CN110279415B - Image distortion threshold coefficient estimation method based on electroencephalogram signals - Google Patents
Image distortion threshold coefficient estimation method based on electroencephalogram signals Download PDFInfo
- Publication number
- CN110279415B CN110279415B CN201910583773.XA CN201910583773A CN110279415B CN 110279415 B CN110279415 B CN 110279415B CN 201910583773 A CN201910583773 A CN 201910583773A CN 110279415 B CN110279415 B CN 110279415B
- Authority
- CN
- China
- Prior art keywords
- image
- electroencephalogram
- signal
- distortion
- subject
- 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.)
- Active
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
- A61B5/24—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]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Psychiatry (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Artificial Intelligence (AREA)
- Power Engineering (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image distortion threshold coefficient estimation method based on electroencephalogram signals, which mainly solves the problem that the image quality evaluation accuracy is low due to the fact that human visual characteristics are not fully considered in the prior art, and adopts the scheme that stimulus images with different distortion levels are designed; collecting electroencephalogram signals caused by observing the stimulated images by a subject; sequentially carrying out reference conversion, baseline correction, filtering and segmentation processing on the acquired electroencephalogram signals; calculating the electroencephalogram threshold with the accuracy rate of 50% when the subject observes the distorted image for the processed electroencephalogram signal, obtaining the linear relation between the electroencephalogram threshold of the subject and the image distortion grade, and estimating the image distortion threshold coefficient. The invention fully considers the human visual perception characteristic, utilizes the image distortion threshold coefficient to estimate the electroencephalogram threshold caused by the observation of the distorted image by the subject, improves the objectivity and the accuracy of the image quality evaluation, and can be used for the image quality evaluation, the image compression and the image detection.
Description
Technical Field
The invention belongs to the technical field of image processing, and further relates to an image distortion threshold coefficient estimation method. The method can be used for image quality evaluation, image compression, image detection and psychological behavior research.
Background
With the continuous development of display technology, the requirements of consumers in modern society for display technology are higher and higher, and not only are the basic things such as large screen, clear image and rich colors required, but also consumers are beginning to pay more attention to deeper things, such as whether the consumers are really watching the image or not and whether the consumers are the image quality which they want to achieve most. As such, the research on image quality evaluation has become a hot spot of research on display technology.
The image quality evaluation method is divided into subjective evaluation and objective evaluation. Subjective evaluation uses a human as an observer to evaluate the quality of an image, and the subjective evaluation is aimed at truly reflecting the visual perception of the human. However, the evaluation result is easily affected by subjective factors such as mood, environment, taste, and experience. The objective evaluation is to establish a mathematical model according to a subjective vision system of human eyes and calculate the quality of an image through a specific formula. However, due to the complexity of the human eye system, the objective evaluation method does not have good consistency with subjective quality evaluation.
The patent document of the university of electronic science and technology, namely the distorted image quality perception evaluation method based on electroencephalogram signals (publication number: CN10760492A, publication date: 2018, 01, 19 and application date: 2017, 08, 25) discloses a distorted image quality perception evaluation method based on electroencephalogram signals. According to the method, through designing and researching an experimental paradigm, the electroencephalogram signals of a subject are extracted, a support vector machine classifier is used for sorting and classifying, the change condition of the electroencephalogram signals of human beings along with the change of image quality is researched, and a more objective image quality evaluation method is obtained. However, the method has the disadvantages that specific reference coefficients are not given, the human visual characteristics are not fully considered, and the evaluation result is not complete.
Xiwen Liu et al, in their published paper, "Calibrating human perception threshold of video distortion using EEG" (IEEE International Conference on Image processing.2018), propose a method of using electroencephalogram signals to assess human-perceived video distortion. The method extracts event-related potential caused by video distortion, and obtains the area under the curve of the receiver operation characteristic through a classification method based on linear discriminant analysis to measure the separability of the P300 component. By correlating the brain electrical signals with the behavioral data, an S-shaped relationship between perceptibility of distortion and separability of P300 components was discovered, providing a potential physiological method for calibrating the perception threshold of video distortion. However, the method still has the defect that the accuracy of video quality evaluation is not high because a universal relation between a distortion perception threshold and an electroencephalogram signal is not obtained.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an image distortion threshold coefficient estimation method based on an electroencephalogram signal so as to improve the accuracy of image quality evaluation.
