CN110276331A - The inspection modification method of Identification of Images result - Google Patents
The inspection modification method of Identification of Images result Download PDFInfo
- Publication number
- CN110276331A CN110276331A CN201910575289.2A CN201910575289A CN110276331A CN 110276331 A CN110276331 A CN 110276331A CN 201910575289 A CN201910575289 A CN 201910575289A CN 110276331 A CN110276331 A CN 110276331A
- Authority
- CN
- China
- Prior art keywords
- identification
- characteristic area
- recognition result
- images
- portrait
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to portrait recognition technology, solve the problems, such as to lack a kind of visual tool for checking amendment Identification of Images result at present.Technical solution is summarized are as follows: the inspection modification method of Identification of Images result obtains portrait feature corresponding to the characteristic area and characteristic area identified corresponding to target identification picture, target identification picture；Target identification picture is shown in the preset drawing area of display interface according to Identification of Images data, and shows corresponding characteristic area on the target recognition chart piece upper layer of display；Portrait feature corresponding with characteristic area can be shown in display interface；Portrait feature and characteristic area can be corrected respectively in the display interface by preset tool software.Beneficial effect is: scheme through the invention, and user can visually check portrait recognition result and be modified to it, and then calculates the reason of Identification of Images result accuracy, the position of auxiliary development personnel positioning identification mistake and identification mistake.
Description
Technical field
The present invention relates to portrait recognition technologies, in particular to the inspection correction technique of Identification of Images result.
Background technique
The recognition result of Identification of Images model algorithm cannot reach 100% accuracy at present, it is therefore desirable to portrait
Recognition result carries out inspection amendment, and Identification of Images model is constantly optimized and trained according to the problem of checking, with
Improve accuracy.Have in the prior art Identification of Images result is recorded accordingly, is managed, is analyzed, is inquired method and
System, but be the absence of one kind and visually check and correct the tool of Identification of Images result to assist user's checking and correct portrait
Recognition result, and analyze position and the identification of the accuracy and auxiliary development personnel positioning identification mistake of Identification of Images result
The reason of mistake.
Summary of the invention
The present invention is to solve the problems, such as to lack a kind of visual tool for checking amendment Identification of Images result at present, is provided
A kind of inspection modification method of Identification of Images result.
To solve the above problems, the technical solution adopted by the present invention is that:
The inspection modification method of Identification of Images result, comprising:
Identification of Images data are obtained, the Identification of Images data include corresponding to target recognition chart piece and target identification picture
Identification of Images destination file, be able to record in corresponding target identification picture in the Identification of Images destination file identify it is each
Portrait feature corresponding to a characteristic area and each characteristic area；
Target identification picture is shown in the preset drawing area of display interface according to Identification of Images data, and in display
Target recognition chart piece upper layer shows corresponding characteristic area；Portrait feature corresponding with characteristic area can be in display interface
It is shown；
Portrait feature and characteristic area can be corrected respectively in the display interface by preset tool software, and amendment is completed
Confirmation is checked and is finished afterwards.
As advanced optimizing, the amendment portrait feature and characteristic area include: moving characteristic region position and/or
It adjusts the shape of characteristic area and/or characteristic area is labeled as mistake and/or newly-increased feature region and adds corresponding portrait
Feature and/or modification portrait feature.
As advanced optimizing, the above method further include:
Identification of Images data to get add corresponding description information, and the description information includes: whether to be original
Whether whether accurate indication and recognition result are identified mark for Identification of Images Data Labels, recognition result, and whether described be original
Identification of Images Data Labels are initially, and whether accurate indication is initially empty the recognition result, the recognition result whether by
Acknowledgement indicator is initially no；
After confirmation checks:
If the position of characteristic area, the shape of characteristic area and portrait feature are not all modified, and do not have characteristic area
Be marked as mistake, and there is no newly-increased feature region, then by recognition result, whether accurate indication is set to is, recognition result whether by
Acknowledgement indicator, which is set to, is；
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or spy is modified or had to portrait feature
Sign region is marked as mistake or has newly-increased feature region, then by recognition result, whether accurate indication is set to no, and recognition result is
It is no to be identified that mark is set to and be.
As advanced optimizing, the above method further includes calculating portrait according to the description information of all Identification of Images data to know
Whether the calculation method of other accuracy, the Identification of Images accuracy uses: being to be and know for original Identification of Images Data Labels
Whether the quantity of the other result Identification of Images data whether accurate indication is yes is divided by be original Identification of Images Data Labels being yes
Identification of Images data quantity.
As advanced optimizing, the description information further includes unique ID and recognition result primary source mark, described
Recognition result primary source mark is initially mark one, and wherein mark one indicates that recognition result primary source is original Identification of Images
Or newly-increased Identification of Images result as a result；
After confirmation checks:
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or spy is modified or had to portrait feature
Sign region is marked as mistake, and does not have newly-increased feature region, then by recognition result, whether accurate indication is set to no, recognition result
Whether being identified that mark is set to is, and after being checked according to confirmation by modifier as recognition result generate one it is new
Identification of Images data, are then that the newly-generated Identification of Images data add corresponding description information, and by the newly-generated people
As identification data are corresponding, whether to be that original Identification of Images Data Labels are set to no, and whether accurate indication is set to recognition result is,
Whether recognition result is identified that mark is set to, and it is raw that recognition result primary source mark is set to the newly-generated Identification of Images data
At when based on Identification of Images data ID；
If there is newly-increased feature region, by recognition result, whether accurate indication is set to no, and whether recognition result is identified mark
Will, which is set to, is, and according to confirmation check after by modifier as recognition result generate a new Identification of Images number
According to being then that the newly-generated Identification of Images data add corresponding description information, and by the newly-generated Identification of Images data
Corresponding whether to be that original Identification of Images Data Labels are set to no, and whether accurate indication is set to recognition result is that recognition result is
It is no to be identified that mark is set to and be.
As advanced optimizing, when displaying target identifies picture, guaranteeing the ratio of the Gao Yukuan of target identification picture not
On the basis of change, maximization shows target identification picture.
As advanced optimizing, portrait feature volume having the same corresponding to any feature region and this feature region
Number, it shows and shows corresponding number when characteristic area and portrait feature simultaneously.
As advanced optimizing, show all people as feature in the preset non-drawing region of display interface；And/or root
People corresponding to the characteristic area that accordingly selects is shown in the preset non-drawing region of display interface according to the characteristic area of selection
As feature；And/or the characteristic area according to selection, portrait corresponding to the characteristic area accordingly selected is shown in the form of pop-up
Feature.
Beneficial effect is: the present invention draws identification according to Identification of Images result data, in the target recognition chart on piece of display
Characteristic area out, and can show portrait feature corresponding to characteristic area, user verifies according to the content shown
It checks, recognition result can be corrected by related tool when checking wrong, i.e. amendment portrait feature and characteristic area.Pass through
The solution of the present invention, user can visually check portrait recognition result and be modified to it, and then know to calculate portrait
The reason of other result accuracy, the position of auxiliary development personnel positioning identification mistake and identification mistake provides data supporting.
Specific embodiment
Technical solution of the present invention is further illustrated below.
The inspection modification method of Identification of Images result of the invention, comprising:
Identification of Images data are obtained, the Identification of Images data include corresponding to target recognition chart piece and target identification picture
Identification of Images destination file, be able to record in corresponding target identification picture in the Identification of Images destination file identify it is each
Portrait feature corresponding to a characteristic area and each characteristic area；
Target identification picture is shown in the preset drawing area of display interface according to Identification of Images data, and in display
Target recognition chart piece upper layer shows corresponding characteristic area；Portrait feature corresponding with characteristic area can be in display interface
It is shown；
Portrait feature and characteristic area can be corrected respectively in the display interface by preset tool software, and amendment is completed
Confirmation is checked and is finished afterwards.
By the above method, user can manually check Identification of Images as a result, and correct identification mistake portrait feature and
Characteristic area.
