CN113642557A - System and method for supplementing historical data in airworthiness field - Google Patents
System and method for supplementing historical data in airworthiness field Download PDFInfo
- Publication number
- CN113642557A CN113642557A CN202110910905.2A CN202110910905A CN113642557A CN 113642557 A CN113642557 A CN 113642557A CN 202110910905 A CN202110910905 A CN 202110910905A CN 113642557 A CN113642557 A CN 113642557A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- template
- character
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000001502 supplementing effect Effects 0.000 title claims description 10
- 238000012545 processing Methods 0.000 claims abstract description 57
- 230000009467 reduction Effects 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000013479 data entry Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 description 12
- 230000008569 process Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Character Input (AREA)
Abstract
The invention discloses a history data additional recording system and method in the airworthiness field, which comprises an input module, an image preprocessing module, an image-text analysis and identification module, a character identification module and a template identification additional recording module which are sequentially connected, wherein the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binaryzation module, and the character identification module is used for performing character identification on a character area in a binaryzation image and extracting character data; the template identification and additional recording module comprises a template comparison module, a keyword extraction module and an entry module, wherein the template comparison module is used for comparing and finding the corresponding certificate template, and the keyword extraction module is used for extracting keywords from character data corresponding to the character area of the binary image according to the certificate template and entering data through the entry module. The invention reduces the error rate and labor cost of manual data logging, improves the efficiency and quality of data logging, can store the original data and is convenient for timely tracing.
Description
Technical Field
The invention relates to the field of airworthiness approval operation management, in particular to a historical data supplement system and method in the airworthiness field.
Background
In order to better serve national major strategies such as 'big aircraft engineering' and the like, practically guarantee civil aviation safety and promote the approval work of national key model items such as large airliners and the like, the requirements of an implementation party group on strengthening a seaworthy approval system and improving seaworthy approval ability are met, and a seaworthy approval operation management system is developed at will. In the past time, all management organizations issue certificates in an offline mode, so that a large number of paper certificates are generated, and in order to guarantee the normal operation of the airworthiness approval operation management system, historical certificate data needs to be imported into the system. Therefore, in the process of program construction, how to ensure accurate supplementary recording of the historical data and improve the supplementary recording efficiency of the historical data become a problem which needs to be paid attention to. The airworthiness field has huge data volume of historical certificates, and is easy to make mistakes by manual entry, time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to overcome the problems of the conventional historical data supplement and record, provides a historical data supplement and record system and method in the airworthiness field, and aims to reduce the workload of recording certificate information of related management mechanisms and improve the historical data supplement and record efficiency of each working unit.
The purpose of the invention is realized by the following technical scheme:
a seaworthiness field historical data additional recording system comprises an input module, an image preprocessing module, an image-text analysis and identification module, a character identification module and a template identification additional recording module which are sequentially connected, wherein the input module is used for inputting images, and the images comprise scanning pieces and/or photos; the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module is used for graying an image and carrying out weighted average on the grayed image, the image noise reduction module is used for carrying out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the image binarization module is used for carrying out binarization processing on the image processed by the image noise reduction module according to a threshold value and obtaining a binarization image; the image-text analysis and identification module is used for respectively identifying a picture area and a character area of the binary image and extracting a character area, and the character identification module is used for identifying characters in the character area of the binary image and extracting character data; the module is drawed in additional including template comparison module, keyword and types the module in template discernment, the module storage is compared to the template has certificate template database, contains a plurality of certificate template in the certificate template database, and the template is compared the module and is used for comparing and finding the certificate template that corresponds in certificate template database according to the picture region of binary image, characters region, keyword draw the module and compare the certificate template that the module found according to the template and carry out the keyword extraction and carry out data entry through type the module to the regional corresponding text data of binary image characters.
In order to better realize the airworthiness field historical data supplementary recording system, the graying processing module carries out graying processing according to R, G, B three channels of the image, the graying processing module carries out weighted average processing on each pixel of the image according to a formula (1),
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image.
The invention discloses a preferable technical scheme of a history data supplement system in the airworthiness field, which comprises the following steps: the character recognition module establishes a Tesseract character recognition engine, performs character recognition through the Tesseract character recognition engine and extracts character data.
The invention discloses a preferable technical scheme of a history data supplement system in the airworthiness field, which comprises the following steps: the entry module comprises an entry window module.
A method for supplementing historical data in the airworthiness field comprises the following steps:
A. inputting an image through an input module, wherein the image is an R, G, B three-channel color image, and the image comprises a scanning piece and/or a photo (the scanning piece is various airworthiness certificate scanning pieces, and the photo is various airworthiness certificate photos);
B. the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module grays the image according to R, G, B three-channel pixel values, and the R, G, B three-channel pixel values are all 0-255; and performs weighted average processing according to formula (1) for each pixel of the image,
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image;
C. the image noise reduction module carries out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the Gaussian filtering noise reduction processing adopts Gaussian low-pass filtering to carry out noise reduction; the image binarization module is used for carrying out binarization processing on the image processed by the image denoising module according to a threshold value to obtain a binarized image, wherein the gray value of the pixel which is greater than or equal to the threshold value after binarization is 255, and the gray value of the pixel which is smaller than the threshold value after binarization is 0;
D. the image preprocessing module transmits the processed binary image to the image-text analysis and identification module, and the image-text analysis and identification module performs image area and character area identification processing on the binary image and extracts a character area; establishing a Tesseract character recognition engine through a character recognition module to perform character recognition on a character area in the binary image and extracting character data;
E. the image preprocessing module and the character recognition module are respectively connected with a template recognition and additional recording module, the template recognition and additional recording module comprises a template comparison module, a keyword extraction module and an entry module, a certificate template database is stored in the template comparison module, a plurality of certificate templates are contained in the certificate template database, the template comparison module compares the image region and the character region of the binary image in the certificate template database and finds the corresponding certificate template, and the keyword extraction module extracts keywords from the character data corresponding to the character region of the binary image according to the certificate template found by the template comparison module and performs data entry through the entry module.
The preferred technical scheme of the method for supplementing historical data in the airworthiness field is as follows: and the template comparison module performs image identification according to the picture area of the binary image and performs comparison identification on the certificate template by combining key data of the character area of the binary image.
The preferred technical scheme of the method for supplementing historical data in the airworthiness field is as follows: the keyword extraction module is used for extracting keywords from the character data and removing useless information data; and the input module is used for inputting data according to the structure of the certificate template.
The preferred technical scheme of the method for supplementing historical data in the airworthiness field is as follows: the method for supplementing historical data in the airworthiness field further comprises the following steps:
F. the entry module is provided with an entry window module, and the certificate module is directly selected through the entry window module and data is input for entry.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) the invention can process the input images such as scanning pieces and/or photos, then carries out template comparison through the template recognition and additional recording module to select the correct template, extracts key information according to the template structure to realize the additional recording operation of data, greatly improves the additional recording working efficiency, reduces the labor cost and the error probability, can store the original data and is convenient for timely tracing.
(2) The invention greatly reduces the error rate of manual data supplement and recording, remarkably reduces the workload of the workers for data supplement and recording, enables the working gravity center of the workers to be separated from the complex information arrangement and recording, and improves the efficiency of the whole data supplement and recording.
Drawings
FIG. 1 is a schematic structural block diagram of a history data additional recording system in the airworthiness field of the present invention;
FIG. 2 is a schematic flow chart of a method for supplementing historical data in the airworthiness field according to the present invention;
FIG. 3 is a first example of a data entry application of the present invention;
FIG. 4 is a second example of the application of data supplement according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples:
examples
As shown in fig. 1, a seaworthiness field historical data additional recording system comprises an input module, an image preprocessing module, an image-text analysis and identification module, a character identification module and a template identification additional recording module which are connected in sequence, wherein the input module is used for inputting images, and the images comprise scanned parts and/or photos; the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module is used for graying an image and carrying out weighted average on the grayed image, the image noise reduction module is used for carrying out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the image binarization module is used for carrying out binarization processing on the image processed by the image noise reduction module according to a threshold value and obtaining a binarization image; the image-text analysis and identification module is used for respectively identifying a picture area and a character area of the binary image and extracting a character area, and the character identification module is used for identifying characters in the character area of the binary image and extracting character data; the module is drawed in additional including template comparison module, keyword and types the module in template discernment, the module storage is compared to the template has certificate template database, contains a plurality of certificate template in the certificate template database, and the template is compared the module and is used for comparing and finding the certificate template that corresponds in certificate template database according to the picture region of binary image, characters region, keyword draw the module and compare the certificate template that the module found according to the template and carry out the keyword extraction and carry out data entry through type the module to the regional corresponding text data of binary image characters.
According to an embodiment of the airworthiness domain history data entry system of the present invention, the graying processing module performs graying processing according to R, G, B channels of the image, the graying processing module performs weighted average processing on each pixel of the image according to formula (1),
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image.
According to one embodiment of the airworthiness field historical data supplement system, the text recognition module establishes a Tesseract text recognition engine, performs text recognition through the Tesseract text recognition engine, and extracts text data.
According to one embodiment of the airworthiness field historical data entry system, the entry module comprises an entry window module.
A method for supplementing historical data in the airworthiness field comprises the following steps:
A. inputting an image through an input module, wherein the image is an R, G, B three-channel color image, the image comprises a scanning piece and/or a photo, the scanning piece is a seaworthy certificate scanning piece of various types, and the photo is a seaworthy certificate photo of various types;
B. the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module grays the image according to R, G, B three-channel pixel values, and the R, G, B three-channel pixel values are all 0-255; and performs weighted average processing according to formula (1) for each pixel of the image,
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image;
in this embodiment, the scanned or photographed image is an R, G, B three-channel color image (i.e., an image input by the input module), the pixel level of each channel is 256 orders of magnitude from 0 to 255, and the graying is to change the three-channel color image into a single-channel image, i.e., the brightness of 0 to 255 gradually increases. The color image is divided into three components, r (red), g (green), and b (blue), and the color image displays red, green, and blue, respectively, and the graying is a process of equalizing R, G, B components of the color image. And carrying out graying processing on the image by adopting a weighted average algorithm. The weighted average method is selected according to the formula WrR + WgG + WbB, wherein Wr, Wg and Wb are weight values of R, G, B, and different gray level images are generated by selecting different values. In the embodiment, the parameter COLOR _ BGR2GRAY of the cvtColor function in the openCV realizes image graying, and at this time, the following parameters are selected in the embodiment: the best grayscale image is obtained by setting the weights to Wr to 0.299, Wg to 0.587 and Wb to 0.114. The value of R, G, B is weighted and averaged, and the amount of data in the image is reduced by graying.
C. The image noise reduction module carries out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the Gaussian filtering noise reduction processing adopts Gaussian low-pass filtering to carry out noise reduction; and the image binarization module is used for carrying out binarization processing on the image processed by the image denoising module according to a threshold value to obtain a binarized image, wherein the gray value of the pixel which is greater than or equal to the threshold value after binarization is 255, and the gray value of the pixel which is smaller than the threshold value after binarization is 0.
In the embodiment, the scanning hardware of the scanning element causes a plurality of noise points on the image, and aiming at the characteristic, the image denoising module adopts Gaussian low-pass filtering denoising to achieve an ideal image effect. A gaussian low pass filter (gaussian lowpass filter) is a linear smoothing filter with a transfer function that is a gaussian function, also because gaussian functions are normally distributed density functions. The gaussian low-pass filter is very effective for removing noise that follows normal distribution (Normaldistribution), and since an image is generally a two-dimensional signal, image denoising generally uses a two-dimensional gaussian function as a transfer function, and the gaussian function has separable characteristics, so that the two-dimensional gaussian function is reduced to one-dimensional gaussian filtering by performing gaussian filtering on rows and columns.
In this embodiment, the gray value of a pixel point on an image is set to 0 or 255, that is, the image is not black or white, and the final image exhibits the effect of only black and white. In this embodiment, the gray-scale picture is divided into two categories, namely a foreground category and a background category, according to the gray-scale value of the pixel by an adaptive threshold value calculation algorithm (also called "tsu", abbreviated as OTSU45 "), and the degree of significance of the difference between the foreground and the background is determined by calculating the inter-class variance (intra-class variance) of the two categories. And the class division boundary for making the inter-class variance optimal is searched as an optimal threshold. All pixels with the gray levels larger than or equal to the threshold are judged to belong to the specific object, the gray level of the pixels is 255 for representation, otherwise the pixels are excluded from the object area, the gray level is 0, and the pixels represent the background or the exceptional object area.
D. The image preprocessing module transmits the processed binary image to the image-text analysis and identification module, and the image-text analysis and identification module performs image area and character area identification processing on the binary image and extracts a character area. The image-text analysis and identification module identifies the text area and the picture area in the image through layout analysis, carries out attribute calibration, and can directly process the text area during subsequent character detection.
Establishing a Tesseract character recognition engine through a character recognition module to perform character recognition on a character area in the binary image and extracting character data; according to one embodiment of the airworthiness field historical data additional recording method, the keyword extraction module is used for extracting keywords from character data and removing useless information data; and the input module is used for inputting data according to the structure of the certificate template. The Tesseract character recognition engine has very high recognition accuracy, finds block areas and text lines and words by analyzing connected areas, and obtains recognition results by four steps of character recognition.
E. The image preprocessing module and the character recognition module are respectively connected with a template recognition and additional recording module, the template recognition and additional recording module comprises a template comparison module, a keyword extraction module and an entry module, a certificate template database is stored in the template comparison module, a plurality of certificate templates are contained in the certificate template database, the template comparison module compares the image region and the character region of the binary image in the certificate template database and finds the corresponding certificate template, and the keyword extraction module extracts keywords from the character data corresponding to the character region of the binary image according to the certificate template found by the template comparison module and performs data entry through the entry module. According to one embodiment of the airworthiness field historical data additional recording method, the template comparison module carries out image identification according to the picture area of the binary image and carries out comparison identification on the certificate template by combining key data of the character area of the binary image.
After the text recognition result is obtained, because the invention only needs to record key information on some certificates, the recognized text information needs to be filtered, useless information in the text is removed, and key information is extracted.
In template comparison, the problems of the airworthiness certificate can be found through the integral analysis of the airworthiness certificate:
a: the certificate file has large historical data volume and large format difference of different types of certificates;
b: multiple historical versions exist in the same type of certificate;
aiming at the problem, the invention can manufacture different license templates, and extracts structured data through the matching of the license templates to complete the integration of historical data. Key information required by a user in the certificate is replaced and manufactured into a certificate template of a corresponding version in a fixed format variable mode, for example: the certificate information is (number 001, model 001) the template can be labeled (number [ certificateNumber ], [ model ]). The template comparison is that the result of the character recognition processing is matched with the template content to find the certificate template corresponding to the certificate.
When extracting the keywords, comparing the template matched by template comparison with the character recognition result to remove useless information in the text, extracting certificate contents corresponding to the fixed format variables on the template by a keyword extraction module, carrying out structuralization processing on the extracted keywords, and returning effective data required by the airworthiness field historical data supplement system.
In practical use, the system of the invention can adopt a three-layer system architecture technology: the functional modules are divided into three layers of structures, namely a presentation layer (UI), a Business Logic Layer (BLL) and a Data Access Layer (DAL), the layers are mutually accessed by adopting interfaces, an entity class (Model) of an object Model is used as a carrier for data transmission, the entity classes of different object models generally correspond to different tables of a database, and the attribute of the entity class is consistent with the field name of the database table. The three-layer architecture is used for distinguishing the hierarchical architecture, so that the programming idea of high cohesion and low coupling is realized, the dependence between layers is reduced, the layers are independent, the program is easier to transplant and maintain, the standardization and the multiplexing of logic of each layer are facilitated, and meanwhile, a user side can only call a data access layer through a service logic layer, so that the entry points are reduced, and the system safety is improved. Meanwhile, the application service in the system is suitable for a micro-service architecture, the service can be registered in a registration center and deployed in a plurality of application server virtual machines, load balance is realized, reasonable workload is distributed to the plurality of virtual machines, the disaster tolerance processing capacity of the system is enhanced, the system performance is optimized, and the service computing capacity is greatly improved.
According to an embodiment of the seaworthiness field historical data entry method of the present invention, the seaworthiness field historical data entry method further includes the following steps:
F. the entry module is provided with an entry window module, and the certificate module is directly selected through the entry window module and data is input for entry. As shown in fig. 3, in the airworthiness field history data additional recording system and method (the specific implementation module is an entry window module), when a user manually additionally records a form (a first example of an additional recording interface is shown in fig. 3), the user clicks the security capability in a left menu bar, an item additional recording module, and selects an item to be additionally recorded, the user can enter an item additional recording page, and after selecting a corresponding additional recording process, the user can select to manually fill related information of the item, or can click a scanning piece or a photo of an uploaded paper file in a file identification area at the lower left corner, character identification is performed by the system, the scanning piece or the photo is matched with a certificate template, related structured data of the page is screened out, and the structured data is automatically filled into a corresponding input box.
