CN108985272A - Put on record authentication approach based on the high confidence level painting and calligraphy that are merged with fluoroscopy images of reflection - Google Patents
Put on record authentication approach based on the high confidence level painting and calligraphy that are merged with fluoroscopy images of reflection Download PDFInfo
- Publication number
- CN108985272A CN108985272A CN201810939647.9A CN201810939647A CN108985272A CN 108985272 A CN108985272 A CN 108985272A CN 201810939647 A CN201810939647 A CN 201810939647A CN 108985272 A CN108985272 A CN 108985272A
- Authority
- CN
- China
- Prior art keywords
- image
- calligraphy
- painting
- light source
- plate light
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/80—Recognising image objects characterised by unique random patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Put on record authentication approach the invention discloses a kind of based on the high confidence level painting and calligraphy that merges with fluoroscopy images of reflection, the equipment that this method uses includes inner wall for the work box of black, upper layer and lower layer flat-plate light source, width visual field camera, microcosmic camera；Computer improves the reliability of identity verifying by different image co-registrations by control upper layer and lower layer flat-plate light source timesharing illumination, ingestible reflected texture image and perspective texture image.This method includes two steps of stage and the stage of discerning of putting on record.The present invention has merged two kinds of texture images of reflection and perspective, and is finally matched using region feature, and the confidence level that painting and calligraphy are discerned is not only increased, and also reduces painting and calligraphy and discerns requirement to use environment.
Description
Technical field
Put on record authentication approach more particularly to a kind of based on the height that is merged with fluoroscopy images of reflection the present invention relates to a kind of painting and calligraphy
Confidence level painting and calligraphy are put on record authentication approach.
Background technique
Current painting and calligraphy put on record authentication approach be usually pass through shooting painting and calligraphy pieces surface fine textures, by extracting it
The characteristic point (such as SIFT) of texture image is matched, and by the matching degree of consistency of these characteristic points decide whether matching at
Function.But such methods have the disadvantage that
(1) texture image may be influenced similar to this point-like character of SIFT by external condition etc. and unstable,
Have an adverse effect to matching；
(2) merely with the textural characteristics of paper surface, the fiber distribution characteristics inside paper is not made full use of, from
And affect the confidence level discerned.
Summary of the invention
In order to solve shortcoming present in above-mentioned technology, the present invention provides one kind to be melted based on reflection with fluoroscopy images
The high confidence level painting and calligraphy closed are put on record authentication approach.
In order to solve the above technical problems, the technical solution adopted by the present invention is that: one kind is melted based on reflection with fluoroscopy images
The high confidence level painting and calligraphy closed are put on record authentication approach, and the equipment used includes the work box that inner wall is black；The lower end of work box is set
It is equipped with workbench, the upper end of workbench is provided with lower flat-plate light source；Transparency glass plate, painting and calligraphy are provided with above lower flat-plate light source
Works are smooth to be layed on transparency glass plate；The upper end of work box is provided with upper flat plate light source；Among the lower end of upper flat plate light source
It is provided with wide visual field camera；It is provided with mobile bracket on the inner sidewall of work box, is fixedly installed microcosmic camera on mobile bracket；
It is additionally provided on workbench for controlling the mobile and matched computer of micro image, computer passes through control upper layer and lower layer plate
Light source timesharing illumination, ingestible reflected texture image and perspective texture image improve identity by different image co-registrations and test
The reliability of card；
The overall step of this method are as follows:
One, put on record the stage:
A, it only opens upper flat plate light source to be illuminated, with the overall reflective image of wide visual field camera shooting painting and calligraphy pieces, obtain
To painting and calligraphy sample；It is required that the breadth of shooting covers the big portion region of painting and calligraphy pieces；
B, characteristic point in figure is extracted, and obtains its respective characteristic attribute description；
C, characteristic point is screened, more equably selects multiple invariant feature points；
D, microcosmic camera is moved to shooting enlarged drawing at selected characteristic point, extracts the figure again according to preceding method
It is saved after the characteristic point and its description of picture；
E, in the block region of the white space selection fritter texture-rich of painting and calligraphy sample as matching candidate position, by spy
After sign transformation, characteristic image and original texture image are saved, and mark fritter deviation post and size；
F, it closes upper flat plate light source and opens lower flat-plate light source, shoot fluoroscopy images, it then equally will be in painting and calligraphy sample
White space chooses the block region of fritter texture-rich as matching candidate position, after eigentransformation, characteristic image and
Original texture image is saved；
G, the process for repeating e~f, selects multiple and different microscopic feature matching candidate point positions；
H, features described above point and attribute description, image or characteristic image block and its deviation post, size are saved to setting
File directory in, be recorded as template image data；
Two, the stage is discerned:
A, it only opens upper flat plate light source to be illuminated, the overall reflective figure of painting and calligraphy sample to be certified is shot with wide visual field camera
Picture；It is required that the breadth of shooting covers the big portion region of painting and calligraphy image；
B, it extracts and schemes upper characteristic point, and obtain its respective characteristic attribute description；
C, features described above point is matched with the characteristic point in painting and calligraphy sample, if successful match points are less than setting ratio
Example, then it is assumed that it fails to match, exits certification；Otherwise it is assumed that successful match, calculates position, the angle of authentication image and sample image
And dimensional deviations, and continue next step；
D, microcosmic camera is moved to successful match position, extracts the image characteristic point of the position again, later and template
In characteristic point match, if successful match, calculate current sample image and template position, angle and dimensional deviations；If matching
Failure, then rechange a repetition aforesaid operations；
E, it closes upper flat plate light source and opens lower flat-plate light source, shoot transmission image；According to the matching result of above-mentioned image
It is corrected to current sample image and with the position of template, angle and dimensional deviations, obtains corresponding templates matching candidate position
The matching candidate image or characteristic image block set；Characteristic image block is divided into reflectance signature image block, transmission feature image block；
F, reflectance signature image block, transmission feature image block respectively characteristic image block corresponding with template move left and right into
Row matching sees whether to be more than given threshold；If being more than, successful match；Otherwise it fails to match；
G, selection matching points are required according to confidence level, if the points of successful match are greater than the ratio of setting, then it is assumed that one
Cause property is examined successfully, otherwise it is assumed that failure.
Further, characteristic point includes SIFT, Surf point, angle point.
The present invention has merged two kinds of texture images of reflection and perspective, and is finally matched using region feature, not only improves
The confidence level that painting and calligraphy are discerned also reduces painting and calligraphy and discerns requirement to use environment.
Detailed description of the invention
Fig. 1 is the structural schematic diagram for the equipment that the present invention uses.
Fig. 2 is the reflected texture image of painting and calligraphy pieces.
Fig. 3 is the transmission texture image of painting and calligraphy pieces same position in Fig. 2.
In figure: 1, upper flat plate light source；2, wide visual field camera；3, mobile bracket；4, microcosmic camera；5, transparency glass plate；6,
Lower flat-plate light source；7, workbench；8, work box.
Specific embodiment
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
It is a kind of to be put on record authentication approach based on the high confidence level painting and calligraphy that are merged with fluoroscopy images of reflection, the equipment used such as Fig. 1
It is shown, it is the work box of black including inner wall；The lower end of work box is provided with workbench, and the upper end of workbench is provided with lower plate
Light source；Transparency glass plate is provided with above lower flat-plate light source, painting and calligraphy pieces are smooth to be layed on transparency glass plate；Work box
Upper end is provided with upper flat plate light source；Wide visual field camera is provided among the lower end of upper flat plate light source；It is set on the inner sidewall of work box
It is equipped with mobile bracket, is fixedly installed microcosmic camera on mobile bracket；It is additionally provided on workbench mobile and microcosmic for controlling
The computer of images match, computer pass through control upper layer and lower layer flat-plate light source timesharing illumination, ingestible reflected texture image (figure
Shown in 2) and perspective texture image (shown in Fig. 3), the reliability of identity verifying is improved by different image co-registrations；Above and below
Flat-plate light source can also be with equivalent replacement for other distributed lighting light sources, it is therefore an objective to eliminate the influence of shade.
The overall step of this method are as follows:
One, put on record the stage:
A, it only opens upper flat plate light source to be illuminated, with the overall reflective image of wide visual field camera shooting painting and calligraphy pieces, obtain
To painting and calligraphy sample；It is required that the breadth of shooting covers the big portion region of painting and calligraphy pieces；
B, characteristic point in figure, such as SIFT, Surf point, angle point are extracted, and obtains its respective characteristic attribute description；
C, characteristic point is screened, more equably selects multiple invariant feature points；
D, microcosmic camera is moved to shooting enlarged drawing at selected characteristic point, extracts the figure again according to preceding method
It is saved after the characteristic point and its description of picture；
E, in the block region of the white space selection fritter texture-rich of painting and calligraphy sample as matching candidate position, by spy
Sign transformation is as characteristic image and original texture image saved, and mark fritter deviation post and size after gradient transformation；
F, it closes upper flat plate light source and opens lower flat-plate light source, shoot fluoroscopy images, it then equally will be in painting and calligraphy sample
White space chooses the block region of fritter texture-rich as matching candidate position, after eigentransformation, characteristic image and
Original texture image is saved；
The step can also turn off upper flat plate light after the point feature of reflected image and block feature all shooting storages
Source opens lower flat-plate light source, shoots fluoroscopy images, extracts point, region feature again and save；
G, the process for repeating e~f, selects multiple and different microscopic feature matching candidate point positions；
H, features described above point and attribute description, image or characteristic image block and its deviation post, size are saved to setting
File directory in, be recorded as template image data；
Two, the stage is discerned:
A, it only opens upper flat plate light source to be illuminated, the overall reflective figure of painting and calligraphy sample to be certified is shot with wide visual field camera
Picture；It is required that the breadth of shooting covers the big portion region of painting and calligraphy image；
B, it extracts and schemes upper characteristic point, and obtain its respective characteristic attribute description；
C, features described above point is matched with the characteristic point in painting and calligraphy sample, if successful match points are less than setting ratio
Example, then it is assumed that it fails to match, exits certification；Otherwise it is assumed that successful match, calculates position, the angle of authentication image and sample image
And dimensional deviations, and continue next step；
D, microcosmic camera is moved to successful match position, extracts the image characteristic point of the position again, later and template
In characteristic point match, if successful match, calculate current sample image and template position, angle and dimensional deviations；If matching
Failure, then rechange a repetition aforesaid operations；
E, it closes upper flat plate light source and opens lower flat-plate light source, shoot transmission image；According to the matching result of above-mentioned image
It is corrected to current sample image and with the position of template, angle and dimensional deviations, obtains corresponding templates matching candidate position
The matching candidate image or characteristic image block set；Characteristic image block is divided into reflectance signature image block, transmission feature image block；
F, reflectance signature image block, transmission feature image block respectively characteristic image block corresponding with template move left and right into
Row matching sees whether to be more than given threshold；If being more than, successful match；Otherwise it fails to match；
G, selection matching points are required according to confidence level, if the points of successful match are greater than the ratio of setting, then it is assumed that one
Cause property is examined successfully, otherwise it is assumed that failure.
Here image Block- matching is the related coefficient calculated between image or characteristic image, and putting on record in discerning used in painting and calligraphy has
Feature insensitive for environmental changes such as illumination, stability is good, a small amount of image disturbances will not have an impact to result is discerned,
It is preferably unified to achieve consistency and stability.
The present invention can take in reflected texture image and perspective texture figure in such a way that upper layer and lower layer light source timesharing illuminates
Picture is remarkably improved the reliability of identity verifying by different image co-registrations.
This method using the painting and calligraphy that merge with transmission image of reflection despite based on being put on record authentication approach, but based on above-mentioned two
Kind of image, which can also independently be carried out painting and calligraphy, to be put on record and discerns work.
Above embodiment is not limitation of the present invention, and the present invention is also not limited to the example above, this technology neck
The variations, modifications, additions or substitutions that the technical staff in domain is made within the scope of technical solution of the present invention, also belong to this hair
Bright protection scope.
Claims (2)
- A kind of authentication approach 1. high confidence level painting and calligraphy merged based on reflection with fluoroscopy images are put on record, it is characterised in that: the mirror The equipment that card method uses includes the work box that inner wall is black；The lower end of the work box is provided with workbench, workbench Upper end is provided with lower flat-plate light source；Transparency glass plate is provided with above the lower flat-plate light source, painting and calligraphy pieces are smooth to be layed in On transparency glass plate；The upper end of the work box is provided with upper flat plate light source；Wide view is provided among the lower end of upper flat plate light source Wild camera；It is provided with mobile bracket on the inner sidewall of the work box, is fixedly installed microcosmic camera on mobile bracket；The work Make to be additionally provided on platform for controlling the mobile and matched computer of micro image, computer passes through control upper layer and lower layer plate light Source timesharing illumination, ingestible reflected texture image and perspective texture image improve identity verifying by different image co-registrations Reliability；The overall step of the authentication approach are as follows:One, put on record the stage:A, it only opens upper flat plate light source to be illuminated, with the overall reflective image of wide visual field camera shooting painting and calligraphy pieces, obtains book Draw sample；It is required that the breadth of shooting covers the big portion region of painting and calligraphy pieces；B, characteristic point in figure is extracted, and obtains its respective characteristic attribute description；C, characteristic point is screened, more equably selects multiple invariant feature points；D, microcosmic camera is moved to shooting enlarged drawing at selected characteristic point, extracts the image again according to preceding method It is saved after characteristic point and its description；E, become as matching candidate position by feature in the block region that the white space of painting and calligraphy sample chooses fritter texture-rich After changing, characteristic image and original texture image are saved, and mark fritter deviation post and size；F, it closes upper flat plate light source and opens lower flat-plate light source, shoot fluoroscopy images, it then equally will be in the blank of painting and calligraphy sample Region choose fritter texture-rich block region as matching candidate position, after eigentransformation, characteristic image with it is original Texture image is saved；G, the process for repeating e~f, selects multiple and different microscopic feature matching candidate point positions；H, features described above point and attribute description, image or characteristic image block and its deviation post, size are saved to the text of setting In part catalogue, it is recorded as template image data；Two, the stage is discerned:A, it only opens upper flat plate light source to be illuminated, the overall reflective image of painting and calligraphy sample to be certified is shot with wide visual field camera； It is required that the breadth of shooting covers the big portion region of painting and calligraphy image；B, it extracts and schemes upper characteristic point, and obtain its respective characteristic attribute description；C, features described above point is matched with the characteristic point in painting and calligraphy sample, if successful match points are less than setting ratio, Think that it fails to match, exits certification；Otherwise it is assumed that successful match, calculates position, angle and the ruler of authentication image and sample image Deviation is spent, and continues next step；D, microcosmic camera is moved to successful match position, extracts the image characteristic point of the position again, later and in template Characteristic point matches, if successful match, calculates current sample image and template position, angle and dimensional deviations；If it fails to match, Then rechange a repetition aforesaid operations；E, it closes upper flat plate light source and opens lower flat-plate light source, shoot transmission image；According to the matching result of above-mentioned image to working as It preceding sample image and is corrected with the position of template, angle and dimensional deviations, obtains corresponding templates matching candidate position Matching candidate image or characteristic image block；Characteristic image block is divided into reflectance signature image block, transmission feature image block；F, reflectance signature image block, transmission feature image block, characteristic image block corresponding with template moves left and right progress respectively Match, sees whether to be more than given threshold；If being more than, successful match；Otherwise it fails to match；G, selection matching points are required according to confidence level, if the points of successful match are greater than the ratio of setting, then it is assumed that consistency It examines successfully, otherwise it is assumed that failure.
- The authentication approach 2. the high confidence level painting and calligraphy according to claim 1 merged based on reflection with fluoroscopy images are put on record, Be characterized in that: the characteristic point includes SIFT, Surf point, angle point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810939647.9A CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810939647.9A CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108985272A true CN108985272A (en) | 2018-12-11 |
| CN108985272B CN108985272B (en) | 2021-11-23 |
Family
ID=64553976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810939647.9A Active CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985272B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114125295A (en) * | 2021-11-25 | 2022-03-01 | 大势大非(北京)文化有限公司 | Private data painting and calligraphy right confirming method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020052809A1 (en) * | 2000-11-02 | 2002-05-02 | Orell Fussli Security Documents Ag | Method for verifying the authenticity of articles |
| US20100284569A1 (en) * | 2008-01-11 | 2010-11-11 | Kazuyuki Sakurai | Lane recognition system, lane recognition method, and lane recognition program |
| US20110188102A1 (en) * | 2010-02-02 | 2011-08-04 | Sony Corporation | Hologram-including medium, hologram-including medium producing apparatus, and information authentication method |
| US20120070088A1 (en) * | 2009-06-02 | 2012-03-22 | Kousuke Yoshimi | Picture image processor, method for processing picture image and method for processing picture image |
| CN103116755A (en) * | 2013-01-27 | 2013-05-22 | 深圳市书圣艺术品防伪鉴定有限公司 | Automatic painting and calligraphy authenticity degree detecting system and method thereof |
| CN105323208A (en) * | 2014-06-07 | 2016-02-10 | 李季 | Method for tracing calligraphy and painting identity tag |
| CN105654216A (en) * | 2014-11-15 | 2016-06-08 | 北京翰易得科技有限公司 | Calligraphy and painting management and selling system based on intelligent handset platform |
| CN106131389A (en) * | 2016-08-24 | 2016-11-16 | 北京雅昌艺术印刷有限公司 | Apparatus and method for painting and calligraphy pieces put on record and identify |
| CN106529506A (en) * | 2016-12-05 | 2017-03-22 | 沈阳毓沣恒装饰材料有限公司 | A calligraphy and painting record authentication device based on multistage magnification times |
-
2018
- 2018-08-17 CN CN201810939647.9A patent/CN108985272B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020052809A1 (en) * | 2000-11-02 | 2002-05-02 | Orell Fussli Security Documents Ag | Method for verifying the authenticity of articles |
| US20100284569A1 (en) * | 2008-01-11 | 2010-11-11 | Kazuyuki Sakurai | Lane recognition system, lane recognition method, and lane recognition program |
| US20120070088A1 (en) * | 2009-06-02 | 2012-03-22 | Kousuke Yoshimi | Picture image processor, method for processing picture image and method for processing picture image |
| US20110188102A1 (en) * | 2010-02-02 | 2011-08-04 | Sony Corporation | Hologram-including medium, hologram-including medium producing apparatus, and information authentication method |
| CN103116755A (en) * | 2013-01-27 | 2013-05-22 | 深圳市书圣艺术品防伪鉴定有限公司 | Automatic painting and calligraphy authenticity degree detecting system and method thereof |
| CN105323208A (en) * | 2014-06-07 | 2016-02-10 | 李季 | Method for tracing calligraphy and painting identity tag |
| CN105654216A (en) * | 2014-11-15 | 2016-06-08 | 北京翰易得科技有限公司 | Calligraphy and painting management and selling system based on intelligent handset platform |
| CN106131389A (en) * | 2016-08-24 | 2016-11-16 | 北京雅昌艺术印刷有限公司 | Apparatus and method for painting and calligraphy pieces put on record and identify |
| CN106529506A (en) * | 2016-12-05 | 2017-03-22 | 沈阳毓沣恒装饰材料有限公司 | A calligraphy and painting record authentication device based on multistage magnification times |
Non-Patent Citations (1)
| Title |
|---|
| 关晓惠: "计算机辅助的国画：分类、鉴别与系统", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114125295A (en) * | 2021-11-25 | 2022-03-01 | 大势大非(北京)文化有限公司 | Private data painting and calligraphy right confirming method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108985272B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230419444A1 (en) | Systems, devices, and methods for providing feedback on and improving the accuracy of super-resolution imaging | |
| CN101128838B (en) | Recognition graph | |
| US8515208B2 (en) | Method for document to template alignment | |
| US11408829B2 (en) | Macro inspection systems, apparatus and methods | |
| JP6872670B2 (en) | Dimension measuring device, dimensional measuring program and semiconductor manufacturing system | |
| CN102834845A (en) | Method and arrangement for multi-camera calibration | |
| CN109784342A (en) | A kind of OCR recognition methods and terminal based on deep learning model | |
| WO2016114898A1 (en) | Systems, methods and devices for the automated verification and quality control and assurance of vehicle identification plates | |
| KR102502486B1 (en) | Image generating system | |
| JP2023134712A (en) | System, method, and apparatus for macroscopic inspection of reflective specimen | |
| CN100437628C (en) | Automatic digitization of garment patterns | |
| CN1173283C (en) | Document image processing apparatus and its method and recording medium with all program | |
| CN102831578B (en) | Image processing method and image processing device | |
| CN102473278A (en) | Image processing apparatus, image processing method, and storage medium | |
| US20060193525A1 (en) | Extracting embedded information from a document | |
| CN108985272A (en) | Put on record authentication approach based on the high confidence level painting and calligraphy that are merged with fluoroscopy images of reflection | |
| AU2011265380A1 (en) | Determining transparent fills based on a reference background colour | |
| KR100987094B1 (en) | Method for automatically defining a part model | |
| CN110378167A (en) | A kind of bar code image correction algorithm based on deep learning | |
| Hagg et al. | On recognizing transparent objects in domestic environments using fusion of multiple sensor modalities | |
| JP6890849B2 (en) | Information processing system | |
| CN114758346A (en) | High-precision image global microscopic printing document identification system | |
| CN207264408U (en) | A kind of iris identification device | |
| CN113096219A (en) | Light control method and device | |
| CN102262614A (en) | Longitudinal proofreading method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |