CN109089008B - High-definition processing method and system for cadre personnel files based on DLS model - Google Patents
High-definition processing method and system for cadre personnel files based on DLS model Download PDFInfo
- Publication number
- CN109089008B CN109089008B CN201810846638.5A CN201810846638A CN109089008B CN 109089008 B CN109089008 B CN 109089008B CN 201810846638 A CN201810846638 A CN 201810846638A CN 109089008 B CN109089008 B CN 109089008B
- Authority
- CN
- China
- Prior art keywords
- image
- definition
- processing
- file
- scanning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 93
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 29
- 230000007547 defect Effects 0.000 claims description 27
- 238000012795 verification Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000005202 decontamination Methods 0.000 claims description 9
- 230000003588 decontaminative effect Effects 0.000 claims description 9
- 238000012550 audit Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000006748 scratching Methods 0.000 claims 2
- 230000002393 scratching effect Effects 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000003860 storage Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/00127—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture
- H04N1/00204—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture with a digital computer or a digital computer system, e.g. an internet server
- H04N1/00244—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture with a digital computer or a digital computer system, e.g. an internet server with a server, e.g. an internet server
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/38—Circuits or arrangements for blanking or otherwise eliminating unwanted parts of pictures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/387—Composing, repositioning or otherwise geometrically modifying originals
-
- 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
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a high-definition processing method and a high-definition processing system for cadre personnel files based on a DLS model, wherein the DLS model for image processing is constructed and used for recording and analyzing image boundary information, the square of an L2 model of a gradient is used as a regular constraint condition to constrain the gradient of the boundary, and a regular denoising algorithm and an image smooth distribution logic are introduced to ensure that the total variation is limited to be minimum while an optimal image is obtained; based on the image processing DLS model, original image scanning is carried out on the cadre personnel archive to obtain a scanning image, the scanning image is stored, and meanwhile, the obtained scanning image is transmitted to a server to be subjected to high-definition processing to obtain a high-definition image. The invention innovatively adopts an image high-definition processing technology, and avoids the problems of image color and shape distortion, reduced identification degree and the like caused by unreasonable application of an image acquisition technology.
Description
Technical Field
The invention relates to the technical field of archive image processing, in particular to a high-definition processing method and a high-definition processing system for cadre personnel archives based on a DLS model.
Background
While enjoying the convenience of modern archive management to work, some problems have been in the process of time delay. Because the cadre personnel's archives are deposited for a long time for the phenomenon in the aspects such as stain, fracture, distortion, shade, deformation often appears in the original image in the archives at the scanning in-process, thereby lead to image colour, the shape distortion in the archives, the degree of discernment descends, has increased the degree of difficulty for the work of characters identification to a great extent. Therefore, in the process of managing the cadre personnel file, the image in the file needs to be processed, and the degraded image is restored and restored to the maximum extent by applying the digital image processing technology.
Data of cadre personnel files need to be processed based on a national cadre index system and a technical specification framework framed by a data structure, and the requirements on safety and accuracy of data processing are high.
The existing image processing technology mainly has the following defects:
in the acquisition and processing of complex and high-precision requirement cadre personnel file original images in all existing file processing systems, firstly, the resolution is not high or the image is seriously deformed after the processing is finished, secondly, the influence of subjective factors of operators in the processing process is large, the processed file information is not accurate enough, and thirdly, the images can be compressed by a common image processing technology, so that the images are difficult to be completely and correctly restored and corrected in the later stage.
In summary, the conventional image processing technology cannot meet the requirements of image processing on the personnel files of the cadres.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a high-definition processing method of the cadre personnel archive based on a DLS (Data Live scattering Data real-time processing) model. And performing image high-definition processing on the basis of the new image high-definition processing DLS model.
A high-definition processing method for cadre personnel files based on a DLS model comprises the following steps:
constructing an image processing DLS model for recording and analyzing image boundary information, using the square of an L2 model of a gradient as a regular constraint condition to constrain the gradient of the boundary, and introducing a regularized denoising algorithm and an image smooth distribution logic to ensure that the total variation is limited to be minimum while the optimal image is obtained;
based on the image processing DLS model, original image scanning is carried out on the cadre personnel archive to obtain a scanning image, the scanning image is stored, and meanwhile, the obtained scanning image is transmitted to a server to be subjected to high-definition processing to obtain a high-definition image.