As shown in fig. 4, in the airworthiness field history data entry system and method of the present invention (the input module may be used to upload an image), the automatic entry form data (the present invention performs automatic entry processing according to the uploaded image) is automatically entered, after the user selects an item to be entered, a scanned part or a scanned picture of a paper document related to the item is uploaded, for example, in the TC process, after the user uploads an application form, accepts a notice, a model pass and a model pass attachment, the user clicks the next step, after the system automatically identifies according to the uploaded document, the screened structured data is automatically classified, and a new item is created according to the identified information. And the user completes the project information, thereby completing project additional entry.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. The utility model provides a seaworthiness field historical data additional recording system which characterized in that: the system comprises an input module, an image preprocessing module, an image-text analysis and identification module, a character identification module and a template identification and additional recording module which are connected in sequence, wherein the input module is used for inputting images, and the images comprise scanning pieces and/or photos; the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module is used for graying an image and carrying out weighted average on the grayed image, the image noise reduction module is used for carrying out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the image binarization module is used for carrying out binarization processing on the image processed by the image noise reduction module according to a threshold value and obtaining a binarization image; the image-text analysis and identification module is used for respectively identifying a picture area and a character area of the binary image and extracting a character area, and the character identification module is used for identifying characters in the character area of the binary image and extracting character data; the module is drawed in additional including template comparison module, keyword and types the module in template discernment, the module storage is compared to the template has certificate template database, contains a plurality of certificate template in the certificate template database, and the template is compared the module and is used for comparing and finding the certificate template that corresponds in certificate template database according to the picture region of binary image, characters region, keyword draw the module and compare the certificate template that the module found according to the template and carry out the keyword extraction and carry out data entry through type the module to the regional corresponding text data of binary image characters.
2. The airworthiness domain historical data entry system of claim 1, wherein: the graying processing module performs graying processing according to R, G, B three channels of the image, the graying processing module performs weighted average processing on each pixel of the image according to the formula (1),
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image.
3. The airworthiness domain historical data entry system of claim 1, wherein: the character recognition module establishes a Tesseract character recognition engine, performs character recognition through the Tesseract character recognition engine and extracts character data.
4. The airworthiness domain historical data entry system of claim 1, wherein: the entry module comprises an entry window module.
5. A method for supplementing historical data in the airworthiness field is characterized by comprising the following steps: the method comprises the following steps:
A. inputting an image through an input module, wherein the image is an R, G, B three-channel color image, and the image comprises a scanning piece and/or a photo;
B. the image preprocessing module comprises a graying processing module, an image noise reduction module and an image binarization module, wherein the graying processing module grays the image according to R, G, B three-channel pixel values, and the R, G, B three-channel pixel values are all 0-255; and performs weighted average processing according to formula (1) for each pixel of the image,
WrR+WgG+WbB (1)
wg > Wr > Wb, wherein R represents a pixel value corresponding to a R channel of a pixel in the image, G represents a pixel value corresponding to a G channel of the pixel in the image, and B represents a pixel value corresponding to a B channel of the pixel in the image;
C. the image noise reduction module carries out Gaussian filtering noise reduction processing on the image processed by the graying processing module, and the Gaussian filtering noise reduction processing adopts Gaussian low-pass filtering to carry out noise reduction; the image binarization module is used for carrying out binarization processing on the image processed by the image denoising module according to a threshold value to obtain a binarized image, wherein the gray value of the pixel which is greater than or equal to the threshold value after binarization is 255, and the gray value of the pixel which is smaller than the threshold value after binarization is 0;
D. the image preprocessing module transmits the processed binary image to the image-text analysis and identification module, and the image-text analysis and identification module performs image area and character area identification processing on the binary image and extracts a character area; establishing a Tesseract character recognition engine through a character recognition module to perform character recognition on a character area in the binary image and extracting character data;
E. the image preprocessing module and the character recognition module are respectively connected with a template recognition and additional recording module, the template recognition and additional recording module comprises a template comparison module, a keyword extraction module and an entry module, a certificate template database is stored in the template comparison module, a plurality of certificate templates are contained in the certificate template database, the template comparison module compares the image region and the character region of the binary image in the certificate template database and finds the corresponding certificate template, and the keyword extraction module extracts keywords from the character data corresponding to the character region of the binary image according to the certificate template found by the template comparison module and performs data entry through the entry module.
6. The airworthiness domain historical data entry method according to claim 5, characterized in that: and the template comparison module performs image identification according to the picture area of the binary image and performs comparison identification on the certificate template by combining key data of the character area of the binary image.
7. The airworthiness domain historical data entry method according to claim 5, characterized in that: the keyword extraction module is used for extracting keywords from the character data and removing useless information data; and the input module is used for inputting data according to the structure of the certificate template.
8. The airworthiness domain historical data entry method according to claim 5, characterized in that: the method also comprises the following steps:
F. the entry module is provided with an entry window module, and the certificate module is directly selected through the entry window module and data is input for entry.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110910905.2A CN113642557A (en) | 2021-08-10 | 2021-08-10 | System and method for supplementing historical data in airworthiness field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110910905.2A CN113642557A (en) | 2021-08-10 | 2021-08-10 | System and method for supplementing historical data in airworthiness field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642557A true CN113642557A (en) | 2021-11-12 |
Family
ID=78420275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110910905.2A Pending CN113642557A (en) | 2021-08-10 | 2021-08-10 | System and method for supplementing historical data in airworthiness field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642557A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593642A (en) * | 2012-08-16 | 2014-02-19 | 阿里巴巴集团控股有限公司 | Card-information acquisition method and system |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN109492643A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Certificate recognition methods, device, computer equipment and storage medium based on OCR |
| WO2021057138A1 (en) * | 2019-09-27 | 2021-04-01 | 支付宝(杭州)信息技术有限公司 | Certificate recognition method and apparatus |
-
2021
- 2021-08-10 CN CN202110910905.2A patent/CN113642557A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593642A (en) * | 2012-08-16 | 2014-02-19 | 阿里巴巴集团控股有限公司 | Card-information acquisition method and system |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN109492643A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Certificate recognition methods, device, computer equipment and storage medium based on OCR |
| WO2021057138A1 (en) * | 2019-09-27 | 2021-04-01 | 支付宝(杭州)信息技术有限公司 | Certificate recognition method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516208B (en) | System and method for extracting PDF document form | |
| CN111460138B (en) | BIM-based digital engineering supervision method and system | |
| CN109658042B (en) | Review method, device, equipment and storage medium based on artificial intelligence | |
| CN111027297A (en) | Method for processing key form information of image type PDF financial data | |
| US6243501B1 (en) | Adaptive recognition of documents using layout attributes | |
| CN110414927B (en) | Method and device for automatically generating voucher during bill processing | |
| CN105678612A (en) | Mobile terminal original certificate electronic intelligent filling system and method | |
| CN106126585B (en) | The unmanned plane image search method combined based on quality grading with perceived hash characteristics | |
| CN104463195A (en) | Printing style digital recognition method based on template matching | |
| CN105260428A (en) | Picture processing method and apparatus | |
| CN107506362B (en) | Image classification brain-imitation storage method based on user group optimization | |
| Yan et al. | Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images | |
| CN109213886A (en) | Image search method and system based on image segmentation and Fuzzy Pattern Recognition | |
| CN110675121A (en) | Method for collecting picture type file material | |
| CN114581928A (en) | Form identification method and system | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| CN117150138A (en) | Scientific and technological resource organization method and system based on high-dimensional space mapping | |
| CN108648245B (en) | Information extraction method and device for well logging interpretation curve | |
| CN113642557A (en) | System and method for supplementing historical data in airworthiness field | |
| CN110555219B (en) | Three-dimensional CAD model similarity retrieval system and method based on image recognition | |
| US20200210748A1 (en) | Intelligent recognition and extraction of numerical data from non-numerical graphical representations | |
| CN115661904A (en) | Data labeling and domain adaptation model training method, device, equipment and medium | |
| CN115391567A (en) | Fan standard operation knowledge graph construction method and device and operation machine | |
| CN114332866A (en) | Document curve separation and coordinate information extraction method based on image processing | |
| CN114936279A (en) | Unstructured chart data analysis method for collaborative manufacturing enterprise |
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 |