Aiming at the problem that the visual characteristics of human beings are not considered sufficiently due to limitation and uncertainty existing in the existing image quality evaluation method, the electroencephalogram signal of a subject is extracted by designing an electroencephalogram experimental research paradigm, the electroencephalogram signal and behavior data are correlated, the perceptible threshold of the electroencephalogram signal of images with different distortion degrees is estimated, and the relation between the distortion degree of the image and the perceptible threshold is obtained, so that the image distortion threshold coefficient is obtained, and the implementation steps comprise the following steps:
(1) setting a stimulation image:
(1a) the checkerboard pictures embedded with the water ripples are used as stimulation images to avoid the influence of image content on image quality perception;
(1b) setting the type of the stimulation image distortion as Gaussian blur;
(1c) setting five Gaussian fuzzy distortion levels delta for the stimulus image to obtain five reference stimulus images;
(1d) ten Gaussian blur distortion levels near an image distortion threshold value are set for each reference stimulation image, and fifty distorted images are obtained in total;
(2) acquiring an electroencephalogram signal:
(2a) under the state of an experimental environment, applying two kinds of stimuli, namely a reference stimulus image and a distortion image, to n subjects respectively, wherein n is more than or equal to 7, and each subject receives five groups of experiments;
(2b) respectively recording the electroencephalogram signals W of the subject caused by each group of experimental stimulation images by using an electroencephalogram signal acquisition system;
(3) extracting a single electroencephalogram signal:
(3a) performing reference conversion on the recorded electroencephalogram W of the subject to obtain a converted electroencephalogram WZ；
(3b) For the EEG signal W after the reference conversionZPerforming baseline correction to obtain the electroencephalogram signal W after the baseline correctionJ；
(3c) Using a Butterworth third-order filter to correct the base line of the electroencephalogram signal WJFiltering to obtain the filtered EEG signal WL；
(3d) For the filtered EEG signal WLSegmenting to obtain single electroencephalogram signal W corresponding to the reference stimulation imageBAnd a single electroencephalogram signal W corresponding to the distorted imageD；
(4) Correlating the electroencephalogram signals with the behavioral data:
(4a) judging single electroencephalogram signal W with accuracy rate of 50% for subject under each distortion level deltaDFinding out the wave crest P and the latent period t, and simultaneously finding out the single electroencephalogram signal W at the moment tBAmplitude P oftObtaining the electroencephalogram threshold value of the subject under the corresponding distortion degree: Δ P ═ P-Pt；
(4b) Obtaining an image distortion threshold coefficient K according to the electroencephalogram threshold value delta P and the distortion grade delta of the reference stimulation image in five groups of experiments:
when K is 1.5, the electroencephalogram threshold value delta P corresponding to one can be well fitted with the image distortion level delta.
Compared with the prior art, the invention has the following advantages:
firstly, the invention provides a specific image distortion threshold coefficient, so that the problem that a specific reference coefficient is lacked in quality perception based on electroencephalogram signals in the prior art is solved, and the invention has the advantage that the result obtained when the electroencephalogram signals are combined to research the image quality is more objective.
Secondly, because the electroencephalogram signals corresponding to the perception quality threshold are collected, the visual perception characteristics of human are fully considered, and the problem that the visual characteristics of human are not fully considered in the image quality evaluation research method in the prior art is overcome, so that the method has the advantage of better conforming to the subjective evaluation of human when the image quality is researched.
Thirdly, when the electroencephalogram signal is extracted, the checkerboard picture embedded with the ripple is used as experimental stimulus, so that the influence of image content on image quality perception in the prior art is avoided, and the method has the advantage of more accurate image quality evaluation result.