In a further preferred technical solution, the DLS model-based cadre personnel archive high-definition processing method further includes a step of performing matching verification on the high-definition image.
Further preferably, the image processing DLS model includes:
gradient algorithm:
wherein f refers to a degraded image, u represents an image to be restored, and λ is an equalization coefficient;
and (3) a weighted denoising algorithm:
wherein g is an original image, b is an equalization coefficient, and λ > 0.
Smooth distribution coefficient: and setting smooth and smooth distribution parameters.
Further, according to a preferred technical scheme, scanning the original image to obtain a scanned image and storing the scanned image, specifically:
the paper cadre personnel archive document is scanned into a digital image by setting and calling a scanner, and the image is preprocessed and verified and then uploaded to a server.
According to a further preferable technical scheme, a tree structure is generated according to calling logic, class files are displayed on a first layer, the class files are displayed on a second layer, and when the class files on the first layer are selected, downloading of the class image file data, uploading of the class image file data and emptying of the class image file data are achieved.
According to a further preferable technical scheme, when image data are uploaded, the number of the image files is verified, if errors are found, a verification list is automatically opened, and a verification result is displayed.
According to a further preferable technical scheme, when the image file is selected from the image list frame, the image browsing frame loads and displays the image file, and the image is viewed and the data processing is realized.
In a further preferred embodiment, when uploading an image file to the server, the server inserts a record in the RS _ describe _ XX table for each image file.
According to a further preferred technical scheme, when the server calls the scanner to scan, the server receives the image file transmitted from the scanner.
In a further preferred technical solution, the process of performing high-definition processing on the image in the server to obtain a high-definition image is as follows:
original file processing, comprising:
the arrangement sequence of the images is consistent with the original image ordering requirement;
the condition of picture image distortion can occur in the high-definition conversion process, and a scanned picture is moved to a high-definition image in an original image by using the function of 'picking the picture' to restore a distorted picture file;
starting image optimization, and enabling the image to be gradually changed and clear;
the original image processing defaults to be equal in width so as to ensure that the image is adapted in a full display mode;
and removing stains, black points and black edges of the image to realize high-definition conversion.
Further preferably, the process of removing stains, black spots and black edges from the image to realize high-definition conversion is as follows:
the method comprises the following steps: firstly, searching holes on a scanned image file, directly clicking the holes remained on the file, removing black holes, and removing binding holes;
step two: after the photo is scratched, removing the mottle of some original images of the scratched photo tape to change the original ground color of the high-definition image file, setting common settings and picture information settings in parameter settings of a system maintenance module in the range of removing the selected mottle, wherein the larger the value of the removed color is, the larger the removed color range is, the more the removed content is; the smaller the value is, the larger the range of removing similar colors is, and the less the content is removed;
step three: the method comprises the steps that a gamma value is needed to be set for removing stains, the larger the value is, the more stains are removed, the smaller the value is, the less stains are removed, the brightness of an interface is adjusted, the larger the value is, the smaller the brightness is, and the smaller the value is;
firstly, setting the height and width of a desmutting point, then selecting global decontamination or regional decontamination, and after the selection is finished, clicking the decontamination in high-definition image data;
step four: setting deviation correction parameters, wherein the deviation correction setting and the deviation correction setting in scanning have the same function, and one place is set in scanning or high-definition image manufacturing, and the two places are effective;
step five: high-definition parameters are set, and the system is internally provided with high-definition conversion parameters and is self-adjusted.
In a further preferred technical solution, after the high definition conversion, the processing steps are as follows:
the method comprises the following steps: and continuously blackening aiming at the unclear and black high-definition image fonts of the file handwriting.
Step two: the shape of a stamp to be scratched out is selected, and then the stamp to be scratched out, a rectangular stamp is scratched out, or a circular stamp is scratched out from the original image data.
Further, in a preferred embodiment, the matching check includes:
the method comprises the following steps: summarizing the audit conditions of the file catalog and the audit conditions of the file scanning files, processing the problem description submitted when the file catalog and the scanning file have problems, and marking the problem description as processed or deleting the problem description;
step two: the defects are as follows: catalogs and scan pieces; the defect types are: defects and missing pieces; the defect description list may be maintained manually: the "add defect description to list" can add defect descriptions, and the "delete list defect descriptions" can delete defect descriptions;
step three: the verification content comprises the following steps: checking the quantity of the high-definition images and the original images, checking that the basic information content is empty, and automatically generating an operation log after the checking is finished.
