CN109259775A - A kind of face stimulation normal form generation method and self-closing disease analysis system - Google Patents
A kind of face stimulation normal form generation method and self-closing disease analysis system Download PDFInfo
- Publication number
- CN109259775A CN109259775A CN201811005733.9A CN201811005733A CN109259775A CN 109259775 A CN109259775 A CN 109259775A CN 201811005733 A CN201811005733 A CN 201811005733A CN 109259775 A CN109259775 A CN 109259775A
- Authority
- CN
- China
- Prior art keywords
- face
- pupil diameter
- picture
- sequence
- stimulation
- 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
- A61B5/16—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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/163—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state by tracking eye movement, gaze, or pupil change
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Hospice & Palliative Care (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Heart & Thoracic Surgery (AREA)
- Educational Technology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Veterinary Medicine (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of face stimulation normal form generation method and self-closing disease analysis systems.This method comprises: obtaining face picture；Face picture is pre-processed to obtain face stimulation picture, wherein pretreatment includes rotating face picture to default rotation angle, presetting rotation angle includes at least two different rotation angles；Generating face using face stimulation picture stimulates sequence of pictures；Display duration is set to obtain face stimulation normal form for the face stimulation picture in face stimulation sequence of pictures.The self-closing disease analysis system includes: display device, for showing that the face for utilizing the above method to generate stimulates normal form；Data acquisition device, for acquiring pupil diameter data when subject watches face stimulation normal form；The processor connecting with data acquisition device determines that the self-closing disease of subject analyzes result for extracting the characteristic value of pupil diameter data, and according to characteristic value.Objective self-closing disease can be obtained by the acceptable mode of subject as a result, and analyze result.
Description
Technical field
The present invention relates to medical image technical field, relate more specifically to a kind of face stimulation normal form generation method and self-closing
Disease analysis system.
Background technique
With the development of science and technology, the enhancing of equipment disposal ability is calculated, more and more image datas are applied to doctor
Field.
For example, carrying out self-closing disease analysis and research using stimulating image is a kind of new technological means, independent of parent
The observation and understanding of child are judged, the limitation too much by parent's human-subject test is thus avoided.But current
The design of stimulating image is difficult to meet to the requirement of self-closing disease precision of analysis.
Summary of the invention
The present invention is proposed in view of the above problem.The present invention provides a kind of face stimulation normal form generation method and certainly
Close disease analysis system.
According to an aspect of the present invention, a kind of face stimulates normal form generation method, comprising:
Obtain face picture；
The face picture is pre-processed, to obtain face stimulation picture, wherein the pretreatment includes by the face
For picture rotation to default rotation angle, the default rotation angle includes at least two different rotation angles；
Generating face using face stimulation picture stimulates sequence of pictures；
Display duration is set for the face stimulation picture in face stimulation sequence of pictures, to obtain the face thorn
Swash normal form.
Illustratively, the pretreatment further include:
Face correction process is carried out to the face picture, the eyes, nose and mouth of every face are all incident upon phase
Same position；
The face picture is processed into grayscale image and is adjusted to same grayscale range, same brightness range；
The face picture is cut to the ellipse of same size, so that the oval face picture after cutting only includes
Facial area and do not include ear region；
Oval face picture after the cutting is placed in the center of the completely black picture of same size.
Illustratively, described to include: using face stimulation picture generation face stimulation sequence of pictures
Face stimulation picture arrangement is stimulated into sequence of pictures at the face, wherein the face of different rotary angle
Stimulate picture staggered-sequence.
Illustratively, described to include: at face stimulation sequence of pictures by face stimulation picture arrangement
The face stimulation picture for being 0 degree based at least one rotation angle rotates the people that angle is 180 degree at least one
Face stimulation picture is alternately sequentially generated the face stimulation sequence of pictures.
Illustratively, display duration is set to obtain for the face stimulation picture in face stimulation sequence of pictures
Stating face stimulation normal form includes:
For the face stimulation picture in face stimulation sequence of pictures, a variety of display durations are set.
Illustratively, the face picture includes three classes photo: children's photo, young people's photo and the elderly's photo,
In every class photo include male's photo and women photo.
According to a further aspect of the invention, a kind of self-closing disease analysis system is additionally provided, comprising:
Display device stimulates normal form using the face generated such as any one of claim 1 to 6 the method for showing；
Data acquisition device, for acquiring pupil diameter data when subject watches the face stimulation normal form；
The processor being connect with the data acquisition device, for extracting the characteristic value of the pupil diameter data, and root
Determine that the self-closing disease of the subject analyzes result according to the characteristic value.
Illustratively, the display device is also used to before showing the face stimulation normal form, first shows completely black picture；
The data acquisition device is also used to acquire the pupil diameter data when subject watches the completely black picture,
Using as pupil diameter base-line data；
The processor is also used to pre-process the pupil diameter data using the pupil diameter base-line data,
To obtain the pupil diameter sequence for extracting the characteristic value.
Illustratively, the pretreatment is accomplished by the following way in the processor:
Primary pupil diameter sequence is established according to the pupil diameter data；
The vacancy value of the primary pupil diameter sequence is filled up, to obtain complete pupil diameter sequence；
Pupil diameter data in the complete pupil diameter sequence are subtracted into the pupil diameter base-line data, to obtain
The pupil diameter sequence.
Illustratively, the processor is also used to:
Noise reduction process is filtered to the pupil diameter sequence；And/or
Down-sampled processing is carried out to the pupil diameter sequence.