Drawings
FIG. 1 is a general flow chart of an implementation of the present invention;
FIG. 2 is a sub-flowchart of the experiment performed on a subject according to the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, the specific steps of the present invention are as follows.
Step 1, setting a stimulation image.
Downloading a checkerboard picture embedded with water ripples disclosed in a paper "calibration human perception threshold of video perception using EEG" (IEEE International Conference on Image processing.2018) published by Xiwen Liu et al as a stimulus Image to avoid the influence of Image content on Image quality perception;
setting the type of the stimulation image distortion as Gaussian blur;
setting five Gaussian blur distortion levels delta to the stimulus image, wherein the Gaussian blur distortion levels delta are respectively 0.5,1.5,2.5,3.5 and 4.5, and obtaining five reference stimulus images;
ten gaussian blur distortion levels around the image distortion threshold are set again for each reference stimulus image, respectively at 0, 0.2,0.25,0.3,0.35,0.4,0.45,0.5,0.55,0.6, and a total of fifty distorted images are obtained.
And 2, acquiring an electroencephalogram signal.
Referring to fig. 2, the specific implementation of this step is as follows:
the testee sits upright in a room with mild light and proper temperature, wears a 64-channel electroencephalogram signal acquisition system, faces the display, and is 48 centimeters away from the display;
the experimental paradigm consists of 5 parts: a fixation point, a reference stimulation image, a distorted image, a judgment screen and a black screen;
the fixation point enables the subject to focus the eye at the center of the screen, and the presentation time of the fixation point is 0.8 s;
after the fixation point disappears, a reference stimulation image is presented firstly, then the images are switched between 1s and 1.5s through random time, the reference stimulation image is changed into a distorted image, the total display duration of the reference stimulation image and the distorted image is ensured to be 2.5s, and the images switched at random time can enable a subject to concentrate on attention and avoid habitual judgment;
presenting a judgment screen after the distorted image disappears, and prompting the subject to press a keyboard to reflect whether distortion is observed or not;
when the subject presses the keyboard, a black screen is presented, which indicates that a new fixation point is about to be presented, and the presentation time of the black screen is 0.5 s;
and (3) respectively recording the electroencephalogram signals W of the testee, which are caused by each group of experimental stimulation images, by using an electroencephalogram signal acquisition system.
And 3, extracting the single electroencephalogram signal.
3.1) carrying out reference conversion on the recorded electroencephalogram W of the subject, selecting bilateral mastoid electrodes from the electroencephalogram acquisition system, taking the average value of the signals acquired by the selected bilateral mastoid electrodes as a reference signal C, and subtracting the reference signal C from the recorded electroencephalogram W of the subject to obtain the electroencephalogram W after the reference conversionZ：
WZ＝W-C；
3.2) to the electroencephalogram signal W after the reference conversionZPerforming baseline correction, namely selecting the EEG signal 0.2s before the distorted image appears as a baseline B, and using the EEG signal W after the reference conversionZSubtracting the base line B to obtain the electroencephalogram after base line correctionSignal WJ：
WJ＝WZ-B；
3.3) using a Butterworth third-order filter with the cut-off frequency of 30Hz to correct the base line of the electroencephalogram signal WJFiltering to obtain the filtered EEG signal WL；
3.4) taking the time length of 0.2s before the occurrence of the distorted image and 0.8s after the occurrence as a segmentation interval to filter the EEG signal W after the occurrenceLSegmenting to obtain single electroencephalogram signal W corresponding to the reference stimulation imageBAnd a single electroencephalogram signal W corresponding to the distorted imageD。
And 4, correlating the electroencephalogram signals with the behavior data.
