CN110400351A - A kind of X-ray front end of emission automatic adjusting method and system - Google Patents
A kind of X-ray front end of emission automatic adjusting method and system Download PDFInfo
- Publication number
- CN110400351A CN110400351A CN201910697369.5A CN201910697369A CN110400351A CN 110400351 A CN110400351 A CN 110400351A CN 201910697369 A CN201910697369 A CN 201910697369A CN 110400351 A CN110400351 A CN 110400351A
- Authority
- CN
- China
- Prior art keywords
- emission
- ray
- subsystem
- displacement
- point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 238000006073 displacement reaction Methods 0.000 claims description 48
- 238000004891 communication Methods 0.000 claims description 5
- 241001269238 Data Species 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/54—Control of apparatus or devices for radiation diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Optics & Photonics (AREA)
- Heart & Thoracic Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- High Energy & Nuclear Physics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention belongs to field of artificial intelligence, a kind of X-ray front end of emission automatic adjusting method and system are disclosed.Method includes the following steps: S1: obtaining nature image data using front camera；S2: according to critical point detection model, detect and obtain the characteristic point of user in nature image data；S3: the motion vector at acquisition nature image data center to characteristic point；S4: front end of emission is automatically moved；S5: detecting and judges whether position is consistent.The present invention solve the problems, such as it is of the existing technology there are biggish deviation, efficiency is very low, loss of learning of shooting position causes to be unfavorable for diagnosis.
Description
Technical field
The invention belongs to field of artificial intelligence, and in particular to a kind of X-ray front end of emission automatic adjusting method and system.
Background technique
When carrying out radiodiagnosis, X-ray collection surface center is usually the most interested region of diagnosis, and in X-ray light field
The region of the heart and often X-ray most standard (being approximately perpendicular to collection surface), allows area-of-interest to be located at X-ray light field center,
Area-of-interest can be allowed as undistorted as possible, otherwise angled, X-ray, which can allow, is ultimately imaged result generation artifact, therefore needs
Above-mentioned two center is overlapped to (area-of-interest had not only been in X-ray light field center, but also in X-ray collection surface
The heart), reach ideal diagnosis effect.
Problem of the existing technology:
1) relative position for manually adjusting front end and sufferer, there are biggish deviations, and efficiency is very low；
2) relatively large deviation is easy to cause the position to be captured not include by X-ray image completely: characteristic point is usually default
Image center point, and X-ray light field is limited, and the position that characteristic point is excessively deviateed at light field center will lead to opposite direction
Some parts are in except light field, this means that the loss of learning at shooting position, are unfavorable for diagnosing.
Summary of the invention
In order to solve the above problems existing in the present technology, it is an object of that present invention to provide X-ray front end of emission adjust automaticallies
Method and system, for solve the prior art there are biggish deviation, that efficiency is very low, loss of learning of shooting position causes is unfavorable
In diagnosis the problem of.
The technical scheme adopted by the invention is as follows:
A kind of X-ray front end of emission automatic adjusting method, includes the following steps:
S1: the natural image data of user are obtained automatically using front camera；
S2: it according to critical point detection model, is detected using data process subsystem and obtains user in nature image data
Characteristic point；
S3: the motion vector at acquisition nature image data center to characteristic point；
S4: according to the motion vector, front end of emission is automatically moved using displacement subsystem；
S5: detecting and judge subpoint position that light source position and characteristic point correspond in acquisition device plane whether one
It causes, if then ending method, otherwise return step S1.
Further, in the step S2, the method for building up of critical point detection model includes the following steps:
A1: existing several human body image datas are subjected to scaling processing, obtain image after several scalings of pre-set dimension
Data, and label is set；
A2: image data after scaling and corresponding label are formed into binary group, composing training sample set；
A3: being trained using training sample set, and the prediction output that will acquire is calculated with corresponding label by cross entropy
Loss；
A4: if judge loss whether reach part perhaps global minima then make loss reach part or global minima
Reasonable weight be model hidden parameter, the critical point detection model of output is model structure and corresponding hidden parameter, knot
Otherwise Shu Fangfa updates the weight of current key point detection model, return step A4 using gradient descent method.
Further, the label are as follows: the Gaussian Profile centered on coordinate of the key point after scaling in image data.
Further, in the step S2, the acquisition formula of the characteristic point are as follows:
P (x=k | x)
In formula, P is the probability that each point is characteristic point in image, and x is the point in image；K is the characteristic point of image；Image
Middle maximum probability PmaxPoint be characteristic point.