Illustratively, the characteristic value that the processor extracts the pupil diameter data is accomplished by the following way:
Pupil diameter change curve is generated using the pupil diameter sequence, and is mentioned using the pupil diameter change curve
Take that mean value, variance, maximum value, minimum value, the pupil diameter of pupil diameter reach the time of maximum value and pupil diameter reaches
The time of minimum value；And/or
Pupil speed change curves are generated using the pupil diameter sequence, and are mentioned using the pupil speed change curves
Mean value, variance, maximum value, minimum value, the pupil diameter pace of change of pupil diameter pace of change is taken to reach the time of maximum value
And pupil diameter pace of change reaches the time of minimum value；And/or
Pupil acceleration change curve is generated using the pupil diameter sequence, and bent using the pupil acceleration change
The mean value of line drawing pupil diameter variation acceleration, variance, maximum value, minimum value, pupil diameter variation acceleration reach maximum
The time of value and pupil diameter variation acceleration reach the time of minimum value.
Illustratively, the pupil diameter data are the data acquisition devices based on the list in face stimulation normal form
The pupil diameter data of a face stimulation picture or all faces stimulation picture collection.
Illustratively, the processor is also used to:
Using sample data training self-closing disease disaggregated model, to obtain the classifier for determining self-closing disease analysis result.
Illustratively, the disaggregated model is support vector cassification model.
Illustratively, the data acquisition device includes eye tracker and/or iris corder.
Face stimulation normal form generation method and self-closing disease analysis system according to an embodiment of the present invention, using subject to people
The specificity that pupil when the sensibility of face cognition, especially subject watch the face of different rotary angle changes, extracts quilt
Examination person observes pupil diameter variation characteristic when face stimulation normal form, is obtained by the acceptable mode of subject objective and accurate
Self-closing disease analyze result.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 shows the schematic flow chart of face stimulation normal form generation method according to an embodiment of the invention；
Fig. 2 shows the schematic flow charts of the pre-treatment step of face picture according to an embodiment of the invention；
Fig. 3 A, Fig. 3 B, Fig. 3 C and Fig. 3 D show pretreated face stimulation figure according to an embodiment of the invention
Piece；
Fig. 4 shows the schematic diagram of face stimulation normal form according to an embodiment of the invention；
Fig. 5 shows the schematic block diagram of self-closing disease analysis system according to an embodiment of the invention；
Fig. 6 shows the display process schematic of self-closing disease analysis system according to an embodiment of the invention；And
Fig. 7 shows the pretreated schematic flow chart of pupil diameter data according to an embodiment of the invention.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
The sensibility that the present invention utilizes subject to recognize face especially has the subject of self-closing disease tendency and without certainly
The specificity that pupil when closing the face of subject's viewing different rotary angle of disease tendency changes, provides a kind of face stimulation
Normal form generation method.In the following, face stimulation normal form generation method according to an embodiment of the present invention will be described with reference to Fig. 1.Fig. 1 is shown
The schematic flow chart of face stimulation normal form generation method 100 according to an embodiment of the invention.
As shown in Figure 1, method 100 includes step S110, step S120, step S130 and step S140.
Step S110 obtains face picture.
Face picture can be the photo for the shooting of face front, be also possible to from include positive face photo in extract
Face picture can also be the face picture extracted in video.As long as including clearly face direct picture.
Step S120 pre-processes the face picture that step S110 is obtained, to obtain face stimulation picture, wherein described
Pretreatment includes rotating the face picture that step S110 is obtained to default rotation angle, and the default rotation angle includes at least
Two different rotation angles.
The step S110 face picture obtained is pre-processed, non-face factor is reduced, subject is seen to reduce
The influence of pupil diameter variation when seeing, in order to avoid influence self-closing disease precision of analysis.
When watching postrotational face picture, the subject for thering is self-closing disease to be inclined to and the subject without self-closing disease tendency
There are different variation characteristics for pupil diameter.For this purpose, face picture can be rotated by pretreatment to default rotation angle.For
Self-closing disease analysis is carried out using more evolutions characteristic, above-mentioned default rotation angle includes at least two different rotation angles.
For example, part face Picture section can be rotated to a certain angle, another part face picture is rotated to another kind and is rotated
Angle.For example, can be by the same face picture rotation to two different rotation angles, to obtain two different rotary angles
The face picture of degree.
Step S130, the face stimulation picture pre-processed using step S120 generate face stimulation sequence of pictures.
The face stimulation picture group that step S120 is pre-processed stimulates sequence of pictures at face, forms orderly variation
Sequence of pictures, so as to obtain pupil diameter variation when subject persistently watches the face that orderly changes and stimulates picture,
To be analyzed for self-closing disease.Illustratively, the face stimulation picture that can use different rotary angle generates face stimulation picture
Sequence, the face that different angle is persistently watched to obtain subject stimulates pupil diameter when picture to change, to be used for self-closing disease
Analysis.Illustratively, the face stimulation picture that can use different people generates face stimulation sequence of pictures, holds to obtain subject
The face of continuous viewing different people stimulates pupil diameter variation when picture, to analyze for self-closing disease.Illustratively, it can use
The face stimulation picture of the different rotary angle of different people, which generates face, stimulates sequence of pictures, persistently watches not to obtain subject
With pupil diameter variation of the people when the face of different rotary angle stimulates picture, to be analyzed for self-closing disease.So as to benefit
It is analyzed with the pupil diameter variation in a variety of situations, to promote the universality and accuracy of self-closing disease analysis.
Step S140, when display is arranged in the face stimulation picture in face stimulation sequence of pictures generated for step S130
It is long, to obtain the face stimulation normal form.
Suitable display duration is arranged in the face stimulation picture in face stimulation sequence of pictures generated for step S130.
If for individual human face stimulation picture display duration it is too long, subject be easy it is absent-minded, so that knot cannot be analyzed correctly
Fruit.If too short for the display duration of individual human face stimulation picture, the data of acquisition may be insufficient for analysis demand.Show
Example property, the display duration of individual human face stimulation picture can be set to 2 seconds~5 seconds.On the other hand, subject is mostly
Child, can not accept the test of long time, therefore be also required to consider that whole display duration cannot be too long.Illustratively, whole aobvious
Show that duration can control in 1 minute.
According to an embodiment of the invention, the face picture using different rotary angle carries out self-closing disease point as stimulus
Analysis, is easy to receive, is particularly suitable for the case where subject is children, it is ensured that analysis result is objective, accurate.
Fig. 2 shows the schematic flows of the pre-treatment step S120 of face picture according to an embodiment of the invention
Figure.As shown in Fig. 2, step S120 includes following sub-step:
Step S121: face correction process is carried out to face picture, the eyes, nose and mouth of every face are all projected
In identical position.
Using face correction algorithm, the eyes, nose and mouth of every face are all being incident upon identical position, so that
Face picture " handsome ", is suitable as face stimulation picture.
Step S122: after the face correction of step S121, face picture being rotated to default rotation angle, described pre-
If rotating angle includes at least two different rotation angles.Specifically as previously mentioned, which is not described herein again.
Step S123: being processed into grayscale image for face picture and is adjusted to same grayscale range, same brightness range.
It is processed into interference of the grayscale image to avoid pupil by color, is adjusted to same grayscale range, same brightness range
To avoid pupil by different gray scales, the interference of different brightness.
Face picture: being cut to the ellipse of same size by step S124, so that the oval face picture after cutting
Only comprising facial area and not comprising ear region.The step removes the extraneous areas such as ear, to ensure subject to face
Attention rate.
Step S125: above-mentioned oval face picture is placed in the center of the completely black picture of same size.
Oval face picture is placed in the center of the completely black picture of same size, so that subject is easy at concern
Face in center.
It is appreciated that above-mentioned steps S122, step S123 and step S124 do not limit execute sequence.In other words,
Step S122, step S123 and step S124, which can be exchanged, executes sequence, input of the output of previous step as next step,
The input of final output same size, same grayscale range, the oval face picture of same brightness range as step S125,
Wherein, rotation angle is only preset to need to include at least two different rotation angles.
Illustratively, after the face picture obtained by step S110 is carried out face normalization processing by execution step S121,
The ellipse that the face picture after step S121 correction process is cut to same size by step S124 can be first carried out, so that
Oval face picture after cutting only includes facial area and does not include ear region.Step S123 can be executed again will be through
Oval face picture after step S124 is cut is processed into grayscale image and is adjusted to same grayscale range, same brightness range
Oval face picture.Step S122 can be executed again to be rotated through step S123 oval face picture adjusted to default
Angle is rotated, the default rotation angle includes at least two different rotation angles.It will be through step finally, executing step S125
The postrotational oval face picture of S122 is placed in the center of the completely black picture of same size, to obtain can be used for self-closing
The face of disease analysis stimulates picture.
Fig. 3 A, Fig. 3 B, Fig. 3 C and Fig. 3 D show pretreated face stimulation figure according to an embodiment of the invention
Piece.As can be seen that Fig. 3 A is to rotate the positive face face that angle is 0 degree to stimulate picture, Fig. 3 B is to rotate the face that falls that angle is 180 degree
Face stimulates picture, and Fig. 3 C is that rotation angle is that 90 degree of face clockwise stimulates picture, and Fig. 3 D is that rotation angle is clockwise
270 degree of face stimulates picture.
By carrying out above-mentioned pretreatment to face picture, acquisition obviates various disturbing factors and including different rotary angle
Face stimulate picture.These disturbing factors such as face size, the background parts in face picture, the gray scale of image and brightness
Deng.Thereby ensure that the accurate and effective of self-closing disease analytic process.
In one embodiment, step S130 is utilized stimulates picture to generate people by the face that step S120 is pre-processed
Face stimulation sequence of pictures includes: that the face pre-processed by step S120 stimulation picture arrangement is stimulated picture sequence at face
Column, wherein the face of different rotary angle stimulates picture staggered-sequence.
Face stimulation picture arrangement is stimulated sequence of pictures at face, available subject pierces the face orderly changed
The dynamic response of picture is swashed, it is possible thereby to which the feature based on pupil variation carries out self-closing disease analysis.
The face of different rotary angle is stimulated picture staggered-sequence, people of the available subject to different rotary angle
The understanding and reaction of face carry out self-closing disease analysis hereby based on the feature of pupil variation.On the other hand, the people of different rotary angle
Face can excite " curiosity " of subject, so that the good attention rate of subject is kept, to guarantee the effective of self-closing disease analysis
Property and accuracy.
In one embodiment, face stimulation picture arrangement is stimulated sequence of pictures at face in step S130 includes: base
Rotating the face that angle is 180 degree at least one in the face stimulation picture that at least one rotation angle is 0 degree stimulates picture
Alternately it is sequentially generated face stimulation sequence of pictures.
Rotating the face that angle is 0 degree to stimulate picture is positive face, and rotation angle is that the face of 180 degree stimulates picture to be down
Face.Positive face is the most familiar of face image of subject, and face and positive face contrast are maximum.Fig. 4 shows one according to the present invention
The schematic diagram of the face stimulation normal form of embodiment.It includes that 12 faces stimulate picture (part face that the face, which stimulates sequence of pictures,
Stimulation picture is not shown), by 2 positive faces, 1 fall face, 3 positive faces, 1 face forms by face, 2 positive faces and 3.Pass through
Positive face and face are alternately sequentially generated face stimulation sequence of pictures, available subject to most familiar of positive face and contrast most
The dynamic of big face understands and reaction, it is possible thereby to which the feature based on pupil variation carries out self-closing disease analysis.
Step S140 is directed to stimulates the face in sequence of pictures to stimulate picture setting aobvious by the face that step S130 is generated
Showing duration to obtain face stimulation normal form includes: to stimulate the face in sequence of pictures to pierce for the face generated by step S130
Swash picture and a variety of display durations are set.For example, 2 kinds of display durations of setting or more.As shown in figure 4, the face stimulates normal form
Including two kinds of display durations: 2 seconds and 4 seconds.A length of each display 2 seconds, rear 3 faces when display is arranged in preceding 9 faces stimulation picture
Stimulate picture that a length of each display 4 seconds when showing are set.It is 30 seconds a length of when the display of entire face stimulation normal form.
By the way that different display durations is arranged, relatively filled as that subject can be allowed to have current face under longer display duration
The time divided understands reaction, and such as shorter display duration can test subject and react the understanding of fast-changing face.
Self-closing disease analysis is carried out to obtain subject's situation of change of pupil in different display durations,
Illustratively, above-mentioned face picture includes three classes photo: children's photo, young people's photo and the elderly's photo,
In every class photo include male's photo and women photo.
Children, young people and the elderly embody children to the psychological cognition degree of face to a certain extent.Such as the age
Similar children's photo is that most familiar of same sensitivity is highest, is finally old followed by similar to young people's photo of Papa and Mama
Year people's photo.Thus, it is possible to be sequentially generated face stimulation normal form, root by children's photo, young people's photo and the elderly's photo
According to the understanding reaction of the mutation analysis subject of pupil, to carry out self-closing disease analysis.It is optional in order to avoid the influence of gender
Ground, every class photo include male's photo and women photo.Optionally, every class photo include equivalent amount male's photo and
Women photo influences to avoid the different brings in the number of pictures of different sexes.Thus, it is possible to obtain it is more objective from
Close disease analysis result.
According to an aspect of the present invention, a kind of self-closing disease analysis system is provided.Fig. 5 shows an implementation according to the present invention
The schematic block diagram of the self-closing disease analysis system 500 of example.As shown in figure 5, system 500 includes display device 510, data acquisition dress
The processor 530 setting 520 and being connect with data acquisition device 520.
Display device 510 is used to show the face stimulation normal form generated using the above method.
Illustratively, display device 510 can be screen, show that face stimulates the face in normal form to stimulate figure by screen
Piece.Illustratively, display device 510 can be projector, stimulate the face in normal form to stimulate picture projection to curtain face
On upper or wall.Illustratively, display device 510 can be slide projector, and the face stimulation picture in face stimulation normal form is made into
Lantern slide carries out Projection Display.Illustratively, display device 510 can also be reading plate, directly place papery on reading plate
Face stimulation picture give subject viewing.In short, display device 510 is only required to stimulating face into the face thorn in normal form
Sharp picture is shown to subject's viewing, and passes through electronic equipment or the corresponding display duration of manual mode control.The present invention
It is without limitation.
When data acquisition device 520 is used to acquire the face stimulation normal form that subject's viewing is shown by display device 510
Pupil diameter data.
Data acquisition device 520 can be the device that can acquire pupil diameter data of any existing or following exploitation
Or equipment, the pupil diameter data that subject's viewing can be acquired with it when stimulating normal form by the face that display device 510 is shown.
Illustratively, data acquisition device 520 can be the equipment such as eye tracker or iris corder, be also possible to the combination of the two.Pass through it
The acquisition devices such as included camera capture the pupil diameter data of subject's eyes, to analyze for self-closing disease.For example, can adopt
With the non-intrusion type eye tracker of model SMI RED500, display is passed through in viewing with the sample frequency record subject of 120Hz
The face that device 510 is shown stimulates pupil diameter data when normal form.Data acquisition device 520 is used as noninvasive equipment, Ke Yitong
The pupil diameter data for crossing non-intruding mode acquisition subject, will not bring discomfort to subject, acceptant to be particularly suitable for
The case where subject is children.
Processor 530 is connect with data acquisition device 520, for extracting the pupil for passing through data acquisition device 520 and acquiring
The characteristic value of diameter data, and determine that the self-closing disease of subject analyzes result according to this feature value.
Common normal person, self-closing disease tendency type (patients with mild) personnel and self-closing disease patient pass through display device in viewing
The face of 510 displays stimulates pupil diameter changing rule when normal form different, can pass through the various change of pupil diameter data
Feature instantiation.Processor 530 extracts the various change of the pupil diameter data of the subject acquired by data acquisition device 520
Characteristic value, can be determined according to this feature value the subject self-closing disease analysis result.It is, for example, not that self-closing disease, which analyzes result,
There is self-closing tendency, confidence level 95% can then determine that the subject does not have the problem of self-closing disease aspect substantially, belong to common
Normal person.In another example being to have self-closing tendency, confidence level 65% can then determine that the subject belongs to self-closing disease tendency substantially
The slight self-closing disease patient of type, needs to keep a close eye on.In another example be to have self-closing tendency, confidence level 95% then substantially can be with
It determines that the subject is self-closing disease patient, needs to treat and nurse.
Above-mentioned self-closing disease analysis system obtains subject and watches above-mentioned face thorn by the acceptable mode of subject
Swash pupil diameter data when normal form, and then the analysis based on the variation characteristic to pupil diameter data obtains oneself of the subject
Close disease analysis result.Test process is simple and is easy to receive, and self-closing disease analysis result is objective and accurate, is particularly suitable for self-closing disease morning
The application of phase screening etc..
In one embodiment, display device 510 is also used to before showing above-mentioned face stimulation normal form, is first shown completely black
Picture.Data acquisition device 520 is also used to acquire pupil diameter data when subject watches completely black picture, using straight as pupil
Diameter base-line data.
It is appreciated that all ages and classes, dissimilarity others, pupil size is all different.Utilize pupil diameter data
Pupil mutation analysis is carried out, needs to know the baseline value of pupil diameter.For this purpose, can use completely black picture as reference stimuli figure
Piece first watches completely black picture, acquires the subject during this for each subject before viewing face stimulation normal form
Pupil diameter data as pupil diameter base-line data.The display time of completely black picture is unsuitable too long, is otherwise switched to viewing
The pupil of subject has been easy sense of discomfort when face stimulates normal form, influences test effect.Also should not be too short, the data otherwise acquired
It is accurate to be not sufficiently stable.Illustratively, the display time of completely black picture can be set to 2 to 5 seconds.Fig. 6 is shown according to the present invention
The display process schematic of the self-closing disease analysis system of one embodiment.As shown in fig. 6, before display face stimulation normal form,
First show 4 seconds completely black pictures.Illustratively, the average value of the pupil diameter data during taking subject to watch completely black picture is made
For pupil diameter base-line data.
Processor 530 is also used to pre-process pupil diameter data using pupil diameter base-line data, to be used
In the pupil diameter sequence for extracting the characteristic value.
Under normal circumstances, the data that data acquisition device 520 acquires are imperfect, and contain noise.Therefore, in order to obtain standard
True analysis can embody accurate pupil to obtain as a result, it is desirable to the pupil diameter data to acquired original are pre-processed
The pupil diameter sequence of diameter change.Among these, it is necessary to be carried out in advance using above-mentioned pupil diameter base-line data as a reference value
Processing.Pupil diameter sequence contains timeliness, and in other words, the data element in pupil diameter sequence is by uniform sampling
The sequence of time granularity.For example, pupil diameter sequence is { D1, D2, D3, D4, D5, D6, D7, D8 }, sampling time granularity
For 10ms, then the sampling instant point of the pupil diameter sequence is { 0,10ms, 20ms, 30ms, 40ms, 50ms, 60ms, 70ms }.
Therefore, the feature of pupil diameter variation can be extracted based on pupil diameter sequence.
Fig. 7 shows the pretreated schematic flow chart of pupil diameter data according to an embodiment of the invention.Such as
Shown in Fig. 7, the pretreatment is accomplished by the following way in processor 530, executes following steps:
Step S710 establishes primary pupil diameter sequence according to the pupil diameter data that data acquisition device 520 acquires.
Subject watch face stimulation normal form when, if blink or it is absent-minded see otherwise, eyes do not stare at screen,
Data acquisition device 520 will likely not acquire data, i.e. the moment does not have sampled value.Data acquisition device 520 is acquired
Pupil diameter data are arranged in primary pupil diameter sequence by sampling instant, wherein vacancy is left at the time of no sampled value
Value.
For example, the pupil diameter data such as table 1 that data acquisition device 520 acquires, wherein with first sampled data when
Between point be initial time.
1 pupil diameter data record sheet of table
| Sampling instant | 0 | 10ms | 20ms | 30ms | 40ms | 50ms | 60ms | 70ms |
| Sampled value | S1 | S2 | S4 | S5 | S6 | S8 |
As shown in table 1, at 20ms the and 60ms moment, without sampled value.The primary pupil diameter sequence obtained based on table 1 is
{ S1, S2, NULL, S4, S5, S6, NULL, S8 }, wherein NULL indicates vacancy value.
Step S720 fills up the vacancy value by the step S710 primary pupil diameter sequence established, to obtain complete pupil
Bore dia sequence.
As described above, the pupil diameter data that data acquisition device 520 acquires may be imperfect.For pass through step S710
The primary pupil diameter sequence of acquisition, first counts its shortage of data rate.Shortage of data rate is the quantity and primary pupil of vacancy value
The ratio of element total quantity in diameter sequence.If shortage of data rate is more than preset threshold, current primary pupil diameter sequence is indicated
The missing values of column are excessive, should not be used as self-closing disease analyze in case analyze result it is not accurate enough.Abandon current primary pupil diameter sequence
Column re-use data acquisition device 520 when necessary and acquire data again.The preset threshold for example can be 25%, self-closing
The administrator of disease analysis system can reset the preset threshold.If shortage of data rate is less than preset threshold, can use
" forward approach " is filled up missing values, i.e., is made with the previous sampled value of the hollow missing value of primary pupil diameter sequence to fill up the vacancy
Value.Still with the above-mentioned primary pupil diameter sequence { S1, S2, NULL, S4, S5, S6, NULL, S8 } obtained based on table 1 for, number
According to miss rate=25%, be not above preset threshold, the complete pupil diameter sequence after completion be S1, S2, S2, S4, S5, S6,
S6, S8 }.The complete pupil diameter sequence for having obtained the sampled value including each sampling instant point as a result, ensure that for subsequent
The integrality of the data of self-closing disease analysis.
Step S730 subtracts the pupil diameter data in the complete pupil diameter sequence obtained by step S720 above-mentioned
Pupil diameter base-line data, to obtain pupil diameter sequence.
As previously mentioned, all ages and classes, dissimilarity others, pupil size is all different.Utilize pupil diameter data
Pupil mutation analysis is carried out, needs to subtract the pupil diameter data in the complete pupil diameter sequence obtained by step S720
Above-mentioned pupil diameter base-line data.The pupil diameter sequence of pupil diameter variation is obtained to embody as a result,.It is straight based on pupil
Diameter sequence accurately analyzes pupil variation, to guarantee the accuracy of self-closing disease analysis.
Illustratively, the processor is also used to execute step S740, to the pupil diameter sequence obtained by step S730
Column are filtered noise reduction process.
Noise reduction process, such as low-pass filtering treatment are filtered to the pupil diameter sequence obtained by step S730, gone
Except noise jamming, to improve the accuracy of self-closing disease analysis.
Illustratively, the processor is also used to execute step S750, to the pupil diameter sequence obtained by step S730
Column carry out down-sampled processing.
Data acquisition device 520 for example acquires pupil diameter data with the sample frequency of 120Hz or 60Hz.Since pupil becomes
Change speed without that so fastly, data scale can be reduced by down-sampled, such as the pupil obtained by step S730 is straight
Diameter sequence is downsampled to 20Hz.Data scale is reduced as a result, improves the processing speed and analysis efficiency of self-closing disease analysis.
It should be understood that above-mentioned steps S730, step S740 and step S750 can be exchanged and be executed sequence.Such as it can first carry out
Step S740 is filtered noise reduction process, then executes step S750 and carry out down-sampled processing, finally executes step S730 again and subtracts
Above-mentioned pupil diameter base-line data obtains pupil diameter sequence.
Processor 530 can be analyzed based on above-mentioned pupil diameter sequential extraction procedures various features value for self-closing disease.Such as with
The relevant characteristic value of pupil diameter: mean value, variance, maximum value, minimum value, the pupil diameter of pupil diameter reach maximum value when
Between and pupil diameter reach time of minimum value.Such as characteristic value relevant to pupil diameter pace of change: pupil diameter becomes
Mean value, variance, maximum value, minimum value, the pupil diameter pace of change for changing speed reach time and the pupil diameter of maximum value
Pace of change reaches the time of minimum value.Such as characteristic value relevant to pupil diameter variation acceleration: pupil diameter variation adds
The mean value of speed, variance, maximum value, minimum value, pupil diameter variation acceleration reach time and the pupil diameter of maximum value
Variation acceleration reaches the time of minimum value.
In one example, processor 530 is also used to generate pupil diameter change curve using above-mentioned pupil diameter sequence,
And reached most using mean value, variance, maximum value, minimum value, the pupil diameter that the pupil diameter change curve extracts pupil diameter
The time and pupil diameter that are worth greatly reach the time of minimum value.Using above-mentioned pupil diameter sequence, pass through the side such as curve matching
Method generates pupil diameter change curve, is equivalent to discrete pupil diameter Sequentially continuous, the characteristic value of extraction is more smart
Really.Pupil diameter change procedure visualization simultaneously, convenient for observation.
In one example, processor 530 is also used to generate pupil speed change curves using above-mentioned pupil diameter sequence,
And it is straight using the mean value of pupil speed change curves extraction pupil diameter pace of change, variance, maximum value, minimum value, pupil
Diameter pace of change reaches the time of maximum value and pupil diameter pace of change reaches time of minimum value.It is straight using above-mentioned pupil
Diameter sequence generates pupil diameter speed change curves by the methods of curve matching, is equivalent to discrete pupil diameter sequence
The characteristic value of serialization, extraction is more accurate.Pupil diameter velocity variations process visualization simultaneously, convenient for observation.
In one example, processor 530 is also used to generate pupil acceleration change using above-mentioned pupil diameter sequence bent
Line, and using the pupil acceleration change curve extract the pupil diameter variation mean value of acceleration, variance, maximum value, minimum value,
Pupil diameter variation acceleration reaches the time of maximum value and pupil diameter changes the time that acceleration reaches minimum value.It utilizes
Above-mentioned pupil diameter sequence generates pupil diameter acceleration change curve by the methods of curve matching, is equivalent to discrete
The characteristic value of pupil diameter Sequentially continuous, extraction is more accurate.Pupil diameter acceleration change process visualization simultaneously, just
In observation.
Optionally, above-mentioned pupil diameter data are data acquisition devices 520 based on the individual human face in face stimulation normal form
Stimulate the pupil diameter data of picture or all faces stimulation picture collection.For example, display device 510 show it is as shown in FIG. 6
Face stimulates normal form.Data acquisition device 520 can stimulate picture collection pupil diameter data based on the individual human face in Fig. 6,
12 parts of pupil diameter data are acquired respectively for 12 face stimulation pictures altogether.Data acquisition device 520 can be based in Fig. 6
All faces stimulate picture collection pupil diameter data, obtain 1 part include 12 faces stimulation pictures integrated testability
Pupil diameter data in journey.Pupil diameter data based on individual human face stimulation picture can analyze subject to Static Human Face
Understanding and reaction.It can analyze subject to dynamic based on all face stimulation pictures in the face stimulation normal form orderly changed
The understanding and reaction of face, so that obtaining more comprehensively self-closing disease analyzes result.
In one embodiment, processor 530 is also used to using sample data training self-closing disease disaggregated model, to be used
In the classifier for determining self-closing disease analysis result.
Sample data for example can be the common youngster for the self-closing disease patient of relevant hospital diagnosis and treatment and school, kindergarten
Child, the pupil that the face that display device 510 is shown is passed through by sampler's viewing when stimulating normal form by the acquisition of data acquisition device 520
Bore dia data.Each sample data includes the above-mentioned various characteristic values extracted from the pupil diameter data by sampler, with
And the self-closing disease tag along sort by sampler.Self-closing disease tag along sort for example may is that serious self-closing disease, general self-closing disease,
Slight self-closing disease, non-self-closing disease etc..
It can be based on one of features described above value or sorting algorithm structure a variety of, using any existing or following exploitation
Build disaggregated model.Such as it can use support vector machines (Support Vector Machine, abbreviation SVM) sorting algorithm, determine
Plan tree algorithm scheduling algorithm constructs disaggregated model.Using the parameter of sample data train classification models, to obtain for determining certainly
Close the classifier of disease analysis result.
It is constructed as validity feature point it is alternatively possible to choose the good characteristic value of specific findings from features described above value
Class model.Illustratively, can use sequence selects forward (Sequential Forward Selection, abbreviation SFS) to calculate
Method picks out 5 features to do very well and constructs disaggregated model as validity feature.To reduce the operand of parameter training,
Improve the treatment effeciency of classifier.
The classifier for determining self-closing disease analysis result is obtained as a result,.Subject is acquired by data acquisition device 520
The face that viewing is shown by display device 510 stimulates pupil diameter data when normal form, and processor 530 is from the pupil diameter number
Corresponding characteristic value input classifier is extracted according to middle, the self-closing disease analysis result of the subject can be obtained.Test process is easy
Receive, it is objective and accurate that self-closing disease analyzes result.
Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should not be construed to reflect an intention that i.e. claimed
The present invention claims features more more than feature expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
Sign is to solve corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in this specific
Embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.
It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize some moulds in pattern recognition device according to an embodiment of the present invention
The some or all functions of block.The present invention is also implemented as a part or complete for executing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention can store
On a computer-readable medium, it or may be in the form of one or more signals.Such signal can be from internet
Downloading obtains on website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention
Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection scope.
Claims (15)
1. a kind of face stimulates normal form generation method, comprising:
Obtain face picture；
The face picture is pre-processed, to obtain face stimulation picture, wherein the pretreatment includes by the face picture
To default rotation angle, the default rotation angle includes at least two different rotation angles for rotation；
Generating face using face stimulation picture stimulates sequence of pictures；
Display duration is set for the face stimulation picture in face stimulation sequence of pictures, to obtain the face stimulation model
Formula.
2. according to the method described in claim 1, wherein, the pretreatment further include:
The face picture is being rotated to before default rotation angle, face correction process is carried out to the face picture, it will
Eyes, nose and the mouth of every face are all incident upon identical position；
The face picture is processed into grayscale image and is adjusted to same grayscale range, same brightness range；
The face picture is cut to the ellipse of same size, so that the oval face picture after cutting only includes face
Region and do not include ear region；
Oval face picture after the cutting is placed in the center of the completely black picture of same size.
3. according to the method described in claim 2, wherein, utilization face stimulation picture, which generates face, stimulates picture sequence
Column include:
Face stimulation picture arrangement is stimulated into sequence of pictures at the face, wherein the face of different rotary angle stimulates
Picture staggered-sequence.
4. according to the method described in claim 3, wherein, described stimulate face stimulation picture arrangement at the face is schemed
Piece sequence includes:
The face stimulation picture for being 0 degree based at least one rotation angle rotates the face thorn that angle is 180 degree at least one
Sharp picture is alternately sequentially generated the face stimulation sequence of pictures.
5. method according to any one of claims 1 to 4, wherein for the face in face stimulation sequence of pictures
Display duration is arranged to obtain the face stimulation normal form and include: in stimulation picture
For the face stimulation picture in face stimulation sequence of pictures, a variety of display durations are set.
6. method according to any one of claims 1 to 4, wherein the face picture includes three classes photo: Er Tongzhao
Piece, young people's photo and the elderly's photo, wherein every class photo includes male's photo and women photo.
7. a kind of self-closing disease analysis system, comprising:
Display device stimulates normal form using the face generated such as any one of claim 1 to 6 the method for showing；
Data acquisition device, for acquiring pupil diameter data when subject watches the face stimulation normal form；
The processor being connect with the data acquisition device, for extracting the characteristic value of the pupil diameter data, and according to institute
State the self-closing disease analysis result that characteristic value determines the subject.
8. system as claimed in claim 7, wherein
The display device is also used to before showing the face stimulation normal form, first shows completely black picture；
The data acquisition device is also used to acquire the pupil diameter data when subject watches the completely black picture, to make
For pupil diameter base-line data；
The processor is also used to pre-process the pupil diameter data using the pupil diameter base-line data, with
To the pupil diameter sequence for extracting the characteristic value.
9. system as claimed in claim 8, wherein the pretreatment is accomplished by the following way in the processor:
Primary pupil diameter sequence is established according to the pupil diameter data；
The vacancy value of the primary pupil diameter sequence is filled up, to obtain complete pupil diameter sequence；
Pupil diameter data in the complete pupil diameter sequence are subtracted into the pupil diameter base-line data, it is described to obtain
Pupil diameter sequence.
10. system as claimed in claim 9, wherein the processor is also used to:
Noise reduction process is filtered to the pupil diameter sequence；And/or
Down-sampled processing is carried out to the pupil diameter sequence.
11. such as the described in any item systems of claim 7 to 10, wherein the processor extracts the pupil diameter data
Characteristic value is accomplished by the following way:
Pupil diameter change curve is generated using the pupil diameter sequence, and extracts pupil using the pupil diameter change curve
Mean value, variance, maximum value, minimum value, the pupil diameter of bore dia reach the time of maximum value and pupil diameter reaches minimum
The time of value；And/or
Pupil speed change curves are generated using the pupil diameter sequence, and extract pupil using the pupil speed change curves
Mean value, variance, maximum value, minimum value, the pupil diameter pace of change of bore dia pace of change reach maximum value time and
Pupil diameter pace of change reaches the time of minimum value；And/or
Pupil acceleration change curve is generated using the pupil diameter sequence, and is mentioned using the pupil acceleration change curve
It takes mean value, variance, maximum value, minimum value, the pupil diameter of pupil diameter variation acceleration to change acceleration and reaches maximum value
Time and pupil diameter variation acceleration reach the time of minimum value.
12. such as the described in any item systems of claim 7 to 10, wherein the pupil diameter data are the data acquisition dresses
Set the pupil diameter number based on individual human face stimulation picture or all faces stimulation picture collection in face stimulation normal form
According to.
13. such as the described in any item systems of claim 7 to 10, wherein the processor is also used to:
Using sample data training self-closing disease disaggregated model, to obtain the classifier for determining self-closing disease analysis result.
14. system as claimed in claim 13, wherein the disaggregated model is support vector cassification model.
15. such as the described in any item systems of claim 7 to 10, wherein the data acquisition device includes eye tracker and/or pupil
Kong Yi.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005733.9A CN109259775A (en) | 2018-08-30 | 2018-08-30 | A kind of face stimulation normal form generation method and self-closing disease analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005733.9A CN109259775A (en) | 2018-08-30 | 2018-08-30 | A kind of face stimulation normal form generation method and self-closing disease analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109259775A true CN109259775A (en) | 2019-01-25 |
Family
ID=65154735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811005733.9A Pending CN109259775A (en) | 2018-08-30 | 2018-08-30 | A kind of face stimulation normal form generation method and self-closing disease analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109259775A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517772A (en) * | 2019-09-24 | 2019-11-29 | 清华大学 | A kind of self-closing disease screening system |
| CN112163512A (en) * | 2020-09-25 | 2021-01-01 | 杨铠郗 | Autism spectrum disorder face screening method based on machine learning |
| CN113362961A (en) * | 2020-03-05 | 2021-09-07 | 北京力泰克科技有限公司 | Rapid autism screening system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504390A (en) * | 2015-01-14 | 2015-04-08 | 北京工业大学 | On-line user state recognition method and device based on eye movement data |
| US20150099946A1 (en) * | 2013-10-09 | 2015-04-09 | Nedim T. SAHIN | Systems, environment and methods for evaluation and management of autism spectrum disorder using a wearable data collection device |
| CN104888331A (en) * | 2015-03-30 | 2015-09-09 | 徐志强 | Training system for treating infantile autism |
| CN104968270A (en) * | 2012-12-11 | 2015-10-07 | 阿米·克林 | Systems and methods for detecting blink inhibition as a marker of engagement and perceived stimulus salience |
| CN105069304A (en) * | 2015-08-18 | 2015-11-18 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Machine learning-based method for evaluating and predicting ASD |
| CN105163648A (en) * | 2013-03-11 | 2015-12-16 | 亚特兰大儿童医疗保健公司 | Systems and methods for detection of cognitive and developmental conditions |
| CN105559802A (en) * | 2015-07-29 | 2016-05-11 | 北京工业大学 | Tristimania diagnosis system and method based on attention and emotion information fusion |
| CN107133584A (en) * | 2017-04-27 | 2017-09-05 | 贵州大学 | Implicit intention assessment sorting technique based on eye-tracking |
-
2018
- 2018-08-30 CN CN201811005733.9A patent/CN109259775A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104968270A (en) * | 2012-12-11 | 2015-10-07 | 阿米·克林 | Systems and methods for detecting blink inhibition as a marker of engagement and perceived stimulus salience |
| CN105163648A (en) * | 2013-03-11 | 2015-12-16 | 亚特兰大儿童医疗保健公司 | Systems and methods for detection of cognitive and developmental conditions |
| US20150099946A1 (en) * | 2013-10-09 | 2015-04-09 | Nedim T. SAHIN | Systems, environment and methods for evaluation and management of autism spectrum disorder using a wearable data collection device |
| CN104504390A (en) * | 2015-01-14 | 2015-04-08 | 北京工业大学 | On-line user state recognition method and device based on eye movement data |
| CN104888331A (en) * | 2015-03-30 | 2015-09-09 | 徐志强 | Training system for treating infantile autism |
| CN105559802A (en) * | 2015-07-29 | 2016-05-11 | 北京工业大学 | Tristimania diagnosis system and method based on attention and emotion information fusion |
| CN105069304A (en) * | 2015-08-18 | 2015-11-18 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Machine learning-based method for evaluating and predicting ASD |
| CN107133584A (en) * | 2017-04-27 | 2017-09-05 | 贵州大学 | Implicit intention assessment sorting technique based on eye-tracking |
Non-Patent Citations (4)
| Title |
|---|
| D. HEDLEY等: "The Effect of Inversion on Face Recognition in Adults with Autism Spectrum Disorder", 《SPRINGER》 * |
| TERJE FALCK-YTTER: "Face Inversion Effects in Autism: A Combined Looking Time and Pupillometric Study", 《INASR》 * |
| 孙红艳 等: ""基于人脸范式的P300 拼写系统的参数优化"", 《中国生物医学工程学报》 * |
| 张洁: ""自闭症谱系障碍儿童的面孔位置视觉预期"", 《中国优秀硕士学位论文全文数据库 哲学与人文科学辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517772A (en) * | 2019-09-24 | 2019-11-29 | 清华大学 | A kind of self-closing disease screening system |
| CN113362961A (en) * | 2020-03-05 | 2021-09-07 | 北京力泰克科技有限公司 | Rapid autism screening system |
| CN112163512A (en) * | 2020-09-25 | 2021-01-01 | 杨铠郗 | Autism spectrum disorder face screening method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bone et al. | Eye movement reinstatement and neural reactivation during mental imagery | |
| Weymouth et al. | Visual acuity within the area centralis and its relation to eye movements and fixation | |
| US20150282705A1 (en) | Method and System of Using Eye Tracking to Evaluate Subjects | |
| CN109259775A (en) | A kind of face stimulation normal form generation method and self-closing disease analysis system | |
| Chevallier et al. | Review of Riemannian distances and divergences, applied to SSVEP-based BCI | |
| de Almeida et al. | Computational methodology for automatic detection of strabismus in digital images through Hirschberg test | |
| JP2018520820A (en) | Method and system for inspecting visual aspects | |
| CN106264568A (en) | Contactless emotion detection method and device | |
| WO2008129356A2 (en) | Visual attention and emotional response detection and display system | |
| KR20120124772A (en) | Apparatus for analysing focus and nonfocus states and method therof | |
| CN108186030A (en) | A kind of stimulus information provides the cognition index analysis method of device and latent energy value test | |
| CN106175657B (en) | A kind of eyesight automatic checkout system | |
| CN107085464A (en) | Emotion identification method based on P300 characters spells tasks | |
| CN111191639B (en) | Vertigo type identification method and device based on eye shake, medium and electronic equipment | |
| CN106096544B (en) | Non-contact blink and heart rate joint detection system and method based on second-order blind identification | |
| CN108451494A (en) | The method and system of time domain cardiac parameters are detected using pupillary reaction | |
| Madhusanka et al. | Biofeedback method for human–computer interaction to improve elder caring: Eye-gaze tracking | |
| Satriawan et al. | Predicting future eye gaze using inertial sensors | |
| JP5782540B2 (en) | Beauty counseling method | |
| RU2289310C2 (en) | Method for obtaining information about psychophysiological state of alive object | |
| KR20140132864A (en) | easy measuring meathods for physical and psysiological changes on the face and the body using users created contents and the service model for healing and wellness using these techinics by smart devices | |
| CN114527875A (en) | Electroencephalogram data acquisition system and method for synchronously tracking reading content | |
| CN110517772A (en) | A kind of self-closing disease screening system | |
| Nasim et al. | Multicore and GPU based pupillometry using parabolic and elliptic hough transform | |
| Gurnsey et al. | Peripheral sensitivity to biological motion conveyed by first and second-order signals |
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: 20190125 |