CN109101885A - A kind of work of fine arts screening display systems and method - Google Patents
A kind of work of fine arts screening display systems and method Download PDFInfo
- Publication number
- CN109101885A CN109101885A CN201810752941.9A CN201810752941A CN109101885A CN 109101885 A CN109101885 A CN 109101885A CN 201810752941 A CN201810752941 A CN 201810752941A CN 109101885 A CN109101885 A CN 109101885A
- Authority
- CN
- China
- Prior art keywords
- work
- fine arts
- image
- screening
- 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.)
- Pending
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention belongs to display technique fields, a kind of work of fine arts screening display systems and method are disclosed, display systems include: image capture module, image setup module, central processing module, optical sieving module, image adding module, image-erasing module, identification module, display module.The present invention is by identifying that module effectively overcomes the limitation that traditional painting and calligraphy identify, greatly improve the accuracy of painting and calligraphy pieces identification, and reduce the workload manually marked during conventional identification, determination rates are also increased exponentially, technical support can also be provided for digital library, the digital painting and calligraphy pieces web browsing of digital museum and retrieval simultaneously, be with a wide range of applications;It meanwhile can be to remind the work of fine arts filtered out according to corresponding viewing, and the interpretation data that may make the type of screening to watch work of fine arts simultaneously is more convenient according to the interpretation data received by the type that display module screens.
Description
Technical field
The invention belongs to display technique field more particularly to a kind of work of fine arts screening display systems and methods.
Background technique
Currently, the prior art commonly used in the trade is such that
Work of fine arts refers to the independent artistic work that can only watch for people, such as oil painting, traditional Chinese Painting, etching, water
Colour painting, pen-and-ink drawing etc..Practical artistic work refers to and combines the content of work of fine arts with the object having use value, object
Body has both ornamental value and practical value by means of the artistic grade of work of fine arts, such as ceramic art etc..However, the fine arts
Works, traditional manual recognition methods are using magnifying glass or high-power microscope, and manually experience identifies the true of painting and calligraphy pieces
Puppet, this method depend critically upon artificial experience for a long time, and determination rates are very low;Work of fine arts quantity is more in exhibition simultaneously,
Type is different, and the browsing mode of the type (exhibition viewer) of screening is substantially all to use and browses or overflow without mesh one by one
Ground browsing, and for the type of certain screenings, purpose is primarily to browsing particular work with participating in exhibition, i.e.,
Oneself interested works, and will be unable to provide more easily service for the type of such screening, when wasting the type of screening
Between.
In conclusion problem of the existing technology is:
Work of fine arts, traditional manual recognition methods are using magnifying glass or high-power microscope, and manually experience identifies
The true and false of painting and calligraphy pieces, this method depend critically upon artificial experience for a long time, and determination rates are very low;The fine arts in exhibition simultaneously
Works quantity is more, and type is different, and the browsing mode of the type (exhibition viewer) of screening is substantially all clear using carrying out one by one
It lookes at or aimlessly browses, and for the type of certain screenings, purpose is primarily to browsing with participating in exhibition
Particular work, i.e. oneself interested works, and will be unable to provide more easily service for the type of such screening, waste
The type of time of screening.
In the prior art, inputting the type of screening, to filter out corresponding work of fine arts image effect poor, obtains the figure of classification
Image sharpness is poor.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of works of fine arts to screen display systems.
The invention is realized in this way a kind of work of fine arts screens methods of exhibiting, the work of fine arts screens methods of exhibiting
Include:
Acquire work of fine arts original image;
Sorting parameter is arranged to the work of fine arts figure of acquisition;
Corresponding work of fine arts image is filtered out by the type of input screening;Each work of fine arts image acquires respectively
The class state information for the type screened initializes relevant parameter, the type n measurement of the screening in n-th of smallcell
Downlink classification power gain of the work of fine arts image n to oneselfAnd work of fine arts image n is fed back to, and wherein n=1,2 ...,
N, N are the number of fine arts work images in network, and k=1,2 ..., K, K is the number of orthogonal categories in network, then, each
Work of fine arts image initializes required parameter respectively;Each work of fine arts image repeats to update certainly according to the disturbed condition of surrounding
Oneself the number of iterations counter and policy counter, work of fine arts image update changing for oneself according to the disturbed condition of surrounding
Generation counter and policy counter;Respective the number of iterations counter t is set to t+ respectively by all work of fine arts images
1;N-th work of fine arts image n is according to oneself state α after the t-1 times iterationn(t-1) and selected classification collection
Close sn(t-1), it calculates and selects category set f at this timen∈SnProbability Qn(fn): if αn(t-1)=0,It is no
Then, if αn(t-1)=1,Wherein, n=1,2 ..., N, | Sn| indicate set SnIn
The number of element, ε is one and is greater than 0 constant less than 1, and ω is the constant for being greater than N;N-th of work of fine arts image n root
According to probability distribution Qn, update selected classification sn(t), data, n=1,2 ..., N and in classification are sent;According to selected
Category set sn(t), the type n of n-th of screening measures received interferenceAnd will be conveyed to work of fine arts image n,
Wherein l ∈ sn(t), work of fine arts image n calculates the capacity of present smallcellWherein B0For the bandwidth of each classification,For the fine arts
Transmission power of the work images n on classification l,Indicate power gain of the work of fine arts image n on classification l, N0For noise
Power spectral density;N-th of work of fine arts image n updates oneself state α at this timen(t), n=1,2 ..., N;Work as update times
Predetermined threshold value, the category set that each work of fine arts image selection finally uses are reached, each work of fine arts image judgement changes
Whether generation counter meets t≤T, i.e. the number of iterations is less than threshold T;N-th of work of fine arts image n according to oneself
Policy counter Cn, select the category set finally usedN=1,2 ..., N;Its
Middle sn_ ind is set snIn set SnIn number, Cn(1,sn_ ind) indicate policy counter CnIn the 1st row sn_ ind column
The value of element;
Add the work of fine arts original image of information;
Delete the work of fine arts image of undercarriage
By establish database, the image data of acquisition painting and calligraphy pieces to be identified, illumination consistency processing, extract angle point,
Characteristic matching operation, abnormal point identification, identify the true and false of work of fine arts;
Push a works by the type terminals of screening of from the server to exhibition and screen interface, the type of screening according to
The hobby of oneself filters out the characteristic style of works that need to be browsed and/or author at works screening interface and uploads, according to screening
The hobby of type shows corresponding work of fine arts.
Further, the method for the parameter is initialized are as follows:
The first step, n-th of work of fine arts image n is to available category set SnIt is numbered, and randomly chooses one group of class
Other sn(0)∈SnIt is transmitted, n=0,1 ..., N;
WhereinK is the number of orthogonal categories in network, | sn| it is vector snIn
The number of element, KnFor classification needed for n-th of work of fine arts image, sn(0) it changes for n-th of work of fine arts image at the 0th time
For when used category set, N is the number of fine arts work images in isomery cellular network;
Second step, n-th of work of fine arts image n is by oneself state αn(0) it is set to 0, while resetting the number of iterations counter
T and policy counter
Wherein, αn(0) state of the work of fine arts image n in the 0th iteration is indicated, | Sn| indicate set SnMiddle element
Number,Indicate an a line | Sn| the full null vector of column.
Further, the state α of n-th of work of fine arts image update oneself at this timen(t), n=1,2 ..., N specific method
Are as follows:
(1) state α of the observation after the t-1 times iterationn(t-1), if αn(t-1) it is 1, executes step 2, otherwise hold
Row step 3;
(2) judge category set sn(t-1) it is equal to sn(t) with capacity Rn(t-1) it is equal to Rn(t) whether set up simultaneously, such as
Fruit is set up, by αn(t) it is set as 1;Otherwise step 3 is executed;
(3) with probabilityBy αn(t) it is set as 1;With probability 1- ρ by αn(t) it is set as 0,
Wherein, parameter ε and second step) in definition it is identical, β is the constant for belonging to real number set,For a constant, parameter B0,And N0Definition with
It is identical in 4th step;
(4) n-th of work of fine arts image n are according to the category set s of selectionn(t) and update state αn(t), it updates
Policy counter Cn, n=1,2 ..., N:
If αn(t) it is equal to 1, Cn(1,sn(t) _ ind)=Cn(1,sn(t) _ ind)+1, wherein sn(t) _ ind indicates classification
Collect sn(t) in set SnIn number
Further, identification method includes:
A, database is established: using high-precision digital scanner or high-definition digital camera that genuine piece painting and calligraphy pieces are digital
Change, forms the local high definition picture or photo of whole picture or photo and Chosen Point, establish the number of 3,000,000 pixels or more
Painting and calligraphy pieces database backup includes the spy on standard reference image corresponding to every genuine piece painting and calligraphy pieces in database
Levy point set;
B, the image data of painting and calligraphy pieces to be identified is acquired: by painting and calligraphy pieces to be identified with number same in a step
Change mode forms picture or photo, and is input to identification systems;
C, illumination consistency is handled: the local picture or photo of painting and calligraphy pieces to be identified are carried out at illumination consistency
Reason, so that local picture or photo illumination of the illumination of painting and calligraphy pieces picture or photo with painting and calligraphy pieces to be identified in database
Unanimously;
D, angle point is extracted: the Local map using the Robust Algorithm of Image Corner Extraction based on image border to painting and calligraphy pieces to be identified
Piece or photo extract angle point, and on the basis of the angle point of extraction, construct corresponding spin matrix, match corresponding angle point, build
Found the feature point set on image subject to registration;
E, it characteristic matching operation: according to the feature point set on known database Plays reference picture, is incorporated in wait reflect
Fixed painting and calligraphy pieces obtain the feature point set on the image subject to registration obtained, establish the corresponding relationship between two point sets, benefit
Transformation model parameter is solved with corresponding relationship, and then realizes registration;
F, abnormal point is identified: the affine transformation matrix after the registration of acquisition being matched with the image in database, is counted
The difference between the feature and database Plays art work character pair at identified position is calculated, provides matching rate, and then obtain
Out for judging the qualification result of the painting and calligraphy pieces true and false.
Further, methods of exhibiting includes:
Firstly, pushing a works by the type terminals of screening of the server into exhibition screens interface, the type of screening
The characteristic style of works that need to be browsed and/or author are filtered out at works screening interface according to the hobby of oneself and are uploaded;
Secondly, the type terminals of the screening are by the content of the type upload of screening together with the type terminals of the screening
The wireless address Mac be sent to the server;
Then, the server obtains out the type screened according to the content of upload and filters out the characteristic style of works that need to be browsed
And/or author and work of fine arts corresponding to the characteristic style of works that need to be browsed and/or author is found out in built-in database, it orders
Entitled work of fine arts to be browsed,
Then, the wireless address Mac of the type terminals of the screening is sent to work of fine arts to be browsed by the server
On the wireless transceiver of binding, it is named as and presets the wireless address Mac;The type terminals sending of the screening carries wireless Mac
The wireless signal of address;
Finally, the wireless receiver receives the nothing for carrying the wireless address Mac that the type terminals of the screening issue
Line signal simultaneously judges whether the wireless address Mac is identical as the wireless address Mac is preset, if they are the same, then by the built-in correspondence fine arts
The interpretation data transmission of works gives the type terminals of the screening;Wherein, the wireless receiver only receives in a pre-determined distance
Wireless signal.
Another object of the present invention is to provide a kind of computer journeys for realizing the work of fine arts screening methods of exhibiting
Sequence.
Another object of the present invention is to provide at a kind of information data for realizing the work of fine arts screening methods of exhibiting
Manage terminal.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the work of fine arts and screens methods of exhibiting.
Another object of the present invention is to provide a kind of work of fine arts sieves for realizing the work of fine arts screening methods of exhibiting
Display systems are selected, the work of fine arts screening display systems include:
Image capture module is connect with central processing module, for acquiring work of fine arts original image by image pick-up device;
Image setup module, connect with central processing module, for sorting parameter to be arranged to the work of fine arts figure of acquisition;
Central processing module, with image capture module, image setup module, optical sieving module, image adding module,
Image-erasing module, identification module, display module connection, work normally for controlling modules;
Optical sieving module, connect with central processing module, for filtering out corresponding beauty by the type of input screening
Art work images;
Image adding module, connect with central processing module, for adding the work of fine arts original image of information;
Image-erasing module, connect with central processing module, for deleting the work of fine arts image of undercarriage;
It identifies module, connect with central processing module, identified for the true and false to work of fine arts;
Display module is connect with central processing module, and the hobby for the type according to screening shows that the corresponding fine arts are made
Product.
Another object of the present invention is to provide a kind of work of fine arts sieves for carrying the work of fine arts screening display systems
Select presentation device.
Advantages of the present invention and good effect are as follows:
The present invention is started with by identification module from feature stroke extractive technique, and the formalization performance side of pen and ink track is passed through
Contacting between formula, and the stroke feature and paper lines composition of analysis part, locks subtle specific to each painting and calligraphy pieces
Feature avoids the heavy dependence in conventional identification method to human eye power and experience.The present invention uses image procossing and computer
Vision technique extracts stroke feature and the intelligent of paper lines layout pattern feature, and establishes database, passes through template
Matching, the mode identification technology based on statistical analysis realize the quick identification to the painting and calligraphy pieces true and false.The present invention effectively overcomes
The limitation that traditional painting and calligraphy identify greatly improves the accuracy of painting and calligraphy pieces identification, and reduces conventional identification process
In the workload that manually marks, determination rates are also increased exponentially, while can also be rich for digital library, number
The digital painting and calligraphy pieces web browsing in object shop and retrieval provide technical support, are with a wide range of applications;Meanwhile passing through exhibition
Show the type of module screening when exhibition browses work of fine arts, nothing bound in the work of fine arts filtered out according to oneself hobby
Line transceiver can by the corresponding interpretation data transmission of work of fine arts on the type terminals of the screening of the type of the screening, in this way,
The type of screening can be to remind the work of fine arts filtered out according to corresponding viewing, and simultaneously may be used according to the interpretation data received
So that the interpretation data of the type viewing work of fine arts of screening is more convenient.
The present invention filters out corresponding work of fine arts image by the type of input screening;Each work of fine arts image difference
The class state information of screened type is acquired, relevant parameter, the type of the screening in n-th of smallcell are initialized
N measures work of fine arts image n to the downlink classification power gain of oneselfAnd work of fine arts image n is fed back to, wherein n=1,
2 ..., N, N are the number of fine arts work images in network, and k=1,2 ..., K, K is the number of orthogonal categories in network, then,
Each work of fine arts image initializes required parameter respectively;Each work of fine arts image repeats more according to the disturbed condition of surrounding
Newly the number of iterations counter and policy counter of oneself, work of fine arts image update oneself according to the disturbed condition of surrounding
The number of iterations counter and policy counter;All work of fine arts images respectively set respective the number of iterations counter t
For t+1;N-th of work of fine arts image n is according to oneself state α after the t-1 times iterationn(t-1) and selected class
Not set sn(t-1), it calculates and selects category set f at this timen∈SnProbability Qn(fn), corresponding work of fine arts figure can be filtered out
Picture, effect is good, and the image definition for obtaining classification is high.It improves compared with the prior art very much.
Detailed description of the invention
Fig. 1 is work of fine arts screening display systems structural block diagram provided in an embodiment of the present invention.
Fig. 2 is display module methods of exhibiting flow chart provided in an embodiment of the present invention.
In figure: 1, image capture module;2, image setup module;3, central processing module;4, optical sieving module;5,
Image adding module;6, image-erasing module;7, module is identified;8, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached
Detailed description are as follows for figure.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, work of fine arts provided by the invention screening display systems include: that image capture module 1, image are set
Set module 2, central processing module 3, optical sieving module 4, image adding module 5, image-erasing module 6, identification module 7, exhibition
Show module 8.
Image capture module 1 is connect with central processing module 3, for acquiring work of fine arts original image by image pick-up device;
Image setup module 2 is connect with central processing module 3, for the work of fine arts figure setting classification ginseng to acquisition
Number;
Central processing module 3 adds mould with image capture module 1, image setup module 2, optical sieving module 4, image
Block 5, image-erasing module 6, identification module 7, display module 8 connect, and work normally for controlling modules;
Optical sieving module 4 is connect with central processing module 3, for being filtered out accordingly by the type of input screening
Work of fine arts image;
Image adding module 5 is connect with central processing module 3, for adding the work of fine arts original image of information;
Image-erasing module 6 is connect with central processing module 3, for deleting the work of fine arts image of undercarriage;
It identifies module 7, connect with central processing module 3, identified for the true and false to work of fine arts;
Display module 8 is connect with central processing module 3, and the hobby for the type according to screening shows the corresponding fine arts
Works.
7 identification methods of identification module provided by the invention are as follows:
A, database is established: using high-precision digital scanner or high-definition digital camera that genuine piece painting and calligraphy pieces are digital
Change, forms the local high definition picture or photo of whole picture or photo and Chosen Point, establish the number of 3,000,000 pixels or more
Painting and calligraphy pieces database backup includes the spy on standard reference image corresponding to every genuine piece painting and calligraphy pieces in database
Levy point set;
B, the image data of painting and calligraphy pieces to be identified is acquired: by painting and calligraphy pieces to be identified with number same in a step
Change mode forms picture or photo, and is input to identification systems;
C, illumination consistency is handled: the local picture or photo of painting and calligraphy pieces to be identified are carried out at illumination consistency
Reason, so that local picture or photo illumination of the illumination of painting and calligraphy pieces picture or photo with painting and calligraphy pieces to be identified in database
Unanimously;
D, angle point is extracted: the Local map using the Robust Algorithm of Image Corner Extraction based on image border to painting and calligraphy pieces to be identified
Piece or photo extract angle point, and on the basis of the angle point of extraction, construct corresponding spin matrix, match corresponding angle point, build
Found the feature point set on image subject to registration;
E, it characteristic matching operation: according to the feature point set on known database Plays reference picture, is incorporated in wait reflect
Fixed painting and calligraphy pieces obtain the feature point set on the image subject to registration obtained, establish the corresponding relationship between two point sets, benefit
Transformation model parameter is solved with corresponding relationship, and then realizes registration;
F, abnormal point is identified: the affine transformation matrix after the registration of acquisition being matched with the image in database, is counted
The difference between the feature and database Plays art work character pair at identified position is calculated, provides matching rate, and then obtain
Out for judging the qualification result of the painting and calligraphy pieces true and false.
Such as Fig. 2,8 side of displaying of display module provided by the invention:
S101: a works are pushed by the type terminals of screening of the server into exhibition and screen interface, the type of screening
The characteristic style of works that need to be browsed and/or author are filtered out at works screening interface according to the hobby of oneself and are uploaded;
S102: type terminals of the content that the type terminals of the screening upload the type of screening together with the screening
The wireless address Mac be sent to the server;
S103: the server obtains out the type screened according to the content of upload and filters out the characteristic style of works that need to be browsed
And/or author and work of fine arts corresponding to the characteristic style of works that need to be browsed and/or author is found out in built-in database, it orders
Entitled work of fine arts to be browsed,
S104: the wireless address Mac of the type terminals of the screening is sent to work of fine arts to be browsed by the server
On the wireless transceiver of binding, it is named as and presets the wireless address Mac;The type terminals sending of the screening carries wireless Mac
The wireless signal of address;
S105: the wireless receiver receives the nothing for carrying the wireless address Mac that the type terminals of the screening issue
Line signal simultaneously judges whether the wireless address Mac is identical as the wireless address Mac is preset, if they are the same, then by the built-in correspondence fine arts
The interpretation data transmission of works gives the type terminals of the screening;Wherein, the wireless receiver only receives in a pre-determined distance
Wireless signal.
When the present invention is shown, work of fine arts original image is acquired by image capture module 1;By image setup module 2 to adopting
Sorting parameter is arranged in the work of fine arts figure of collection;Central processing module 3 dispatches image screening module 4 and passes through the type of input screening
Filter out corresponding work of fine arts image;Then, the work of fine arts original image of information is added by image adding module 5;Pass through figure
As removing module 6 deletes the work of fine arts image of undercarriage;By identifying that module 7 identifies the true and false of work of fine arts;Most
Afterwards, corresponding work of fine arts is shown according to the hobby of the type of screening by display module 8.
Below with reference to concrete analysis, the invention will be further described.
Work of fine arts provided in an embodiment of the present invention screens methods of exhibiting, comprising:
Acquire work of fine arts original image;
Sorting parameter is arranged to the work of fine arts figure of acquisition;
Corresponding work of fine arts image is filtered out by the type of input screening;Each work of fine arts image acquires respectively
The class state information for the type screened initializes relevant parameter, the type n measurement of the screening in n-th of smallcell
Downlink classification power gain of the work of fine arts image n to oneselfAnd work of fine arts image n is fed back to, and wherein n=1,2 ...,
N, N are the number of fine arts work images in network, and k=1,2 ..., K, K is the number of orthogonal categories in network, then, each
Work of fine arts image initializes required parameter respectively;Each work of fine arts image repeats to update certainly according to the disturbed condition of surrounding
Oneself the number of iterations counter and policy counter, work of fine arts image update changing for oneself according to the disturbed condition of surrounding
Generation counter and policy counter;Respective the number of iterations counter t is set to t+ respectively by all work of fine arts images
1;N-th work of fine arts image n is according to oneself state α after the t-1 times iterationn(t-1) and selected classification collection
Close sn(t-1), it calculates and selects category set f at this timen∈SnProbability Qn(fn): if αn(t-1)=0,It is no
Then, if αn(t-1)=1,Wherein, n=1,2 ..., N, | Sn| indicate set SnIn
The number of element, ε is one and is greater than 0 constant less than 1, and ω is the constant for being greater than N;N-th of work of fine arts image n root
According to probability distribution Qn, update selected classification sn(t), data, n=1,2 ..., N and in classification are sent;According to selected
Category set sn(t), the type n of n-th of screening measures received interferenceAnd will be conveyed to work of fine arts image n,
Wherein l ∈ sn(t), work of fine arts image n calculates the capacity of present smallcellWherein B0For the bandwidth of each classification,For the fine arts
Transmission power of the work images n on classification l,Indicate power gain of the work of fine arts image n on classification l, N0For noise
Power spectral density;N-th of work of fine arts image n updates oneself state α at this timen(t), n=1,2 ..., N;Work as update times
Predetermined threshold value, the category set that each work of fine arts image selection finally uses are reached, each work of fine arts image judgement changes
Whether generation counter meets t≤T, i.e. the number of iterations is less than threshold T;N-th of work of fine arts image n according to oneself
Policy counter Cn, select the category set finally usedN=1,2 ..., N;Its
Middle sn_ ind is set snIn set SnIn number, Cn(1,sn_ ind) indicate policy counter CnIn the 1st row sn_ ind column
The value of element;
Add the work of fine arts original image of information;
Delete the work of fine arts image of undercarriage
By establish database, the image data of acquisition painting and calligraphy pieces to be identified, illumination consistency processing, extract angle point,
Characteristic matching operation, abnormal point identification, identify the true and false of work of fine arts;
Push a works by the type terminals of screening of from the server to exhibition and screen interface, the type of screening according to
The hobby of oneself filters out the characteristic style of works that need to be browsed and/or author at works screening interface and uploads, according to screening
The hobby of type shows corresponding work of fine arts.
Further, the method for the parameter is initialized are as follows:
The first step, n-th of work of fine arts image n is to available category set SnIt is numbered, and randomly chooses one group of class
Other sn(0)∈SnIt is transmitted, n=0,1 ..., N;
WhereinK is the number of orthogonal categories in network, | sn| it is vector snIn
The number of element, KnFor classification needed for n-th of work of fine arts image, sn(0) it changes for n-th of work of fine arts image at the 0th time
For when used category set, N is the number of fine arts work images in isomery cellular network;
Second step, n-th of work of fine arts image n is by oneself state αn(0) it is set to 0, while resetting the number of iterations counter
T and policy counter
Wherein, αn(0) state of the work of fine arts image n in the 0th iteration is indicated, | Sn| indicate set SnMiddle element
Number,Indicate an a line | Sn| the full null vector of column.
Further, the state α of n-th of work of fine arts image update oneself at this timen(t), n=1,2 ..., N specific method
Are as follows:
(1) state α of the observation after the t-1 times iterationn(t-1), if αn(t-1) it is 1, executes step 2, otherwise hold
Row step 3;
(2) judge category set sn(t-1) it is equal to sn(t) with capacity Rn(t-1) it is equal to Rn(t) whether set up simultaneously, such as
Fruit is set up, by αn(t) it is set as 1;Otherwise step 3 is executed;
(3) with probabilityBy αn(t) it is set as 1;With probability 1- ρ by αn(t) it is set as 0,
Wherein, parameter ε and second step) in definition it is identical, β is the constant for belonging to real number set,For a constant, parameter B0,And N0Definition with
It is identical in 4th step;
(4) n-th of work of fine arts image n are according to the category set s of selectionn(t) and update state αn(t), it updates
Policy counter Cn, n=1,2 ..., N:
If αn(t) it is equal to 1, Cn(1,sn(t) _ ind)=Cn(1,sn(t) _ ind)+1, wherein sn(t) _ ind indicates classification
Collect sn(t) in set SnIn number.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
A computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from
One web-site, computer, server or data center by it is wired (such as coaxial cable, optical fiber, number screening class
Molded line (DSL) or wireless (such as infrared, wireless, microwave etc.) mode are to another web-site, computer, server or number
It is transmitted according to center).The computer-readable storage medium can be any usable medium that computer can access or
Person is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can
To be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid-state
Hard disk Solid State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of work of fine arts screens methods of exhibiting, which is characterized in that the work of fine arts screens methods of exhibiting and includes:
Acquire work of fine arts original image;
Sorting parameter is arranged to the work of fine arts figure of acquisition;
Corresponding work of fine arts image is filtered out by the type of input screening;Each work of fine arts image acquires respectively to be screened
Type class state information, initialize relevant parameter, the type n of the screening in n-th of smallcell measures work of fine arts
Downlink classification power gain of the image n to oneselfAnd work of fine arts image n is fed back to, wherein n=1,2 ..., N, N are net
The number of fine arts work images in network, k=1,2 ..., K, K are the number of orthogonal categories in network, then, each work of fine arts
Image initializes required parameter respectively;Each work of fine arts image repeats the iteration for updating oneself according to the disturbed condition of surrounding
Number counter and policy counter, work of fine arts image update the number of iterations meter of oneself according to the disturbed condition of surrounding
Number device and policy counter;Respective the number of iterations counter t is set to t+1 respectively by all work of fine arts images;N-th of beauty
Art work images n is according to oneself state α after the t-1 times iterationn(t-1) and selected category set sn(t-1), it counts
It calculates and selects category set f at this timen∈SnProbability Qn(fn): if αn(t-1)=0,Otherwise, if αn(t-1)
=1,Wherein, n=1,2 ..., N, | Sn| indicate set SnThe number of middle element, ε are
One is greater than 0 constant less than 1, and ω is the constant for being greater than N;N-th of work of fine arts image n is according to probability distribution Qn, more
New selected classification sn(t), data, n=1,2 ..., N and in classification are sent;According to selected category set sn(t),
The type n of n-th of screening measures received interferenceAnd will be conveyed to work of fine arts image n, wherein l ∈ sn(t), the fine arts
Work images n calculates the capacity of present smallcell
Wherein B0For the bandwidth of each classification,For transmission power of the work of fine arts image n on classification l,Indicate that the fine arts are made
Power gain of the product image n on classification l, N0For noise power spectral density;N-th of work of fine arts image n updates oneself at this time
State αn(t), n=1,2 ..., N;When update times reach predetermined threshold value, each work of fine arts image selection finally makes
Category set, each work of fine arts image judge whether the number of iterations counter meets t≤T, i.e., the number of iterations is less than door
Limit value T;N-th of work of fine arts image n is according to oneself policy counter Cn, select the category set finally usedN=1,2 ..., N;Wherein sn_ ind is set snIn set SnIn number, Cn
(1,sn_ ind) indicate policy counter CnIn the 1st row snThe value of _ ind column element;
Add the work of fine arts original image of information;
Delete the work of fine arts image of undercarriage
By establishing database, the image data of acquisition painting and calligraphy pieces to be identified, illumination consistency processing, extracting angle point, feature
Matching operation, abnormal point identification, identify the true and false of work of fine arts;
Push a works by the type terminals of screening of from the server to exhibition and screen interface, the type of screening according to oneself
Hobby filters out the characteristic style of works that need to be browsed and/or author at works screening interface and uploads, according to the type of screening
Hobby shows corresponding work of fine arts.
2. work of fine arts as described in claim 1 screens methods of exhibiting, which is characterized in that
The method for initializing the parameter are as follows:
The first step, n-th of work of fine arts image n is to available category set SnIt is numbered, and randomly chooses one group of classification sn
(0)∈SnIt is transmitted, n=0,1 ..., N;
WhereinK is the number of orthogonal categories in network, | sn| it is vector snMiddle element
Number, KnFor classification needed for n-th of work of fine arts image, sn(0) made by n-th of work of fine arts image in the 0th iteration
Category set, N are the number of fine arts work images in isomery cellular network;
Second step, n-th of work of fine arts image n is by oneself state αn(0) be set to 0, at the same reset the number of iterations counter t and
Policy counter
Wherein, αn(0) state of the work of fine arts image n in the 0th iteration is indicated, | Sn| indicate set SnThe number of middle element,Indicate an a line | Sn| the full null vector of column.
3. work of fine arts as claimed in claim 2 screens methods of exhibiting, which is characterized in that n-th of work of fine arts image update is certainly
Oneself is state α at this timen(t), n=1,2 ..., N method particularly includes:
(1) state α of the observation after the t-1 times iterationn(t-1), if αn(t-1) it is 1, executes step 2, it is no to then follow the steps
Three;
(2) judge category set sn(t-1) it is equal to sn(t) with capacity Rn(t-1) it is equal to Rn(t) whether set up simultaneously, if set up,
By αn(t) it is set as 1;Otherwise step 3 is executed;
(3) with probabilityBy αn(t) it is set as 1;With probability 1- ρ by αn(t) it is set as 0, wherein
Parameter ε and second step) in definition it is identical, β is the constant for belonging to real number set,For a constant, parameter B0,And N0Definition with
It is identical in 4th step;
(4) n-th of work of fine arts image n are according to the category set s of selectionn(t) and update state αn(t), more new strategy meter
Number device Cn, n=1,2 ..., N:
If αn(t) it is equal to 1, Cn(1,sn(t) _ ind)=Cn(1,sn(t) _ ind)+1, wherein sn(t) _ ind indicates classification collection sn
(t) in set SnIn number.
4. work of fine arts as described in claim 1 screens methods of exhibiting, which is characterized in that identification method includes:
A, it establishes database: being digitized genuine piece painting and calligraphy pieces using high-precision digital scanner or high-definition digital camera, shape
The local high definition picture or photo of integral picture or photo and Chosen Point, establish the digital book paintings of 3,000,000 pixels or more
Product database backup includes the feature point set on standard reference image corresponding to every genuine piece painting and calligraphy pieces in database;
B, the image data of painting and calligraphy pieces to be identified is acquired: by painting and calligraphy pieces to be identified with same digitlization side in a step
Formula forms picture or photo, and is input to identification systems;
C, illumination consistency is handled: the local picture or photo of painting and calligraphy pieces to be identified being carried out illumination consistency processing, made
It is consistent with the local picture of painting and calligraphy pieces to be identified or photo illumination to obtain the illumination of painting and calligraphy pieces picture or photo in database;
D, angle point is extracted: local picture or photograph using the Robust Algorithm of Image Corner Extraction based on image border to painting and calligraphy pieces to be identified
Piece extracts angle point, and on the basis of the angle point of extraction, constructs corresponding spin matrix, match corresponding angle point, establish wait match
Feature point set on quasi- image;
E, it characteristic matching operation: according to the feature point set on known database Plays reference picture, is incorporated in be identified
Painting and calligraphy pieces obtain the feature point set on the image subject to registration that obtains, establish the corresponding relationship between two point sets, using pair
It should be related to solve transformation model parameter, and then realize registration;
F, abnormal point is identified: the affine transformation matrix after the registration of acquisition being matched with the image in database, is calculated
Difference between the feature and database Plays art work character pair at identified position, provides matching rate, and then obtain use
In the qualification result for judging the painting and calligraphy pieces true and false.
5. work of fine arts as described in claim 1 screens methods of exhibiting, which is characterized in that methods of exhibiting includes:
Firstly, pushing a works by the type terminals of screening of from the server to exhibition screens interface, the type of screening according to
The hobby of oneself filters out the characteristic style of works that need to be browsed and/or author at works screening interface and uploads;
Secondly, the type terminals of the screening content that uploads the type of screening together with the screening type terminals it is wireless
The address Mac is sent to the server;
Then, the server according to the content of upload obtain out the type screened filter out the characteristic style of works that need to be browsed and/or
Author simultaneously finds out work of fine arts corresponding to the characteristic style of works that need to be browsed and/or author in built-in database, be named as to
Work of fine arts is browsed,
Then, the wireless address Mac of the type terminals of the screening is sent to work of fine arts to be browsed and bound by the server
Wireless transceiver on, be named as and preset the wireless address Mac;The type terminals sending of the screening carries the wireless address Mac
Wireless signal;
Finally, the wireless receiver receives the wireless communication for carrying the wireless address Mac that the type terminals of the screening issue
Number and judge whether the wireless address Mac identical as the wireless address Mac is preset, if they are the same, then by built-in correspondence work of fine arts
Interpretation data transmission give the type terminals of the screening;Wherein, the wireless receiver only receives the nothing in a pre-determined distance
Line signal.
6. a kind of computer program for realizing the screening methods of exhibiting of work of fine arts described in Claims 1 to 5 any one.
7. a kind of information data processing terminal for realizing the screening methods of exhibiting of work of fine arts described in Claims 1 to 5 any one.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires work of fine arts described in 1-5 any one to screen methods of exhibiting.
9. a kind of work of fine arts screening display systems for realizing the screening methods of exhibiting of work of fine arts described in claim 1, feature
It is, the work of fine arts screening display systems include:
Image capture module is connect with central processing module, for acquiring work of fine arts original image by image pick-up device;
Image setup module, connect with central processing module, for sorting parameter to be arranged to the work of fine arts figure of acquisition;
Central processing module is deleted with image capture module, image setup module, optical sieving module, image adding module, image
Except module, identification module, display module connection, worked normally for controlling modules;
Optical sieving module, connect with central processing module, makees for filtering out the corresponding fine arts by the type of input screening
Product image;
Image adding module, connect with central processing module, for adding the work of fine arts original image of information;
Image-erasing module, connect with central processing module, for deleting the work of fine arts image of undercarriage;
It identifies module, connect with central processing module, identified for the true and false to work of fine arts;
Display module is connect with central processing module, and the hobby for the type according to screening shows corresponding work of fine arts.
10. a kind of work of fine arts for carrying the screening display systems of work of fine arts described in claim 9 screens presentation device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810752941.9A CN109101885A (en) | 2018-07-10 | 2018-07-10 | A kind of work of fine arts screening display systems and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810752941.9A CN109101885A (en) | 2018-07-10 | 2018-07-10 | A kind of work of fine arts screening display systems and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109101885A true CN109101885A (en) | 2018-12-28 |
Family
ID=64846130
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810752941.9A Pending CN109101885A (en) | 2018-07-10 | 2018-07-10 | A kind of work of fine arts screening display systems and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109101885A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112732988A (en) * | 2021-01-12 | 2021-04-30 | 青岛农业大学 | System and method for screening and displaying artwork |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103619066A (en) * | 2013-11-07 | 2014-03-05 | 西安电子科技大学 | Method for distributing downlink interference mitigation based on distributed channel |
CN104636733A (en) * | 2015-02-12 | 2015-05-20 | 湖北华中文化产权交易所有限公司 | Image characteristic-based painting and calligraphy work authenticating method |
CN105681468A (en) * | 2016-03-22 | 2016-06-15 | 苏州马尔萨斯文化传媒有限公司 | Method of exhibiting art works screened based on user hobbies |
CN106649701A (en) * | 2016-12-20 | 2017-05-10 | 新乡学院 | Art work screening display system |
-
2018
- 2018-07-10 CN CN201810752941.9A patent/CN109101885A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103619066A (en) * | 2013-11-07 | 2014-03-05 | 西安电子科技大学 | Method for distributing downlink interference mitigation based on distributed channel |
CN103619066B (en) * | 2013-11-07 | 2017-05-10 | 西安电子科技大学 | Method for distributing downlink interference mitigation based on distributed channel |
CN104636733A (en) * | 2015-02-12 | 2015-05-20 | 湖北华中文化产权交易所有限公司 | Image characteristic-based painting and calligraphy work authenticating method |
CN105681468A (en) * | 2016-03-22 | 2016-06-15 | 苏州马尔萨斯文化传媒有限公司 | Method of exhibiting art works screened based on user hobbies |
CN106649701A (en) * | 2016-12-20 | 2017-05-10 | 新乡学院 | Art work screening display system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112732988A (en) * | 2021-01-12 | 2021-04-30 | 青岛农业大学 | System and method for screening and displaying artwork |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109284733B (en) | Shopping guide negative behavior monitoring method based on yolo and multitask convolutional neural network | |
CN108596108B (en) | Aerial remote sensing image change detection method based on triple semantic relation learning | |
CN106548169B (en) | Fuzzy literal Enhancement Method and device based on deep neural network | |
US8682072B2 (en) | Image segmentation | |
DE102017010210A1 (en) | Image Matting by means of deep learning | |
CN108124184A (en) | A kind of method and device of living broadcast interactive | |
CN109711345A (en) | A kind of flame image recognition methods, device and its storage medium | |
CN103201769A (en) | Image processing device, image processing method, program, integrated circuit | |
CN109165682A (en) | A kind of remote sensing images scene classification method merging depth characteristic and significant characteristics | |
CN103578098B (en) | Method and device for extracting commodity body in commodity picture | |
CN108447064A (en) | A kind of image processing method and device | |
CN107038408A (en) | Image-recognizing method and device based on augmented reality | |
WO2020037940A1 (en) | Method and device for screening image data of character clothing | |
KR101832680B1 (en) | Searching for events by attendants | |
CN106203454A (en) | The method and device that certificate format is analyzed | |
CN108986125A (en) | Object edge extracting method, device and electronic equipment | |
CN105825228B (en) | Image-recognizing method and device | |
CN106650795A (en) | Sorting method of hotel room type images | |
Shaffrey et al. | Unsupervised image segmentation via Markov trees and complex wavelets | |
CN106027902A (en) | Photographing method and mobile terminal | |
CN110489659A (en) | Data matching method and device | |
CN110837829B (en) | Control method and system of sweeping robot | |
CN108537095A (en) | Method, system, server and the virtual reality device of identification displaying Item Information | |
CN108256520A (en) | A kind of method, terminal device and computer readable storage medium for identifying the coin time | |
CN109101885A (en) | A kind of work of fine arts screening display systems and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181228 |
|
RJ01 | Rejection of invention patent application after publication |