CN109009096A - The system and method that a kind of pair of films and television programs objectively evaluate online - Google Patents
The system and method that a kind of pair of films and television programs objectively evaluate online Download PDFInfo
- Publication number
- CN109009096A CN109009096A CN201810783595.0A CN201810783595A CN109009096A CN 109009096 A CN109009096 A CN 109009096A CN 201810783595 A CN201810783595 A CN 201810783595A CN 109009096 A CN109009096 A CN 109009096A
- Authority
- CN
- China
- Prior art keywords
- module
- signal
- eeg signal
- films
- television programs
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- 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
- A61B5/16—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
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6803—Head-worn items, e.g. helmets, masks, headphones or goggles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6814—Head
-
- 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
- A61B5/7271—Specific aspects of physiological measurement analysis
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Educational Technology (AREA)
- Radiology & Medical Imaging (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The system and method that a kind of pair of films and television programs of the invention objectively evaluate online, which includes video display display module, signal acquisition module, signal pre-processing module, characteristic extracting module, mood categorization module, result display module；Acquire eeg signal and facial expression image or video of the measurand when watching films and television programs, feeling polarities classification is carried out to the eeg signal by the SVM emotion classifiers of building, and the recognition result of facial expression is combined to improve nicety of grading, the feeling polarities of acquisition are classified, it is objective to the films and television programs that people can further be obtained, reliable impression, it is objectively evaluated to realize, it is particularly applicable in the evaluation of films and television programs, improve etc., so that video display industry can with a definite target in view improve films and television programs, become the cultural industry that people increasingly like.
Description
Technical field
The invention belongs to artificial intelligence fields, are related to the system and method that a kind of pair of films and television programs objectively evaluate online, especially
Its brain wave acquired when being to viewing films and television programs is analyzed, and mood classification is obtained, to realize the method objectively evaluated.
Background technique
Recently, due to the raising of people's quality of life, video display industry is more and more flourishing, in order to support cultural restructuring
And Development of Cultural Industry, push national culture field structural adjustment, reasonable disposition cultural resource, optimization industry development entirety cloth
Innings, video display industry wishes itself making improvement, becomes the more and more favorite culture of people with a definite target in view.
Nowadays general by the way of questionnaire survey.But questionnaire survey, which is passed through, fills out question and answer volume frequently with by measured oneself
Mode, subjectivity is strong, and dependent on memory, confidence level needs to be investigated, so the quality of its investigation result usually cannot be guaranteed,
And the rate of recovery of questionnaire survey is difficult to ensure, the improvement idea effect obtained is general.
Therefore need one kind that can correctly reflect that people to the method for objectively evaluating content of films and television programs, have reliability
And objectivity, so that video display industry can become the culture that people increasingly like and produce with a definite target in view to improvement itself is made
Industry.
Summary of the invention
The present invention provides the system and methods that a kind of pair of films and television programs objectively evaluate online, pass through dimensionality reduction, machine learning
Method, the eeg signal that acquires carries out feature extraction when to viewing films and television programs, obtains mood classification, further obtains people
Objective to the films and television programs, reliable impression, thus realize objectively evaluate, be particularly applicable in films and television programs evaluation, improve
Etc., so that video display industry can with a definite target in view improve films and television programs, become the culture that people increasingly like
Industry.
The system that a kind of pair of films and television programs of the invention objectively evaluate online, including video display display module, signal acquisition module,
Signal pre-processing module, characteristic extracting module, mood categorization module, result display module；
The video display display module wishes the films and television programs of evaluation and test for playing investigator；
The signal acquisition module, including picture pick-up device and electrode cap, the electrode cap are used to acquire the brain of measurand
Electric wave signal, the picture pick-up device are used to acquire the facial expression image or video of measurand, and collected brain wave is believed
Number it is sent to signal pre-processing module, facial expression image/video is sent to sentiment analysis module；
The signal pre-processing module is pre-processed to original eeg signal is obtained from signal acquisition module,
The pretreatment includes not available semaphore in removal eeg signal, filtering, signal deletion processing, normalized；
The characteristic extracting module passes through pretreated eeg signal from signal pre-processing module for receiving,
Dimension-reduction treatment is carried out to pretreated eeg signal using Principal Component Analysis PCA, and will treated eeg signal
It is sent to sentiment analysis module；
The sentiment analysis module receives the eeg signal from characteristic extracting module, with the method for machine learning
SVM emotion classifiers are constructed, feeling polarities classification is carried out to the eeg signal, which is divided into actively or is disappeared
Pole carries out facial knowledge to the facial expression image or video that receive the measured that picture pick-up device acquires in signal acquisition module
Not, using the result of the face recognition as auxiliary, for carrying out smart classification to sorted eeg signal, finally by brain wave
Signal label is actively or after passiveness, and the analysis result as sentiment analysis module is exported to result display module.
Semi-supervised learning method of the method selection of the machine learning based on cluster core, includes the following steps:
Step 1, in marker samples and unmarked sample, establish weighted undirected graph, give the emotional semantic classification based on figure
The mathematical model of problem；
Step 2, according to existing cluster accounting method, the semi-supervised clustering core based on the weighted undirected graph is solved, as structure
Build the kernel function of classifier；
Step 3, the training that the kernel function of step 2 is used for SVM emotion classifiers, by trained SVM emotional semantic classification
Device is used to carry out feeling polarities classification to eeg signal.
Any one described method that the system that films and television programs objectively evaluate online is objectively evaluated online, including such as
Lower step:
Step 1, measurand wear signal acquisition module, and the electrode cap in signal acquisition module is allowed to acquire quilt
The eeg signal of object is surveyed, the picture pick-up device in signal acquisition module can acquire the facial expression image or view of measurand
Frequently；
Step 2, investigator play the films and television programs for wanting evaluation and test on video display display module；It is worn by measurand
Electrode cap and picture pick-up device obtain the eeg signal and facial expression that measurand is generated when watching the films and television programs respectively
Image or video, and collected eeg signal is sent to signal pre-processing module, facial expression image or video are sent out
Give sentiment analysis module；
Step 3, signal pre-processing module are sent to feature extraction mould after pre-processing to the eeg signal got
Block, this feature extraction module carry out dimension-reduction treatment to pretreated eeg signal；
Step 4, the sentiment analysis module receive the eeg signal from characteristic extracting module, use machine learning
Method building SVM emotion classifiers, to the eeg signal carry out feeling polarities classification, which is divided into actively
Or it is passive, to the facial expression image or video data for receiving the measured that picture pick-up device acquires in signal acquisition module
Face recognition is carried out, using the result of the face recognition as auxiliary, for the sorted eeg signal of SVM emotion classifiers
Smart classification is carried out, final eeg signal is by the analysis result output that label is actively or after passiveness, as sentiment analysis module
To result display module；
Step 5 summarizes feeling polarities classification of the measurand to the films and television programs of the broadcasting, obtains measurand and is watching
The emotion of the films and television programs is positive or passive analysis as a result, the ginseng modified as investigator to films and television programs
It examines.
For technical solution of the present invention compared with traditional emotional semantic classification system, what it is due to acquisition is measurand in viewing video display
Eeg signal and facial expression image/video when works, by the SVM emotion classifiers of building to the eeg signal into
The classification of row feeling polarities, and the recognition result of facial expression is combined to improve nicety of grading, the feeling polarities of measurand are analyzed
As a result applied to the improvement aspect of films and television programs, films and television programs can be made more very popular.
Detailed description of the invention
Fig. 1 is the working principle of the invention figure；
Fig. 2 is the schematic diagram that measured of the present invention wears electrode cap；
Fig. 3 is that the present invention is based on the flow charts of the semi-supervised learning method of figure.
The present invention is further described below in conjunction with drawings and examples.
Specific embodiment
As shown in Figure 1, the system that a kind of pair of films and television programs objectively evaluate online, including video display display module 100, signal are adopted
Collect module 200, signal pre-processing module 300, characteristic extracting module 400, mood categorization module 500, result display module 600；
The video display display module 100 wishes the films and television programs of evaluation and test for playing investigator, it should be placed on tested pair
Comfortable position is felt as watching films and television programs, and resolution ratio is high as far as possible, does not influence the displaying of films and television programs, best feelings
Condition is that have the function of that investigator can show content with remote control, which is mature technology, and this will not be repeated here by the present invention；
The signal acquisition module 200, as shown in Fig. 2, including picture pick-up device 220 and electrode cap 210, the electrode cap
210 for acquiring the eeg signal of measurand, the picture pick-up device 220 be used to acquire the facial expression image of measurand/
Video, and collected eeg signal is sent to signal pre-processing module 300, facial expression image/video is sent to
Sentiment analysis module 500；
The signal pre-processing module 300 carries out in advance to original eeg signal is obtained from signal acquisition module 200
Processing, the pretreatment include not available semaphore in removal eeg signal, filtering, signal deletion processing, normalized
Deng；
Wherein, by the method for the eeg signal normalized are as follows: since emotion behavior lags, successively take every 10 brains
Electric wave signal data are one group, take its average value, recycle standard deviation standardization, formula are as follows:
Wherein, μ is average value, and σ is standard deviation, xiFor i-th of eeg signal data in every group, z is nothing after normalization
The data of dimension, N are the representations of ecologicaI distribution, i.e., the data fit standardized normal distribution after normalized and uniformly
It is mapped on [0,1] section, which is data each column to be subtracted to the column average value, and divided by the column standard deviation, pass through
Data fit standardized normal distribution after processing, i.e. mean value are 0, standard deviation 1, and data can remove number after normalized
According to unit limitation, be converted into nondimensional pure values；
The characteristic extracting module 400 passes through pretreated brain wave from signal pre-processing module 300 for receiving
Signal carries out characteristic processing to the pretreated eeg signal, and the effect of characteristic processing is to reduce other unnecessary letters
Number interference, leave behind useful signal, using Principal Component Analysis (PCA) to pretreated eeg signal carry out dimensionality reduction at
Reason, and eeg signal is sent to sentiment analysis module 500 by treated；
The sentiment analysis module 500 receives the eeg signal from characteristic extracting module 400, uses machine learning
Method building SVM emotion classifiers, to the eeg signal carry out feeling polarities classification, which is divided into actively
Or it is passive, to the facial expression image/view for receiving the measured that picture pick-up device 220 acquires in signal acquisition module 200
Frequency carries out face recognition, using the result of the face recognition as auxiliary, for carrying out smart classification to sorted eeg signal,
It is finally actively or after passiveness by eeg signal label, the analysis result as sentiment analysis module 500 exports aobvious to result
Show module 600；
Wherein, semi-supervised learning method of the method selection of machine learning based on cluster core, as shown in figure 3, specifically including
Following steps:
Step 1, in marker samples and unmarked sample, establish weighted undirected graph, give the emotional semantic classification based on figure
The mathematical model of problem；Semi-supervised learning is fewer than supervised learning to carry out sample labeling, and it is more accurate to classify than unsupervised learning, with
Machine marks some samples；
Step 2, according to existing cluster accounting method, the semi-supervised clustering core based on the weighted undirected graph is solved, as structure
Build the kernel function of classifier；
Step 3, the training that the kernel function of step 2 is used for SVM emotion classifiers, by trained SVM emotional semantic classification
Device is used to carry out feeling polarities classification to eeg signal；
The result display module 600 receives the analysis from sentiment analysis module 500 as a result, can be display point
The display screen of class result, alternatively, can be the memory for saving classification results, alternatively, can be the printing of output analysis result
Machine.
The method that a kind of pair of films and television programs of the invention objectively evaluate online, includes the following steps:
Step 1, measurand wear signal acquisition module 200, so that the electrode cap 210 in signal acquisition module 200
The eeg signal of measurand can be acquired, the picture pick-up device 220 in signal acquisition module 200 can acquire measurand
Facial expression image/video；
Step 2, investigator play the films and television programs for wanting evaluation on video display display module 100；It is worn by measurand
The electrode cap 210 and picture pick-up device 220 worn obtain the eeg signal that measurand is generated when watching the films and television programs respectively
With facial expression image/video, and collected eeg signal is sent to signal pre-processing module 300, by facial expression
Image/video is sent to sentiment analysis module 500；
Step 3, signal pre-processing module 300 are sent to feature extraction after pre-processing to the eeg signal got
Module 400, this feature extraction module 400 carry out dimension-reduction treatment to pretreated eeg signal；
Step 4, the sentiment analysis module 500 receive the eeg signal from characteristic extracting module 400, use machine
The method of device study constructs SVM emotion classifiers, carries out feeling polarities classification to the eeg signal, which is divided into
It is actively or passive, to the facial expression figure for receiving the measured that picture pick-up device 220 acquires in signal acquisition module 200
Picture/video data carries out face recognition, using the result of the face recognition as auxiliary, after to the classification of SVM emotion classifiers
Eeg signal carry out smart classification, final eeg signal is actively or after passiveness, as sentiment analysis module 500 by label
Analysis result export to result display module 600；
Step 5 summarizes feeling polarities classification of the measurand to the films and television programs of the broadcasting, obtains measurand and is watching
The emotion of the films and television programs is positive or passive analysis as a result, the ginseng modified as investigator to films and television programs
It examines.
The above is only present pre-ferred embodiments, is not intended to limit the scope of the present invention, therefore
Any subtle modifications, equivalent variations and modifications to the above embodiments according to the technical essence of the invention, still belong to
In the range of technical solution of the present invention.
Claims (3)
1. the system that a kind of pair of films and television programs objectively evaluate online, it is characterised in that: including video display display module, signal acquisition mould
Block, signal pre-processing module, characteristic extracting module, mood categorization module, result display module；
The video display display module wishes the films and television programs of evaluation and test for playing investigator；
The signal acquisition module, including picture pick-up device and electrode cap, the electrode cap are used to acquire the brain wave of measurand
Signal, the picture pick-up device are used to acquire the facial expression image or video of measurand, and collected eeg signal is sent out
It send to signal pre-processing module, facial expression image/video is sent to sentiment analysis module；
The signal pre-processing module is pre-processed to original eeg signal is obtained from signal acquisition module, this is pre-
Processing includes not available semaphore in removal eeg signal, filtering, signal deletion processing, normalized；
The characteristic extracting module is passed through pretreated eeg signal from signal pre-processing module for receiving, is utilized
Principal Component Analysis PCA carries out dimension-reduction treatment to pretreated eeg signal, and eeg signal is sent by treated
To emotion analysis module；
The sentiment analysis module receives the eeg signal from characteristic extracting module, is constructed with the method for machine learning
SVM emotion classifiers, to the eeg signal carry out feeling polarities classification, which is divided into it is positive or passive, it is right
The facial expression image or video for receiving the measured that picture pick-up device acquires in signal acquisition module carry out face recognition, will
The result of the face recognition is as auxiliary, for carrying out smart classification to sorted eeg signal, finally by eeg signal
Label is actively or after passiveness, and the analysis result as sentiment analysis module is exported to result display module.
2. the system that a kind of pair of films and television programs according to claim 1 objectively evaluate online, it is characterised in that: the machine
Semi-supervised learning method of the method selection based on cluster core of device study, includes the following steps:
Step 1, in marker samples and unmarked sample, establish weighted undirected graph, give the emotional semantic classification problem based on figure
Mathematical model；
Step 2, according to existing cluster accounting method, the semi-supervised clustering core based on the weighted undirected graph is solved, as building point
The kernel function of class device；
Step 3, the training that the kernel function of step 2 is used for SVM emotion classifiers use trained SVM emotion classifiers
In to eeg signal progress feeling polarities classification.
3. according to claim 1, any one objectively evaluates the system that films and television programs objectively evaluate online online described in 2
Method, it is characterised in that include the following steps:
Step 1, measurand wear signal acquisition module, and the electrode cap in signal acquisition module is allowed to acquire tested pair
The eeg signal of elephant, the picture pick-up device in signal acquisition module can acquire the facial expression image or video of measurand；
Step 2, investigator play the films and television programs for wanting evaluation and test on video display display module；The electrode worn by measurand
Cap and picture pick-up device obtain the eeg signal and facial expression image that measurand is generated when watching the films and television programs respectively
Or video, and collected eeg signal is sent to signal pre-processing module, facial expression image or video are sent to
Sentiment analysis module；
Step 3, signal pre-processing module are sent to characteristic extracting module after pre-processing to the eeg signal got, should
Characteristic extracting module carries out dimension-reduction treatment to pretreated eeg signal；
Step 4, the sentiment analysis module receive the eeg signal from characteristic extracting module, with the side of machine learning
Method building SVM emotion classifiers, to the eeg signal carry out feeling polarities classification, by the feeling polarities be divided into actively or
Passiveness carries out the facial expression image or video data that receive the measured that picture pick-up device acquires in signal acquisition module
Face recognition, using the result of the face recognition as auxiliary, for being carried out to the sorted eeg signal of SVM emotion classifiers
Essence classification, final eeg signal are actively or after passiveness by label, and the analysis result as sentiment analysis module is exported to knot
Fruit display module；
Step 5 summarizes feeling polarities classification of the measurand to the films and television programs of the broadcasting, obtains measurand and is watching the shadow
The emotion for being regarded as product is positive or passive analysis as a result, the reference modified as investigator to films and television programs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810783595.0A CN109009096A (en) | 2018-07-17 | 2018-07-17 | The system and method that a kind of pair of films and television programs objectively evaluate online |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810783595.0A CN109009096A (en) | 2018-07-17 | 2018-07-17 | The system and method that a kind of pair of films and television programs objectively evaluate online |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109009096A true CN109009096A (en) | 2018-12-18 |
Family
ID=64643542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810783595.0A Pending CN109009096A (en) | 2018-07-17 | 2018-07-17 | The system and method that a kind of pair of films and television programs objectively evaluate online |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109009096A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110166836A (en) * | 2019-04-12 | 2019-08-23 | 深圳壹账通智能科技有限公司 | A kind of TV program switching method, device, readable storage medium storing program for executing and terminal device |
| CN112365447A (en) * | 2020-10-20 | 2021-02-12 | 四川长虹电器股份有限公司 | Multidimensional movie and television scoring method |
| CN112911770A (en) * | 2021-01-26 | 2021-06-04 | 上海交通大学 | Interactive method for enhancing artistic appreciation |
| CN113509190A (en) * | 2021-03-18 | 2021-10-19 | 上海交通大学 | Product design evaluation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541261A (en) * | 2012-01-19 | 2012-07-04 | 北京工业大学 | Film editing and selecting auxiliary instrument and realization method based on characteristics of electroencephalogram signal |
| CN104361356A (en) * | 2014-12-08 | 2015-02-18 | 清华大学 | Movie audience experience assessing method based on human-computer interaction |
| KR20160113538A (en) * | 2015-03-13 | 2016-09-30 | 한국생산기술연구원 | Apparatus and method for providing contents, helmet and glasses including the same |
| CN107479702A (en) * | 2017-08-04 | 2017-12-15 | 西南大学 | A kind of human emotion's dominance classifying identification method using EEG signals |
| CN108090698A (en) * | 2018-01-08 | 2018-05-29 | 聚影汇（北京）影视文化有限公司 | A kind of film test and appraisal service system and method |
-
2018
- 2018-07-17 CN CN201810783595.0A patent/CN109009096A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541261A (en) * | 2012-01-19 | 2012-07-04 | 北京工业大学 | Film editing and selecting auxiliary instrument and realization method based on characteristics of electroencephalogram signal |
| CN104361356A (en) * | 2014-12-08 | 2015-02-18 | 清华大学 | Movie audience experience assessing method based on human-computer interaction |
| KR20160113538A (en) * | 2015-03-13 | 2016-09-30 | 한국생산기술연구원 | Apparatus and method for providing contents, helmet and glasses including the same |
| CN107479702A (en) * | 2017-08-04 | 2017-12-15 | 西南大学 | A kind of human emotion's dominance classifying identification method using EEG signals |
| CN108090698A (en) * | 2018-01-08 | 2018-05-29 | 聚影汇（北京）影视文化有限公司 | A kind of film test and appraisal service system and method |
Non-Patent Citations (1)
| Title |
|---|
| 郑文静: "基于聚类核的半监督情感分类算法研究", 《计算机技术与发展》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110166836A (en) * | 2019-04-12 | 2019-08-23 | 深圳壹账通智能科技有限公司 | A kind of TV program switching method, device, readable storage medium storing program for executing and terminal device |
| CN110166836B (en) * | 2019-04-12 | 2022-08-02 | 深圳壹账通智能科技有限公司 | Television program switching method and device, readable storage medium and terminal equipment |
| CN112365447A (en) * | 2020-10-20 | 2021-02-12 | 四川长虹电器股份有限公司 | Multidimensional movie and television scoring method |
| CN112911770A (en) * | 2021-01-26 | 2021-06-04 | 上海交通大学 | Interactive method for enhancing artistic appreciation |
| CN113509190A (en) * | 2021-03-18 | 2021-10-19 | 上海交通大学 | Product design evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109009096A (en) | The system and method that a kind of pair of films and television programs objectively evaluate online | |
| Lu et al. | An experimental evaluation of covariates effects on unconstrained face verification | |
| Witham | Automated face recognition of rhesus macaques | |
| CN111523462B (en) | Video sequence expression recognition system and method based on self-attention enhanced CNN | |
| CN111329474B (en) | Electroencephalogram identity recognition method and system based on deep learning and information updating method | |
| CN108491077A (en) | A kind of surface electromyogram signal gesture identification method for convolutional neural networks of being divided and ruled based on multithread | |
| CN106599800A (en) | Face micro-expression recognition method based on deep learning | |
| CN104143079A (en) | Method and system for face attribute recognition | |
| CN108776774A (en) | A kind of human facial expression recognition method based on complexity categorization of perception algorithm | |
| CN110353673A (en) | A kind of brain electric channel selection method based on standard mutual information | |
| CN105512609A (en) | Multi-mode fusion video emotion identification method based on kernel-based over-limit learning machine | |
| CN109213853A (en) | A kind of Chinese community's question and answer cross-module state search method based on CCA algorithm | |
| Halkias et al. | Classification of mysticete sounds using machine learning techniques | |
| CN109492105A (en) | A kind of text sentiment classification method based on multiple features integrated study | |
| CN106960176A (en) | A kind of pedestrian's gender identification method based on transfinite learning machine and color characteristic fusion | |
| CN109544523A (en) | Quality of human face image evaluation method and device based on more attribute face alignments | |
| CN109685071A (en) | Brain electricity classification method based on the study of common space pattern feature width | |
| CN109222966A (en) | A kind of EEG signals sensibility classification method based on variation self-encoding encoder | |
| CN106295708B (en) | A kind of continuous data preprocess method based on Fisher classifier group | |
| CN110188750A (en) | A kind of natural scene picture character recognition method based on deep learning | |
| CN101051344B (en) | Sensitive video frequency identifying method based on light stream direction histogram and skin color stream form variation | |
| CN113069117A (en) | Electroencephalogram emotion recognition method and system based on time convolution neural network | |
| CN106599834A (en) | Information pushing method and system | |
| CN109523514A (en) | To the batch imaging quality assessment method of Inverse Synthetic Aperture Radar ISAR | |
| CN103745242A (en) | Cross-equipment biometric feature recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181218 |