CN103577797B - Image recognition system and image recognition method thereof - Google Patents
Image recognition system and image recognition method thereof Download PDFInfo
- Publication number
- CN103577797B CN103577797B CN201210276146.XA CN201210276146A CN103577797B CN 103577797 B CN103577797 B CN 103577797B CN 201210276146 A CN201210276146 A CN 201210276146A CN 103577797 B CN103577797 B CN 103577797B
- Authority
- CN
- China
- Prior art keywords
- search
- identification
- image
- square
- setting module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of image recognition system and image recognition method thereof.This image recognition system comprises a setting module and an identification module.One image setting is divided into several Search Areas by setting module, and each Search Area optionally sets a search interval respectively.Identification module connects setting module, when identification module carries out identification to image under one first recognition mode, make a search window move according to corresponding search interval in each Search Area, carry out detecting identification with the pixel corresponding to position that search window is moved to.The present invention can promote the efficiency of overall image identification effectively, and can maintain the quality that identification detects.
Description
Technical field
The invention relates to a kind of image recognition system and image recognition method thereof, in particular to one
A specific move mode or a shade can carry out image identification, and then reach image fast and accurately and distinguish
Knowledge system and image recognition method thereof.
Background technology
Along with the prosperity of science and technology, image processing technique is more and more polynary, its purposes the most all the more extensive.Can
Image processing software/system is installed or is embedded among the devices such as PC, mobile phone or camera, or from
Group is an image processor.Containing image identification function in image processing technique, it can be used for detecting shadow
As the special characteristic in photo, to carry out identification comparison with other reference images.Such as: may be used to executor
Thing face feature comparison, and then carry out the operation of identity inspection etc..
At present, for existing image identification technology, when performing image identification operation, it is to use mostly
Single or fixed form moves a search window sequentially, so that (each image unit in image is comprised picture
Prime number amount is 22*22) carry out identification process, so do not have the operating type of elastic choice, the money processed will be made
Material becomes many, simultaneously need to the access execution time the most relatively becomes tediously long.Visible Fig. 1, image 100 can divide
For several image units 101, when carrying out image identification, then it is that mobile search form 200 comes each
Individual image unit 101 carries out image identification.Wherein, this figure is only simpler labeling method, actually adjacent
Image unit 101 have part overlap.For example, it is assumed that the upper left of first image unit 101 in upper left
Angle location of pixels is the coordinate (0,0) in image 100, the upper left corner picture of the image unit 101 on its adjacent the right
Element position is then coordinate (1,0), and the upper left pixel location of the image unit 101 of adjacent lower section is then coordinate
(0,1).Search window 200 is then to be its distance of taking action with pixel, and such as first to the upper left corner
The image unit 101 of location of pixels (0,0) does identification and processes, and then moves a pixel to the upper left corner after having performed
The image unit 101 of position (1,0) carries out identification.
It addition, process operation for further speeding up image identification, some image identification method can make search window 200
Search interval 300 modes with one to move, so that the image unit 101 moved to is carried out identification, such as Fig. 2 institute
Show.But, total image 100 only can be done and set single search interval 300 by this kind of mode, makes system sharp
Search interval 300 with this to carry out detecting identification to image 100, and the zones of different of image 100 cannot be divided
Do not set different search intervals 300, more not enough processing in operation elasticity, and it is likely to cause image
The coarse problem of identification.
Summary of the invention
Because above-mentioned known technology problem, the purpose of the present invention is exactly to provide image recognition system and shadow thereof
As discrimination method, only can single or fixed model mobile search in proper order with the known image identification technology of solution
Form is slow with the treatment effeciency carrying out identification and being caused, and only can set total image and single search interval institute
Cause the process logy problem of operation.
For achieving the above object, the present invention is by the following technical solutions:
A kind of image recognition system, it comprises a setting module and an identification module.Setting module is by an image
Setting district is divided into several Search Areas, and each Search Area optionally sets a search interval respectively.
Identification module connects setting module, when identification module carries out identification to image under one first recognition mode,
A search window is made to move according to corresponding search interval, with to search window in each Search Area
The pixel corresponding to position moved to carries out detecting identification.Wherein, setting module the most optionally will be each
Search Area setting district respectively is divided into several to search square, and each search square includes several respectively and searches
Seek unit.Setting module also sets the search shade of a correspondence respectively to each search square, make identification module in
When image being carried out identification under one second recognition mode, it is to utilize each search shade to come respectively each correspondence is searched
Several search unit sought in square optionally detect identification.
It is preferred that setting module can provide resource-user cost method ground to set the range size of each Search Area respectively
And the interval at this search interval of each correspondence.
It is preferred that each search shade is also set by setting module respectively comprises at least one search window, make to distinguish
When knowledge module carrys out the execution image detecting of the search square to each correspondence with each search shade, only to each search square
In corresponding to search window search unit pixel carry out detect identification.
It is preferred that the scope that setting module can provide resource-user cost method ground to set each search square respectively is big
Little, with so that determine corresponding to each search square search unit quantity, and provide resource-user cost method ground
Set the quantity of search window included in each search shade respectively.
It is preferred that it is with the first recognition mode or two that setting module can provide user to select to set identification module
Recognition mode carries out identification.
According to the purpose of the present invention, proposing again a kind of image recognition method, it comprises the steps of and utilizes one
One image setting is divided into several Search Areas by setting module, and each Search Area is set one respectively searches
Seek interval；And when an identification module carries out identification to image, make a search window in each Search Area
Move according to corresponding search interval, with the pixel corresponding to position that search window is moved to
Carry out detecting identification.Wherein, also via this setting module by user set respectively respectively in this Search Area horizontal
To this search interval and longitudinal direction this search interval.
According to the purpose of the present invention, reintroducing a kind of image recognition method, it comprises the steps of and utilizes one
One image setting is divided into several Search Areas by setting module, and each Search Area is set differentiation respectively
Searching square for several, each square of searching is included as several search unit respectively；Utilize setting module pair
Each square of searching sets the search shade of a correspondence respectively；And when an identification module carries out identification to image
Time, it is that several that utilize each search shade to come respectively to search each correspondence in square are searched unit and selected
Detect identification to selecting property.
From the above, image recognition system under this invention and image recognition method thereof, it can have one or many
Individual following advantage:
(1) this image recognition system and image recognition method thereof, it is possible to provide image setting is divided into by user
Several Search Areas, more each Search Area is respectively set as different search intervals, to utilize this to search
Interval carries out the process of image identification, can avoid wasting time over unessential region and search, with main pin
The region that may have feature is carried out identification detecting, consequently, it is possible to overall image identification can be promoted effectively
Efficiency, and the quality that identification detects can be maintained.
(2) this image recognition system and image recognition method thereof, it is possible to provide user sets different identification moulds
Formula, with further by image setting for different imagery zones, square, unit etc., can more efficiently use
Identification detecting processes resource, makes efficiency effectively promote.
Accompanying drawing explanation
Fig. 1 is the first schematic diagram of the known image identification mode of the present invention.
Fig. 2 is the second schematic diagram of the known image identification mode of the present invention.
Fig. 3 is the block chart of the image recognition system of the present invention.
Fig. 4 is the first pass figure of the image recognition method of the present invention.
Fig. 5 is the second flow chart of the image recognition method of the present invention.
Fig. 6 is the schematic diagram of the first embodiment of the image recognition system of the present invention and image recognition method thereof.
Fig. 7 is the schematic diagram of the second embodiment of the image recognition system of the present invention and image recognition method thereof.
Fig. 8 is the signal of an other embodiment of the image recognition system of the present invention and image recognition method thereof
Figure.
Fig. 9 is the schematic diagram of the another embodiment of the image recognition system of the present invention and image recognition method thereof.
Detailed description of the invention
For the technical characteristic of the present invention, content and advantage and the effect that can reach thereof being described, below by this
Bright cooperation accompanying drawing, and describe in detail as follows with the expression-form of embodiment, and the accompanying drawing used in it, its
Purport be only signal and aid in illustrating book be used, may not for the present invention enforcement after actual proportions with precisely join
Put, therefore the right the model ratio of accompanying drawing should do not understood with configuration relation, be limited the invention in actual enforcement
Enclose, state in advance.
Referring to Fig. 3, it is the block chart of image recognition system of the present invention.In figure, image recognition system
1 includes setting module 11 and an identification module 12, and setting module 11 is connected with identification module 12.
This image recognition system 1 can be software or circuit chip etc., with install or be embedded at PC, mobile phone or
Among the devices such as camera, or it is an image processor from group.Setting module 11 can comprise physical button or
Virtual key and corresponding process circuit thereof.
In above-mentioned, when user is intended to carry out detecting identification to an image 2, available setting module 11 is to shadow
As 2 setting districts are divided into several Search Areas 21, and optionally each Search Area 21 is set one respectively
Search interval 3.After user has set in this way, identification module 12 can the first recognition mode
121 pairs of images 2 carry out identification, so that a search window is in each Search Area 21, respectively according to user
Set search interval 3 moves, with the image 2 corresponding to the position that moves to search window
Pixel carries out detecting identification.Wherein, setting module 11 can provide resource-user cost method ground to set respectively respectively
The range size of Search Area 21 and the search of each correspondence are spaced the interval of 3, and setting module 11 can carry
The search interval 3 searching interval 3 and longitudinal direction horizontal in each Search Area 21 is set respectively for user.
Additionally, image 2 can also another kind of form be carried out detecting identification by this image recognition system 1.Use
Person may utilize setting module 11 and image 2 setting district be divided into several Search Areas 21, then by each search district
Setting district respectively, territory 21 is divided into several to search square 211, and if making each search square 211 include respectively
Search unit 2111 for dry.Each search square 211 can be set respectively by user again by setting module 11
The search shade 4 of one correspondence.Then, identification module 12 can one second recognition mode 122 to image 2
Carry out detecting identification, some with utilize each search shade 4 to come respectively each correspondence is searched in square 211
Individual search unit 2111 optionally detects identification.In more detail, setting module 11 can provide and make
Each search shade 4 is set and comprises at least one search window by user respectively, consequently, it is possible in identification module
12 when performing image detecting with each search shade 4 to the search square 211 of each correspondence, identification module 12
Only in each search square 211, corresponding to searching the search unit 2111 of the search window in shade 4
Pixel carries out detecting identification.Wherein, setting module 11 can provide resource-user cost method ground to set respectively respectively
Search the range size of square 211, the search list corresponding to each search square 211 the most just and then can be determined
The quantity of unit 2111.And setting module 11 sets each search shade with may also provide resource-user cost method respectively
The quantity of search window included in 4.
In above-mentioned, setting module 11 can provide region segmentation that user first sets image 2 and be stored up
Depositing, when the time comes, during user image identification to be used function, user only needs to be selected by setting module 11
Select setting identification module 12 to be intended to carry out identification with the first recognition mode 121 or the second recognition mode 122,
Identification module 12 will set pattern according to user image 2 set in advance and carry out image identification.
In above-mentioned, the mode that setting module 11 provides user that image 2 is made a distinction setting is only for example,
Setting module 11 also can provide user that image 2 setting district is directly divided into several search unit 2111,
Reset identification module 12 and the unit 2111 of partly or entirely searching in image 2 is done image detecting identification.
The above neither should have been limited so that the present invention illustrates.
Referring to Fig. 4, it is the first pass figure of image recognition method of the present invention, and its process step is:
S41: utilize a setting module that one image setting is divided into several Search Areas, and to each search
Region sets a search interval respectively.
S42: when an identification module carries out identification to image, make a search window depend in each Search Area
Move according to corresponding search interval, click on the pixel corresponding to position that search window is moved to
Row detecting identification.
Referring to Fig. 5, it is the second flow chart of image recognition method of the present invention, and its process step is:
S51: utilize a setting module that one image setting is divided into several Search Areas, and by each search
Setting district respectively, region is divided into several to search square, and each square of searching comprises several search unit respectively.
S52: utilize setting module that each search square is set the search shade of a correspondence respectively.
S53: when an identification module carries out identification to image, utilizes each search shade to come respectively to each correspondence
Search in square several search unit and optionally detect identification.
Referring to Fig. 6, it is image recognition system and the first embodiment of image recognition method thereof of the present invention
Schematic diagram.In this embodiment, having an image A, user can be via the image identification system of the present invention
System this image A is set, optionally image A is respectively set as the first Search Area A1,
Second Search Area A2, the 3rd Search Area A3 and the 4th Search Area A4.Wherein, above search district
The setting of territory quantity and range size can not limit, and is only signal in this figure.User can be the most right
First Search Area A1, the second Search Area A2, the 3rd Search Area A3 and the 4th Search Area A4
Set corresponding search interval C1, C2, C3 and a C4 respectively.Then, this image recognition system is just
Can be according to the setting of user, by a search window B respectively at the first Search Area A1, the second search district
In territory A2, the 3rd Search Area A3 and the 4th Search Area A4, according to each corresponding search interval
C1, C2, C3 and C4 move, and the pixel being moved to search window B carries out detecting and distinguishes
Know.As shown in Figure 6, the search interval C1 corresponding to the first Search Area A1 is transverse direction and longitudinal direction difference
At a distance of 2 location of pixels, the search interval C2 corresponding to the second Search Area A2 is that transverse direction and longitudinal direction is divided
Not at a distance of 3 location of pixels, the search interval C3 corresponding to the 3rd Search Area A3 is transverse direction and longitudinal direction
Respectively at a distance of 1 location of pixels, the search interval C4 corresponding to the 4th Search Area A4 is then horizontal
And the most respectively at a distance of 2 location of pixels.Wherein, setting of interval C1, C2, C3 and C4 is searched at this
Surely it is only an embodiment, has not limited with this.
Referring to Fig. 7, it is image recognition system and second embodiment of image recognition method thereof of the present invention
Schematic diagram.In this embodiment, having an image D, user can be via the image identification system of the present invention
System this image D is set, optionally image D is respectively set as the first Search Area D1,
Second Search Area D2, the 3rd Search Area D3 and the 4th Search Area D4.User also can will respectively be searched
Seeking region and divide into several search squares, with the first Search Area D1 for example, user can be by it
Differentiation is set as the first search square D11, the second search square D12, the 3rd search square D13 and the 4th
Search square D14.Each search further includes several search unit in square, search square with first
For example, it includes nine and searches cells D 111 D11.Then, user can be further to respectively
Search square and set a corresponding search shade, search square D11 for example with first, it is set
One searches shade E, and optionally sets at least one search window in searching in shade E, sets at this
Search window E1, E2, E3 and E4.Wherein, the setting of each search window position can be not limited fixed,
An embodiment it is only at this.After the search shade that each search square has been set its correspondence, this image identification
System just will utilize set by respectively search shade, respectively each correspondence to be searched those searches in square
Unit optionally detects identification.Searching square D11 for example with first, first searches square
D11 is divided into nine to search cells D 111, and the search shade E of its correspondence also divides into nine blocks, part
Block Set search window E1, E2, E3 and E4, but, this image recognition system is just searched according to this
Shade E, searches square D11 to first and carries out image detecting identification, with identification corresponding to search window
Whether the search cells D 111 of E1, E2, E3 and E4 position has feature exists (character features etc.).
In above-mentioned, the image recognition system of the present invention and image recognition method thereof, it is set via to image,
And then with different search intervals or search shade, image is carried out detecting identification, mainly seek to promote shadow
As the efficiency of identification, the most do not lose identification accuracy simultaneously.Allow the user can be in image, may
The position of feature occurs, sets higher search density, be less likely to the position that feature occurs, search density
Just can set reduction, the most just can effectively promote the efficiency of image identification, as shown in Figure 8.In figure, shadow
If it (can be that search of the present invention regards that the square oblique line dark end in Xiang is identification point 500 to be detected
Window).
Additionally, when determining to search shade for each search square, can determine according to following two ways, but
This only implements example, is not limited.
Mode one:
Using software set, software can depend on various demands and different application, select the search that it is to be suitable for hide
Cover.The elasticity of the variation of this kind of mode is big, it is desirable to which type of searches shade with, it is possible to use software in advance
Judgment mode is ready to the search shade used.Will go according to the search shade made when hardware performs
Carry out image processing, but the method needs to expend the resource of central processor CPU, can be according to different
Demand removes the search shade judging to seek more to meet.
Mode two:
Hardware goes to determine that each 3x3 searches the search that in shade, which pixel corresponds to according to weight (priority)
Unit (this searches unit and is exemplified as a window of 22x22, does not limits with this) needs processed.If such as
5th, 1 and 9 pixels are set to high weight (being the search window of setting of the present invention) by us, when this
3 corresponding search unit contain face message or it is the image with the presence of important message, the most then
Reprocess remaining search unit corresponding to point, as shown in Figure 9.If this 3 point (5,1 and 9) correspondence
Search unit and all there is no face message or the most inessential, the most do not reprocess other and search shade correspondence at 3x3
Point (the such as the 4th, 6,2,3,8 and 7 pixel).Certainly we can also only set the 5th pixel
This 1 pixel is high weight, and other pixel judges as according to other weight height, it is judged that
Go out and process again when having important message.Hardware so can be made automatically to be processed by image according to individual rule
Complete, CPU is just not required to expend resource and goes to make a decision.
Summary, the image recognition system of the present invention and image recognition method thereof, it is possible to provide user is to shadow
As being set, and set required recognition mode further, search interval that can be different or search shade
Carry out image detecting identification, consequently, it is possible to the efficiency of image identification can be promoted effectively, it is possible to simultaneously
Take into account quality during detecting identification.
The foregoing is only illustrative, rather than be restricted person.Any spirit and scope without departing from the present invention,
And the equivalent modifications that it is carried out or change, it is intended to be limited solely by appended claims scope.
Claims (9)
1. an image recognition system, it is characterised in that it comprises:
Setting module, divides into several Search Areas by image setting, and optionally to respectively this search district
Territory sets search interval respectively；And
Identification module, connects this setting module, when this image is entered under the first recognition mode by this identification module
During row identification, search window is made to move according to corresponding this search interval in respectively this Search Area,
Carry out detecting identification with the pixel corresponding to position that this search window is moved to；
Wherein, respectively this Search Area setting district respectively is the most optionally divided into several to search by this setting module
Square, and respectively this search square includes several respectively and searches unit, this setting module to respectively this search
Square sets the search shade of a correspondence respectively, makes this identification module enter this image under the second recognition mode
During row identification, utilize respectively this search shade to come respectively and those in this search square of each correspondence are searched unit
Optionally detect identification.
2. image recognition system as claimed in claim 1, it is characterised in that this setting module provides and makes
Set to user's activeness the range size of respectively this Search Area and the district at this search interval of each correspondence respectively
Between.
3. image recognition system as claimed in claim 1, it is characterised in that this setting module is also to respectively
This search shade sets respectively and comprises at least one this search window, makes this identification module with respectively this search shade
When carrying out the execution image detecting of this search square to each correspondence, only to respectively this search square corresponds to this search
The pixel of this search unit of form carries out detecting identification.
4. image recognition system as claimed in claim 3, it is characterised in that this setting module provides and makes
Set to user's activeness the range size of respectively this search square respectively, with so that determine each this search square institute
The quantity of this corresponding search unit, and provide resource-user cost method ground to set respectively institute in this search shade respectively
Comprise the quantity of this search window.
5. image recognition system as claimed in claim 1, it is characterised in that this setting module provides and makes
It is to carry out identification with this first recognition mode or this two recognition mode that user selects to set this identification module.
6. an image recognition method, it is characterised in that comprise the steps of
Utilize setting module that image setting is divided into several Search Areas, and to respectively this Search Area difference
Set and search interval；And
When identification module carries out identification to this image, make search window foundation institute in respectively this Search Area right
This search interval answered moves, and carries out with the pixel corresponding to the position that moves to this search window
Detecting identification；
Wherein, also this search horizontal in each this Search Area is set via this setting module respectively by user
This search interval of interval and longitudinal direction.
7. an image recognition method, it is characterised in that comprise the steps of
Utilize setting module that image setting is divided into several Search Areas, and by respectively this Search Area difference
Setting district is divided into several to search square, and respectively this search square comprises several search unit respectively；
Utilize this setting module that respectively this search square sets the search shade of correspondence respectively；And
When identification module carries out identification to this image, respectively this search shade is utilized respectively each correspondence to be somebody's turn to do
Those search unit searched in square optionally detect identification.
8. image recognition method as claimed in claim 7, it is characterised in that also comprise the steps of
Utilize this setting module that respectively this search shade is set respectively and comprise at least one search window, make this identification
When module carrys out the execution image detecting of this search square to each correspondence with respectively this search shade, only to respectively this search
The pixel having this search unit corresponding to this search window in square carries out detecting identification.
9. image recognition method as claimed in claim 8, it is characterised in that also comprise the steps of
This setting module is provided to set the range size of respectively this search square respectively by resource-user cost method, with
And then determine the quantity of respectively this search unit corresponding to this search square, and divide while resource-user cost method is provided
Do not set the quantity of this search window included in each this search shade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210276146.XA CN103577797B (en) | 2012-08-03 | 2012-08-03 | Image recognition system and image recognition method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210276146.XA CN103577797B (en) | 2012-08-03 | 2012-08-03 | Image recognition system and image recognition method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103577797A CN103577797A (en) | 2014-02-12 |
| CN103577797B true CN103577797B (en) | 2016-08-24 |
Family
ID=50049552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210276146.XA Active CN103577797B (en) | 2012-08-03 | 2012-08-03 | Image recognition system and image recognition method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103577797B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680118B (en) * | 2017-08-29 | 2020-10-20 | 苏州佳世达光电有限公司 | Image identification tracking method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4590717B2 (en) * | 2000-11-17 | 2010-12-01 | ソニー株式会社 | Face identification device and face identification method |
| TW201224955A (en) * | 2010-12-15 | 2012-06-16 | Ind Tech Res Inst | System and method for face detection using face region location and size predictions and computer program product thereof |
-
2012
- 2012-08-03 CN CN201210276146.XA patent/CN103577797B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN103577797A (en) | 2014-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807385A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN103065134B (en) | A kind of fingerprint identification device and method with information | |
| CN104268498B (en) | A kind of recognition methods of Quick Response Code and terminal | |
| CN104809452A (en) | Fingerprint identification method | |
| CN101834986B (en) | Imaging apparatus, mobile body detecting method, mobile body detecting circuit and program | |
| CN109271870A (en) | Pedestrian recognition methods, device, computer equipment and storage medium again | |
| US20130243343A1 (en) | Method and device for people group detection | |
| CN104809453A (en) | Authentication method based on fingerprints | |
| CN104853668A (en) | Tiled image based scanning for head position for eye and gaze tracking | |
| CN102017606B (en) | Image processing device, camera, image processing method, and program | |
| CN101751572A (en) | Pattern detection method, device, equipment and system | |
| CN103208008A (en) | Fast adaptation method for traffic video monitoring target detection based on machine vision | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN105321350A (en) | Method and device for detection of fake plate vehicles | |
| CN109446364A (en) | Capture search method, image processing method, device, equipment and storage medium | |
| CN105308618A (en) | Face recognition with parallel detection and tracking, and/or grouped feature motion shift tracking | |
| CN111291641A (en) | Image recognition method and device, computer readable medium and system | |
| CN106331848B (en) | The recognition methods of panoramic video and equipment play video method and equipment | |
| CN104915944A (en) | Method and device for determining black margin position information of video | |
| CN103577797B (en) | Image recognition system and image recognition method thereof | |
| CN103688139A (en) | Method and device for detecting the gait of a pedestrian for a portable terminal | |
| CN111340837A (en) | Image processing method, device, equipment and storage medium | |
| CN111539390A (en) | Small target image identification method, equipment and system based on Yolov3 | |
| CN106599889A (en) | Method and apparatus for recognizing characters | |
| CN103235951A (en) | Preliminary positioning method for matrix type two-dimensional bar code |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20161222 Address after: China Taiwan Hsinchu Science Park Hsinchu City Road No. 12 5 floor Patentee after: Glomerocryst semiconductor limited company Address before: China Taiwan Hsinchu Science Park Hsinchu City Road No. 12 Patentee before: Huajing Science & Technology Co., Ltd. |
|
| TR01 | Transfer of patent right |