4.1) judging the single EEG signal W with the accuracy rate of 50% from the testee at each distortion level deltaDFinding a wave crest P and a latent period t, and simultaneously finding a single electroencephalogram signal W at the time of tBAmplitude P oftObtaining the electroencephalogram threshold value of the subject under the corresponding distortion degree: Δ P ═ P-Pt；
4.2) obtaining an image distortion threshold coefficient K according to the electroencephalogram threshold value delta P and the distortion grade delta of the reference stimulation image in five groups of experiments:
for each subject, the electroencephalogram threshold value delta P changes along with the change of the distortion level delta and is represented as linear regularity, when the distortion degree is larger, the caused electroencephalogram threshold value is larger, the ratio of the two is a constant, namely, an image distortion threshold value coefficient K, and when the K is 1.5, the electroencephalogram threshold value delta P corresponding to each subject can be well fitted with the image distortion level delta by performing the experiment on 10 subjects.
In practical use, under the condition of setting the image distortion level, the electroencephalogram threshold value of a subject when the subject observes the distorted image can be estimated according to the image distortion threshold value coefficient K, when the electroencephalogram signal of the subject is higher than the electroencephalogram threshold value, the subject can observe the image distortion, when the electroencephalogram signal of the subject is lower than the electroencephalogram threshold value, the situation that the subject cannot observe the image distortion is shown, and therefore the accuracy of image quality evaluation is improved.
The foregoing description is only an example of the present invention and is not intended to limit the invention, so that it will be apparent to those skilled in the art that various changes and modifications in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (5)
1. An image distortion threshold coefficient estimation method based on electroencephalogram signals is characterized by comprising the following steps:
(1) setting a stimulation image:
(1a) the checkerboard pictures embedded with the water ripples are used as stimulation images to avoid the influence of image content on image quality perception;
(1b) setting the type of the stimulation image distortion as Gaussian blur;
(1c) setting five Gaussian fuzzy distortion levels delta for the stimulus image to obtain five reference stimulus images;
(1d) ten Gaussian blur distortion levels near an image distortion threshold value are set for each reference stimulation image, and fifty distorted images are obtained in total;
(2) acquiring an electroencephalogram signal:
(2a) under the state of an experimental environment, applying two kinds of stimuli, namely a reference stimulus image and a distortion image, to n subjects respectively, wherein n is more than or equal to 7, and each subject receives five groups of experiments;
(2b) respectively recording the electroencephalogram signals W of the subject caused by each group of experimental stimulation images by using an electroencephalogram signal acquisition system;
(3) extracting a single electroencephalogram signal:
(3a) performing reference conversion on the recorded electroencephalogram W of the subject to obtain a converted electroencephalogram WZ；
(3b) After conversion referenceElectroencephalogram signal WZPerforming baseline correction to obtain the electroencephalogram signal W after the baseline correctionJ；
(3c) Using a Butterworth third-order filter to correct the base line of the electroencephalogram signal WJFiltering to obtain the filtered EEG signal WL；
(3d) For the filtered EEG signal WLSegmenting to obtain single electroencephalogram signal W corresponding to the reference stimulation imageBAnd a single electroencephalogram signal W corresponding to the distorted imageD；
(4) Correlating the electroencephalogram signals with the behavioral data:
(4a) judging single electroencephalogram signal W with accuracy rate of 50% for subject under each distortion level deltaDFinding out the wave crest P and the latent period t, and simultaneously finding out the single electroencephalogram signal W at the moment tBAmplitude P oftObtaining the electroencephalogram threshold value of the subject under the corresponding distortion degree: Δ P ═ P-Pt；
(4b) Obtaining an image distortion threshold coefficient K according to the electroencephalogram threshold value delta P and the distortion grade delta of the reference stimulation image in five groups of experiments:
when K is 1.5, the electroencephalogram threshold value delta P corresponding to one can be well fitted with the image distortion level delta.
2. The method of claim 1, wherein: (2a) the experimental environment state refers to that the testee sits upright in a room with mild light and proper temperature, wears a 64-channel electroencephalogram signal acquisition system, faces the display and is 48 centimeters away from the display; the experimental paradigm consists of 5 parts: a fixation point, a reference stimulation image, a distorted image, a judgment screen and a black screen.
3. The method of claim 1, wherein: (3a) the recorded EEG signal W of the subject is converted from the brainSelecting bilateral mastoid process electrodes in the electric signal acquisition system, taking the average value of the signals acquired by the selected bilateral mastoid process electrodes as a reference signal C, and subtracting the reference signal C from the recorded electroencephalogram signal W of the subject to obtain an electroencephalogram signal W after reference conversionZ：
WZ＝W-C。
4. The method of claim 1, wherein: (3b) middle pair converted reference EEG signal WZPerforming baseline correction by selecting 0.2s of electroencephalogram signal before the distorted image as baseline B and using electroencephalogram signal W after reference conversionZSubtracting the base line B to obtain the electroencephalogram signal W after base line correctionJ：
WJ＝WZ-B。
5. The method of claim 1, wherein: (3d) middle pair of filtered EEG signals WLAnd (4) segmenting by taking the time length of 0.2s before the occurrence of the distorted image and 0.8s after the occurrence of the distorted image as a segmentation interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583773.XA CN110279415B (en) | 2019-07-01 | 2019-07-01 | Image distortion threshold coefficient estimation method based on electroencephalogram signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583773.XA CN110279415B (en) | 2019-07-01 | 2019-07-01 | Image distortion threshold coefficient estimation method based on electroencephalogram signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110279415A CN110279415A (en) | 2019-09-27 |
| CN110279415B true CN110279415B (en) | 2021-11-02 |
Family
ID=68021323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910583773.XA Active CN110279415B (en) | 2019-07-01 | 2019-07-01 | Image distortion threshold coefficient estimation method based on electroencephalogram signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110279415B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383829B (en) * | 2019-11-06 | 2022-06-24 | 致讯科技(天津)有限公司 | Experience quality evaluation method and device |
| CN111528834B (en) * | 2020-03-25 | 2021-09-24 | 西安电子科技大学 | Real-time SAR image target detection system and method |
| CN111510710B (en) * | 2020-04-27 | 2021-04-30 | 西安电子科技大学 | Video quality evaluation method based on electroencephalogram signals and space-time distortion |
| CN113255789B (en) * | 2021-05-31 | 2023-01-24 | 西安电子科技大学 | Video quality evaluation method based on confrontation network and multi-tested electroencephalogram signals |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060011074A (en) * | 2004-07-29 | 2006-02-03 | 학교법인 포항공과대학교 | Method of estimating user's preference of a product using event related potential |
| CN105141935A (en) * | 2015-05-21 | 2015-12-09 | 天津大学 | Method for analyzing relevance between influence of dimension deviation on stereo image viewing comfort levels and ERP |
| CN105915889A (en) * | 2016-04-19 | 2016-08-31 | 天津大学 | Method for evaluating comfort level of compressed three-dimensional image through employing ERP technology |
| CN107071380A (en) * | 2016-11-03 | 2017-08-18 | 天津大学 | ERP analysis method of the horizontal delayed movement to viewing comfort degree |
| CN107220599A (en) * | 2017-05-16 | 2017-09-29 | 北京信息科技大学 | Image quality evaluating method based on EEG signal |
| CN107609492A (en) * | 2017-08-25 | 2018-01-19 | 西安电子科技大学 | Distorted image quality based on EEG signals perceives evaluation method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346529A (en) * | 2016-05-07 | 2017-11-14 | 浙江大学 | A kind of digital picture quality evaluation method and device |
| RU2653239C1 (en) * | 2017-05-02 | 2018-05-07 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Саратовский государственный технический университет имени Гагарина Ю.А." (СГТУ имени Гагарина Ю.А.) | Method of person identification by eeg-response to ambiguous images |
| CN107590445B (en) * | 2017-08-25 | 2019-05-21 | 西安电子科技大学 | Aesthetic images quality evaluating method based on EEG signals |
| CN108769671B (en) * | 2018-06-13 | 2020-09-22 | 天津大学 | Stereo image quality evaluation method based on self-adaptive fusion image |
-
2019
- 2019-07-01 CN CN201910583773.XA patent/CN110279415B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060011074A (en) * | 2004-07-29 | 2006-02-03 | 학교법인 포항공과대학교 | Method of estimating user's preference of a product using event related potential |
| CN105141935A (en) * | 2015-05-21 | 2015-12-09 | 天津大学 | Method for analyzing relevance between influence of dimension deviation on stereo image viewing comfort levels and ERP |
| CN105915889A (en) * | 2016-04-19 | 2016-08-31 | 天津大学 | Method for evaluating comfort level of compressed three-dimensional image through employing ERP technology |
| CN107071380A (en) * | 2016-11-03 | 2017-08-18 | 天津大学 | ERP analysis method of the horizontal delayed movement to viewing comfort degree |
| CN107220599A (en) * | 2017-05-16 | 2017-09-29 | 北京信息科技大学 | Image quality evaluating method based on EEG signal |
| CN107609492A (en) * | 2017-08-25 | 2018-01-19 | 西安电子科技大学 | Distorted image quality based on EEG signals perceives evaluation method |
Non-Patent Citations (2)
| Title |
|---|
| Calibrating Human Perception Threshold of Video Distortion Using EEG;Liu X , Tao X , Zhan Y;《2018 25th IEEE International Conference on Image Processing (ICIP)》;20180906;第3543-3547页 * |
| 基于脑电技术的图像质量评价研究;贺亚光;《中国优秀硕士学位论文全文数据库信息科技辑》;20160815;正文第14-15,24-28,38,51-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110279415A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110279415B (en) | Image distortion threshold coefficient estimation method based on electroencephalogram signals | |
| Scholler et al. | Toward a direct measure of video quality perception using EEG | |
| Lee et al. | The comparative measurements of eyestrain caused by 2D and 3D displays | |
| Rossion et al. | Does physical interstimulus variance account for early electrophysiological face sensitive responses in the human brain? Ten lessons on the N170 | |
| CN107609492B (en) | Distorted image quality based on EEG signals perceives evaluation method | |
| Joshi et al. | Colour retinal image enhancement based on domain knowledge | |
| Moon et al. | Perceptual experience analysis for tone-mapped HDR videos based on EEG and peripheral physiological signals | |
| Zhang et al. | Gender, facial attractiveness, and early and late event-related potential components | |
| Kim et al. | EEG based comparative measurement of visual fatigue caused by 2D and 3D displays | |
| Zhao et al. | Video quality assessment based on measuring perceptual noise from spatial and temporal perspectives | |
| Palanisamy et al. | An improved luminosity and contrast enhancement framework for feature preservation in color fundus images | |
| CN108769671B (en) | Stereo image quality evaluation method based on self-adaptive fusion image | |
| CN107220599A (en) | Image quality evaluating method based on EEG signal | |
| US11006834B2 (en) | Information processing device and information processing method | |
| Strauss et al. | Exploiting the self-similarity in ERP images by nonlocal means for single-trial denoising | |
| CN113554597B (en) | Image quality evaluation method and device based on electroencephalogram characteristics | |
| Engelke et al. | Visual attention modelling for subjective image quality databases | |
| CN105141935A (en) | Method for analyzing relevance between influence of dimension deviation on stereo image viewing comfort levels and ERP | |
| US9552629B2 (en) | Medical thermal image processing for subcutaneous detection of veins, bones and the like | |
| Akamine et al. | Video quality assessment using visual attention computational models | |
| CN105915889A (en) | Method for evaluating comfort level of compressed three-dimensional image through employing ERP technology | |
| CN105959681A (en) | ERP analysis method for influences of depth delay motion on watching comfort level | |
| Liu et al. | Neurophysiological assessment of image quality from EEG using persistent homology of brain network | |
| Bosse et al. | On the stimulation frequency in ssvep-based image quality assessment | |
| Darcy et al. | Physiological capture of augmented viewing states: objective measures of high-dynamic-range and wide-color-gamut viewing experiences |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |