CN111887867A - Method and system for analyzing character formation based on expression recognition and psychological test - Google Patents
Method and system for analyzing character formation based on expression recognition and psychological test Download PDFInfo
- Publication number
- CN111887867A CN111887867A CN202010661664.8A CN202010661664A CN111887867A CN 111887867 A CN111887867 A CN 111887867A CN 202010661664 A CN202010661664 A CN 202010661664A CN 111887867 A CN111887867 A CN 111887867A
- Authority
- CN
- China
- Prior art keywords
- character
- module
- psychological
- testee
- facial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Human Computer Interaction (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Ophthalmology & Optometry (AREA)
- Computational Linguistics (AREA)
- Child & Adolescent Psychology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
Abstract
The invention belongs to the technical field of character analysis, and discloses a character analysis method and system based on expression recognition and psychological test generation, wherein the character analysis system based on expression recognition and psychological test generation comprises the following steps: the facial image recognition system comprises a facial image acquisition module, an identity information acquisition module, a main control module, an image feature extraction module, a facial expression recognition module, a psychological evaluation module, a character prediction module, an analysis module and a display module. The psychological evaluation module can comprehensively analyze the psychological activity change of the testee according to the eye movement data recorded by analysis, so that real and effective psychological evaluation data are obtained; meanwhile, the personality prediction module can conveniently, quickly and accurately judge the personality type of the testee only through one face image of the testee, so that the efficiency and the precision of personality prediction are improved, and the prediction result can objectively reflect the real personality of the testee without depending on professional judgment of experts and a specific personality test questionnaire.
Description
Technical Field
The invention belongs to the technical field of character analysis, and particularly relates to a character analysis method and system based on expression recognition and psychological test.
Background
The personality is a stable attitude of a person to reality and personality characteristics expressed in a habituated behavior mode corresponding to the attitude. Once formed, the character is relatively stable, but not permanent, but rather plastic. The character is different from the temperament, the social attribute of the personality is reflected more, and the core of the personality difference among individuals is the character difference. However, the existing analysis method based on expression recognition and psychology test generation character can not really and effectively obtain the psychological state data of the testee; meanwhile, the accuracy of the character evaluation result obtained through the questionnaire is low, only a plurality of common characters can be usually judged, the character classification is not fine enough, the requirements of different services on character subdivision cannot be met, and the answer of the questionnaire can be controlled consciously by the tested person, so that the questionnaire cannot reflect the true character of the tested person.
In summary, the problems of the prior art are as follows: the existing analysis method for generating the character based on expression recognition and psychological test cannot really and effectively obtain the psychological state data of a testee; meanwhile, the accuracy of the character evaluation result obtained through the questionnaire is low, only a plurality of common characters can be usually judged, the character classification is not fine enough, the requirements of different services on character subdivision cannot be met, and the answer of the questionnaire can be controlled consciously by the tested person, so that the questionnaire cannot reflect the true character of the tested person.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for analyzing a generated character based on expression recognition and psychological test.
The invention is realized in such a way that the analysis method for generating the character based on the expression recognition and the psychological test comprises the following steps:
the method comprises the following steps that firstly, a facial image acquisition module acquires a facial image of a testee by using a camera; the information of the name, age, academic calendar, work and the like of the testee is acquired through an identity information acquisition module;
step two, the main control module obtains the facial image of the testee obtained in the step one by an image feature extraction module through an image extraction program; preprocessing the obtained face image, namely converting the face image into a gray image;
processing the gray level image obtained in the step two, and extracting facial image features; identifying facial expressions according to the extracted facial image features by using a facial expression identification module through an identification program; meanwhile, basic information, emotion information and position information of a name and a head portrait picture of the testee are obtained through a psychological evaluation module by using an evaluation program; establishing a perfect psychological assessment questionnaire database, generating different assessment questionnaires aiming at different test purposes, performing questionnaire test on a tested person, and generating a corresponding questionnaire assessment analysis report according to a test result;
step four, acquiring basic information of the tested person according to the data of the questionnaire evaluation analysis report obtained in the step three, establishing a psychological evaluation model based on the sex, age group, psychology, intelligence, cognition and other related information of the tested person, and performing psychological evaluation by utilizing the established psychological evaluation model;
generating different virtual setting scenes based on the psychological evaluation model obtained in the fourth step, matching the scenes of the testee according to the questionnaire evaluation analysis report, performing psychological test, tracking the sight of the testee, collecting the eye movement data of the testee, monitoring the data change of the physiological index of the testee, and importing the eye movement data and the physiological index test data into a test system to generate a corresponding eye movement data and physiological index test data curve;
step six, acquiring the related information and the face image of the testee obtained in the step one by using a character prediction module, and acquiring the instant physiological information, the psychological information, the intelligence information and the cognitive information of the testee by using a prediction program;
step seven, inputting the acquired face image information of the testee into a pre-trained first character evaluation model based on a convolutional neural network, extracting a feature map of the face picture of the testee through the first character evaluation model, and obtaining a first character evaluation result corresponding to the face picture of the testee according to the feature map and a preset corresponding relation between the feature map and character dimensions;
step eight, acquiring the facial feature vector of the tested person extracted in the step three, and determining a second character evaluation result corresponding to the facial picture of the tested person according to the facial feature vector and the corresponding relation between a preset facial feature dimension set and character dimensions; fusing the first personality evaluation result and the second personality evaluation result to obtain a personality prediction result;
step nine, based on the character prediction result obtained in the step eight, comprehensively analyzing the character of the testee by an analysis module by utilizing an analysis program; and simultaneously, the display module is used for displaying the acquired facial image, the identity information, the expression recognition result, the psychological evaluation result, the character prediction result and the comprehensive analysis result of the testee by utilizing the display.
Further, in the third step, the questionnaire test comprises a social adaptation ability test, a mental health state test, a compression resistance ability test, an intelligence test, a self-consciousness test, a temperament test and an emotion test.
Further, in step five, the gaze tracking includes: and acquiring and analyzing the pupil image by adopting an infrared camera shooting and capturing mode.
Further, the fifth step further includes:
(3.1) acquiring galvanic skin response data, and generating a corresponding change curve based on a virtual setting scene; acquiring brain wave change data, and generating a corresponding change curve based on a virtual setting scene; acquiring chest and abdomen respiratory frequency data, and generating a corresponding change curve based on a virtual setting scene; acquiring pulse beating frequency and blood pressure change data, and generating a corresponding change curve based on a virtual setting scene;
and (3.2) importing the eye movement data and the physiological index test data curve into a test system for analysis, generating a comprehensive evaluation report, and generating a solution for the adverse psychological state in the psychological evaluation.
Further, in the seventh step, the training method of the first character evaluation model includes:
obtaining face pictures and character attributes of testees of a plurality of testees, and labeling the corresponding face pictures of the testees according to the character attributes to obtain sample data, wherein the character attributes comprise scores of the testees in a plurality of character dimensions;
inputting the sample data into a first convolution neural network by taking the sample data as a training set;
calculating a difference value between an output result of the first convolutional neural network and a pre-labeled character attribute through a loss function;
if the difference value is larger than a preset expected value, optimizing the weight parameter of the first convolution neural network by adopting an optimization algorithm;
and continuing to train the optimized first convolution neural network by using the training set until the difference value obtained by calculating the loss function is converged.
Further, in step eight, the determining a second personality evaluation result corresponding to the face picture of the subject according to the facial feature vector and a corresponding relationship between a preset facial feature dimension set and a personality dimension includes:
and inputting the facial feature vector into a preset character classifier to obtain a second character judgment result corresponding to the face picture of the testee, wherein the second character judgment result is used for indicating the probability of the face picture of the testee on each preset character dimension.
Further, the determining a second personality evaluation result corresponding to the face picture of the subject according to the facial feature vector and the corresponding relationship between the preset facial feature dimension set and the personality dimensions further includes:
determining the influence value of each dimension value in the facial feature vector on each character dimension according to a preset matching rule;
and fusing the influence scores of the values of all dimensions in the facial feature vector on all character dimensions to determine a second character judgment result corresponding to the face picture of the tested person, wherein the second character judgment result is used for indicating the scores of the face picture of the tested person on the preset all character dimensions.
Another object of the present invention is to provide an analysis system for generating a character based on facial expression recognition and psychological test, which implements the analysis method for generating a character based on facial expression recognition and psychological test, the analysis system comprising:
the facial image analysis system comprises a facial image acquisition module, an identity information acquisition module, a main control module, an image feature extraction module, a facial expression recognition module, a psychological evaluation module, a character prediction module, an analysis module and a display module;
the facial image acquisition module is connected with the main control module and is used for acquiring a facial image of the testee through the camera;
the identity information acquisition module is connected with the main control module and is used for acquiring information such as the name, age, academic calendar, work and the like of the testee;
the main control module is connected with the facial image acquisition module, the identity information acquisition module, the image feature extraction module, the facial expression recognition module, the psychological evaluation module, the character prediction module, the analysis module and the display module and is used for controlling the normal work of each module through a host;
the image feature extraction module is connected with the main control module and used for extracting facial image features through an image extraction program;
the facial expression recognition module is connected with the main control module and used for recognizing facial expressions according to facial image features through a recognition program;
the psychological evaluation module is connected with the main control module and used for evaluating the psychology of the testee through an evaluation program;
the character prediction module is connected with the main control module and used for predicting character characteristics of the testee according to the facial expression and the psychological state through a prediction program;
the analysis module is connected with the main control module and is used for comprehensively analyzing the character of the testee through an analysis program;
and the display module is connected with the main control module and used for displaying the collected facial image, the identity information, the expression recognition result, the psychological evaluation result, the character prediction result and the comprehensive analysis result of the testee through the display.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing said method for generating a personality analysis based on facial expression recognition and psychological testing when executed on an electronic device.
It is another object of the present invention to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method for generating a personality analysis based on facial expression recognition and psychological testing.
The invention has the advantages and positive effects that: the invention utilizes scientific, objective and standard measuring means to measure, analyze and evaluate the specific psychological quality of a person through a psychological evaluation module, establishes a psychological evaluation model aiming at the basic information of the tested person, utilizes eye movement data and related physiological index parameters to analyze and evaluate in the model, leads the eye movement data and the physiological index test data curve into a test system to analyze, generates a comprehensive evaluation report, generates a solution for the adverse psychological state in the psychological evaluation, and can comprehensively analyze the psychological activity change of the tested person according to the eye movement data recorded by analysis, thereby obtaining real and effective psychological evaluation data; meanwhile, the personality prediction module integrates technologies such as a convolutional neural network and facial feature extraction, the personality type of the testee can be conveniently, quickly and accurately judged only through one face image of the testee, the efficiency and the precision of personality prediction are improved, and the fact that the expert judges professionally and a specific personality test questionnaire are not relied on is not relied on, so that the prediction result can objectively reflect the real personality of the testee.
Drawings
Fig. 1 is a flowchart of an analysis method for generating a character based on expression recognition and psychological tests according to an embodiment of the present invention.
Fig. 2 is a block diagram of an analysis system for generating a character based on expression recognition and psychological testing according to an embodiment of the present invention.
Fig. 3 is a flowchart of a psychological assessment module 6 assessment method according to an embodiment of the present invention.
FIG. 4 is a flowchart of a method for providing data of physiological indicators according to an embodiment of the present invention.
Fig. 5 is a flowchart of a prediction method of the character prediction module 7 according to an embodiment of the present invention.
In fig. 2: 1. a facial image acquisition module; 2. an identity information acquisition module; 3. a main control module; 4. an image feature extraction module; 5. a facial expression recognition module; 6. a psychological evaluation module; 7. a personality prediction module; 8. an analysis module; 9. and a display module.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for analyzing the generated character based on the expression recognition and the psychological test provided by the embodiment of the present invention includes the following steps:
s101, acquiring a facial image of a testee by using a camera through a facial image acquisition module; the information of the name, age, academic calendar, work and the like of the testee is acquired through an identity information acquisition module;
s102, the main control module extracts facial image features through an image feature extraction module by using an image extraction program; identifying facial expressions according to facial image features by using an identification program through a facial expression identification module;
s103, evaluating the psychology of the tested person by utilizing an evaluation program through a psychology evaluation module; predicting the character characteristics of the testee according to the facial expression and the psychological state by using a character prediction module through a prediction program; comprehensively analyzing the character of the testee by using an analysis program through an analysis module;
and S104, displaying the collected facial image, identity information, expression recognition result, psychological evaluation result, character prediction result and comprehensive analysis result of the testee by using the display through the display module.
As shown in fig. 2, an analysis system for generating a character based on expression recognition and psychological test according to an embodiment of the present invention includes: the facial image evaluation system comprises a facial image acquisition module 1, an identity information acquisition module 2, a main control module 3, an image feature extraction module 4, a facial expression recognition module 5, a psychological evaluation module 6, a character prediction module 7, an analysis module 8 and a display module 9.
The facial image acquisition module 1 is connected with the main control module 3 and is used for acquiring a facial image of a testee through a camera;
the identity information acquisition module 2 is connected with the main control module 3 and is used for acquiring information such as the name, age, academic calendar, work and the like of the testee;
the main control module 3 is connected with the facial image acquisition module 1, the identity information acquisition module 2, the image feature extraction module 4, the facial expression recognition module 5, the psychological evaluation module 6, the character prediction module 7, the analysis module 8 and the display module 9 and is used for controlling the normal work of each module through a host;
the image feature extraction module 4 is connected with the main control module 3 and is used for extracting facial image features through an image extraction program;
the facial expression recognition module 5 is connected with the main control module 3 and used for recognizing facial expressions according to facial image features through a recognition program;
the psychological evaluation module 6 is connected with the main control module 3 and is used for evaluating the psychology of the testee through an evaluation program;
the character prediction module 7 is connected with the main control module 3 and used for predicting the character characteristics of the testee according to the facial expression and the psychological state through a prediction program;
the analysis module 8 is connected with the main control module 3 and is used for comprehensively analyzing the character of the testee through an analysis program;
and the display module 9 is connected with the main control module 3 and used for displaying the collected facial image, the identity information, the expression recognition result, the psychological evaluation result, the character prediction result and the comprehensive analysis result of the testee through a display.
The technical solution of the present invention is further illustrated by the following specific examples.
Example 1
The analysis method for generating the character based on expression recognition and psychological test provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 3, the psychological evaluation method provided by the embodiment of the invention is as follows:
s201, acquiring basic information, emotion information and position information of a testee; wherein the basic information at least comprises the name and the head portrait picture of the monitored object; establishing a perfect psychological assessment questionnaire database, generating different assessment questionnaires aiming at different test purposes, performing questionnaire test on a tested person, and generating a corresponding questionnaire assessment analysis report according to a test result;
s202, aiming at the data of the questionnaire evaluation analysis report, obtaining basic information of a tested person, establishing a psychological evaluation model based on the information of the tested person such as sex, age group, psychology, intelligence, cognition and the like, and carrying out psychological evaluation in the model;
s203, generating different virtual setting scenes based on a psychological evaluation model, matching scenes of a testee according to a questionnaire evaluation analysis report, performing psychological test, tracking the sight of the testee, collecting eye movement data of the testee, monitoring the data change of physiological indexes of the testee, and importing the eye movement data and the physiological indexes into a test system to generate corresponding eye movement data and physiological index test data curves;
as shown in fig. 4, the data of the physiological indexes provided by the embodiment of the present invention specifically include:
s301, acquiring galvanic skin response data, and generating a corresponding change curve based on a virtual setting scene; acquiring brain wave change data, and generating a corresponding change curve based on a virtual setting scene; acquiring chest and abdomen respiratory frequency data, and generating a corresponding change curve based on a virtual setting scene; acquiring pulse beating frequency and blood pressure change data, and generating a corresponding change curve based on a virtual setting scene;
s302, the eye movement data and the physiological index test data curve are led into a test system to be analyzed, a comprehensive evaluation report is generated, and a solution is generated for the adverse psychological state in the psychological evaluation.
The questionnaire test provided by the embodiment of the invention comprises a social adaptation ability test, a mental health state test, a pressure resistance ability test, an intelligence test, a self-consciousness test, a temperament test and an emotion test.
The sight tracking provided by the embodiment of the invention adopts an infrared camera shooting capture mode to acquire and analyze the pupil image.
Example 2
The method for analyzing the character based on the expression recognition and the psychological test provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 5, the method for predicting the character provided by the embodiment of the invention is as follows:
s401, acquiring instant physiological information, facial images, psychological information, intelligence information, cognitive information and basic information including age groups of an evaluated object; inputting a face picture of a tested person into a pre-trained first character evaluation model based on a convolutional neural network, extracting a feature map of the face picture of the tested person through the first character evaluation model, and obtaining a first character evaluation result corresponding to the face picture of the tested person according to the feature map and a preset corresponding relation between the feature map and character dimensions;
s402, extracting a facial feature vector of the face picture of the detected person, and determining a second character evaluation result corresponding to the face picture of the detected person according to the facial feature vector and a corresponding relation between a preset facial feature dimension set and character dimensions; and fusing the first character evaluation result and the second character evaluation result to obtain a character prediction result.
The method for extracting the facial feature vector of the face picture of the testee, provided by the embodiment of the invention, comprises the following steps:
and inputting the face picture of the tested person into a pre-trained facial feature recognition model based on a convolutional neural network to obtain a facial feature vector corresponding to the face picture of the tested person.
The determining of the second personality evaluation result corresponding to the face picture of the testee according to the facial feature vector and the corresponding relationship between the preset facial feature dimension set and the personality dimensions, provided by the embodiment of the invention, includes:
and inputting the facial feature vector into a preset character classifier to obtain a second character judgment result corresponding to the face picture of the testee, wherein the second character judgment result is used for indicating the probability of the face picture of the testee on each preset character dimension.
The determining of the second personality evaluation result corresponding to the face picture of the testee according to the facial feature vector and the corresponding relationship between the preset facial feature dimension set and the personality dimensions, provided by the embodiment of the invention, includes:
determining the influence value of each dimension value in the facial feature vector on each character dimension according to a preset matching rule;
and fusing the influence scores of the values of all dimensions in the facial feature vector on all character dimensions to determine a second character judgment result corresponding to the face picture of the tested person, wherein the second character judgment result is used for indicating the scores of the face picture of the tested person on the preset all character dimensions.
The training method of the first character evaluation model provided by the embodiment of the invention comprises the following steps:
obtaining face pictures and character attributes of testees of a plurality of testees, and labeling the corresponding face pictures of the testees according to the character attributes to obtain sample data, wherein the character attributes comprise scores of the testees in a plurality of character dimensions;
inputting the sample data into a first convolution neural network by taking the sample data as a training set;
calculating a difference value between an output result of the first convolutional neural network and a pre-labeled character attribute through a loss function;
if the difference value is larger than a preset expected value, optimizing the weight parameter of the first convolution neural network by adopting an optimization algorithm;
and continuing to train the optimized first convolution neural network by using the training set until the difference value obtained by calculating the loss function is converged.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (10)
1. The analysis method for generating the character based on the expression recognition and the psychological test is characterized by comprising the following steps of:
the method comprises the following steps that firstly, a facial image acquisition module acquires a facial image of a testee by using a camera; the information of the name, age, academic calendar, work and the like of the testee is acquired through an identity information acquisition module;
step two, the main control module obtains the facial image of the testee obtained in the step one by an image feature extraction module through an image extraction program; preprocessing the obtained face image, namely converting the face image into a gray image;
processing the gray level image obtained in the step two, and extracting facial image features; identifying facial expressions according to the extracted facial image features by using a facial expression identification module through an identification program; meanwhile, basic information, emotion information and position information of a name and a head portrait picture of the testee are obtained through a psychological evaluation module by using an evaluation program; establishing a perfect psychological assessment questionnaire database, generating different assessment questionnaires aiming at different test purposes, performing questionnaire test on a tested person, and generating a corresponding questionnaire assessment analysis report according to a test result;
step four, acquiring basic information of the tested person according to the data of the questionnaire evaluation analysis report obtained in the step three, establishing a psychological evaluation model based on the sex, age group, psychology, intelligence, cognition and other related information of the tested person, and performing psychological evaluation by utilizing the established psychological evaluation model;
generating different virtual setting scenes based on the psychological evaluation model obtained in the fourth step, matching the scenes of the testee according to the questionnaire evaluation analysis report, performing psychological test, tracking the sight of the testee, collecting the eye movement data of the testee, monitoring the data change of the physiological index of the testee, and importing the eye movement data and the physiological index test data into a test system to generate a corresponding eye movement data and physiological index test data curve;
step six, acquiring the related information and the face image of the testee obtained in the step one by using a character prediction module, and acquiring the instant physiological information, the psychological information, the intelligence information and the cognitive information of the testee by using a prediction program;
step seven, inputting the acquired face image information of the testee into a pre-trained first character evaluation model based on a convolutional neural network, extracting a feature map of the face picture of the testee through the first character evaluation model, and obtaining a first character evaluation result corresponding to the face picture of the testee according to the feature map and a preset corresponding relation between the feature map and character dimensions;
step eight, acquiring the facial feature vector of the tested person extracted in the step three, and determining a second character evaluation result corresponding to the facial picture of the tested person according to the facial feature vector and the corresponding relation between a preset facial feature dimension set and character dimensions; fusing the first personality evaluation result and the second personality evaluation result to obtain a personality prediction result;
step nine, based on the character prediction result obtained in the step eight, comprehensively analyzing the character of the testee by an analysis module by utilizing an analysis program; and simultaneously, the display module is used for displaying the acquired facial image, the identity information, the expression recognition result, the psychological evaluation result, the character prediction result and the comprehensive analysis result of the testee by utilizing the display.
2. The method for analyzing personality based on expression recognition and psychological test of claim 1, wherein in step three, the questionnaire test comprises a social adaptation ability test, a mental health state test, a compression resistance ability test, an intelligence test, a self-consciousness test, a temperament test and an emotion test.
3. The method for generating personality analysis based on expression recognition and psychological testing as claimed in claim 1, wherein in step five, the gaze tracking comprises: and acquiring and analyzing the pupil image by adopting an infrared camera shooting and capturing mode.
4. The method for generating a character based on expression recognition and psychological test as claimed in claim 1, wherein said step five further comprises:
(3.1) acquiring galvanic skin response data, and generating a corresponding change curve based on a virtual setting scene; acquiring brain wave change data, and generating a corresponding change curve based on a virtual setting scene; acquiring chest and abdomen respiratory frequency data, and generating a corresponding change curve based on a virtual setting scene; acquiring pulse beating frequency and blood pressure change data, and generating a corresponding change curve based on a virtual setting scene;
and (3.2) importing the eye movement data and the physiological index test data curve into a test system for analysis, generating a comprehensive evaluation report, and generating a solution for the adverse psychological state in the psychological evaluation.
5. The method for analyzing character generation based on expression recognition and psychological test as claimed in claim 1, wherein in step seven, the training method of the first character judgment model comprises:
obtaining face pictures and character attributes of testees of a plurality of testees, and labeling the corresponding face pictures of the testees according to the character attributes to obtain sample data, wherein the character attributes comprise scores of the testees in a plurality of character dimensions;
inputting the sample data into a first convolution neural network by taking the sample data as a training set;
calculating a difference value between an output result of the first convolutional neural network and a pre-labeled character attribute through a loss function;
if the difference value is larger than a preset expected value, optimizing the weight parameter of the first convolution neural network by adopting an optimization algorithm;
and continuing to train the optimized first convolution neural network by using the training set until the difference value obtained by calculating the loss function is converged.
6. The method for analyzing character generation based on expression recognition and psychological test as claimed in claim 1, wherein in step eight, said determining the second character judgment result corresponding to the face picture of the subject according to the facial feature vector and the corresponding relationship between the preset facial feature dimension set and character dimensions comprises:
and inputting the facial feature vector into a preset character classifier to obtain a second character judgment result corresponding to the face picture of the testee, wherein the second character judgment result is used for indicating the probability of the face picture of the testee on each preset character dimension.
7. The method for analyzing character generation based on facial expression recognition and psychological test as claimed in claim 6, wherein said determining the second character evaluation result corresponding to the face picture of the subject according to the facial feature vector and the corresponding relationship between the preset facial feature dimension set and the character dimension further comprises:
determining the influence value of each dimension value in the facial feature vector on each character dimension according to a preset matching rule;
and fusing the influence scores of the values of all dimensions in the facial feature vector on all character dimensions to determine a second character judgment result corresponding to the face picture of the tested person, wherein the second character judgment result is used for indicating the scores of the face picture of the tested person on the preset all character dimensions.
8. An analysis system for generating a character based on facial recognition and psychological test, which implements the analysis method for generating a character based on facial recognition and psychological test according to claims 1 to 7, wherein the analysis system for generating a character based on facial recognition and psychological test comprises:
the facial image analysis system comprises a facial image acquisition module, an identity information acquisition module, a main control module, an image feature extraction module, a facial expression recognition module, a psychological evaluation module, a character prediction module, an analysis module and a display module;
the facial image acquisition module is connected with the main control module and is used for acquiring a facial image of the testee through the camera;
the identity information acquisition module is connected with the main control module and is used for acquiring information such as the name, age, academic calendar, work and the like of the testee;
the main control module is connected with the facial image acquisition module, the identity information acquisition module, the image feature extraction module, the facial expression recognition module, the psychological evaluation module, the character prediction module, the analysis module and the display module and is used for controlling the normal work of each module through a host;
the image feature extraction module is connected with the main control module and used for extracting facial image features through an image extraction program;
the facial expression recognition module is connected with the main control module and used for recognizing facial expressions according to facial image features through a recognition program;
the psychological evaluation module is connected with the main control module and used for evaluating the psychology of the testee through an evaluation program;
the character prediction module is connected with the main control module and used for predicting character characteristics of the testee according to the facial expression and the psychological state through a prediction program;
the analysis module is connected with the main control module and is used for comprehensively analyzing the character of the testee through an analysis program;
and the display module is connected with the main control module and used for displaying the collected facial image, the identity information, the expression recognition result, the psychological evaluation result, the character prediction result and the comprehensive analysis result of the testee through the display.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing a method for generating a personality analysis based on facial recognition and psychological testing according to any one of claims 1-7 when executed on an electronic device.
10. A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method of analyzing a personality generation based on expression recognition and psychological testing of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010661664.8A CN111887867A (en) | 2020-07-10 | 2020-07-10 | Method and system for analyzing character formation based on expression recognition and psychological test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010661664.8A CN111887867A (en) | 2020-07-10 | 2020-07-10 | Method and system for analyzing character formation based on expression recognition and psychological test |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111887867A true CN111887867A (en) | 2020-11-06 |
Family
ID=73192518
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010661664.8A Pending CN111887867A (en) | 2020-07-10 | 2020-07-10 | Method and system for analyzing character formation based on expression recognition and psychological test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111887867A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112472089A (en) * | 2020-11-17 | 2021-03-12 | 衡阳师范学院 | System and method for judging reliability of psychological test based on eye movement technology |
CN112515676A (en) * | 2020-12-16 | 2021-03-19 | 广东电网有限责任公司电力科学研究院 | Psychological examination method and subjective and objective combined examinee disguise testing method |
CN112603320A (en) * | 2021-01-07 | 2021-04-06 | 岭南师范学院 | Optical nondestructive special children detector based on facial expression analysis and detection method |
CN112716494A (en) * | 2021-01-18 | 2021-04-30 | 上海对外经贸大学 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
CN113010557A (en) * | 2021-03-19 | 2021-06-22 | 四川蓝韵心理咨询服务有限公司 | Method and system for randomly answering questions by using psychological evaluation system scale |
CN113643772A (en) * | 2021-07-09 | 2021-11-12 | 杭州天资洪睿智能科技发展有限公司 | System for generating character based on psychological test and algorithm analysis |
CN114399827A (en) * | 2022-03-14 | 2022-04-26 | 潍坊护理职业学院 | College graduate career personality testing method and system based on facial micro-expression |
CN114511934A (en) * | 2022-01-26 | 2022-05-17 | 北京无明文化咨询有限公司 | Six-type sixteen-type character behavior prediction system and prediction method |
CN117392719A (en) * | 2023-10-08 | 2024-01-12 | 安徽医科大学 | Real-time psychological analysis method in contradiction dispute mediation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140125207A (en) * | 2013-04-18 | 2014-10-28 | (주) 마이크로사이텍 | Method and apparatus for analyzing image for comprehending testee's psychology and recording medium thereof |
CN109409196A (en) * | 2018-08-30 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Personality prediction technique based on face, device, electronic equipment |
CN110309714A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Mental health evaluation method, apparatus and storage medium based on Expression Recognition |
CN110507334A (en) * | 2019-08-21 | 2019-11-29 | 珠海学之渔心理咨询有限公司 | A kind of adult's psychological assessment method |
CN110755091A (en) * | 2018-07-26 | 2020-02-07 | 杨万友 | Personal mental health monitoring system and method |
-
2020
- 2020-07-10 CN CN202010661664.8A patent/CN111887867A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140125207A (en) * | 2013-04-18 | 2014-10-28 | (주) 마이크로사이텍 | Method and apparatus for analyzing image for comprehending testee's psychology and recording medium thereof |
CN110755091A (en) * | 2018-07-26 | 2020-02-07 | 杨万友 | Personal mental health monitoring system and method |
CN109409196A (en) * | 2018-08-30 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Personality prediction technique based on face, device, electronic equipment |
CN110309714A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Mental health evaluation method, apparatus and storage medium based on Expression Recognition |
CN110507334A (en) * | 2019-08-21 | 2019-11-29 | 珠海学之渔心理咨询有限公司 | A kind of adult's psychological assessment method |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112472089A (en) * | 2020-11-17 | 2021-03-12 | 衡阳师范学院 | System and method for judging reliability of psychological test based on eye movement technology |
CN112515676A (en) * | 2020-12-16 | 2021-03-19 | 广东电网有限责任公司电力科学研究院 | Psychological examination method and subjective and objective combined examinee disguise testing method |
CN112603320A (en) * | 2021-01-07 | 2021-04-06 | 岭南师范学院 | Optical nondestructive special children detector based on facial expression analysis and detection method |
CN112716494A (en) * | 2021-01-18 | 2021-04-30 | 上海对外经贸大学 | Mental health condition analysis algorithm based on micro-expression and brain wave analysis algorithm |
CN113010557A (en) * | 2021-03-19 | 2021-06-22 | 四川蓝韵心理咨询服务有限公司 | Method and system for randomly answering questions by using psychological evaluation system scale |
CN113643772A (en) * | 2021-07-09 | 2021-11-12 | 杭州天资洪睿智能科技发展有限公司 | System for generating character based on psychological test and algorithm analysis |
CN114511934A (en) * | 2022-01-26 | 2022-05-17 | 北京无明文化咨询有限公司 | Six-type sixteen-type character behavior prediction system and prediction method |
CN114399827A (en) * | 2022-03-14 | 2022-04-26 | 潍坊护理职业学院 | College graduate career personality testing method and system based on facial micro-expression |
CN117392719A (en) * | 2023-10-08 | 2024-01-12 | 安徽医科大学 | Real-time psychological analysis method in contradiction dispute mediation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111887867A (en) | Method and system for analyzing character formation based on expression recognition and psychological test | |
CN108888277B (en) | Psychological test method, psychological test system and terminal equipment | |
KR101689021B1 (en) | System for determining psychological state using sensing device and method thereof | |
CN111326253A (en) | Method for evaluating multi-modal emotional cognitive ability of patients with autism spectrum disorder | |
JP6863563B2 (en) | Stress evaluation system | |
WO2021068781A1 (en) | Fatigue state identification method, apparatus and device | |
CN112472089A (en) | System and method for judging reliability of psychological test based on eye movement technology | |
CN113837153B (en) | Real-time emotion recognition method and system integrating pupil data and facial expressions | |
CN115064246A (en) | Depression evaluation system and equipment based on multi-mode information fusion | |
CN115607153B (en) | Psychological scale answer quality assessment system and method based on eye movement tracking | |
CN105279380A (en) | Facial expression analysis-based depression degree automatic evaluation system | |
CN111265226A (en) | System and method for detecting psychological stress management ability | |
CN112614583A (en) | Depression grade testing system | |
CN113647950A (en) | Psychological emotion detection method and system | |
CN115862868A (en) | Psychological assessment system, psychological assessment platform, electronic device and storage medium | |
WO2023012818A1 (en) | A non-invasive multimodal screening and assessment system for human health monitoring and a method thereof | |
CN113974589B (en) | Multi-modal behavior paradigm evaluation optimization system and cognitive ability evaluation method | |
CN111738234B (en) | Automatic co-situation ability identification method based on individual eye movement characteristics | |
CN115497621A (en) | Old person cognitive status evaluation system | |
CN115444422A (en) | Eye movement data-based real environment psychological load assessment method and system | |
CN115429271A (en) | Autism spectrum disorder screening system and method based on eye movement and facial expression | |
CN111222374A (en) | Lie detection data processing method and device, computer equipment and storage medium | |
KR102565852B1 (en) | Autism spectrum disorder evaluation method based on facial expression analysis | |
CN110781719A (en) | Non-contact and contact cooperative mental state intelligent monitoring system | |
WO2024062935A1 (en) | Information processing device, system, information processing method, and program |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201106 |