CN110992282A - Automatic calibration and virtual repair method for temple mural diseases - Google Patents
Automatic calibration and virtual repair method for temple mural diseases Download PDFInfo
- Publication number
- CN110992282A CN110992282A CN201911202252.1A CN201911202252A CN110992282A CN 110992282 A CN110992282 A CN 110992282A CN 201911202252 A CN201911202252 A CN 201911202252A CN 110992282 A CN110992282 A CN 110992282A
- Authority
- CN
- China
- Prior art keywords
- mural
- calibration
- repair
- algorithm
- diseases
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 74
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 74
- 230000008439 repair process Effects 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000010422 painting Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 230000007547 defect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 27
- 238000007726 management method Methods 0.000 description 20
- 230000008520 organization Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000013523 data management Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/54—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention overcomes the defects of the prior art, and provides a temple mural disease automatic calibration and virtual repair method, the disease automatic calibration function greatly reduces the workload of mural protection work, has an important auxiliary effect on the actual repair work of murals, and lays a foundation for the virtual repair of murals, the virtual repair of murals reduces the secondary damage to the murals caused by multiple repairs in the actual mural repair, and simultaneously provides reference for the actual repair work of the murals; on the basis of obtaining mural data, the method analyzes, calibrates and virtually repairs the existing diseases of the mural, selects or uploads images of the falling-off diseases from a cluster to submit and calibrate, the system automatically calls a TS-RG algorithm to perform automatic calibration, a user can check or download calibration result images on line to perform calibration after calibration is completed, the user uploads calibrated images to a calibration module to submit a repair task after the user meets the user requirement, and the system calls an ASB-LS algorithm to complete repair.
Description
Technical Field
The invention discloses an automatic calibration and virtual repair method for diseases of temple murals, and belongs to the technical field of ancient mural cultural relic protection.
Background
Ancient temple wall painting as one of the main cultural heritages contains rich history, culture and artistic information, vividly records the custom habit and social landscape of each nation, and has extremely high application value in the fields of history, science, art and the like. Due to the history, climate and environment and other reasons, the mural of each temple has phenomena of shedding, lifting and fading and the like in different degrees, wherein the shedding diseases are the most serious, and urgent protection is needed. In recent years, with the development of information technology and the rapid development of image processing and mass data storage, many experts and scholars combine the information technology with mural protection to be applied to ancient mural protection. How to digitize mural information and protect ancient murals by using a digital image processing technology is a problem worthy of research.
At present, since texts, images, videos and other information related to murals are stored in a scattered manner in researchers or temple of each sight spot, retrieval and use of mural information are difficult because a unified mural digital information storage system is not provided. In addition, in the traditional mural repair, the calibration of mural diseases is mainly completed manually, although the calibration effect is good, the calibration is completed manually, the calibration is still time-consuming and labor-consuming, in recent years, many people complete the segmentation of the disease area by utilizing threshold segmentation, good effect is achieved, and manpower and material resources are greatly saved; in the traditional image restoration algorithm, a Criminisi algorithm based on texture synthesis is widely applied, and the Criminisi algorithm has good effect in restoration of natural images and mural images.
The main drawbacks of the above-mentioned techniques are as follows:
1. at present, mural data information is stored in a single database of mural researchers or cultural relic units, the storage and retrieval capacity is limited, and in addition, the storage of newly generated data cannot be updated in time; the scattered storage of data is also not beneficial to the study of murals.
2. Due to the reasons of history, climate environment and the like, the murals have diseases such as falling, cracks, armor raising, hollowing and the like in different degrees, wherein the falling diseases are the most serious. In recent years, research is carried out on crack diseases of murals of a coffin chamber, automatic calibration of crack diseases of murals is realized by mainly using the color and texture characteristics of the murals and combining a connected domain measurement method, the method is suitable for automatic calibration of diseases with small disease areas and obvious lines, and the problem of insufficient calibration exists when large-area scale-off disease calibration is carried out; and analyzing the texture characteristics of the mural by utilizing a spatial autocorrelation function aiming at the mud spot diseases of the mural of the coffin chamber, and separating by combining a threshold segmentation method to obtain a mask of a mud spot area of the mural, so that the automatic calibration of the mud spot is realized, the calibration effect is good, but the time consumption is long.
3. Aiming at repairing mural diseases, at present, a traditional repairing algorithm aiming at natural images is mainly used, a Criminisi algorithm based on sample blocks is applied more, in the process of repairing the natural images, many scholars of the algorithm have problems in repairing the murals and obtain good repairing effect from three main steps of repairing the murals, but when the algorithm is applied to repairing the murals, the specific composition characteristics of the murals are not considered, the effect after repairing is often not satisfactory, in addition, the local characteristics of the murals are not considered in the process of repairing, in the process of repairing by using the Criminisi algorithm, a global search mode is used when the best matching block is found, and the repairing time is long.
Disclosure of Invention
The invention overcomes the defects of the prior art, and provides the automatic disease calibration and virtual repair method for the temple mural, the automatic disease calibration function greatly reduces the workload of mural protection work, has an important auxiliary effect on the actual mural repair work, and lays a foundation for the virtual repair of the mural, the virtual repair of the mural reduces the secondary damage to the mural caused by multiple repairs in the actual mural repair, and meanwhile provides reference for the actual mural repair work.
In order to solve the technical problems, the invention adopts the technical scheme that: a method for automatically calibrating and virtually repairing diseases of temple murals is implemented according to the following steps:
the first step is as follows: obtaining mural data;
the acquisition mode comprises text, images, video and audio data related to the mural;
the second step is that: automatically calibrating the shedding diseases;
selecting a mural image needing to be subjected to shedding disease calibration, designating the name of the calibrated mural image and adding calibration remark information, then completing calibration by using a calibration algorithm, and according to the calibrated result, seeing the task just submitted and the time of starting and ending calibration in the calibrated image result, and if the calibration is completed, displaying image links in the calibrated image column for a user to check or download online;
the third step: virtually repairing the wall painting shedding disease;
and selecting the calibrated falling-off disease mural image, filling in name and remark information, then starting repairing, calling a repairing related algorithm by starting a sub-thread, and storing repaired data information in a database after the repairing is finished.
The calibration algorithm is a TS-RG algorithm, and comprises the following specific steps:
the first step is as follows: reading in a color image;
the second step is that: RGB channel separation, median filtering;
the third step: separating threshold values and determining seed points;
the fourth step: growing the multiple seeds in a dot region;
the fifth step: merging the growth results of the channel regions after the growth of the seed point regions is completed;
and a sixth step: and completing automatic calibration.
The repairing correlation algorithm is an ASB-LS algorithm, and comprises the following specific steps:
the first step is as follows: inputting a mural image of a calibrated area;
the second step is that: determining the boundary of a calibration area;
the third step: determining the pixel point with the highest priority;
the fourth step: determining the average correlation factor of the pixel points in the region with the center of 9 x 9 as the pixel point with the highest priority;
the fifth step: determining a size of an adaptive sample block;
and a sixth step: determining a local search space and searching for an optimal matching block;
the seventh step: copying the best matching block to a calibration area at a corresponding position of the sample block;
eighth step: updating the confidence value of the shedding region in the sample block;
the ninth step: updating the boundary of the calibration area;
the tenth step: repeating the actions from the second step to the ninth step until the calibration area is empty;
the eleventh step: and finishing virtual repair.
Compared with the prior art, the invention has the following beneficial effects.
1. Compared with the traditional single database, the mural database cluster related by the invention has better availability and concurrency. The database cluster in the system for automatically calibrating and virtually repairing the diseases of the temple murals performs cluster storage on structured and unstructured information related to the murals, so that high availability of data is guaranteed; and meanwhile, the high concurrency requirement of the client is realized by adopting load balancing and reverse proxy. In addition, the system integrates the mural defect calibration and repair algorithm, and mural data are stored in the cluster, so that the calibration and repair work can be completed conveniently.
2. When the automatic appearance of the dropping diseases of the temple mural is carried out, a TS-RG (region growing threshold segmentation) algorithm is adopted, a threshold segmentation algorithm and a region growing algorithm which are commonly used in image segmentation are combined, more accurate and efficient disease calibration is realized, compared with the existing calibration algorithm, the algorithm is more accurate in calibration result, and the user satisfaction degree is higher. The automatic disease calibration function provided by the system greatly reduces the workload of mural protection work, has an important auxiliary effect on actual mural repair work, and lays a foundation for virtual repair of murals.
3. The integrated mural disease virtual repair function has a core algorithm of ASB-LS (adaptive sample block and local search). Compared with the existing common image restoration algorithm, the algorithm focuses more on the composition characteristics of mural images, the algorithm takes a Criminisi block restoration algorithm as a basis, the structure tensor is introduced into the priority function definition to distinguish different structure areas of the images, and meanwhile, when a matching block is searched, local search is carried out by adopting the size of a self-adaptive sample block to improve the search efficiency. Compared with the traditional restoration algorithm, the ASB-LS algorithm is improved by 100-150 s in restoration time, the whole restoration effect is obviously improved in visual continuity, and the PSNR value is improved by 1-3 dB in restoration of artificially damaged mural images. The overall effect of the repaired image is satisfactory. In addition, the virtual repair of the mural reduces the secondary damage to the mural caused by multiple repairs in the actual mural repair, and meanwhile, a reference is provided for the actual repair work of the mural.
4. The digital information of the temple mural is sorted and stored for the first time, a data base is provided for mural research work, a strict authority management mechanism is provided, and data security is guaranteed.
5. The invention realizes the online calibration and virtual repair of the detachment diseases of the temple wall painting for the first time, provides a friendly user interface and a data interface, has good expandability and provides a system foundation for the calibration and virtual repair algorithm integration of other diseases.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a schematic diagram of the framework of the present invention, i.e., MySQL Cluster architecture diagram.
Fig. 2 is an overall architecture diagram of the present invention.
FIG. 3 is a flow chart of the TS-RG algorithm in the present invention
Fig. 4 is a flow chart of scaling of the peeling-off disease (peeling-off of the base layer).
FIG. 5 is a flow chart of the ASB-LS algorithm of the present invention.
Detailed Description
As shown in figures 1-5, the automatic calibration and virtual repair method for the diseases of the temple wall painting is implemented according to the following steps:
the first step is as follows: obtaining mural data;
the acquisition mode comprises text, images, video and audio data related to the mural;
the second step is that: automatically calibrating the shedding diseases;
selecting a mural image needing to be subjected to shedding disease calibration, designating the name of the calibrated mural image and adding calibration remark information, then completing calibration by using a calibration algorithm, and according to the calibrated result, seeing the task just submitted and the time of starting and ending calibration in the calibrated image result, and if the calibration is completed, displaying image links in the calibrated image column for a user to check or download online;
the third step: virtually repairing the wall painting shedding disease;
and selecting the calibrated falling-off disease mural image, filling in name and remark information, then starting repairing, calling a repairing related algorithm by starting a sub-thread, and storing repaired data information in a database after the repairing is finished.
The calibration algorithm is a TS-RG algorithm, and comprises the following specific steps:
the first step is as follows: reading in a color image;
the second step is that: RGB channel separation, median filtering;
the third step: separating threshold values and determining seed points;
the fourth step: growing the multiple seeds in a dot region;
the fifth step: merging the growth results of the channel regions after the growth of the seed point regions is completed;
and a sixth step: and completing automatic calibration.
The repairing correlation algorithm is an ASB-LS algorithm, and comprises the following specific steps:
the first step is as follows: inputting a mural image of a calibrated area;
the second step is that: determining the boundary of a calibration area;
the third step: determining the pixel point with the highest priority;
the fourth step: determining the average correlation factor of the pixel points in the region with the center of 9 x 9 as the pixel point with the highest priority;
the fifth step: determining a size of an adaptive sample block;
and a sixth step: determining a local search space and searching for an optimal matching block;
the seventh step: copying the best matching block to a calibration area at a corresponding position of the sample block;
eighth step: updating the confidence value of the shedding region in the sample block;
the ninth step: updating the boundary of the calibration area;
the tenth step: repeating the actions from the second step to the ninth step until the calibration area is empty;
the eleventh step: and finishing virtual repair.
On the basis of obtaining mural data, the method analyzes, calibrates and virtually repairs the existing diseases of the mural, selects or uploads images of the falling-off diseases from a cluster to submit and calibrate, the system automatically calls a TS-RG algorithm to perform automatic calibration, a user can check or download calibration result images on line to perform calibration after calibration is completed, the user uploads calibrated images to a calibration module to submit a repair task after the user meets the user requirement, and the system calls an ASB-LS algorithm to complete repair.
In the Web application system developed based on Java language, foreground development is completed by using a LayUI framework, background development is completed by using an SMM (Spring, Spring MVC and MyBatis) framework, and the authentication and management of the permission are realized by using a Shiro framework. The database uses a MySQL database of MySQL-cluster-7.6.8 cluster version, the load balancing is realized by using Nginx and Keeployed, the system runs in a Tomcat8.5 container, and the database cluster is deployed on a main stream Linux system CentOS 7. The disease calibration and the data preprocessing and the automatic disease calibration during the repair of the system are completed by Matlab, and the repair of the disease is completed by using C + + language.
The invention relates to a temple mural disease automatic calibration and virtual repair system, which integrates data information storage, disease automatic calibration, virtual repair and authority management of system users related to murals, constructs an intelligent and efficient mural intelligent repair auxiliary system and has important significance for digital protection of murals; the storage of the mural data information comprises unstructured data such as texts, images, video and audio data and the like, so that different types of users can upload and retrieve mural record information of the related temple through a system instead of sporadic data information on the network, and the mural detailed understanding of various groups such as researchers and temple visitors is facilitated; the method comprises the steps that automatic calibration of mural diseases is carried out, a user selects a certain mural of a designated temple through a system, a system is submitted to automatically calibrate a disease area aiming at the problem of falling diseases, the system calls a related calibration algorithm through a java interface provided by matlab to complete automatic calibration of the mural diseases, after the calibration is completed, the system prompts completion information and records calibration records into a database, automatic calibration of the mural diseases is carried out, manpower and material resources are greatly saved, and a good foundation is laid for virtual repair of the mural diseases; the virtual restoration of the mural falling diseases is realized, a user selects the mural which is calibrated through the system and submits a restoration task, the system calls a corresponding falling disease restoration algorithm through a java interface provided by C + + to complete restoration, restoration result prompt information is returned, and restoration related information such as restoration time consumption, restoration picture results and other information is stored in a database, the restoration result not only enables the mural to be displayed virtually, but also provides reference for the restoration of the actual mural, and secondary damage to the mural caused by multiple times of restoration in artificial restoration is avoided.
The invention adopts a classic MVC (Model, View, Controller) framework, the Controller adopts a SpringMVC framework to finish the functions of request forwarding, filtering interception and the like, the View layer adopts a LayUI framework and a classic background template thereof, the data asynchronous processing Ajax technology and the like, and the Model layer adopts a MyBatis framework to finish the acquisition and storage of data. All data of the system are stored in a MySQL synchronous cluster, the current cluster is composed of 9 nodes, wherein the current cluster comprises two management nodes, 4 data nodes and 3 SQL nodes, and each type of node is subjected to redundant configuration to ensure high availability of the data. An Nginx server is added between an application system and a database cluster to perform load balancing and reverse proxy, and the cluster is completely transparent to system users. After the user logs in the system, the system submits the data, the system stores the data in the target database server by using the reverse proxy and the load balance, the data in the cluster are acquired and displayed by the reverse proxy, and finally the system displays the data according to the logic.
According to the invention, the data information related to the mural is collected by the user and stored in the database cluster of the system, and then automatic disease calibration and virtual repair are carried out on the mural image with the falling-off disease. The system is mainly divided into three functional modules, namely data management, mural repair and system management.
Firstly, data management:
the data of the module mainly refers to text, images, video and audio and other data related to the murals, and users with related rights can perform related operations on the mural data through the function.
The text data mainly refers to document data related to a mural, wherein the type of the document may be txt, doc, etc. The document type can be configured by a system administrator, and the data is obtained by arranging literature records and news report contents related to the murals by users. Since documents are all information about a certain mural, the title of the document is defined in a temple name plus mural name format for easy retrieval.
The image data refers to mural images shot by tourists or professional photographers, and when uploading the images, a user needs to clearly fill in the storage state of the mural and the temple to which the mural belongs, and selects information such as a county and a district to which the mural belongs through a three-level linkage drop-down box of the regional information. The format supported by the mural image can also be configured by an administrator, and a user can perform operations such as viewing and downloading by clicking an image link on line.
The video and audio data is mainly the video and audio record information of a wall painting when the visitors, the temple staff and the reporter interview the mural experts. Similarly, the title of the video and audio data is also specified in a temple name and mural name format, and information such as shooting time and author of the video is required to be filled in the uploading process. The video supports operations such as online on-demand and downloading.
All data of the module support persons with related authorities to carry out operations of adding, deleting, modifying and checking, wherein the operations comprise functions of batch deleting, conditional searching and the like.
Secondly, repairing the mural:
mural repair is the core function of this system, and this module mainly accomplishes automatic demarcation and virtual restoration of temple mural disease that drops.
And (3) automatic calibration of the falling diseases, adding mural images needing to be calibrated of the falling diseases through a system interface by a user, designating the names of the calibrated mural images, adding calibration remarks and other information, clicking a calibration starting button, and calling a calibration algorithm by the system to finish calibration and returning a calibrated result. At this time, the task just submitted and the start and end times of calibration can be seen in the calibration image list, and if the calibration is completed, the image link can be displayed in the calibration image list for the user to view or download online.
And (3) virtually repairing the mural falling diseases, adding calibrated wall painting images with the falling diseases through a system interface by a user, filling information such as names and remarks, submitting a task to start repairing, starting a sub-thread by the system to call a repairing related algorithm, and storing repaired data information in a database after repairing is finished. Because the repairing time is long, the repairing task state submitted by the current user is displayed on the repairing list page, wherein the repairing task state comprises state information of repairing, repaired and the like, and fields of starting and ending time of a repairing task, links of images before and after repairing and the like are displayed at the same time.
And the functions of batch deletion, condition retrieval and the like are also provided in the automatic calibration and repair of the mural, so that a user can conveniently obtain the required information.
Thirdly, system management:
the system management mainly realizes that some seems not related to the core function of the system, but ensures the availability and the expansibility of the system. The system management module of the system mainly comprises 11 subfunctions.
(1) Menu management
The menu management realizes the dynamic configuration of modules in the whole system, including the names, icons, URL routing, superior modules and other contents of modules with various sizes. And simultaneously, batch deletion and conditional query functions of the modules are provided so as to quickly view the module information.
(2) Role management
The system role management comprises the addition and deletion of roles, and each type of role corresponds to different authorities. The role adding and deleting check can be operated by a system administrator only, and the authorization of system functions can be given to different types of roles after the roles are created. When different users log in, the system interface module with visible ownership is displayed according to the roles of the users. Also, when the user performs an override, the system gives a prompt.
(3) System function
The module mainly comprises operation types owned by each module in the system, such as adding, deleting, modifying, checking, batch deleting, inquiring according to conditions and the like. Each operation type has information such as a menu, a request address, and the like to which it belongs. (4) Dictionary type
The function is mainly to realize the classification of some enumerated types of data, such as the storage state of a mural, the state of a user and the like, the data under the types are fixed, and when the addition is needed, the data can be operated through a data dictionary module.
(5) Data dictionary
The data dictionary is used in conjunction with dictionary types, enumerating several possible values in the dictionary types and numbering. The design of the dictionary type and the design of the database table are reduced, the configuration flexibility is increased, and the two modules provide the functions of batch deletion and conditional retrieval.
(6) Organization information
The organization information includes a list of organizations belonging to each type of user, and each organization has its number and information such as a superior organization and an organization level. The design of the module meets the distribution strategy of the authority on one hand, and facilitates the classification management of users on the other hand. When a new user registers in the system, the default authority can be given by the mechanism to which the new user belongs, so that the operation of the user is facilitated.
(7) URL interception
The module is mainly designed for safety, and prevents illegal users from directly accessing system data through the URL to cause system data leakage. Through the function, a system administrator can configure the URL needing to be intercepted, and only the system super administrator can operate the function.
(8) User management
The module is a general module of the system, and an administrator of a superior mechanism can check the registered user information, check the user information and state, modify and delete the specified user, and simultaneously carry out operations such as distribution, recovery and the like on the authority of the user.
(9) Log management
The administrators of different levels can check the operation performed after the user managed by the administrators logs in the system through the system, wherein the operation includes information such as an operation module, start and stop time, operator IP and the like. The log information is only allowed to be checked, and the operations of deleting and modifying cannot be carried out, and the log deleting is completed by a timing task of the system.
(10) Timed tasks
The module completes tasks such as system detection, overdue log cleaning and the like at a low peak time of a system user according to a timer added by an administrator (the operation is limited to super administrator authority), and meanwhile, the module also realizes the grouping of the timing tasks, and divides different types of timing tasks according to different groups, such as virtual repair with serious mural drop.
(11) Code generation
The foreground and background of the system are completed by utilizing a mature frame, so that the system provides a set of fixed template codes, when the system function needs to be expanded, after a database table is designed, the function is directly used to generate basic codes of the foreground and the background, and then the basic codes are modified according to the characteristics of the modules, so that repeated code compiling is greatly reduced, and the efficiency of system expansion is improved.
The invention can finish the classified uploading of digital information of the mural, such as text, image, video and audio information, and the user can conveniently retrieve and check the related mural information.
The mural automatic calibration function related by the invention can finish automatic calibration on the mural image with the falling-off disease selected by the user, and the calibrated mural image can be checked and downloaded through the system.
According to the method, a user uploads or selects an image which is calibrated, the system carries out restoration after submitting a virtual restoration task, meanwhile, the current restoration progress is displayed in a restoration status bar, and the user is informed and the restoration status is changed after restoration is finished; at the moment, the repaired mural image can be checked and downloaded through the system.
In the invention, each user corresponds to a mechanism to which the user belongs, and an administrator of each mechanism can perform authority distribution such as increasing, deleting, modifying, checking and the like on the subordinate user, and when the user performs unauthorized operation, the system can give a popup for warning; the system user can conveniently acquire the required data to carry out related research.
According to the invention, a user can enter the system through a simple user login interface, each functional module has a relevant description, and the system is simple and easy to use. Meanwhile, other systems can also obtain required data through the API provided by the system. When a new disease repair algorithm is realized, only the interface code of the corresponding module needs to be produced through the code generator, and then the repair algorithm is called when the repair function is realized.
The present invention will be described in detail with reference to specific examples.
The automatic calibration and virtual repair system for the temple mural realizes the clustered storage of various types of digital information related to the mural, the automatic calibration and virtual repair of the mural falling diseases, and the system strictly limits the authority of different types of users to ensure the safety of system data. Different users can see different function module interfaces due to different permissions after logging in the system. Currently, the types of system users are mainly classified into three types, i.e., super administrators, organization administrators, and general users. A super manager can perform all operations of all functions of the system, an organization manager cannot use modules in system management, such as a data dictionary, URL interception, code construction and the like, under the default condition, and a common user can only perform query and upload operations on system mural data.
The mural data management function of the system realizes the storage of text, images, video and audio information related to the mural. After a user logs in the system, form information is filled in by clicking newly added buttons corresponding to various data modules, the data are uploaded to a database cluster, and each piece of data uploaded by the user has a user identification. Similarly, when the user needs to inquire and acquire the required mural information, the condition inquiry function of each sub-module can be used for realizing quick retrieval, and the image, video and audio data support operations such as online playing and downloading. The cluster management of the mural data greatly facilitates the data acquisition of mural works or researchers, and meanwhile, the digital information storage time is longer and more stable, so that the cluster management method has important significance for the protection of murals.
The repairing function of the mural is to analyze, calibrate and virtually repair the diseases existing in the mural on the basis of acquiring the mural data. The prior system only provides automatic calibration and virtual repair of the detachment diseases of the temple wall painting, a user can select or upload images of the detachment diseases from a cluster to submit the calibration, and the system automatically calls a TS-RG algorithm to perform automatic calibration. After calibration is completed, a user can check or download the image of the calibration result on line for calibration, after the user requirements are met, the user uploads the image after calibration to a repair module to submit a repair task, and the system calls an ASB-LS algorithm to complete repair. The repair function of the system greatly reduces the workload of cultural relic workers such as mural repair and the like, and the cultural relic workers can directly use the virtual calibration or the repair result to carry out actual repair work, so that the progress of the mural repair work is accelerated, the expenditure of manpower and material resources is reduced, and meanwhile, the secondary damage to the mural caused by repeated repair in mural repair is also avoided.
The system can provide different authorities for the user conveniently by the administrator through role management, and when a certain user operates without authority, the system can prompt the user to pop up. The system log management can record information such as access IP, operation modules, operation results and the like of all users in the system in detail, can track misoperation and illegal operation of the system, can record the running condition of the system at the same time, and is favorable for timely removing faults of the system when the system breaks down.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (3)
1. A method for automatically calibrating and virtually repairing diseases of temple murals is characterized by comprising the following steps:
the first step is as follows: obtaining mural data;
the acquisition mode comprises text, images, video and audio data related to the mural;
the second step is that: automatically calibrating the shedding diseases;
selecting a mural image needing to be subjected to shedding disease calibration, designating the name of the calibrated mural image and adding calibration remark information, then completing calibration by using a calibration algorithm, and according to the calibrated result, seeing the task just submitted and the time of starting and ending calibration in the calibrated image result, and if the calibration is completed, displaying image links in the calibrated image column for a user to check or download online;
the third step: virtually repairing the wall painting shedding disease;
and selecting the calibrated falling-off disease mural image, filling in name and remark information, then starting repairing, calling a repairing related algorithm by starting a sub-thread, and storing repaired data information in a database after the repairing is finished.
2. The method for automatically calibrating and virtually repairing the diseases of the temple mural according to claim 1, wherein the calibration algorithm is a TS-RG algorithm, and comprises the following specific steps:
the first step is as follows: reading in a color image;
the second step is that: RGB channel separation, median filtering;
the third step: separating threshold values and determining seed points;
the fourth step: growing the multiple seeds in a dot region;
the fifth step: merging the growth results of the channel regions after the growth of the seed point regions is completed;
and a sixth step: and completing automatic calibration.
3. The method for automatically calibrating and virtually repairing the diseases of the temple mural according to claim 1, wherein the repair-related algorithm is an ASB-LS algorithm, and comprises the following specific steps:
the first step is as follows: inputting a mural image of a calibrated area;
the second step is that: determining the boundary of a calibration area;
the third step: determining the pixel point with the highest priority;
the fourth step: determining the average correlation factor of the pixel points in the region with the center of 9 x 9 as the pixel point with the highest priority;
the fifth step: determining a size of an adaptive sample block;
and a sixth step: determining a local search space and searching for an optimal matching block;
the seventh step: copying the best matching block to a calibration area at a corresponding position of the sample block;
eighth step: updating the confidence value of the shedding region in the sample block;
the ninth step: updating the boundary of the calibration area;
the tenth step: repeating the actions from the second step to the ninth step until the calibration area is empty;
the eleventh step: and finishing virtual repair.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911202252.1A CN110992282A (en) | 2019-11-29 | 2019-11-29 | Automatic calibration and virtual repair method for temple mural diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911202252.1A CN110992282A (en) | 2019-11-29 | 2019-11-29 | Automatic calibration and virtual repair method for temple mural diseases |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110992282A true CN110992282A (en) | 2020-04-10 |
Family
ID=70088458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911202252.1A Pending CN110992282A (en) | 2019-11-29 | 2019-11-29 | Automatic calibration and virtual repair method for temple mural diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110992282A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504764A (en) * | 2009-01-19 | 2009-08-12 | 西安交通大学 | Ancient architecture oil-decorative painting virtual repairing system and method |
| CN103295199A (en) * | 2013-05-29 | 2013-09-11 | 西安建筑科技大学 | Intelligent repair assistance system for cracks of ancient wall murals |
| CN104766283A (en) * | 2015-04-15 | 2015-07-08 | 中北大学 | Digitized repairing method for grave mural image |
| CN106056546A (en) * | 2016-05-25 | 2016-10-26 | 广东工业大学 | Image restoration method and device based on sample block matching |
| CN108346135A (en) * | 2018-03-12 | 2018-07-31 | 湖南理工学院 | A kind of improved Criminisi image repair methods |
| CN108665416A (en) * | 2017-03-29 | 2018-10-16 | 清华大学 | Damaged mural painting restorative procedure and system |
-
2019
- 2019-11-29 CN CN201911202252.1A patent/CN110992282A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504764A (en) * | 2009-01-19 | 2009-08-12 | 西安交通大学 | Ancient architecture oil-decorative painting virtual repairing system and method |
| CN103295199A (en) * | 2013-05-29 | 2013-09-11 | 西安建筑科技大学 | Intelligent repair assistance system for cracks of ancient wall murals |
| CN104766283A (en) * | 2015-04-15 | 2015-07-08 | 中北大学 | Digitized repairing method for grave mural image |
| CN106056546A (en) * | 2016-05-25 | 2016-10-26 | 广东工业大学 | Image restoration method and device based on sample block matching |
| CN108665416A (en) * | 2017-03-29 | 2018-10-16 | 清华大学 | Damaged mural painting restorative procedure and system |
| CN108346135A (en) * | 2018-03-12 | 2018-07-31 | 湖南理工学院 | A kind of improved Criminisi image repair methods |
Non-Patent Citations (5)
| Title |
|---|
| 何雨亭等: "结构张量的改进Criminisi修复", 《中国图象图形学报》 * |
| 曹建芳等: "改进的区域生长算法在寺观壁画脱落病害标定中的应用", 《新疆大学学报(自然科学版)》 * |
| 李彩艳等: "唐墓室壁画泥斑病害自动标定及虚拟修复", 《计算机工程与应用》 * |
| 欧先锋等: "一种改进的Criminisi图像修复算法", 《成都工业学院学报》 * |
| 王展等: "新津观音寺明代壁画图像的计算机自动虚拟修复研究", 《文物保护与考古科学》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115198B (en) | Urban remote sensing intelligent service platform | |
| CN104794572B (en) | Building design data information and experience sharing platform | |
| US6816868B1 (en) | Database system | |
| CN109344223A (en) | A kind of Building Information Model management system and method based on cloud computing technology | |
| CN102012817B (en) | Flex technology-based large public building energy consumption monitoring platform development method | |
| CN110080549B (en) | Protection decision-making method for wooden frame ancient architecture in architecture cultural heritage | |
| CN109670783A (en) | A kind of think tank, construction enterprises method for building up based on BIM | |
| CN104573231A (en) | BIM based smart building system and method | |
| CN116089555B (en) | CIM platform-based three-dimensional space data acquisition and light weight system and method | |
| CN110166525A (en) | Resource information processing management system applied to garden | |
| CN108846334A (en) | A kind of other automatic identifying method of the varieties of clouds and system | |
| CN110070624B (en) | Urban geomorphology feature identification method based on VR combined with eye movement tracking | |
| CN104021205B (en) | Method and device for establishing microblog index | |
| CN110083720B (en) | Method and device for constructing real scene semantic structure model | |
| Lu et al. | Design and implementation of virtual interactive scene based on unity 3D | |
| CN106611438B (en) | Local area updating and map cutting method and device of three-dimensional simulation map | |
| CN111210521A (en) | Ship giant data model lightweight method, system, terminal and medium for VR | |
| CN114820975A (en) | Three-dimensional scene simulation reconstruction system and method based on all-element parameter symbolization | |
| KR20120034383A (en) | Automatic map update system and method thereof | |
| CN104899426A (en) | Processing method and apparatus for high speed train indicator system | |
| CN114036603A (en) | Three-dimensional BIM (building information modeling) model optimization method for highway operation and maintenance period | |
| CN110992282A (en) | Automatic calibration and virtual repair method for temple mural diseases | |
| CN112632303A (en) | Distributed storage method, analysis method and device for image data | |
| KR100797518B1 (en) | System and method for reading forest image and fabricating digital forest map | |
| CN107589924A (en) | A kind of quick methods of exhibiting in remotely-sensed data mobile terminal of five layer of ten Pyatyi institutional framework |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200410 |
|
| WD01 | Invention patent application deemed withdrawn after publication |