps:
step S10: acquiring meeting information and declaration information of participants;
step S12: downloading declaration information of the personnel to be participated as an identification training sample set, wherein the declaration information of the personnel to be participated comprises names of the personnel to be participated, certificate numbers of the personnel to be participated, mobile phone numbers of the personnel to be participated and photos of the personnel to be participated;
step S13: extracting face recognition characteristic values of photos of participants in the recognition training sample set to obtain a first face characteristic value combination;
step S20: taking a scene photo of the participant;
step S32: extracting characteristic values of a face recognition technology from the live photos to obtain second face characteristic values;
step S34: judging whether the second face characteristic value is matched with the first face characteristic value combination, if the second face characteristic value is matched with a certain first face characteristic in the first face characteristic value combination, executing a step S36; if the second face feature value is not matched with any first face feature in the first face feature value combination, executing step S38;
step S36: prompting that the check-in is successful, saving the matched live photo, and then executing the step S40;
step S38: prompting the sign-in failure;
step S40: performing face recognition characteristic value decomposition on the matched face recognition characteristic values of the participants and analyzing to obtain gender attributes, emotion attributes, age attributes and complexion attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants;
step S50: and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
Through the extraction and comparison processing of the face characteristic values, the participants are signed in a face recognition mode, and the phenomenon of pretending to be signed is effectively avoided. And the matched field photos are stored by using the face recognition result, so that the pre-meeting declaration, the mid-meeting recognition and the post-meeting statistics have continuity, and irrelevant information interference is effectively eliminated.
Assuming that the obtained matched participants have 100 persons in common, the post-meeting statistics of the dimension information are as follows,
step S50 is statistically derived from the gender attributes of the participants:
male: 80 persons, women: 20 persons.
Step S50 obtains from the age attributes of the participants:
20-30 years old: 20 persons, 30-40 years old: 51 persons, 40-50 years old: 8 persons, over 50 years old: 21 persons.
Step S50 is obtained according to the skin color attribute statistics of the participants:
black race: 5 persons, white race: 25, yellow race: 70 people.
Step S50 is statistically obtained from the clothing attributes of the participants:
formal western-style clothes: 60 people, leisure western-style clothes: 25 persons, jacket: 10 persons, wind coat: 5 persons.
Step S50 statistically obtains from the emotional attributes of the participants:
happy: 60 people, anger: 15 persons, sadness: 0 person, panic: 0 person, aversion: 25 persons.
The participation degree can be obtained by the proportion of happy persons in the emotion attribute, and the higher the proportion of happy persons in the emotion attribute is, the higher the participation degree is; the lower the proportion of happy persons in the emotional attribute, the lower the degree of participation. The engagement level may be obtained by comparing the set engagement threshold, assuming that the engagement threshold is: 0.5, the emotional attribute statistics obtained 60/100 > 0.5, indicating high engagement. If the dimension information of the emotion attribute is summarized as: happy: 10 people, anger: 25 persons, sadness: 0 person, panic: 0 person, aversion: 65, statistically obtained with emotional attributes 10/100 < 0.5, indicating low engagement.
The engagement degree can also be obtained by weighting the calculated score range according to different emotion attributes, such as happy weight of 5, angry weight of 4, sadness weight of 3, startle weight of 2, aversion weight of 1, and score of happy weight × happy number + angry weight of × angry number + sad weight of × sad number + startle weight of × startle number + aversive weight of × aversion number.
Referring to fig. 4, the present invention provides a conference check-in system 1, which includes:
the face input module 10 is used for storing meeting information and declaration information of participants;
the face recognition module 20 is used for taking the scene photos of the participants, extracting the face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
the user attribute analysis module 30 is used for performing face recognition characteristic value decomposition on the face recognition characteristic values of the matched participants and analyzing the face recognition characteristic values to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants;
wherein the analysis process of the gender attribute comprises: reducing the face recognition characteristic value of the participant from a high-dimensional space to a low-dimensional space, calculating to obtain a gender sample of the most similar low-dimensional space, and obtaining gender according to the gender sample;
the analysis process of the emotion attribute comprises the following steps: the face recognition characteristic value is obtained by analyzing and judging the position of the mouth of the face, the opening degree of the mouth and the angle of the mouth in the face recognition characteristic value; the emotional attributes comprise joy, anger, sadness, startle, disgust;
the analysis process of the age attribute is as follows: extracting characteristic values of forehead, canthus and cheek regions from the face recognition characteristic values of the participants, and combining the shape and wrinkles of the face by using a flexible model to obtain the age;
the analysis process of the skin color attribute comprises the following steps: applying image segmentation preprocessing based on skin color information and front face identification verification from the face identification characteristic value of the participant, performing cluster analysis on skin color by using color space characteristics, mapping the skin color to generate a binary image, and then obtaining the skin color according to the shape characteristic of the face;
and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
The conference information stored by the face input module 10 includes conference subject, conference time, conference place and conference number;
the declaration information of the participants stored in the face entry module 10 includes a plurality of mandatory items, the mandatory items can also form part of dimension information in the portrait attributes of the participants, and in order to save the declaration program, the mandatory items only set dimension information that cannot be obtained from the live photos, for example, the declaration information of the participants includes names of the participants, certificate numbers of the participants, mobile phone numbers of the participants, and photos of the participants, where the names of the participants, the certificate numbers of the participants, and the mobile phone numbers of the participants are mandatory items.
The face input module 10 can load declaration information of the participants through single addition, batch addition or two-dimensional code addition.
a. Single new mode: inputting names of the participants, certificate numbers of the participants, mobile phone numbers of the participants and photos of the participants;
b. a batch new adding mode: downloading a newly added excel template in batch, and inputting and uploading names of the participants, certificate numbers of the participants, mobile phone numbers of the participants and photos of the participants in batch;
c. two-dimensional code newly increases the mode: the participants obtain and recognize the two-dimensional codes of the participants, and input personal names, the certificate numbers of the participants, the mobile phone numbers of the participants and the photos of the participants.
The face input module 10 is further configured to detect declaration information of the participants to screen the participants meeting the requirements, where the detection includes photo quality detection and certificate number detection.
And (3) photo quality detection: judging whether the quality of the photos of the participants meets the requirement of face recognition by using a living body detection technology, for example, whether the background in the photos of the participants meets the requirement of face recognition, whether the face direction in the photos of the participants meets the requirement of face recognition, whether the light brightness in the photos of the participants meets the requirement of face recognition, and whether the proportion of the faces in the photos of the participants meets the requirement of face recognition; primary screening photographs were obtained by photograph quality testing.
And (3) certificate number detection: and further carrying out witness comparison on the primary screening photo and the certificate number associated with the primary screening photo by using a public security V3 system so as to screen declaration information of the meeting personnel meeting the meeting requirements as declaration information of the meeting personnel.
The face recognition module 20 is specifically configured to download declaration information of a meeting attendee as a recognition training sample set; extracting face recognition characteristic values of photos of participants in the recognition training sample set to obtain a first face characteristic value combination; extracting characteristic values of a face recognition technology from the live photos to obtain second face characteristic values; judging whether the second face characteristic value is matched with the first face characteristic value combination, if the second face characteristic value is matched with one first face characteristic in the first face characteristic value combination, prompting that the check-in is successful, and storing a matched field photo; and if the second face characteristic value is not matched with any first face characteristic in the first face characteristic value combination, prompting that the sign-in fails.
The user attribute analysis module 30 obtains portrait attributes of the participant including at least one of gender attributes, mood attributes, age attributes, skin color attributes, or clothing attributes.
Image attribute analysis of gender attribute: reducing a characteristic value high-dimensional image extracted from the face of a participant to a low latitude space by using a face characteristic value algorithm, simultaneously mapping a gender sample trained by the face recognition algorithm to the low latitude space, then calculating a sample most similar to the extracted characteristic value image, assigning the gender of the sample to the image of the participant, and finally determining the gender of the participant; the purpose of determining the gender is that the conference check-in system can support various conferences, such as product release/marketing and the like, and can directionally analyze the gender characteristics of the participants, so that accurate advertisement putting and popularization can be performed during and after the conference, and ineffective popularization is reduced. In the face input module arranged in the conference sign-in system, the number of necessary items is reduced, for example, the gender is not the necessary item, the live photos of the participants are further acquired through the face recognition module, the gender of the participants is recognized through the user attribute analysis module 30, and the portrait attributes of the participants are supplemented and perfected.
Portrait attribute analysis of emotional attributes: analyzing a face characteristic value algorithm, and obtaining whether the mood of the user is happy or sad for the extracted features of the position of the face of the user, the opening degree of the mouth, the angle of the mouth and the like; the traditional conference analysis cannot accurately know the participation degree of participants, the participation degree is mainly analyzed and judged through the emotion attributes, and the emotion attributes can calculate the emotional characteristics such as joy, anger, sadness, startle, disgust and the like. The user attribute analysis module increases the collection of the dimension information of the emotion attribute, so that the host knows the user participation degree from data analysis.
Age attribute profile analysis: when a face characteristic value algorithm is extracted, the shape and wrinkles of a face are organically combined by using a flexible model, characteristic values of the forehead, the canthus, the cheek and other regions are fully extracted, and the age is estimated; the age of the participant is not an indispensable item in the declaration information of the participant, and the complete information is further supplemented by face recognition to provide more definite portrait attributes of the participant. Meanwhile, the statistics of the dimension information of the age characteristics can provide the age distribution of the participants more clearly.
And (3) analyzing the image attribute of the skin color attribute: and when extracting the face characteristic value, performing image segmentation preprocessing and front face identification verification based on skin color information, performing cluster analysis on skin colors by using the color space characteristics, performing skin color mapping in a YCbCr space to generate a binary image, and then confirming the skin colors according to the shape characteristics of the face. And for images under different light rays, distinguishing and distinguishing skin colors through classification optimization of an algorithm neural network.
Image attribute analysis of clothing attributes: and performing feature extraction on the photo by using a trained convolutional neural network for image retrieval, and retrieving clothes with high similarity value so as to distinguish the clothes types of the photo people. The invention can also provide interesting experience matched with the clothing type according to the clothing type, so that the participants can feel better when signing in.
After the analysis of the multiple attributes is completed, the conference check-in system 1 automatically performs the statistics of the dimension information, thereby realizing the readability of the data.
The user attribute analysis module 30 has the core function of providing more capacity for expanding application to a user, and the conference sign-in system carries out data association based on sex, age, emotion, clothing, skin color attribute combination field, appearance time and associated participants, and finally carries out statistics and outputs a complete picture of the user, so that the user can accurately judge multi-dimensional information of the participants based on the information.
The method comprises the steps of obtaining associated information by classifying portrait attributes of participants who successfully check in, wherein the associated information comprises age group distribution conditions and Chinese and western person distribution conditions, and analyzing person personalities and the like according to clothing attributes.
In addition, the declaration information of the successful attendee is compared with the declaration information of the attendee, so that the occupation ratio of the on-site attendee and the attendee can be counted, and the real participation degree of the attendee can be referred by the host.
In conclusion, the invention can count the participants who successfully check in through the portrait attribute analysis so as to obtain real and readable data, thereby not only providing a powerful data support, but also greatly improving the value conversion of the conference. The scene photos of the participants and the declaration information of the participants are matched and compared to obtain real check-in data, and the user attribute analysis module is used for carrying out portrait analysis on the matched participants to obtain portrait attributes of the participants, so that dimension information can be counted conveniently to obtain readable data. The associated information obtained by the image attribute analysis is obtained by the field photo analysis without being loaded in advance by the registration participant, thereby saving the registration program. In addition, the invention provides a plurality of modes for loading the declaration information of the participants, thereby increasing the convenience of information loading. And detecting the declaration information of the participants so as to automatically screen the participants.
Referring to fig. 5, the present invention further provides a computer device 2, where the computer device 2 includes:
a memory 21 for storing executable program code; and
a processor 22 for calling said executable program code in said memory 21, the execution steps including the above-mentioned conference check-in method.
One processor 22 is illustrated in fig. 5.
The memory 21, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the conference check-in method in the embodiments of the present invention. The processor 22 executes various functional applications and data processing of the computer device 2, i.e. implementing the conference check-in method in any of the above-described method embodiments, by running non-volatile software programs, instructions and modules stored in the memory 21.
The memory 21 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store meeting information of a user at the computer device 2, declaration information of the participants, live photographs of the participants, and face recognition feature values. Further, the memory 21 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 21 may optionally include memory 21 located remotely from processor 22, and these remote memories 21 may be connected to conference check-in system 1 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 21 and, when executed by the one or more processors 22, perform a conference check-in method in any of the method embodiments described above, e.g., the programs of fig. 1-3 described above.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
The computer device 2 of the present embodiment exists in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic devices with data interaction functions.
Still another embodiment of the present application provides a non-transitory computer-readable storage medium storing computer-executable instructions for execution by one or more processors, such as one of the processors 22 of fig. 5, to cause the one or more processors 22 to perform a conference check-in method in any of the method embodiments described above, such as to perform the programs of fig. 1-3 described above.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on at least two network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random Access Memory (RAM), or the like.
The sequence numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation method.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A conference check-in method, characterized by comprising the steps of:
step S10: acquiring meeting information and declaration information of participants;
step S20: taking a scene photo of the participant;
step S30: extracting face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
step S40: performing face recognition characteristic value decomposition on the matched face recognition characteristic values of the participants and analyzing to obtain gender attributes, emotion attributes, age attributes and complexion attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants;
step S50: and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
2. The conference check-in method of claim 1, wherein the step S10 further comprises:
step S110: a preset conference database is established in advance, and conference information is loaded in the preset conference database, wherein the conference information comprises conference subjects, conference time, conference places and conference people;
step S120: loading declaration information of the participants in a preset conference database;
step S130: and detecting the declaration information of the participants to screen the participants meeting the requirements.
3. The conference sign-in method according to claim 2, wherein the step S120 is implemented by loading declaration information of the participants through single addition, batch addition or two-dimensional code addition, and the declaration information of the participants includes names of the participants, certificate numbers of the participants, mobile phone numbers of the participants, and photos of the participants.
4. The conference check-in method of claim 3, wherein the detection of the step S130 comprises photo quality detection and certificate number detection.
5. The conference check-in method of claim 4, wherein the photo quality detection comprises detecting whether a background in the photo of the participant meets a face recognition requirement, detecting whether a face direction in the photo of the participant meets the face recognition requirement, detecting whether a light brightness in the photo of the participant meets the face recognition requirement, detecting whether a proportion of a face in the photo of the participant meets the face recognition requirement, and obtaining the primary screening photo through photo quality detection.
6. The conference check-in method of claim 5, wherein the certificate numbers associated with the primary screening photo and the primary screening photo are further subjected to witness comparison to screen declaration information of the participants meeting the meeting requirements as declaration information of the participants.
7. The conference check-in method of claim 6, wherein the step S20 is implemented by taking live photos of the participants at a plurality of moments in the conference, respectively, for analyzing and obtaining emotional attributes of the participants, wherein the moments are random sampling points or timed sampling points.
8. A conference check-in system, comprising:
the face input module is used for storing meeting information and declaration information of participants;
the face recognition module is used for taking the scene photos of the participants, extracting the face recognition characteristic values in the scene photos, comparing whether the face recognition characteristic values of the participants are matched with the declaration information of the participants or not, and acquiring the scene photos and the face recognition characteristic values of the matched participants;
the user attribute analysis module is used for carrying out face recognition characteristic value decomposition on the face recognition characteristic values of the matched participants and analyzing to obtain gender attributes, emotion attributes, age attributes and skin color attributes of the participants; the matched scene photos of the participants are subjected to clothing feature extraction and are analyzed to obtain clothing attributes of the participants; and carrying out dimension information statistics according to the gender attribute, the emotion attribute, the age attribute, the skin color attribute and the clothing attribute of the participants, and judging the conference participation degree according to the dimension information and the participants.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the conference check-in method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the conference check-in method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174883.3A CN111445591A (en) | 2020-03-13 | 2020-03-13 | Conference sign-in method, system, computer equipment and computer readable storage medium |
| PCT/CN2020/134832 WO2021179706A1 (en) | 2020-03-13 | 2020-12-09 | Meeting check-in method and system, computer device, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174883.3A CN111445591A (en) | 2020-03-13 | 2020-03-13 | Conference sign-in method, system, computer equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111445591A true CN111445591A (en) | 2020-07-24 |
Family
ID=71627523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010174883.3A Pending CN111445591A (en) | 2020-03-13 | 2020-03-13 | Conference sign-in method, system, computer equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111445591A (en) |
| WO (1) | WO2021179706A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329638A (en) * | 2020-11-06 | 2021-02-05 | 上海优扬新媒信息技术有限公司 | Image scoring method, device and system |
| CN112396391A (en) * | 2020-11-09 | 2021-02-23 | 上海凌立健康管理股份有限公司 | Off-line training sign-in anti-cheating system |
| CN112396392A (en) * | 2020-11-09 | 2021-02-23 | 上海凌立健康管理股份有限公司 | Off-line training sign-in anti-cheating method |
| WO2021179706A1 (en) * | 2020-03-13 | 2021-09-16 | 平安科技（深圳）有限公司 | Meeting check-in method and system, computer device, and computer readable storage medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140863A (en) * | 2022-01-29 | 2022-03-04 | 深圳市中讯网联科技有限公司 | Sign-in method and device based on face recognition, storage medium and electronic equipment |
| CN114999017A (en) * | 2022-06-06 | 2022-09-02 | 重庆酉辰戌智能科技有限公司 | Campus face identification enabling system |
| CN114882608A (en) * | 2022-06-23 | 2022-08-09 | 淮阴工学院 | Method for improving real-time performance of electronic sign-in |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251898A (en) * | 2008-03-25 | 2008-08-27 | 腾讯科技（深圳）有限公司 | Skin color detection method and apparatus |
| CN101650782A (en) * | 2009-09-16 | 2010-02-17 | 上海电力学院 | Method for extracting front human face outline based on complexion model and shape constraining |
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102324025A (en) * | 2011-09-06 | 2012-01-18 | 北京航空航天大学 | Human face detection and tracking method based on Gaussian skin color model and feature analysis |
| CN103902958A (en) * | 2012-12-28 | 2014-07-02 | 重庆凯泽科技有限公司 | Method for face recognition |
| CN104506562A (en) * | 2015-01-13 | 2015-04-08 | 东北大学 | Two-dimension code and face recognition fused conference identity authentication device and method |
| CN104732602A (en) * | 2015-02-04 | 2015-06-24 | 四川长虹电器股份有限公司 | Attendance checking method based on cloud human face and expression recognition |
| CN108416286A (en) * | 2018-03-02 | 2018-08-17 | 浙江天悦信息技术有限公司 | A kind of robot interactive approach based on real-time video chat scenario |
| CN109614508A (en) * | 2018-12-12 | 2019-04-12 | 杭州知衣科技有限公司 | A kind of image of clothing searching method based on deep learning |
| CN109658040A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the computer storage medium of conference management |
| CN109903411A (en) * | 2019-01-26 | 2019-06-18 | 北方民族大学 | A kind of meeting signature device and application method based on recognition of face |
| CN110072075A (en) * | 2019-04-30 | 2019-07-30 | 平安科技（深圳）有限公司 | Conference management method, system and readable storage medium based on face recognition |
| CN110648186A (en) * | 2018-06-26 | 2020-01-03 | 杭州海康威视数字技术股份有限公司 | Data analysis method, device, equipment and computer readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020030584A1 (en) * | 2000-09-13 | 2002-03-14 | Dore Perler | Biometric access control system with time and attendance data logging and reporting capabilities |
| US9152837B2 (en) * | 2007-06-11 | 2015-10-06 | Jeffrey A. Matos | Apparatus and method for verifying the identity of an author and a person receiving information |
| CN109446880A (en) * | 2018-09-05 | 2019-03-08 | 广州维纳斯家居股份有限公司 | Intelligent subscriber participation evaluation method, device, intelligent elevated table and storage medium |
| CN109522829B (en) * | 2018-11-02 | 2021-10-26 | 南京邮电大学 | Smart phone face-brushing conference registration method based on deep learning |
| CN111445591A (en) * | 2020-03-13 | 2020-07-24 | 平安科技（深圳）有限公司 | Conference sign-in method, system, computer equipment and computer readable storage medium |
-
2020
- 2020-03-13 CN CN202010174883.3A patent/CN111445591A/en active Pending
- 2020-12-09 WO PCT/CN2020/134832 patent/WO2021179706A1/en active Application Filing
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251898A (en) * | 2008-03-25 | 2008-08-27 | 腾讯科技（深圳）有限公司 | Skin color detection method and apparatus |
| CN101650782A (en) * | 2009-09-16 | 2010-02-17 | 上海电力学院 | Method for extracting front human face outline based on complexion model and shape constraining |
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102324025A (en) * | 2011-09-06 | 2012-01-18 | 北京航空航天大学 | Human face detection and tracking method based on Gaussian skin color model and feature analysis |
| CN103902958A (en) * | 2012-12-28 | 2014-07-02 | 重庆凯泽科技有限公司 | Method for face recognition |
| CN104506562A (en) * | 2015-01-13 | 2015-04-08 | 东北大学 | Two-dimension code and face recognition fused conference identity authentication device and method |
| CN104732602A (en) * | 2015-02-04 | 2015-06-24 | 四川长虹电器股份有限公司 | Attendance checking method based on cloud human face and expression recognition |
| CN108416286A (en) * | 2018-03-02 | 2018-08-17 | 浙江天悦信息技术有限公司 | A kind of robot interactive approach based on real-time video chat scenario |
| CN110648186A (en) * | 2018-06-26 | 2020-01-03 | 杭州海康威视数字技术股份有限公司 | Data analysis method, device, equipment and computer readable storage medium |
| CN109658040A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the computer storage medium of conference management |
| CN109614508A (en) * | 2018-12-12 | 2019-04-12 | 杭州知衣科技有限公司 | A kind of image of clothing searching method based on deep learning |
| CN109903411A (en) * | 2019-01-26 | 2019-06-18 | 北方民族大学 | A kind of meeting signature device and application method based on recognition of face |
| CN110072075A (en) * | 2019-04-30 | 2019-07-30 | 平安科技（深圳）有限公司 | Conference management method, system and readable storage medium based on face recognition |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021179706A1 (en) * | 2020-03-13 | 2021-09-16 | 平安科技（深圳）有限公司 | Meeting check-in method and system, computer device, and computer readable storage medium |
| CN112329638A (en) * | 2020-11-06 | 2021-02-05 | 上海优扬新媒信息技术有限公司 | Image scoring method, device and system |
| CN112396391A (en) * | 2020-11-09 | 2021-02-23 | 上海凌立健康管理股份有限公司 | Off-line training sign-in anti-cheating system |
| CN112396392A (en) * | 2020-11-09 | 2021-02-23 | 上海凌立健康管理股份有限公司 | Off-line training sign-in anti-cheating method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021179706A1 (en) | 2021-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445591A (en) | Conference sign-in method, system, computer equipment and computer readable storage medium | |
| CN108960409B (en) | Method and device for generating annotation data and computer-readable storage medium | |
| CN109522815B (en) | Concentration degree evaluation method and device and electronic equipment | |
| CN107633207B (en) | AU characteristic recognition methods, device and storage medium | |
| US20190012450A1 (en) | Biometric-based authentication method, apparatus and system | |
| CN109508694A (en) | A kind of face identification method and identification device | |
| CN107633204A (en) | Face occlusion detection method, apparatus and storage medium | |
| CN112148922A (en) | Conference recording method, conference recording device, data processing device and readable storage medium | |
| CN108681390B (en) | Information interaction method and device, storage medium and electronic device | |
| CN105824799B (en) | A kind of information processing method, equipment and terminal device | |
| CN112733802B (en) | Image occlusion detection method and device, electronic equipment and storage medium | |
| CN107911643B (en) | Method and device for showing scene special effect in video communication | |
| CN109522829B (en) | Smart phone face-brushing conference registration method based on deep learning | |
| CN107633205A (en) | lip motion analysis method, device and storage medium | |
| CN113515988B (en) | Palm print recognition method, feature extraction model training method, device and medium | |
| CN111240482A (en) | Special effect display method and device | |
| CN112150349A (en) | Image processing method and device, computer equipment and storage medium | |
| CN112132099A (en) | Identity recognition method, palm print key point detection model training method and device | |
| CN108399401B (en) | Method and device for detecting face image | |
| CN110245573A (en) | A kind of register method, apparatus and terminal device based on recognition of face | |
| CN112241667A (en) | Image detection method, device, equipment and storage medium | |
| CN112306829A (en) | Method and device for determining performance information, storage medium and terminal | |
| Ríos-Sánchez et al. | gb2sμMOD: A MUltiMODal biometric video database using visible and IR light | |
| Sharma et al. | Sign language gesture recognition | |
| CN107832690B (en) | Face recognition method and related product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40032302 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200724 |
|
| RJ01 | Rejection of invention patent application after publication |