Based on DLS model cadre personnel archives high definition processing system, including the server, is used for carrying out the following step:
constructing an image processing DLS model for recording and analyzing image boundary information, using the square of an L2 model of a gradient as a regular constraint condition to constrain the gradient of the boundary, and introducing a regularized denoising algorithm and an image smooth distribution logic to ensure that the total variation is limited to be minimum while the optimal image is obtained;
based on the image processing DLS model, original image scanning is carried out on the cadre personnel archive to obtain a scanning image, the scanning image is stored, and meanwhile, high-definition processing is carried out on the obtained scanning image to obtain a high-definition image.
Compared with the prior art, the invention has the beneficial effects that:
the invention can adopt the double-version storage of the original image data and the high-definition image data (the double-version storage means that the original image and the processed image data are both stored in the server), and the high-definition image generated based on the original image filters the background into light yellow, thereby deepening the handwriting and the seal, enhancing the edge effect and removing the stains influencing reading.
The invention has high technical compatibility (the TWAIN protocol is called by the TWAIN protocol, the TWAIN protocol is an open protocol, and the equipment conforming to the TWAIN protocol can provide data for software calling a TWAIN interface), and is compatible with most TWAIN interface scanners and a part of professional scanners in the market.
The technology of the invention has simple and efficient image processing, practical image processing capacity, batch high-definition conversion function (batch pictures are processed in a BS program in a compressed packet mode), and intelligent data packaging and distributing function (realized by DVR6104K-PL data batch processing technology).
The invention has mature system, strong anti-interference capability in the image high-definition processing process, effectively prevents the influence of network attack, virus and the like, does not cause the reduction of image quality through a series of operations such as correction, decontamination and the like, (the invention corrects the rgb value of a blurred region of an image and does not reduce the image quality.)
According to the method, the image processing DLS model is constructed, parameters are transmitted in the image processing process, the algorithm of the DLS model is called, high-definition processing is carried out on the image, the image processing is carried out by using the same standard, and the influence of artificial subjective factors is eliminated. The same criteria refer to: and uniformly transmitting parameters under a DLS model, and processing images according to the same algorithm.
The invention innovatively adopts an image high-definition processing technology, and avoids the problems of image color and shape distortion, reduced identification degree and the like caused by unreasonable application of an image acquisition technology.
Aiming at special problems of file damage, holes and the like, the invention provides hidden attributes of original image extraction and optimization, and solves the problems.
The invention inspects the processed image page, and comprehensively inspects the quality of file splitting, scanning, correcting, decontaminating, inserting picture, processing picture, matching text and image page, etc.
In the invention, the DLS model sets classification standards and parameters for successful image processing, and unqualified archival images are obtained if the classification standards and parameters are not in accordance with the standards. Therefore, the unqualified archival images can be automatically found and automatically optimized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a block diagram of an overall architecture of an embodiment of the present application;
fig. 2 is a schematic diagram of detailed processing logic of an original image according to an embodiment of the present application.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In a typical embodiment of the present application, a method for high-definition processing of cadre personnel files based on a DLS model is provided, and the present patent provides an archive image DLS processing model for cadre personnel files by analyzing the current situation of the archive image processing model, wherein the DLS model can meet the application requirements of image information acquisition of the cadre personnel files. A simple image high-definition processing technology is established on the basis of a new image high-definition processing DLS model, a background can be filtered into faint yellow based on a high-definition image generated by an original image, handwriting and a seal are deepened, the edge effect is enhanced, stains influencing reading are removed, and the like, so that the sensitive cadre archive original image processing work is more efficient. The archives for each individual can be processed in batches.
In this embodiment of the present application, the system is divided into DLS model design and logic implementation layers, as shown in fig. 1. Wherein DLS is English abbreviation of Data Live scattering, and Chinese meaning is: and (5) processing the data in real time.
In the design level of a DLS model, image boundary information is recorded and analyzed, the square of an L2 model of the gradient is used as a regular constraint condition to constrain the gradient of the boundary, and a regularized denoising algorithm and an image smooth distribution logic are introduced, so that the total variation is limited to be minimum while the optimal image is obtained. The total variation is "a comparison value of the error before and after the processing". The model L2 is used to detect and segment images and is a tool for identifying image files.