The above method is further optimized, specifically may is that
On the one hand, it corrects portrait feature and characteristic area includes: position and/or the adjustment characteristic area in moving characteristic region
Shape and/or characteristic area labeled as mistake and/or newly-increased feature region and is added into corresponding portrait feature and/or modification
Portrait feature.In conjunction with above-mentioned a variety of modification adjustment modes, allow users to easily correct mistake present in recognition result.
Based on above-mentioned correcting mode, the above method can also include:
Identification of Images data to get add corresponding description information, and the description information includes: whether to be original
Whether whether accurate indication and recognition result are identified mark for Identification of Images Data Labels, recognition result, and whether described be original
Identification of Images Data Labels are initially, and whether accurate indication is initially empty the recognition result, the recognition result whether by
Acknowledgement indicator is initially no；
After confirmation checks:
If the position of characteristic area, the shape of characteristic area and portrait feature are not all modified, and do not have characteristic area
Be marked as mistake, and there is no newly-increased feature region, then by recognition result, whether accurate indication is set to is, recognition result whether by
Acknowledgement indicator, which is set to, is；
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or spy is modified or had to portrait feature
Sign region is marked as mistake or has newly-increased feature region, then by recognition result, whether accurate indication is set to no, and recognition result is
It is no to be identified that mark is set to and be.
The above-mentioned flag bit based on addition automatically updates correlating markings position according to amendment situation of the user to recognition result
Value, essential information needed for calculating Identification of Images result accuracy with offer.
Further, on the basis of foregoing description information, the above method further includes according to all Identification of Images data
Whether description information calculates Identification of Images accuracy, and wherein the calculation method of Identification of Images accuracy uses: for the knowledge of original portrait
Other Data Labels are to be and whether the quantity of the recognition result Identification of Images data whether accurate indication is yes is divided by being primitive man
As the quantity for the Identification of Images data that identification Data Labels are yes.
Further, on the basis of foregoing description information, description information further includes that unique ID and recognition result are original
Source indicator, the recognition result primary source mark are initially mark one, and wherein mark one indicates recognition result primary source
It is original portrait recognition result or newly-increased Identification of Images result；
After confirmation checks:
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or spy is modified or had to portrait feature
Sign region is marked as mistake, and does not have newly-increased feature region, then by recognition result, whether accurate indication is set to no, recognition result
Whether being identified that mark is set to is, and after being checked according to confirmation by modifier as recognition result generate one it is new
Identification of Images data, are then that the newly-generated Identification of Images data add corresponding description information, and by the newly-generated people
As identification data are corresponding, whether to be that original Identification of Images Data Labels are set to no, and whether accurate indication is set to recognition result is,
Whether recognition result is identified that mark is set to, and it is raw that recognition result primary source mark is set to the newly-generated Identification of Images data
At when based on Identification of Images data ID；
If there is newly-increased feature region, by recognition result, whether accurate indication is set to no, and whether recognition result is identified mark
Will, which is set to, is, and according to confirmation check after by modifier as recognition result generate a new Identification of Images number
According to being then that the newly-generated Identification of Images data add corresponding description information, and by the newly-generated Identification of Images data
Corresponding whether to be that original Identification of Images Data Labels are set to no, and whether accurate indication is set to recognition result is that recognition result is
It is no to be identified that mark is set to and be.
By the optimization of above-mentioned progress, developer being capable of position according to description information fixation and recognition mistake and identification
The reason of mistake.Such as: when the first ID it is corresponding whether be original Identification of Images Data Labels be no, recognition result it is whether correct
Mark is yes, when recognition result primary source mark is two ID, then it represents that Identification of Images corresponding to the first ID the result is that
The correct Identification of Images result being corrected on the basis of Identification of Images result corresponding to 2nd ID.
On the one hand, when displaying target identifies picture, in the base of the constant rate for the Gao Yukuan for guaranteeing target identification picture
On plinth, maximization shows target identification picture, and to facilitate user more clearly to check, and the adjustable target of user is known
The size of other picture.
On the one hand, portrait feature number having the same corresponding to any feature region and this feature region, display are special
Corresponding number is shown when sign region and portrait feature simultaneously.It numbers, is allowed users to more easily above by addition
Portrait feature corresponding to individual features region is found, for example, the portrait shown is special after clicking the characteristic area that number is 1
Sign includes: number 1, the information such as name, gender of people in the region.
On the one hand, show portrait feature mode can there are many, comprising: it is aobvious in the preset non-drawing region of display interface
All people are shown as feature；And/or phase is shown in the preset non-drawing region of display interface according to the characteristic area of selection
Portrait feature corresponding to the characteristic area that should be selected；And/or the characteristic area according to selection, it is shown in the form of pop-up corresponding
Portrait feature corresponding to the characteristic area of selection.
Claims (8)
1. the inspection modification method of Identification of Images result characterized by comprising
Identification of Images data are obtained, the Identification of Images data include people corresponding to target recognition chart piece and target identification picture
As recognition result file, each spy identified in corresponding target identification picture is able to record in the Identification of Images destination file
Levy portrait feature corresponding to region and each characteristic area；
Target identification picture is shown in the preset drawing area of display interface according to Identification of Images data, and in the target of display
Identification picture upper layer shows corresponding characteristic area；Portrait feature corresponding with characteristic area can be carried out in display interface
Display；
Portrait feature and characteristic area can be corrected respectively in the display interface by preset tool software, it is true after the completion of amendment
Recognize inspection to finish.
2. the inspection modification method of Identification of Images result as described in claim 1, which is characterized in that the amendment portrait feature
Include: the position in moving characteristic region and/or the shape of adjustment characteristic area with characteristic area and/or is labeled as characteristic area
Corresponding portrait feature and/or modification portrait feature are simultaneously added in mistake and/or newly-increased feature region.
3. the inspection modification method of Identification of Images result as claimed in claim 2, which is characterized in that further include:
Identification of Images data to get add corresponding description information, and the description information includes: whether as original portrait
Whether whether accurate indication and recognition result are identified mark for identification Data Labels, recognition result, and whether described be original portrait
It is that whether accurate indication is initially empty the recognition result, and whether the recognition result is identified that identification Data Labels, which are initially,
Mark is initially no；
After confirmation checks:
If the position of characteristic area, the shape of characteristic area and portrait feature are not all modified, and are marked without characteristic area
It is denoted as mistake, and does not have newly-increased feature region, then whether accurate indication is set to is whether recognition result is identified by recognition result
Mark, which is set to, is；
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or characteristic area is modified or had to portrait feature
Domain is marked as mistake or has newly-increased feature region, then by recognition result whether accurate indication be set to it is no, recognition result whether by
Acknowledgement indicator, which is set to, is.
4. the inspection modification method of Identification of Images result as claimed in claim 3, which is characterized in that further include according to owner
As the description information calculating Identification of Images accuracy of identification data, the calculation method of the Identification of Images accuracy is used: whether
For original Identification of Images Data Labels be and the quantity of the recognition result Identification of Images data whether accurate indication is yes divided by
Whether be the Identification of Images data that original Identification of Images Data Labels are yes quantity.
5. the inspection modification method of Identification of Images result as claimed in claim 3, which is characterized in that the description information is also wrapped
Unique ID and recognition result primary source mark are included, the recognition result primary source mark is initially mark one, acceptance of the bid
Will one indicates that recognition result primary source is original portrait recognition result or newly-increased Identification of Images result；
After confirmation checks:
If thering is the position of characteristic area to be modified or the shape of characteristic area is modified or characteristic area is modified or had to portrait feature
Domain is marked as mistake, and does not have newly-increased feature region, then by recognition result, whether accurate indication is set to no, and whether recognition result
Being identified that mark is set to is, and according to confirmation check after by modifier as recognition result generate a new portrait
It identifies data, then adds corresponding description information for the newly-generated Identification of Images data, and the newly-generated portrait is known
Other data are corresponding, and whether to be that original Identification of Images Data Labels are set to no, and whether accurate indication is set to recognition result is to identify
As a result whether being identified that mark is set to is, when recognition result primary source mark is set to the newly-generated Identification of Images data and generates
Based on Identification of Images data ID；
If there is newly-increased feature region, by recognition result, whether accurate indication is set to no, and whether recognition result is identified that mark is set
Be yes, and according to confirmation check after by modifier as recognition result generate a new Identification of Images data, so
Corresponding description information is added for the newly-generated Identification of Images data afterwards, and the newly-generated Identification of Images data are corresponding
It is no whether to be that original Identification of Images Data Labels are set to, whether accurate indication is set to recognition result is whether recognition result is true
Recognizing mark and being set to is.
6. the inspection modification method of Identification of Images result as described in claim 1, which is characterized in that displaying target identifies picture
When, on the basis of guaranteeing the constant rate of Gao Yukuan of target identification picture, maximization shows target identification picture.
7. the inspection modification method of Identification of Images result as described in claim 1, which is characterized in that any feature region and should
Portrait feature number having the same corresponding to characteristic area shows and shows simultaneously accordingly when characteristic area and portrait feature
Number.
8. the inspection modification method of Identification of Images result as described in claim 1, which is characterized in that preset in display interface
Non-drawing region shows all people as feature；And/or according to the characteristic area of selection in the preset non-drawing of display interface
Region shows portrait feature corresponding to the characteristic area accordingly selected；And/or the characteristic area according to selection, with pop-up shape
Formula shows portrait feature corresponding to the characteristic area accordingly selected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910575289.2A CN110276331A (en) | 2019-06-28 | 2019-06-28 | The inspection modification method of Identification of Images result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910575289.2A CN110276331A (en) | 2019-06-28 | 2019-06-28 | The inspection modification method of Identification of Images result |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110276331A true CN110276331A (en) | 2019-09-24 |
Family
ID=67963122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910575289.2A Pending CN110276331A (en) | 2019-06-28 | 2019-06-28 | The inspection modification method of Identification of Images result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110276331A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113035335A (en) * | 2021-04-09 | 2021-06-25 | 青岛商汤科技有限公司 | Screenshot method and device, electronic equipment and storage medium |
| CN113343850A (en) * | 2021-06-07 | 2021-09-03 | 广州市奥威亚电子科技有限公司 | Method, device, equipment and storage medium for checking video character information |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940798A (en) * | 2017-03-08 | 2017-07-11 | 深圳市金立通信设备有限公司 | The modification method and terminal of a kind of Text region |
| CN107092913A (en) * | 2017-03-20 | 2017-08-25 | 上海大学 | A kind of spray printing character ONLINE RECOGNITION and interactive after-treatment system and method |
| CN107358227A (en) * | 2017-06-29 | 2017-11-17 | 努比亚技术有限公司 | A kind of mark recognition method, mobile terminal and computer-readable recording medium |
| JPWO2017043132A1 (en) * | 2015-09-08 | 2018-01-25 | 日本電気株式会社 | Face recognition system, face recognition method, display control apparatus, display control method, and display control program |
| CN107832158A (en) * | 2017-10-16 | 2018-03-23 | 深圳市中钞信达金融科技有限公司 | Face identification method and device |
| CN108053366A (en) * | 2018-01-02 | 2018-05-18 | 联想(北京)有限公司 | A kind of image processing method and electronic equipment |
| CN109254661A (en) * | 2018-09-03 | 2019-01-22 | Oppo（重庆）智能科技有限公司 | Image display method, device, storage medium and electronic equipment |
| CN109740457A (en) * | 2018-12-20 | 2019-05-10 | 杭州当虹科技股份有限公司 | A kind of face recognition algorithms evaluating method |
-
2019
- 2019-06-28 CN CN201910575289.2A patent/CN110276331A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPWO2017043132A1 (en) * | 2015-09-08 | 2018-01-25 | 日本電気株式会社 | Face recognition system, face recognition method, display control apparatus, display control method, and display control program |
| CN106940798A (en) * | 2017-03-08 | 2017-07-11 | 深圳市金立通信设备有限公司 | The modification method and terminal of a kind of Text region |
| CN107092913A (en) * | 2017-03-20 | 2017-08-25 | 上海大学 | A kind of spray printing character ONLINE RECOGNITION and interactive after-treatment system and method |
| CN107358227A (en) * | 2017-06-29 | 2017-11-17 | 努比亚技术有限公司 | A kind of mark recognition method, mobile terminal and computer-readable recording medium |
| CN107832158A (en) * | 2017-10-16 | 2018-03-23 | 深圳市中钞信达金融科技有限公司 | Face identification method and device |
| CN108053366A (en) * | 2018-01-02 | 2018-05-18 | 联想(北京)有限公司 | A kind of image processing method and electronic equipment |
| CN109254661A (en) * | 2018-09-03 | 2019-01-22 | Oppo（重庆）智能科技有限公司 | Image display method, device, storage medium and electronic equipment |
| CN109740457A (en) * | 2018-12-20 | 2019-05-10 | 杭州当虹科技股份有限公司 | A kind of face recognition algorithms evaluating method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113035335A (en) * | 2021-04-09 | 2021-06-25 | 青岛商汤科技有限公司 | Screenshot method and device, electronic equipment and storage medium |
| CN113343850A (en) * | 2021-06-07 | 2021-09-03 | 广州市奥威亚电子科技有限公司 | Method, device, equipment and storage medium for checking video character information |
| CN113343850B (en) * | 2021-06-07 | 2022-08-16 | 广州市奥威亚电子科技有限公司 | Method, device, equipment and storage medium for checking video character information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230072188A1 (en) | Calibration for Augmented Reality | |
| US11151744B1 (en) | Automated data capture | |
| CN110276331A (en) | The inspection modification method of Identification of Images result | |
| CN111784775B (en) | Identification-assisted visual inertia augmented reality registration method | |
| CN104754264A (en) | Feature point based projection deformation correcting method and system | |
| JP2007172621A (en) | Method and system for determining inaccurate information in extended reality sensing system | |
| WO2012127798A1 (en) | Learning assistance apparatus, electronic pen, learning assistance system, learning assistance method, and learning assistance program | |
| CN112017231B (en) | Monocular camera-based human body weight identification method, monocular camera-based human body weight identification device and storage medium | |
| CN108245788B (en) | Binocular distance measuring device and method and accelerator radiotherapy system comprising same | |
| CN107481276A (en) | The automatic identifying method of mark point sequence in a kind of 3 d medical images | |
| CN106202000B (en) | Seven-parameter transformation method between national three-dimensional system of coordinate and anywhere plane coordinate system | |
| CN111695431A (en) | Face recognition method, face recognition device, terminal equipment and storage medium | |
| WO2014091940A1 (en) | Shoe selection support system | |
| CN107122754A (en) | Posture identification method and device | |
| CN110689026B (en) | Method and device for labeling object in image and electronic equipment | |
| CN105139007A (en) | Positioning method and apparatus of face feature point | |
| CN1961340B (en) | A method, a computer program, an apparatus and an imaging system for image processing | |
| CN111149101B (en) | Target pattern searching method and computer readable storage medium | |
| CN110796185A (en) | Method and device for detecting image annotation result | |
| CN103218820A (en) | Camera calibration error compensation method based on multi-dimensional characteristics | |
| KR20110114879A (en) | Apparatus for marking acupuncture point | |
| CN109726728A (en) | A kind of training data generation method and device | |
| CN108604131A (en) | Display system, information processing unit, information processing method and program | |
| EP4140411A1 (en) | Oral image marker detection method, and oral image matching device and method using same | |
| JP2011194105A (en) | Gazing point measuring device, gazing point measuring method, program, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190924 |
|
| RJ01 | Rejection of invention patent application after publication |