CN109800748A - A kind of reading method and device of view-based access control model identification - Google Patents
A kind of reading method and device of view-based access control model identification Download PDFInfo
- Publication number
- CN109800748A CN109800748A CN201910023276.4A CN201910023276A CN109800748A CN 109800748 A CN109800748 A CN 109800748A CN 201910023276 A CN201910023276 A CN 201910023276A CN 109800748 A CN109800748 A CN 109800748A
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic point
- matching
- book contents
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000005435 mesosphere Substances 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses the reading methods and device of a kind of identification of view-based access control model.Wherein, the described method includes: obtaining the image of book contents, and then the image of the book contents according to the acquisition, match the image mesosphere characteristic point, and then image mesosphere characteristic point obtained according to the matching, gather the characteristic point that the matching obtains, store the characteristic point that the matching of the set obtains, and then carrying out image recognition matching to the characteristic point of the storage includes aligning, Geometry rectification, coordinate rearranges, identification matches book contents, and then the book contents matched according to the identification, the voice for playing the book contents that the corresponding identification matches includes transferring coordinate from coordinate file library to compare, point reads judgement and broadcasting multimedia file etc..By the above-mentioned means, can be realized automatic identification book contents and play the voice content of books, so that the time cost that books are read is effectively reduced.
Description
Technical field
The present invention relates to reading methods and device that books reading technique field more particularly to a kind of view-based access control model identify.
Background technique
Existing books read scheme, generally refer to read or recognize reading, but are meeting the word in unacquainted book contents
When body, the pronunciation for being consulted the unacquainted font by means of the access such as dictionary tool is generally required, causes books to be read in this way
Time cost it is higher.
But at least there are the following problems in the prior art for inventor's discovery:
Existing books read scheme, generally refer to read or recognize reading, cannot achieve automatic identification book contents and play book
The voice content of nationality, the time cost for causing books to be read are higher.
Summary of the invention
In view of this, it is an object of the invention to propose the reading method and device of a kind of view-based access control model identification, Neng Goushi
Existing automatic identification book contents and the voice content for playing books, so that the time cost that books are read is effectively reduced.
According to an aspect of the present invention, a kind of reading method of view-based access control model identification is provided, comprising:
Obtain the image of book contents；
According to the image of the book contents of the acquisition, described image mesosphere characteristic point is matched；
According to the described image mesosphere characteristic point for matching and obtaining, gather the characteristic point for matching and obtaining, storage
The characteristic point that the matching of the set obtains；
Image recognition matching is carried out to the characteristic point of the storage to rearrange including aligning, Geometry rectification, coordinate
Deng, identification match book contents；
According to the book contents for identifying and matching, the corresponding voice packet for identifying the book contents matched is played
It includes and transfers coordinate compares, point reads judgement and plays multimedia file etc. from coordinate file library.
Wherein, the image of the book contents according to the acquisition, to the figure of the image of the book contents of the acquisition
As characteristic point is detected, detection obtains image characteristic point descriptor, according to the image characteristic point descriptor for detecting and obtaining,
Match described image mesosphere characteristic point, comprising:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, in the books of the acquisition
The image characteristic point of the image of appearance is detected, and detection obtains image characteristic point descriptor, according to the image for detecting and obtaining
Feature point description symbol, matches described image mesosphere characteristic point.
Wherein, described according to the described image mesosphere characteristic point for matching and obtaining, gather the spy for matching and obtaining
Point is levied, the characteristic point that the matching of the set obtains is stored, comprising:
According to the described image mesosphere characteristic point for matching and obtaining, gathers the characteristic point for matching and obtaining, use
The data structure mode for dividing k dimension data space, stores the characteristic point that the matching of the set obtains.
Wherein, it includes aligning, Geometry rectification, coordinate that the characteristic point to the storage, which carries out image recognition matching,
It rearranges, identification matches book contents, comprising:
Using K- nearest neighbor algorithm mode, to the characteristic point of the storage carry out image recognition matching include aligning, it is several
What correction, coordinate rearrange, and identification matches book contents.
Wherein, described according to the book contents for identifying and matching, it plays in the books that the corresponding identification matches
The voice of appearance includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library, comprising:
It is matched according to the book contents for identifying and matching using random sampling unification algorism mode for the identification
Book contents out configure voice, and play the voice of the book contents of the configuration, play what the corresponding identification matched
The voice of book contents includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
According to another aspect of the present invention, a kind of reading device of view-based access control model identification is provided, comprising:
Obtain module, matching module, memory module, identification module and playing module；
The acquisition module, for obtaining the image of book contents；
The matching module matches described image mesosphere feature for the image according to the book contents of the acquisition
Point；
The memory module gathers the matching for matching obtained described image mesosphere characteristic point according to described
Obtained characteristic point stores the characteristic point that the matching of the set obtains；
The identification module includes aligning, geometry for carrying out image recognition matching to the characteristic point of the storage
Correction, coordinate rearrange, and identification matches book contents；
The playing module plays the corresponding identification and matches for identifying the book contents matched according to described
Book contents voice include transferred from coordinate file library coordinate compare, point read judgement and play multimedia file
Deng.
Wherein, the matching module, is specifically used for:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, in the books of the acquisition
The image characteristic point of the image of appearance is detected, and detection obtains image characteristic point descriptor, according to the image for detecting and obtaining
Feature point description symbol, matches described image mesosphere characteristic point.
Wherein, the memory module, is specifically used for:
According to the described image mesosphere characteristic point for matching and obtaining, gathers the characteristic point for matching and obtaining, use
The data structure mode for dividing k dimension data space, stores the characteristic point that the matching of the set obtains.
Wherein, the identification module, is specifically used for:
Using K- nearest neighbor algorithm mode, to the characteristic point of the storage carry out image recognition matching include aligning, it is several
What correction, coordinate rearrange, and identification matches book contents.
Wherein, the playing module, is specifically used for:
It is matched according to the book contents for identifying and matching using random sampling unification algorism mode for the identification
Book contents out configure voice, and play the voice of the book contents of the configuration, play what the corresponding identification matched
The voice of book contents includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
It can be found that above scheme, the image of available book contents, and then the figure of the book contents according to the acquisition
Picture matches the image mesosphere characteristic point, and then the image mesosphere characteristic point obtained according to the matching, gathers the matching
The characteristic point arrived stores the characteristic point that the matching of the set obtains, and then carries out image recognition to the characteristic point of the storage
With rearranging including aligning, Geometry rectification, coordinate, identification matches book contents, and then is matched according to the identification
Book contents out, the voice for playing the book contents that the corresponding identification matches include transferred from coordinate file library coordinate into
Row comparison puts and reads judgement and play multimedia file etc., in the voice that can be realized automatic identification book contents and broadcasting books
Hold, so that the time cost that books are read is effectively reduced.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of one embodiment of reading method the present invention is based on visual identity；
Fig. 2 is the structural schematic diagram of one embodiment of reading device the present invention is based on visual identity；
Fig. 3 is that the present invention is based on the structural schematic diagrams of another embodiment of the reading device of visual identity.
Specific embodiment
With reference to the accompanying drawings and examples, the present invention is described in further detail.It is emphasized that following implement
Example is merely to illustrate the present invention, but is not defined to the scope of the present invention.Likewise, following embodiment is only portion of the invention
Point embodiment and not all embodiments, institute obtained by those of ordinary skill in the art without making creative efforts
There are other embodiments, shall fall within the protection scope of the present invention.
The present invention provides a kind of reading method of view-based access control model identification, can be realized automatic identification book contents and plays book
The voice content of nationality, so that the time cost that books are read is effectively reduced.
Referring to Figure 1, Fig. 1 is the flow diagram of one embodiment of reading method the present invention is based on visual identity.It needs to infuse
Meaning, if having substantially the same as a result, method of the invention is not limited with process sequence shown in FIG. 1.Such as Fig. 1 institute
Show, this method comprises the following steps:
S101: the image of book contents is obtained.
S102: according to the image of the book contents of the acquisition, the image mesosphere characteristic point is matched.
Wherein, the image of the book contents according to the acquisition, matches the image mesosphere characteristic point, may include:
According to the image of the book contents of the acquisition, the image characteristic point of the image of the book contents of the acquisition is examined
It surveys, detection obtains image characteristic point descriptor, and the image characteristic point descriptor obtained according to the detection matches the image mesosphere
Characteristic point.
Wherein, the image of the book contents according to the acquisition, to the characteristics of image of the image of the book contents of the acquisition
Point is detected, and detection obtains image characteristic point descriptor, and the image characteristic point descriptor obtained according to the detection matches the figure
As mesosphere characteristic point, may include:
According to the image of the book contents of the acquisition, using SURF (Speed Up Robust Features, invariant feature
Accelerating algorithm) algorithm, detects the image characteristic point of the image of the book contents of the acquisition, detection obtains image characteristic point
Descriptor, the image characteristic point descriptor obtained according to the detection match the image mesosphere characteristic point.
S103: the image mesosphere characteristic point obtained according to the matching gathers the characteristic point that the matching obtains, and storage should
The characteristic point that the matching of set obtains.
Wherein, the image mesosphere characteristic point obtained according to the matching, gathers the characteristic point that the matching obtains, storage
The characteristic point that the matching of the set obtains may include:
The image mesosphere characteristic point obtained according to the matching, gathers the characteristic point that the matching obtains, using KD-TREE
(K-Dimensional TREEE divides the data structure in k dimension data space) mode, stores what the matching of the set obtained
Characteristic point.
S104: image recognition matching is carried out to the characteristic point of the storage and is arranged again including aligning, Geometry rectification, coordinate
Column etc., identification match book contents.
Wherein, the characteristic point to the storage carry out image recognition matching include aligning, Geometry rectification, coordinate again
Arrangement etc., identification match book contents, may include:
Using KNN (K-NearestNeighbor, K- nearest neighbor algorithm) algorithmic approach, figure is carried out to the characteristic point of the storage
It is rearranged as identification is matched including aligning, Geometry rectification, coordinate, identification matches book contents.
S105: the book contents matched according to the identification play the voice for the book contents that the corresponding identification matches
It is compared including transferring coordinate from coordinate file library, point is read to judge and play multimedia file etc..
Wherein, the book contents matched according to the identification play the language for the book contents that the corresponding identification matches
Sound includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library, may include:
According to the book contents that the identification matches, using RANSAC (Random Sample Consensus, random pumping
Sample unification algorism) algorithmic approach, voice is configured for the book contents that the identification matches, and play the book contents of the configuration
Voice, the voice for playing the book contents that the corresponding identification matches include transferred from coordinate file library coordinate compare,
Point reads judgement and broadcasting multimedia file etc..
In the present embodiment, original image data can be optimized, matching image mesosphere characteristic point can use mini system reality
Existing light-weighted image recognition can optimize using logic, accelerate recognition speed and accuracy.
In the present embodiment, the result output that by the optimization to image, can accelerate algorithm, mitigates CPU (Central
Processing Unit, central processing unit) operation time, quick image recognition skill can be realized in the small resource decorum
Art realizes the identification of book contents and plays the voice content of books, reduces costs, the application in teaching.
It can be found that in the present embodiment, the image of available book contents, and then according to the book contents of the acquisition
Image, match the image mesosphere characteristic point, and then the image mesosphere characteristic point obtained according to the matching, gather this
With obtained characteristic point, the characteristic point that the matching of the set obtains is stored, and then image knowledge is carried out to the characteristic point of the storage
It Pi Pei not be rearranged including aligning, Geometry rectification, coordinate, identification matches book contents, and then according to the identification
The book contents matched, the voice for playing the book contents that the corresponding identification matches includes that seat is transferred from coordinate file library
Mark compares, point reads judgement and plays multimedia file etc., can be realized automatic identification book contents and plays the language of books
Sound content, so that the time cost that books are read is effectively reduced.
The present invention also provides a kind of reading devices of view-based access control model identification, can be realized automatic identification book contents and broadcasting
The voice content of books, so that the time cost that books are read is effectively reduced.
Fig. 2 is referred to, Fig. 2 is the structural schematic diagram of one embodiment of reading device the present invention is based on visual identity.This reality
It applies in example, the reading device 20 of view-based access control model identification includes obtaining module 21, matching module 22, memory module 23, identification mould
Block 24 and playing module 25.
The acquisition module 21, for obtaining the image of book contents.
The matching module 22 matches the image mesosphere characteristic point for the image according to the book contents of the acquisition.
The memory module 23, the image mesosphere characteristic point for being obtained according to the matching, gathers what the matching obtained
Characteristic point stores the characteristic point that the matching of the set obtains.
The identification module 24 is rectified for carrying out image recognition matching to the characteristic point of the storage including aligning, geometry
Just, coordinate rearranges, and identification matches book contents.
The playing module 25, the book contents for being matched according to the identification play the book that the corresponding identification matches
The voice of nationality content includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
Optionally, the matching module 22, can be specifically used for:
According to the image of the book contents of the acquisition, the image characteristic point of the image of the book contents of the acquisition is examined
It surveys, detection obtains image characteristic point descriptor, and the image characteristic point descriptor obtained according to the detection matches the image mesosphere
Characteristic point.
Optionally, the matching module 22, can be specifically used for:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, to the book contents of the acquisition
The image characteristic point of image is detected, and detection obtains image characteristic point descriptor, the image characteristic point obtained according to the detection
Descriptor matches the image mesosphere characteristic point.
Optionally, the memory module 23, can be specifically used for:
The image mesosphere characteristic point obtained according to the matching, gathers the characteristic point that the matching obtains, using segmentation k dimension
The data structure mode of data space stores the characteristic point that the matching of the set obtains.
Optionally, the identification module 24, can be specifically used for:
Using K- nearest neighbor algorithm mode, carrying out image recognition matching to the characteristic point of the storage includes aligning, geometry
Correction, coordinate rearrange, and identification matches book contents.
Optionally, the playing module 25, can be specifically used for:
It is matched according to the book contents that the identification matches using random sampling unification algorism mode for the identification
Book contents configure voice, and play the voice of the book contents of the configuration, play the book contents that the corresponding identification matches
Voice include transferring that coordinate compares, point reads judgement from coordinate file library and playing multimedia file etc..
It is right in above method embodiment that each unit module of the reading device 20 of view-based access control model identification can execute respectively
Step is answered, therefore each unit module is not repeated herein, the explanation of the above corresponding step is referred to.
Fig. 3 is referred to, Fig. 3 is that the present invention is based on the structural schematic diagrams of another embodiment of the reading device of visual identity.It should
Each unit module of the reading device of view-based access control model identification can execute respectively corresponds to step in above method embodiment.It is related
Content refers to the detailed description in the above method, no longer superfluous herein to chat.
In the present embodiment, the reading device of view-based access control model identification includes: processor 31, deposits with what the processor 31 coupled
Reservoir 32, identifier 33, player 34.
The processor 31, for obtaining the image of book contents, and the image of the book contents according to the acquisition, matching should
Image mesosphere characteristic point.
The memory 32, the instruction executed for storage program area, the processor 31 store the spy that the matching obtains
Sign point etc..
The identifier 33, for the characteristic point of the storage carry out image recognition matching include aligning, Geometry rectification,
Coordinate rearranges, and identification matches book contents.
The player 34, the book contents for being matched according to the identification play the books that the corresponding identification matches
The voice of content includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
Optionally, the processor 31, can be specifically used for:
According to the image of the book contents of the acquisition, the image characteristic point of the image of the book contents of the acquisition is examined
It surveys, detection obtains image characteristic point descriptor, and the image characteristic point descriptor obtained according to the detection matches the image mesosphere
Characteristic point.
Optionally, the processor 31, can be specifically used for:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, to the book contents of the acquisition
The image characteristic point of image is detected, and detection obtains image characteristic point descriptor, the image characteristic point obtained according to the detection
Descriptor matches the image mesosphere characteristic point.
Optionally, the memory 32, can be specifically used for:
The image mesosphere characteristic point obtained according to the matching, gathers the characteristic point that the matching obtains, using segmentation k dimension
The data structure mode of data space stores the characteristic point that the matching of the set obtains.
Optionally, the identifier 33, can be specifically used for:
Using K- nearest neighbor algorithm mode, carrying out image recognition matching to the characteristic point of the storage includes aligning, geometry
Correction, coordinate rearrange, and identification matches book contents.
Optionally, the player 34, can be specifically used for:
It is matched according to the book contents that the identification matches using random sampling unification algorism mode for the identification
Book contents configure voice, and play the voice of the book contents of the configuration, play the book contents that the corresponding identification matches
Voice include transferring that coordinate compares, point reads judgement from coordinate file library and playing multimedia file etc..
It can be found that above scheme, the image of available book contents, and then the figure of the book contents according to the acquisition
Picture matches the image mesosphere characteristic point, and then the image mesosphere characteristic point obtained according to the matching, gathers the matching
The characteristic point arrived stores the characteristic point that the matching of the set obtains, and then carries out image recognition to the characteristic point of the storage
With rearranging including aligning, Geometry rectification, coordinate, identification matches book contents, and then is matched according to the identification
Book contents out, the voice for playing the book contents that the corresponding identification matches include transferred from coordinate file library coordinate into
Row comparison puts and reads judgement and play multimedia file etc., in the voice that can be realized automatic identification book contents and broadcasting books
Hold, so that the time cost that books are read is effectively reduced.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can
To realize by another way.For example, device embodiments described above are only schematical, for example, module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, institute
Display or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit
Indirect coupling or communication connection can be electrical property, mechanical or other forms.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of present embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) or processor (processor) execute each implementation of the present invention
The all or part of the steps of methods.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, RandomAccess Memory), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely section Examples of the invention, are not intended to limit protection scope of the present invention, all utilizations
Equivalent device made by description of the invention and accompanying drawing content or equivalent process transformation are applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of reading method of view-based access control model identification characterized by comprising
Obtain the image of book contents；
According to the image of the book contents of the acquisition, described image mesosphere characteristic point is matched；
Obtained described image mesosphere characteristic point is matched according to described, gathers the characteristic point for matching and obtaining, described in storage
The characteristic point that the matching of set obtains；
Image recognition matching is carried out to the characteristic point of the storage to rearrange including aligning, Geometry rectification, coordinate, is known
Book contents are not matched；
Identify the book contents that match according to described, play the corresponding voice for identifying the book contents matched include from
Coordinate compares, point reads judgement and plays multimedia file etc. is transferred in coordinate file library.
2. the reading method of view-based access control model identification as described in claim 1, which is characterized in that the book according to the acquisition
The image of nationality content detects the image characteristic point of the image of the book contents of the acquisition, and detection obtains characteristics of image
Point descriptor matches described image mesosphere characteristic point according to the image characteristic point descriptor for detecting and obtaining, comprising:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, to the book contents of the acquisition
The image characteristic point of image is detected, and detection obtains image characteristic point descriptor, according to the characteristics of image for detecting and obtaining
Point descriptor, matches described image mesosphere characteristic point.
3. the reading method of view-based access control model identification as claimed in claim 1 or 2, which is characterized in that described according to the matching
Obtained described image mesosphere characteristic point gathers the characteristic point for matching and obtaining, stores the described of the set and match
The characteristic point arrived, comprising:
According to the described image mesosphere characteristic point for matching and obtaining, gather the characteristic point for matching and obtaining, using segmentation k
The data structure mode in dimension data space stores the characteristic point that the matching of the set obtains.
4. the reading method of view-based access control model identification as claimed in claim 3, which is characterized in that the feature to the storage
Point carries out image recognition matching and rearranges including aligning, Geometry rectification, coordinate, and identification matches book contents, wraps
It includes:
Using K- nearest neighbor algorithm mode, image recognition matching is carried out to the characteristic point of the storage and is rectified including aligning, geometry
Just, coordinate rearranges, and identification matches book contents.
5. the reading method of view-based access control model identification as claimed in claim 4, which is characterized in that described to be matched according to the identification
Book contents out, playing the corresponding voice for identifying the book contents matched includes transferring coordinate from coordinate file library
It compares, point is read to judge and play multimedia file etc., comprising:
According to the book contents for identifying and matching, using random sampling unification algorism mode, the identification is matched
Book contents configure voice, and play the voice of the book contents of the configuration, play the books that the corresponding identification matches
The voice of content includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
6. a kind of reading device of view-based access control model identification characterized by comprising
Obtain module, matching module, memory module, identification module and playing module；
The acquisition module, for obtaining the image of book contents；
The matching module matches described image mesosphere characteristic point for the image according to the book contents of the acquisition；
The memory module is gathered the matching and is obtained for matching obtained described image mesosphere characteristic point according to described
Characteristic point, store the characteristic point that the matching of the set obtains；
The identification module, for the characteristic point of the storage carry out image recognition matching include aligning, Geometry rectification,
Coordinate rearranges, and identification matches book contents；
The playing module plays the book that the corresponding identification matches for identifying the book contents matched according to described
The voice of nationality content includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
7. the reading device of view-based access control model identification as claimed in claim 6, which is characterized in that the matching module, it is specific to use
In:
According to the image of the book contents of the acquisition, using invariant feature accelerating algorithm, to the book contents of the acquisition
The image characteristic point of image is detected, and detection obtains image characteristic point descriptor, according to the characteristics of image for detecting and obtaining
Point descriptor, matches described image mesosphere characteristic point.
8. the reading device of view-based access control model identification as claimed in claims 6 or 7, which is characterized in that the memory module, specifically
For:
According to the described image mesosphere characteristic point for matching and obtaining, gather the characteristic point for matching and obtaining, using segmentation k
The data structure mode in dimension data space stores the characteristic point that the matching of the set obtains.
9. the reading device of view-based access control model identification as claimed in claim 8, which is characterized in that the identification module, it is specific to use
In:
Using K- nearest neighbor algorithm mode, image recognition matching is carried out to the characteristic point of the storage and is rectified including aligning, geometry
Just, coordinate rearranges, and identification matches book contents.
10. the reading device of view-based access control model identification as claimed in claim 9, which is characterized in that the playing module, it is specific to use
In: according to the book contents for identifying and matching, using random sampling unification algorism mode, the book matched is identified to be described
Nationality content configures voice, and plays the voice of the book contents of the configuration, plays in the books that the corresponding identification matches
The voice of appearance includes that coordinate compares, point reads judgement and plays multimedia file etc. is transferred from coordinate file library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910023276.4A CN109800748A (en) | 2019-01-10 | 2019-01-10 | A kind of reading method and device of view-based access control model identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910023276.4A CN109800748A (en) | 2019-01-10 | 2019-01-10 | A kind of reading method and device of view-based access control model identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109800748A true CN109800748A (en) | 2019-05-24 |
Family
ID=66557024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910023276.4A Pending CN109800748A (en) | 2019-01-10 | 2019-01-10 | A kind of reading method and device of view-based access control model identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800748A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761892A (en) * | 2014-01-20 | 2014-04-30 | 广东小天才科技有限公司 | Method and device for voice-playing of printing book contents |
| CN104281847A (en) * | 2013-07-12 | 2015-01-14 | 步步高教育电子有限公司 | Point reading method, device and equipment |
| US20150138385A1 (en) * | 2013-11-18 | 2015-05-21 | Heekwan Kim | Digital annotation-based visual recognition book pronunciation system and related method of operation |
| CN106023692A (en) * | 2016-05-13 | 2016-10-12 | 广东博士早教科技有限公司 | AR interest learning system and method based on entertainment interaction |
| CN108845786A (en) * | 2018-05-31 | 2018-11-20 | 北京智能管家科技有限公司 | Intelligent reading partner method, apparatus, equipment and storage medium |
-
2019
- 2019-01-10 CN CN201910023276.4A patent/CN109800748A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281847A (en) * | 2013-07-12 | 2015-01-14 | 步步高教育电子有限公司 | Point reading method, device and equipment |
| US20150138385A1 (en) * | 2013-11-18 | 2015-05-21 | Heekwan Kim | Digital annotation-based visual recognition book pronunciation system and related method of operation |
| CN103761892A (en) * | 2014-01-20 | 2014-04-30 | 广东小天才科技有限公司 | Method and device for voice-playing of printing book contents |
| CN106023692A (en) * | 2016-05-13 | 2016-10-12 | 广东博士早教科技有限公司 | AR interest learning system and method based on entertainment interaction |
| CN108845786A (en) * | 2018-05-31 | 2018-11-20 | 北京智能管家科技有限公司 | Intelligent reading partner method, apparatus, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 胡卓玮: "洪涝灾害应急响应决策支持业务系统关键技术与应用实例", 北京：中国环境科学出版社, pages: 177 - 180 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108171257B (en) | Fine granularity image recognition model training and recognition methods, device and storage medium | |
| US8644551B2 (en) | Systems and methods for tracking natural planar shapes for augmented reality applications | |
| CN106228188A (en) | Clustering method, device and electronic equipment | |
| US20100138634A1 (en) | Devices, systems, and methods to synchronize parallel processing of a single data stream | |
| CN109583389A (en) | Draw this recognition methods and device | |
| CN111241248A (en) | Synonymy question generation model training method and system and synonymy question generation method | |
| CN111243604B (en) | Training method for speaker recognition neural network model supporting multiple awakening words, speaker recognition method and system | |
| CN114022748B (en) | Target identification method, device, equipment and storage medium | |
| CN112569591B (en) | Data processing method, device and equipment and readable storage medium | |
| CN110659631A (en) | License plate recognition method and terminal equipment | |
| CN109800748A (en) | A kind of reading method and device of view-based access control model identification | |
| CN111680514B (en) | Information processing and model training method, device, equipment and storage medium | |
| CN116844006A (en) | Target identification method and device, electronic equipment and readable storage medium | |
| CN110489740A (en) | Semantic analytic method and Related product | |
| CN107220317B (en) | Matching degree evaluation method, device, equipment and storage medium based on artificial intelligence | |
| CN115222047A (en) | Model training method, device, equipment and storage medium | |
| CN109886089A (en) | Palm grain identification method, device and computer equipment | |
| CN113361511A (en) | Method, device and equipment for establishing correction model and computer readable storage medium | |
| CN111291539B (en) | File editing control method, device, computer device and storage medium | |
| CN114443889A (en) | Audio acquisition method and device, electronic equipment and storage medium | |
| CN113553884A (en) | Gesture recognition method, terminal device and computer-readable storage medium | |
| CN109829097A (en) | A kind of method and device of data processing | |
| US11841792B1 (en) | Instructions with multiple memory access modes | |
| CN117851835B (en) | Deep learning internet of things recognition system and method | |
| CN116600176B (en) | Stroke order audio/video generation method and device, computer equipment 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 |