When the DLS model is built, 43 situations such as inclination, stain, blur, water overflow and yellow pages are preset, and different background processing modes are triggered under different situations.
The logic implementation layer mainly implements functions through 3 parts of components such as original image scanning, background processing, matching verification and the like.
Scanning an original image: corresponding adjustment is carried out according to the actual condition of the original, such as the processing of an oversized page, the processing of the depth and the thickness of the paper color, and the resolution, the threshold value, the brightness, the scanning mode and the scanning speed of the image can be adjusted according to the conditions of different original images during scanning, so that the original can be undamaged under the condition of clear quality of the scanned image.
Background processing: according to the quality of the original manuscript, the background automatically starts batch processing functions of inclination correction, automatic decontamination, automatic document division and the like, and the perfection of the image quality is guaranteed.
Matching and checking: and the image pages after the scanning treatment are subjected to matching inspection, the quality of file splitting, scanning, correcting, decontaminating, inserting, processing of pictures, matching of texts and image pages and the like is comprehensively inspected, and logs can be automatically reminded and registered to facilitate reprocessing when the verification is unqualified.
The invention relates to a high-definition image processing technology of a cadre personnel file based on a DSL model, which applies an image gradient algorithm, has higher processing speed and higher definition of a processed image, and realizes intelligent generation, processing, identification, matching and verification of an original image of the cadre personnel file.
Specifically, regarding the DLS model:
gradient algorithm: the gradient of the image boundary is generally relatively large, and the least square of the L2 modulus of the gradient is taken as a regular constraint condition, and the problem of unconditional approximation is the following gradient algorithm:
where f refers to a degraded image, u represents the image to be reconstructed, and λ is the equalization coefficient, the objective of the gradient algorithm is not to deviate the reconstructed image too much from the degraded image.
And (3) denoising the graph: combining with a gradient algorithm, providing a weighted noise model, and then gradually calculating the total variation of the optimal image according to a graph denoising method, wherein a target equation of the weighted denoising algorithm is as follows:
where u represents an image to be restored, g is an original image, b is an equalization coefficient, and λ > 0.
Smooth distribution coefficient: and (3) calling an image denoising method by using gradient algorithm logic, and finding that the image still has less obvious blurring through actual comparison. Smooth-taking smooth distribution parameters need to be set, fuzzy details can be wiped off, and boundaries can be well maintained.
2. Raw image scanning
The paper document is scanned into a digital image by setting and calling a scanner, and the image is processed and verified and then uploaded to a server.
2.1 generating tree structure according to calling logic, the first layer displaying class files and the second layer displaying the files of the class. When the class file of the first layer is selected, the right-click popup menu is clicked, so that the downloading of the class image file data, the uploading of the class image file data and the emptying of the class image file data can be realized.
2.2 when uploading the image data to the server, checking the number of the image files, if an error is found, automatically opening a checking list and displaying a checking result. The verification list server is established during initialization and updated in an untimed manner at the later stage.
2.3 when an image file is selected in the image list box, the image browsing box loads and displays the image file. The image can be viewed in an enlarged mode, a reduced mode, an actual size, a height and a width. And the image can be simply processed by clockwise rotation, anticlockwise rotation, rotation at any angle, removal of the selected area, removal of the outer frame, edge cutting and the like.
2.4 the special configuration requirements of the server for uploading and downloading the images are as follows: an RS _ describe _ XX table, which is a picture processing information record, and is called by the BS program in a background when viewing the processing record, wherein:
ARCHID: file ID;
RSID: the foreign key corresponds to an RS _ INFO table;
SXH: a sequence number;
PATH: a storage path;
oldfilenme: the original file name;
NEWFILENAME: a new file name;
UPTIME: modifying the time;
LENGTH: the size of the original version file;
GAOQINGLENGTH: and (5) high-definition version file size.
When uploading an image file, the server inserts a record in the RS _ describe _ XX table for each image file.
When the system calls the scanner to scan, the server receives the image file transmitted from the scanner and stores the scanned image in the local computer storage device.
The detailed processing logic of the raw image is shown in fig. 2.
3. Background processing
Background high-definition processing is carried out on the scanned original image data of the personnel file, wherein the background high-definition processing comprises decontamination, correction, deviation correction, size adjustment, angle adjustment and the like.
3.1 raw document processing
The method comprises the following steps: the arrangement sequence of the images is consistent with the original image ordering requirement; here and in the following the original image refers to the scanned image.
Step two: the situation of picture image distortion can occur in the high-definition conversion process, and a scanned picture can be moved to a high-definition image in an original image by using the function of 'picking the picture', so that a distorted picture file can be restored. The scratched photo can be obtained by processing a jQueryyphotoClip picture clipping plug-in.
Step three: and an image optimization function of displaying an original image is provided, and the image is gradually changed and becomes clear after the image optimization is started.
Step four: the original image processing defaults to the same width so as to ensure the adaptation of the mode of displaying the image completely.
3.2 the image is clear, straight and clean after being observed by naked eyes after stain, black spots and black edges are removed;
the method comprises the following steps: the holes on the scanned image file are searched firstly, the holes remained on the file are directly clicked, the holes are processed by a hole point repairing tool, the black holes are removed, and then the binding holes can be removed.
Step two: after the photo is scratched, the original image can be taken with the mottle, and the color can be removed to become the original ground color of the high-definition image file. The range of removing the selected variegated color can be set in the parameter setting of the system maintenance module, namely common setting, picture information setting, wherein the larger the value of the color removing size is, the larger the color removing range is, and the more the content is removed; the smaller the value, the larger the range of removed similar colors, and the less the content removed
Step three: the removal of stains requires setting of gamma values, and the larger the value, the more the stains are removed, and the smaller the value, the less the stains are removed. And adjusting the brightness of the interface, wherein the larger the value is, the smaller the brightness is, and the smaller the value is, the larger the brightness is.
Firstly, setting the height and width of the desmutting point, then selecting global desmutting or regional desmutting, and after the selection is finished, clicking desmutting in high-definition image data.
Step four: and setting a deviation correction parameter, wherein the deviation correction setting and the deviation correction setting in scanning have the same function, and one place is set in scanning or high-definition image manufacturing, and the two places are effective.
Step five: high-definition parameters are set, and the system is internally provided with high-definition conversion parameters and can be automatically adjusted.
3.3 the image cannot be too thick or too thin compared with the original image, and the handwriting is clear.
The method comprises the following steps: after high-definition conversion, some file handwriting is still unclear, and special blackening is needed, and high-definition image fonts can be blackened or blackened continuously.
Step two: rectangular stamps and circular stamps can be scratched, the shape of the stamp to be scratched is selected, and then the stamp to be scratched is selected in original image data.
4. Match check
The matching verification of the high-definition image processing comprises the following steps: and performing operations such as image verification, automatic file missing recording, verification and the like on the high-definition image electronic file, and automatically filling verification conditions, working logs and the like.
The method comprises the following steps: and summarizing the file directory audit condition and the file scanning file audit condition. The problem description submitted when the problem exists in the file material catalog and the scanning piece can be marked as processed, and can also be deleted.
Step two: the defects are as follows: catalogs and scan pieces; the defect types are: defects and missing pieces; the defect description list may be maintained manually: the "add defect description to list" may add a defect description, and the "delete list defect description" may delete a defect description. The defects refer to stains, fuzzy characters and the like, and the missing parts refer to holes, breakage and the like; and (4) setting classification standards and parameters by a DLS model, and mainly carrying out program processing and manual assistance.
Step three: the verification content comprises the following steps: checking the quantity of high-definition images and original images (checking through a counter), checking basic information content to be empty (mainly checking by a program, setting checking standards and parameters by a DLS (digital Living system) model and manually assisting checking), and automatically generating an operation log after checking is finished.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (4)
1. A high-definition processing method for cadre personnel files based on a DLS model is characterized by comprising the following steps:
constructing an image processing DLS model for recording and analyzing image boundary information, using the square of an L2 model of the gradient as a regular constraint condition to constrain the gradient of the boundary, and introducing a weighted denoising algorithm and an image smooth distribution logic to ensure that the total variation of pixel difference before and after archive processing is limited to be minimum while obtaining an optimal image;
based on the image processing DLS model, scanning the original image of the cadre personnel file to obtain a scanned image and storing the scanned image, and simultaneously transmitting the obtained scanned image to a server to perform high-definition processing to obtain a high-definition image;
the high-definition processing method for the cadre personnel file based on the DLS model comprises three parts, namely original image scanning, background processing and matching verification;
an original image scan comprising:
generating a tree structure according to calling logic, wherein a first layer displays class files, a second layer displays the class files, and when the class files of the first layer are selected, downloading the class image file data, uploading the class image file data and emptying the class image file data are realized;
when uploading image data, checking the number of image files, if errors are found, automatically opening a checking list, and displaying a checking result;
when an image file is selected in the image list box, the image browsing box loads and displays the image file to realize the viewing and data processing of the image;
background processing, wherein the process of removing stains, black points and black edges of the image to realize high-definition conversion comprises the following steps:
the method comprises the following steps: firstly, searching holes on a scanned image file, directly clicking the holes remained on the file, removing black holes, and removing binding holes;
step two: after the photo is scratched, the mottle of the original image of the scratched photo tape is removed, the original ground color of the high-definition image file is changed, the range of the removed mottle is larger in the common setting and the picture information setting of the parameter setting of the system maintenance module, the value of the removed color size is larger, the removed color range is larger, and the removed content is more; the smaller the value of 'removing color size' is, the larger the range of removing similar color is, and the less the content is removed;
step three: the stain removal needs to be set with a gamma value, the larger the gamma value is, the more stain removal is performed, the smaller the gamma value is, the less stain removal is performed, the brightness of the interface is adjusted, the larger the gamma value is, the smaller the brightness is, and the smaller the gamma value is, the larger the brightness is;
firstly, setting the height and width of a desmutting point, then selecting global decontamination or regional decontamination, and after the selection is finished, clicking the decontamination in high-definition image data;
step four: setting deviation correction parameters, wherein the deviation correction setting and the deviation correction setting in scanning have the same function, and one place is set in scanning or high-definition image manufacturing, and the two places are effective;
step five: setting high-definition parameters, setting high-definition conversion parameters in the system, and automatically adjusting;
after high-definition conversion, the processing steps are as follows:
the method comprises the following steps: continuously blackening the unclear and black high-definition image fonts of the file handwriting;
step two: selecting the shape of a stamp to be scratched out, then selecting the stamp to be scratched out from original image data, scratching a rectangular stamp or scratching a circular stamp;
matching and checking, comprising:
the method comprises the following steps: summarizing the audit conditions of the file catalog and the audit conditions of the file scanning files, processing the problem description submitted when the file catalog and the scanning file have problems, and marking the problem description as processed or deleting the problem description;
step two: the defects are as follows: catalogs and scan pieces; the defect types are: defects and missing pieces; the defect description list may be maintained manually: the "add defect description to list" can add defect descriptions, and the "delete list defect descriptions" can delete defect descriptions;
step three: the verification content comprises the following steps: checking the quantity of the high-definition images and the original images, checking that the basic information content is empty, and automatically generating an operation log after the checking is finished;
constructing an image processing DLS model, transmitting parameters in the image processing process, calling an algorithm of the DLS model, performing high-definition processing on images, and performing image processing by using the same standard to eliminate the influence of artificial subjective factors, wherein the same standard refers to the following steps: and uniformly transmitting parameters under a DLS model, and processing images according to the same algorithm.
2. The DLS model cadre personnel archive high definition processing method as claimed in claim 1, wherein scanning of the original image to obtain the scanned image and storing the scanned image is performed, specifically:
the paper cadre personnel archive document is scanned into a digital image by setting and calling a scanner, and the image is preprocessed and verified and then uploaded to a server.
3. The DLS model-based cadre personnel archive high definition processing method of claim 1, wherein when uploading image files to the server, the server inserts a record in the image processing information record table for each image file;
when the server calls the scanner to scan, the server receives the image file transmitted from the scanner.
4. The DLS model cadre personnel archive high definition processing method as claimed in claim 1, wherein the process of performing high definition processing on the image in the server to obtain a high definition image further comprises:
original file processing, comprising:
the arrangement sequence of the images is consistent with the original image ordering requirement;
the condition of picture image distortion can occur in the high-definition conversion process, and a scanned picture is moved to a high-definition image in an original image by using the function of 'picking the picture' to restore a distorted picture file;
starting image optimization, and enabling the image to be gradually changed and clear;
the original image processing defaults to the same width so as to ensure the adaptation of the mode of displaying the image completely.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846638.5A CN109089008B (en) | 2018-07-27 | 2018-07-27 | High-definition processing method and system for cadre personnel files based on DLS model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846638.5A CN109089008B (en) | 2018-07-27 | 2018-07-27 | High-definition processing method and system for cadre personnel files based on DLS model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109089008A CN109089008A (en) | 2018-12-25 |
| CN109089008B true CN109089008B (en) | 2021-01-22 |
Family
ID=64833270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810846638.5A Active CN109089008B (en) | 2018-07-27 | 2018-07-27 | High-definition processing method and system for cadre personnel files based on DLS model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109089008B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886974B (en) * | 2019-01-28 | 2021-06-11 | 北京易道博识科技有限公司 | Seal removing method |
| CN113793264B (en) * | 2021-09-07 | 2022-11-15 | 北京航星永志科技有限公司 | Archive image processing method and system based on convolution model and electronic equipment |
| CN114155156A (en) * | 2021-10-15 | 2022-03-08 | 杭州京胜航星科技有限公司 | Method for processing digitized image and related device |
| CN116976735A (en) * | 2023-08-01 | 2023-10-31 | 深圳市畅飞扬信息系统有限公司 | File digital quality detection and improvement method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049815A (en) * | 2012-12-14 | 2013-04-17 | 深圳供电局有限公司 | Customer file information management system and method |
| CN105681620B (en) * | 2016-02-05 | 2019-01-15 | 苏州市千尺浪信息技术服务有限公司 | Pictograph acquires integral system |
-
2018
- 2018-07-27 CN CN201810846638.5A patent/CN109089008B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109089008A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109089008B (en) | High-definition processing method and system for cadre personnel files based on DLS model | |
| US8340452B2 (en) | Automatic generation of a photo guide | |
| JP5001256B2 (en) | System and method for processing scanned data | |
| US6233364B1 (en) | Method and system for detecting and tagging dust and scratches in a digital image | |
| US6757081B1 (en) | Methods and apparatus for analyzing and image and for controlling a scanner | |
| US20130208995A1 (en) | Image Defect Map Creation Using Batches of Digital Images | |
| DE102004029976A1 (en) | System and method to allow undo of certain modifications to a digital image | |
| DE69713977T2 (en) | Method and device for retouching a digital color image | |
| CN103093298A (en) | Multi-version digital archive management and application method for image or video file | |
| US20150324958A1 (en) | Method for sliced inpainting | |
| CN1691743A (en) | Method for red eye correction, program, and device thereof | |
| JP2009268085A (en) | Image trimming device and program | |
| WO2001063558A2 (en) | System and method for image processing | |
| WO2006048117A1 (en) | Method for using portable electronic equipment, which comprises a digital camera or can be connected to a digital camera, to scan a surface containing text and/or drawings or sketches | |
| Gargano et al. | A perceptual approach to the fusion of visible and NIR images in the examination of ancient documents | |
| US8457448B2 (en) | Removing inserted text from an image using extrapolation for replacement pixels after optical character recognition | |
| WO2008137056A1 (en) | Automatic image enhancement | |
| US7277589B2 (en) | Image retouching method, apparatus, and program storage medium, image correcting method, apparatus, and program storage medium, and eye detecting and correcting method apparatus, and program storage medium | |
| DE10344074B4 (en) | Manipulating digital images based on a user profile | |
| CN116630203B (en) | Integrated imaging three-dimensional display quality improving method | |
| Van Dormolen | Metamorfoze preservation imaging guidelines | |
| US7215825B2 (en) | Image-generating method and image-generating system | |
| Bayer et al. | Digital microscopy in phycological research, with special reference to microalgae | |
| JP2005063022A (en) | Noise pixel map producing method, device performing the same, program, and photograph printing device | |
| CN104715248B (en) | A kind of recognition methods to email advertisement picture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Yinhe building, 2008 Xinluo street, high tech Industrial Development Zone, Jinan City, Shandong Province, 250098 Patentee after: Shandong luruan Digital Technology Co.,Ltd. Address before: No.185, Jingsi Road, Shizhong District, Jinan City, Shandong Province Patentee before: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |