CN109472266A - Image document checks system and method in a kind of electrical engineering course of receiving - Google Patents
Image document checks system and method in a kind of electrical engineering course of receiving Download PDFInfo
- Publication number
- CN109472266A CN109472266A CN201810086024.1A CN201810086024A CN109472266A CN 109472266 A CN109472266 A CN 109472266A CN 201810086024 A CN201810086024 A CN 201810086024A CN 109472266 A CN109472266 A CN 109472266A
- Authority
- CN
- China
- Prior art keywords
- unit
- electrical engineering
- library
- picture
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the image documents in a kind of electrical engineering course of receiving for automaticly inspecting and managing electrical engineering picture and data to check system and method, solve the problems, such as that electrical engineering picture in the prior art and data can not be automaticly inspected and be managed, image document checks system in a kind of electrical engineering course of receiving, including original image import unit, algorithm comparing unit, database module, comparison result output unit, characteristic point detection unit, description vectors generation unit, Feature Points Matching unit, match point screening unit, description vectors pre-matching unit, by computer image recognition technology, picture library and picture acceptance criteria are checked and accepted in conjunction with electrical, it makes electrical engineering examination picture and automaticly inspects comparison function, in accuracy, it can accomplish to avoid the inspection result Problem-Error as caused by artificial carelessness and erroneous judgement completely, this hair Bright saving manpower, improves accuracy at upgrading speed-raising.
Description
Technical field
The present invention relates to image domains, more particularly, to a kind of electricity for automaticly inspecting and managing electrical engineering picture and data
Image document during the gas acceptance of work checks system and method.
Background technique
In the course of receiving of electrical engineering, having one piece of important content is exactly to carry out to electrical engineering photo and data
The process of journey inspection and control, especially equipment, materials arrival, acceptance of concealed work, major project node is checked and accepted and image money
Material;Traditional test mode is identified by human eye, and it will take a lot of manpower and time, and is held during the inspection process
Easily there is judgement error, check the problems such as omitting, by modernization science and technology, is carried out using the algorithm of computer from cardon
As comparison, identification goes wrong, achievees the purpose that automaticly inspect and manage, and can greatly save human cost, moreover it is possible to effective
Shorten the review time, promoted and check efficiency, while the correctness for checking judgement can also be improved, avoids omission problem.
Summary of the invention
The present invention mainly solves the problems, such as that electrical engineering picture in the prior art and data can not be automaticly inspected and be managed,
Image document inspection in the electrical engineering course of receiving of electrical engineering picture and data can be managed and check automatically by providing one kind
System and method.
Above-mentioned technical problem of the invention is mainly to be addressed by following technical proposals: a kind of electrical engineering examination
Image document checks system, including original image import unit, algorithm comparing unit, database module, comparison result in the process
Output unit, characteristic point detection unit, description vectors generation unit, Feature Points Matching unit, match point screening unit, describe to
Measure pre-matching unit, the original image import unit, algorithm comparing unit, database module, comparison result output unit according to
It is secondary to be connected, the characteristic point detection unit, description vectors generation unit, Feature Points Matching unit, match point screening unit, description
Vector pre-matching unit is connected with algorithm comparing unit respectively, and picture is imported into algorithm and compares list by original image import unit
Member, SIFT feature point search are also referred to as characteristic point detection, are broadly divided into three basic steps: scale space generation, spatial neighborhood pole
Big value search and characteristic point are accurately positioned, and it mainly includes seeking characteristic point principal direction and feature point description two that description vectors, which generate,
Basic step, the purpose of Feature Points Matching are that the high characteristic point pair of similarity degree is found in original image and image to be matched, are led to
Normal characteristic point is all one-one relationship between image, therefore puts and only consider similarity arest neighbors situation to when matching.
As a preferred embodiment, the database module includes system data library unit, quantitative criteria collector unit, electricity
Sub-pattern library import unit, quantitative criteria typing unit, the quantitative criteria collector unit, electronics pattern library import unit, amount
Change standard typing unit is connected with system data library unit respectively, and database module is for storing quantitative criteria and electronics pattern
All acceptance criteria drawings of electrical engineering are arranged, are quickly shot by high-precision high photographing instrument by library, form electronics pattern library,
Electronics pattern management system is developed, electronics pattern library is imported in electric power pattern management system, by electronics pattern library with gridding
Data mode store into the system database of electronics pattern library, for automated graphics check algorithm call and check match, will
Electrical engineering checks and accepts picture passed examination standard collection, and by the language conversion of verbal description at the standard of digitlization and quantization
Value range develops electronic standard library management engineering, these standards quantified are entered into the system of electronic standard library, data are stored in
In library, checks that algorithm compares for automated graphics and use.
It as a preferred embodiment, further include being provided with suggestion module, the suggestion module and comparison result output unit
It is connected.
As a preferred embodiment, the suggestion module includes suggestion and measure library unit, suggests reminding unit, the comparison
As a result output unit, suggestion and measure library unit, suggestion reminding unit are sequentially connected, and check and accept picture library and electrician with reference to electrical engineering
Scheme is established in journey acceptance criteria library, establishes suggestion and measure library, checks that algorithm picture in inspection is underproof for automated graphics
In the case of, measure of advising uses.
As a preferred embodiment, further include be provided with spatial neighborhood maximum searching unit, scale space generation unit,
Characteristic point is accurately positioned unit, and the spatial neighborhood maximum searching unit, scale space generation unit, characteristic point are accurately positioned
Unit is connected with characteristic point detection unit respectively.
It as a preferred embodiment, further include being provided with to seek characteristic point principal direction unit 4, feature point description unit, institute
It states and seeks characteristic point principal direction unit, feature point description unit is connected with description vectors generation unit respectively.
As a preferred embodiment, image document inspection method in a kind of electrical engineering course of receiving, comprising the following steps:
S1. it establishes electrical engineering and checks and accepts picture library and electrical engineering acceptance criteria library;
S2. original image is imported into algorithm comparing unit by original image import unit and is compared;
S3. original image is compared with data in system database according to algorithm and exports result by algorithm comparing unit.
As a preferred embodiment, the specific steps of S1 include:
S11. all acceptance criteria drawings of electrical engineering arrange, and are quickly shot by high-precision high photographing instrument, form electronics pattern
Library;
S12. electrical engineering is checked and accepted into picture passed examination standard collection, and by the language conversion of verbal description at digitlization
With the critical field value of quantization.
As a preferred embodiment, the specific steps of S3 include:
S31. SIFI image recognition algorithm is improved, two basic steps, shape are screened by description vectors pre-matching and matching double points
At SIFI+ image recognition algorithm;
S32. it using SIFT+ algorithm, examination electronics picture library, examination electronic standard library, and is counted by RANSAC calculation formula
It calculates, completes examination picture and automaticly inspect algorithm, realization automaticly inspects function;
S33. picture check and acceptance result is exported, and compares suggestion and measure library, provides suggestion and measure.
Therefore, the invention has the advantages that through the invention, by computer image recognition technology, checking and accepting figure in conjunction with electrical
Library and picture acceptance criteria make electrical engineering examination picture and automaticly inspect comparison function, can thoroughly solve traditional approach
The problems of, in accuracy, it can accomplish to avoid the inspection result mistake as caused by artificial carelessness and erroneous judgement completely
Problem, invention achieves save manpower, upgrading speed-raising, the purpose for improving accuracy.
Detailed description of the invention
Attached drawing 1 is a kind of system structure frame figure of the invention;
Attached drawing 2 is a kind of flowage structure schematic diagram of the invention;
1. 2. scale space generation unit of spatial neighborhood maximum searching unit
3. characteristic point is accurately positioned unit 4. and seeks characteristic point principal direction unit
5. 6. Feature Points Matching unit of feature point description unit, 7. match point screening unit
8. 9. description vectors generation unit of description vectors pre-matching unit
10. 11. original image import unit of characteristic point detection unit, 12. algorithm comparing unit
13. 14. comparison result output unit of system data library unit, 15. suggestion and measure library unit
16. suggesting 17. quantitative criteria collector unit of reminding unit
18. 19. quantitative criteria typing unit of electronics pattern library import unit, 20. database module
21. suggestion module.
Specific embodiment
Image document checks system, including original image import unit in a kind of electrical engineering course of receiving of the present embodiment
11, algorithm comparing unit 12, database module 20, comparison result output unit 14, characteristic point detection unit 10, description vectors are raw
At unit 9, Feature Points Matching unit 6, match point screening unit 7, description vectors pre-matching unit 8, original image import unit,
Algorithm comparing unit, database module, comparison result output unit are sequentially connected, and characteristic point detection unit, description vectors generate
Unit, Feature Points Matching unit, match point screening unit, description vectors pre-matching unit are connected with algorithm comparing unit respectively,
Picture is imported into algorithm comparing unit by original image import unit, and SIFT feature point search is also referred to as characteristic point detection, main to divide
For three basic steps: scale space generates, spatial neighborhood maximum searching and characteristic point are accurately positioned, and description vectors generate master
To include seeking two basic steps of characteristic point principal direction and feature point description, the purpose of Feature Points Matching be original image and to
The high characteristic point pair of similarity degree is found in matching image, usual characteristic point is all one-one relationship between image, therefore point pair
Similarity arest neighbors situation is only considered when matching.
Database module includes system data library unit 13, quantitative criteria collector unit 17, electronics pattern library import unit
18, quantitative criteria typing unit 19, quantitative criteria collector unit, electronics pattern library import unit, quantitative criteria typing unit point
It is not connected with system data library unit, database module is for storing quantitative criteria and electronics pattern library, by the institute of electrical engineering
There is the arrangement of acceptance criteria drawing, quickly shot by high-precision high photographing instrument, form electronics pattern library, develops electronics pattern management system
System imports electronics pattern library in electric power pattern management system, by electronics pattern library with the data mode storage of gridding to electricity
In the system database in sub-pattern library, checks that algorithm is called and checked for automated graphics and match, electrical engineering is checked and accepted into picture inspection
Criterion of acceptability collection is looked into, and the language conversion of verbal description is developed into electronics mark at the critical field value of digitlization and quantization
These standards quantified are entered into the system of electronic standard library, are stored in database, examine for automated graphics by quasi- library management engineering
It looks into algorithm and compares use.
It further include being provided with suggestion module 21, it is proposed that module is connected with comparison result output unit, it is proposed that module includes building
View measure library unit 15, suggest reminding unit 16, comparison result output unit, suggestion and measure library unit, suggest reminding unit according to
It is secondary to be connected, scheme is established with reference to what electrical engineering checked and accepted picture library and electrical engineering acceptance criteria library, suggestion and measure library is established, is provided from
Motion video checks in the underproof situation of algorithm picture in inspection that measure of advising uses.
It further include being provided with spatial neighborhood maximum searching unit 1, scale space generation unit 2, characteristic point to be accurately positioned
Unit 3, spatial neighborhood maximum searching unit, scale space generation unit, characteristic point be accurately positioned unit respectively with characteristic point
Detection unit is connected, and further includes being provided with to seek characteristic point principal direction unit 4, feature point description unit 5, seeks the main side of characteristic point
It is connected respectively with description vectors generation unit to unit, feature point description unit.
Image document inspection method in a kind of electrical engineering course of receiving, comprising the following steps:
S1. it establishes electrical engineering and checks and accepts picture library and electrical engineering acceptance criteria library;
S2. original image is imported into algorithm comparing unit by original image import unit and is compared;
S3. original image is compared with data in system database according to algorithm and exports result by algorithm comparing unit.
The specific steps of S1 include:
S11. all acceptance criteria drawings of electrical engineering arrange, and are quickly shot by high-precision high photographing instrument, form electronics pattern
Library;
S12. electrical engineering is checked and accepted into picture passed examination standard collection, and by the language conversion of verbal description at digitlization
With the critical field value of quantization.
The specific steps of S3 include:
S31. SIFI image recognition algorithm is improved, two basic steps, shape are screened by description vectors pre-matching and matching double points
At SIFI+ image recognition algorithm;
S32. it using SIFT+ algorithm, examination electronics picture library, examination electronic standard library, and is counted by RANSAC calculation formula
It calculates, completes examination picture and automaticly inspect algorithm, realization automaticly inspects function;
S33. picture check and acceptance result is exported, and compares suggestion and measure library, provides suggestion and measure.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Although original image import unit is used more herein, algorithm comparing unit, compares knot at database module
The terms such as fruit output unit, characteristic point detection unit, but it does not exclude the possibility of using other terms.Only using these terms
Merely to being more convenient to describe and explain essence of the invention;Being construed as any additional limitation all is and this
What spirit was disagreed.
Claims (9)
1. image document checks system, including original image import unit (11), algorithm ratio in a kind of electrical engineering course of receiving
It is raw to unit (12), database module (20), comparison result output unit (14), characteristic point detection unit (10), description vectors
It is described original at unit (9), Feature Points Matching unit (6), match point screening unit (7), description vectors pre-matching unit (8)
Picture import unit, algorithm comparing unit, database module, comparison result output unit are sequentially connected, the characteristic point detection
Unit, description vectors generation unit, Feature Points Matching unit, match point screening unit, description vectors pre-matching unit respectively with
Algorithm comparing unit is connected.
2. image document checks system in a kind of electrical engineering course of receiving according to claim 1, it is characterized in that described
Database module include system data library unit (13), quantitative criteria collector unit (17), electronics pattern library import unit (18),
Quantitative criteria typing unit (19), the quantitative criteria collector unit, electronics pattern library import unit, quantitative criteria typing unit
It is connected respectively with system data library unit.
3. image document checks system in a kind of electrical engineering course of receiving according to claim 1, it is characterized in that also wrapping
It includes and is provided with suggestion module (21), the suggestion module is connected with comparison result output unit.
4. image document checks system in a kind of electrical engineering course of receiving according to claim 3, it is characterized in that described
Suggestion module includes suggestion and measure library unit (15), suggestion reminding unit (16), the comparison result output unit, suggestion and measure
Library unit suggests that reminding unit is sequentially connected.
5. image document checks system in a kind of electrical engineering course of receiving according to claim 1, it is characterized in that also wrapping
It includes and is provided with spatial neighborhood maximum searching unit (1), scale space generation unit (2), characteristic point accurate positioning unit (3),
The spatial neighborhood maximum searching unit, scale space generation unit, characteristic point are accurately positioned unit and examine respectively with characteristic point
Unit is surveyed to be connected.
6. image document checks system in a kind of electrical engineering course of receiving described in -5 according to claim 1, it is characterized in that also
Seek characteristic point principal direction unit (4), feature point description unit (5) including being provided with, it is described seek characteristic point principal direction unit,
Feature point description unit is connected with description vectors generation unit respectively.
7. image document inspection method in a kind of electrical engineering course of receiving, special using the system in any one of right 1-7
Sign be the following steps are included:
S1. it establishes electrical engineering and checks and accepts picture library and electrical engineering acceptance criteria library;
S2. original image is imported into algorithm comparing unit by original image import unit and is compared;
S3. original image is compared with data in system database according to algorithm and exports result by algorithm comparing unit.
8. image document inspection method in a kind of electrical engineering course of receiving according to claim 7, it is characterized in that S1
Specific steps include:
S11. all acceptance criteria drawings of electrical engineering arrange, and are quickly shot by high-precision high photographing instrument, form electronics pattern
Library;
S12. electrical engineering is checked and accepted into picture passed examination standard collection, and by the language conversion of verbal description at digitlization
With the critical field value of quantization.
9. image document inspection method in a kind of electrical engineering course of receiving according to claim 7, it is characterized in that S3
Specific steps include:
S31. SIFI image recognition algorithm is improved, two basic steps, shape are screened by description vectors pre-matching and matching double points
At SIFI+ image recognition algorithm;
S32. it using SIFT+ algorithm, examination electronics picture library, examination electronic standard library, and is counted by RANSAC calculation formula
It calculates, completes examination picture and automaticly inspect algorithm, realization automaticly inspects function;
S33. picture check and acceptance result is exported, and compares suggestion and measure library, provides suggestion and measure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810086024.1A CN109472266A (en) | 2018-01-29 | 2018-01-29 | Image document checks system and method in a kind of electrical engineering course of receiving |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810086024.1A CN109472266A (en) | 2018-01-29 | 2018-01-29 | Image document checks system and method in a kind of electrical engineering course of receiving |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109472266A true CN109472266A (en) | 2019-03-15 |
Family
ID=65659882
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810086024.1A Pending CN109472266A (en) | 2018-01-29 | 2018-01-29 | Image document checks system and method in a kind of electrical engineering course of receiving |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109472266A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112990143A (en) * | 2021-04-30 | 2021-06-18 | 杭州品茗安控信息技术股份有限公司 | Model matching method and system of building drawing and related device |
CN113505660A (en) * | 2021-06-22 | 2021-10-15 | 上海工程技术大学 | Paper engineering drawing operation reading device and method thereof |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103366176A (en) * | 2012-03-31 | 2013-10-23 | 湖北山鹰光学有限公司 | Device and method for recognizing optical element defects automatically in batches |
CN106067101A (en) * | 2016-08-02 | 2016-11-02 | 杭州凯达电力建设有限公司 | A kind of distribution power engineering acceptance method and system |
-
2018
- 2018-01-29 CN CN201810086024.1A patent/CN109472266A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103366176A (en) * | 2012-03-31 | 2013-10-23 | 湖北山鹰光学有限公司 | Device and method for recognizing optical element defects automatically in batches |
CN106067101A (en) * | 2016-08-02 | 2016-11-02 | 杭州凯达电力建设有限公司 | A kind of distribution power engineering acceptance method and system |
Non-Patent Citations (1)
Title |
---|
张格森 等: "一种图像局部特征快速匹配算法", 《电子技术应用》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112990143A (en) * | 2021-04-30 | 2021-06-18 | 杭州品茗安控信息技术股份有限公司 | Model matching method and system of building drawing and related device |
CN112990143B (en) * | 2021-04-30 | 2021-08-31 | 杭州品茗安控信息技术股份有限公司 | Model matching method and system of building drawing and related device |
CN113505660A (en) * | 2021-06-22 | 2021-10-15 | 上海工程技术大学 | Paper engineering drawing operation reading device and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103528617B (en) | A kind of cockpit instrument identifies and detection method and device automatically | |
CN113409284B (en) | Circuit board fault detection method, device, equipment and storage medium | |
CN110378206B (en) | Intelligent image examination system and method | |
WO2023115761A1 (en) | Event detection method and apparatus based on temporal knowledge graph | |
CN109858414A (en) | A kind of invoice piecemeal detection method | |
CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
Pekar et al. | Improvement methods for software requirement specifications: a mapping study | |
CN109472266A (en) | Image document checks system and method in a kind of electrical engineering course of receiving | |
CN112559523A (en) | Data detection method and device, electronic equipment and storage medium | |
Yang et al. | Multivariate regression on the grassmannian for predicting novel domains | |
Bajcsy et al. | A method for the evaluation of thousands of automated 3D stem cell segmentations | |
CN115952298A (en) | Supplier performance risk analysis method and related equipment | |
CN103913150B (en) | Intelligent electric energy meter electronic devices and components consistency detecting method | |
CN116703337A (en) | Project document examination system and method based on artificial intelligence technology | |
Aho et al. | Analyzing 3 TB field measurement data set | |
Jubair et al. | A multi‐agent K‐means with case‐based reasoning for an automated quality assessment of software requirement specification | |
CN115880472A (en) | Intelligent diagnosis and analysis system for electric power infrared image data | |
CN116977250A (en) | Defect detection method and device for industrial parts and computer equipment | |
WO2022141838A1 (en) | Model confidence analysis method and apparatus, electronic device and computer storage medium | |
Wu et al. | Hilbert ID considering multi-window feature extraction for transformer deep vision fault positioning | |
Wang et al. | A knowledge discovery case study of software quality prediction: Isbsg database | |
US20110179022A1 (en) | Method of analyzing claims of a patent document and patent analysis system thereof | |
Ilyas et al. | A similarity measurement framework for requirements engineering | |
Maidasani et al. | Entity resolution evaluation measures | |
JP2018190304A (en) | Inspection support device, inspection support method, and inspection support program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190315 |
|
RJ01 | Rejection of invention patent application after publication |