A kind of front end of emission automatic adjustment system based on the above method, including front end of emission, acquisition device, data processing
Subsystem, displacement subsystem and data terminal；
The front end of emission is located at displacement subsystem top, and communicates to connect with data process subsystem, at the data
It manages subsystem to communicate to connect with displacement subsystem and data terminal respectively, the acquisition device and data terminal communicate to connect；
The front end of emission includes light source and front camera, and the light source and front camera are respectively positioned on displacement subsystem
Top same position, and communicated to connect with data process subsystem.
Further, the light source is X-ray light source.
Further, the data process subsystem includes microcontroller and displacement drive module, the microcontroller
It is communicated to connect respectively with X-ray light source, front camera, displacement drive module and data terminal, the displacement drive module
It is connect with displacement subsystem communication.
Further, above-mentioned X-ray front end of emission automatic adjustment system further includes power module, the power module difference
It is electrically connected with front end of emission, data process subsystem and displacement subsystem
The invention has the benefit that
The present invention detects the position of front end of emission automatically, and is adjusted automatically, avoids biggish deviation, and save people
Power；Meanwhile the problem of can not being covered completely by the light field of X-ray image the invention avoids shooting position, it is quasi- to improve irradiation
Exactness and detection efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of X-ray front end of emission automatic adjusting method in embodiment 1；
Fig. 2 is the structural block diagram of X-ray front end of emission automatic adjustment system in embodiment 2.
Specific embodiment
With reference to the accompanying drawing and specific embodiment come the present invention is further elaborated.It should be noted that for
Although the explanation of these way of example is to be used to help understand the present invention, but and do not constitute a limitation of the invention.The present invention
Disclosed function detail is only used for description example embodiments of the present invention.However, this hair can be embodied with many alternative forms
It is bright, and be not construed as limiting the invention in the embodiment that the present invention illustrates.
It should be appreciated that terminology used in the present invention is only used for description specific embodiment, it is not intended to limit of the invention show
Example embodiment.If term " includes ", " including ", "comprising" and/or " containing " are used in the present invention, institute's sound is specified
Bright feature, integer, step, operation, unit and/or component existence, and be not excluded for one or more other features, number
Amount, step, operation, unit, component and/or their combination existence or increase.
It should be appreciated that it will be further noted that the function action occurred may go out with attached drawing in some alternative embodiments
Existing sequence is different.Such as related function action is depended on, it can actually substantially be executed concurrently, or sometimes
Two figures continuously shown can be executed in reverse order.
It should be appreciated that providing specific details, in the following description in order to which example embodiment is understood completely.
However those of ordinary skill in the art are it is to be understood that implementation example embodiment without these specific details.
Such as system can be shown in block diagrams, to avoid with unnecessary details come so that example is unclear.In other instances, may be used
Or not show well-known process, structure and technology unnecessary details, to avoid making example embodiment unclear.
Embodiment 1:
As shown in Figure 1, the present embodiment provides a kind of X-ray front end of emission automatic adjusting method, it is automatic based on X-ray front end of emission
Adjustment system, system include front end of emission, acquisition device, data process subsystem, displacement subsystem and data terminal, transmitting
Front end includes light source and front camera, and data process subsystem includes microcontroller and displacement drive module, is displaced subsystem
System includes that lateral displacement motor, length travel motor and displacement skeleton, method include the following steps:
S1: the natural image data of user are obtained automatically using front camera；
S2: it according to critical point detection model, is detected using data process subsystem and obtains user in nature image data
Characteristic point；
The method for building up of critical point detection model, includes the following steps:
A1: existing several human body image datas are subjected to scaling processing, obtain image after several scalings of pre-set dimension
Data, and label is set；
Label are as follows: the Gaussian Profile centered on coordinate of the key point after scaling in image data；
The formula of Gaussian Profile are as follows:
In formula, G (x, y) is gauss of distribution function；(x0,y0) it is coordinate of the key point after scaling in image data；(x,
It y) is two-dimensional random vector；σ1、σ2To be standard deviation；
A2: image data after scaling and corresponding label are formed into binary group, composing training sample set；
A3: being trained using training sample set, and the prediction output that will acquire is calculated with corresponding label by cross entropy
Loss；
The formula of cross entropy loss function are as follows:
In formula, CE (p, q) is cross entropy loss function；Q is current sample label indicatrix；P is that output point is characteristic point
Probability, and p=P (x=kx)；
Cross entropy loss function is only directly proportional with the difference of output valve and true value for the gradient of the last layer weight, this
When convergence it is very fast；Backpropagation even multiplies again, therefore the update of entire weight matrix can all be accelerated；In addition, more classification intersect
Entropy loss derivation is simpler, loses only related with the probability of correct classification；
A4: judge loss whether to reach part or global minima that (an insufficient condition of necessity is in parameter space
Current gradient is 0), if then making to lose the hidden parameter that the reasonable weight for reaching part or global minima is model, output
Critical point detection model be model structure (function prototype) and corresponding hidden parameter, ending method, otherwise using under gradient
Drop method updates the weight of current key point detection model, return step A4；
Critical point detection model is monitor model, and by being trained to human body image data, the weight of more new model is defeated
Optimal critical point detection model out, improves accuracy, when the natural image data of input user, characteristic point is obtained, after being convenient for
The acquisition of motion vector of the continuous natural image data center to characteristic point；
The acquisition formula of characteristic point are as follows:
P (x=k | x)
In formula, P is the probability that each point is characteristic point in image, and x is the point in image；K is the characteristic point of image；Image
Middle maximum probability PmaxPoint be characteristic point；
S3: nature image data center is obtained to the motion vector of characteristic point, the direction of the motion vector is from natural figure
As data center is to characteristic point, in the present embodiment, by the motion vector be decomposed into X-axis projection vector under rectangular coordinate system and
Y-axis projection vector, convenient for the position of displacement subsystem automatic adjustment front end of emission；
S4: according to the motion vector, front end of emission is automatically moved using displacement subsystem, realizes the automatic tune of front end of emission
It is whole, accuracy and efficiency is improved, avoid makes position to be captured can not quilt completely due to manually adjusting existing relatively large deviation
X-ray image include caused by loss of learning；
S5: detecting and judge subpoint position that light source position and characteristic point correspond in acquisition device plane whether one
It causes, if then ending method, otherwise return step S1；
The inspection of X-ray light source position is carried out, guarantees that X-ray light source position and characteristic point correspond in acquisition device plane
Subpoint position consistency, further decrease error, avoid the error as caused by contingency influence result accuracy.
Embodiment 2:
The present embodiment is based on embodiment 1, provides a kind of X-ray front end of emission automatic adjustment system, as shown in Fig. 2, including hair
Front end, acquisition device, data process subsystem, displacement subsystem and data terminal are penetrated, front end of emission is located at displacement subsystem
Top, and communicated to connect with data process subsystem, data process subsystem is communicated with displacement subsystem with data terminal respectively
Connection, acquisition device and data terminal communicate to connect；
Front end of emission includes light source and front camera, and it is identical that light source and front camera are respectively positioned on displacement subsystem top
Position, and communicated to connect with data process subsystem；Light source is X-ray light source；
Data process subsystem includes microcontroller and displacement drive module, microcontroller respectively with X-ray light source, preceding
Camera, displacement drive module and data terminal communication connection, displacement drive module is set to connect with displacement subsystem communication；
Front camera acquires the natural image data of user, is transmitted to microcontroller, microcontroller according to motion vector,
Command displacement subsystem automatically moves front end of emission；As a preferred embodiment, displacement subsystem includes lateral displacement
Motor, length travel motor and displacement skeleton, lateral displacement motor and length travel motor are respectively positioned on displacement skeletal internal, and
It is communicated to connect with displacement drive module；
Microcontroller controls lateral displacement motor according to motion vector, by displacement drive module, adjustment displacement skeleton
Lateral position controls length travel motor by displacement drive module, and the lengthwise position of adjustment displacement skeleton realizes adjust automatically
The relative position of front end of emission and user, when X-ray light source position and characteristic point correspond to the subpoint in acquisition device plane
When position consistency, X-ray light source, which is started to work, emits X-ray, and acquisition device acquires X-ray image data.
Preferably, system further includes power module, power module respectively with front end of emission, data process subsystem and
It is displaced subsystem to be electrically connected, power module is X-ray light source, front camera, microcontroller and displacement drive module, cross
Operating voltage is provided to displacement motor and length travel motor.
The present invention is not limited to above-mentioned optional embodiment, anyone can show that other are each under the inspiration of the present invention
The product of kind form.Above-mentioned specific embodiment should not be understood the limitation of pairs of protection scope of the present invention, protection of the invention
Range should be subject to be defined in claims, and specification can be used for interpreting the claims.
Claims (8)
1. a kind of X-ray front end of emission automatic adjusting method, characterized by the following steps:
S1: the natural image data of user are obtained automatically using front camera；
S2: it according to critical point detection model, is detected using data process subsystem and obtains the spy of user in nature image data
Sign point；
S3: the motion vector at acquisition nature image data center to characteristic point；
S4: according to the motion vector, front end of emission is automatically moved using displacement subsystem；
S5: detecting and judges whether light source position is consistent corresponding to the subpoint position in acquisition device plane with characteristic point, if
It is then ending method, otherwise return step S1.
2. X-ray front end of emission automatic adjusting method according to claim 1, it is characterised in that: crucial in the step S2
The method for building up of point detection model, includes the following steps:
A1: carrying out scaling processing for existing several human body image datas, obtain image data after several scalings of pre-set dimension,
And label is set；
A2: image data after scaling and corresponding label are formed into binary group, composing training sample set；
A3: being trained using training sample set, and the prediction output that will acquire, which is calculated with corresponding label by cross entropy, loses；
A4: if judging whether loss reaches the part conjunction that perhaps global minima then makes loss reach part or global minima
Reason weight is the hidden parameter of model, and the critical point detection model of output is model structure and corresponding hidden parameter, end side
Otherwise method updates the weight of current key point detection model, return step A4 using gradient descent method.
3. X-ray front end of emission automatic adjusting method according to claim 2, it is characterised in that: the label are as follows: with key
Gaussian Profile centered on coordinate of the point after scaling in image data.
4. X-ray front end of emission automatic adjusting method according to claim 1, it is characterised in that: described in the step S2
The acquisition formula of characteristic point are as follows:
P (x=k | x)
In formula, P is the probability that each point is characteristic point in image, and x is the point in image；K is the characteristic point of image；It is general in image
Rate maximum PmaxPoint be characteristic point.
5. a kind of X-ray front end of emission automatic adjustment system, it is characterised in that: including front end of emission, acquisition device, data processing
System, displacement subsystem and data terminal；
The front end of emission is located at displacement subsystem top, and communicates to connect with data process subsystem, data processing
System is communicated to connect with displacement subsystem and data terminal respectively, and the acquisition device and data terminal communicate to connect；
The front end of emission includes light source and front camera, and the light source and front camera are respectively positioned on displacement subsystem top
Same position, and communicated to connect with data process subsystem.
6. X-ray front end of emission automatic adjustment system according to claim 5, it is characterised in that: the light source is X-ray light
Source.
7. X-ray front end of emission automatic adjustment system according to claim 6, it is characterised in that: the data processing subsystem
System includes microcontroller and displacement drive module, and the microcontroller drives with X-ray light source, front camera, displacement respectively
Dynamic model block and data terminal communication connection, the displacement drive module are connect with displacement subsystem communication.
8. X-ray front end of emission automatic adjustment system according to claim 5, it is characterised in that: it further include power module, institute
Power module is stated to be electrically connected with front end of emission, data process subsystem and displacement subsystem respectively.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910697369.5A CN110400351A (en) | 2019-07-30 | 2019-07-30 | A kind of X-ray front end of emission automatic adjusting method and system |
| US17/268,949 US20220079544A1 (en) | 2019-04-02 | 2020-04-02 | An integrated x-ray precision imaging device |
| CA3135998A CA3135998A1 (en) | 2019-04-02 | 2020-04-02 | An integrated x-ray precision imaging device |
| AU2020255687A AU2020255687A1 (en) | 2019-04-02 | 2020-04-02 | An integrated X-ray precision imaging device |
| PCT/CA2020/050438 WO2020198870A1 (en) | 2019-04-02 | 2020-04-02 | An integrated x-ray precision imaging device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910697369.5A CN110400351A (en) | 2019-07-30 | 2019-07-30 | A kind of X-ray front end of emission automatic adjusting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110400351A true CN110400351A (en) | 2019-11-01 |
Family
ID=68326739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910697369.5A Pending CN110400351A (en) | 2019-04-02 | 2019-07-30 | A kind of X-ray front end of emission automatic adjusting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400351A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292378A (en) * | 2020-03-12 | 2020-06-16 | 南京安科医疗科技有限公司 | CT scanning auxiliary method, device and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102525491A (en) * | 2010-12-15 | 2012-07-04 | 深圳迈瑞生物医疗电子股份有限公司 | X-ray radiation imaging equipment as well as method and device for adjusting optical field of beam limiting device |
| CN102961154A (en) * | 2011-08-31 | 2013-03-13 | Ge医疗系统环球技术有限公司 | Method and device for adjusting exposure field of X-ray system and X-ray system |
| CN105227832A (en) * | 2015-09-09 | 2016-01-06 | 厦门美图之家科技有限公司 | A kind of self-timer method based on critical point detection, self-heterodyne system and camera terminal |
| US20180061067A1 (en) * | 2016-08-31 | 2018-03-01 | General Electric Company | Image processing method and apparatus for x-ray imaging device |
| CN108428251A (en) * | 2018-03-09 | 2018-08-21 | 深圳市中捷视科科技有限公司 | One kind being based on machine vision technique laser structure light automatic calibration method |
| CN109446892A (en) * | 2018-09-14 | 2019-03-08 | 杭州宇泛智能科技有限公司 | Human eye notice positioning method and system based on deep neural network |
-
2019
- 2019-07-30 CN CN201910697369.5A patent/CN110400351A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102525491A (en) * | 2010-12-15 | 2012-07-04 | 深圳迈瑞生物医疗电子股份有限公司 | X-ray radiation imaging equipment as well as method and device for adjusting optical field of beam limiting device |
| CN102961154A (en) * | 2011-08-31 | 2013-03-13 | Ge医疗系统环球技术有限公司 | Method and device for adjusting exposure field of X-ray system and X-ray system |
| CN105227832A (en) * | 2015-09-09 | 2016-01-06 | 厦门美图之家科技有限公司 | A kind of self-timer method based on critical point detection, self-heterodyne system and camera terminal |
| US20180061067A1 (en) * | 2016-08-31 | 2018-03-01 | General Electric Company | Image processing method and apparatus for x-ray imaging device |
| CN108428251A (en) * | 2018-03-09 | 2018-08-21 | 深圳市中捷视科科技有限公司 | One kind being based on machine vision technique laser structure light automatic calibration method |
| CN109446892A (en) * | 2018-09-14 | 2019-03-08 | 杭州宇泛智能科技有限公司 | Human eye notice positioning method and system based on deep neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292378A (en) * | 2020-03-12 | 2020-06-16 | 南京安科医疗科技有限公司 | CT scanning auxiliary method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110032278B (en) | Pose identification method, device and system for human eye interested object | |
| US11645748B2 (en) | Three-dimensional automatic location system for epileptogenic focus based on deep learning | |
| CN105487665B (en) | A kind of intelligent Mobile Service robot control method based on head pose identification | |
| Alberto Funes Mora et al. | Geometric generative gaze estimation (g3e) for remote rgb-d cameras | |
| JP2018148367A (en) | Image processing device, image processing system, image processing method, and program | |
| CN108985210A (en) | A kind of Eye-controlling focus method and system based on human eye geometrical characteristic | |
| EP3154407B1 (en) | A gaze estimation method and apparatus | |
| CN105159452B (en) | A kind of control method and system based on human face modeling | |
| CN106169073A (en) | A kind of expression recognition method and system | |
| CN106203256A (en) | A kind of low resolution face identification method based on sparse holding canonical correlation analysis | |
| CN107103293B (en) | It is a kind of that the point estimation method is watched attentively based on joint entropy | |
| CN112043260B (en) | Electrocardiogram classification method based on local mode transformation | |
| CN113033442B (en) | StyleGAN-based high-freedom face driving method and device | |
| CN110059579A (en) | For the method and apparatus of test alive, electronic equipment and storage medium | |
| CN109620293A (en) | A kind of image-recognizing method, device and storage medium | |
| CN109008937A (en) | Method for detecting diopter and equipment | |
| CN110400351A (en) | A kind of X-ray front end of emission automatic adjusting method and system | |
| JP2023549864A (en) | Method and system for intelligently controlling children's use of monitor terminals | |
| CN109993116A (en) | A kind of pedestrian mutually learnt based on skeleton recognition methods again | |
| CN110246190A (en) | A kind of robot interactive method that more technologies are realized | |
| CN1156248C (en) | Method for detecting moving human face | |
| CN116704401A (en) | Grading verification method and device for operation type examination, electronic equipment and storage medium | |
| CN115601834A (en) | Fall detection method based on WiFi channel state information | |
| CN113379787B (en) | Target tracking method based on 3D convolution twin neural network and template updating | |
| CN111640126B (en) | Artificial intelligent diagnosis auxiliary method based on medical image |
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 | ||
| CB02 | Change of applicant information |
Address after: 610000 north of Chengdu modern industrial port, PI Du District, Chengdu, Sichuan, No. 269 North Road, Hong Kong. Applicant after: Xiaozhi future (Chengdu) Technology Co.,Ltd. Address before: 610000 north of Chengdu modern industrial port, PI Du District, Chengdu, Sichuan, No. 269 North Road, Hong Kong. Applicant before: XIAOZHI TECHNOLOGY (CHENGDU) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191101 |
|
| RJ01 | Rejection of invention patent application after publication |