CN107423651A - A kind of QR codes image position method - Google Patents
A kind of QR codes image position method Download PDFInfo
- Publication number
- CN107423651A CN107423651A CN201610383793.9A CN201610383793A CN107423651A CN 107423651 A CN107423651 A CN 107423651A CN 201610383793 A CN201610383793 A CN 201610383793A CN 107423651 A CN107423651 A CN 107423651A
- Authority
- CN
- China
- Prior art keywords
- image
- code
- quick response
- response code
- noise
- 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
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention is a kind of internet QR code image monitoring methods, following steps:(1) image preprocessing, QR code pictures are pre-processed;(2) witness marker Graph Extraction;(3) vacancy is filled;(4) two-dimension code area is extracted;By above step, Quick Response Code region is obtained.The beneficial effects of the present invention are:The present invention can effectively realize the QR code image position methods in network, meet tight demand of the country to network multimedia information safety under the new situation.
Description
Technical field
The invention belongs to the network information security, technical field of video monitoring, more particularly to a kind of QR codes image position method.
Background technology
Quick Response Code is the readable black and white Matrix Pattern bar code that one-dimensional formation is extended on the basis of bar code.Quick Response Code can
Can be encoded to word, image, video, fingerprint etc. are any with digitized information, and it is expressed as visual rectangular code.Two
Dimension code has the characteristics that information capacity is big, coding range is wide, fault-tolerant error correcting capability is strong, encoding and decoding cost is low, spread speed is fast,
Through being widely used in the fields such as internet rich media information propagation and network payment.With mobile Internet fast development, two
Dimension code has become the important carrier of information interchange, emerges in multitude in internet.Quick Response Code is while convenient people live
There is also some problems.As information carrier, the text that is stored in Quick Response Code, image, link may include harmful information.Such as
Fruit is not added with managing, and the proper network of the harmful information meeting severe jamming people propagated by Quick Response Code is lived, or even threatens state
Family's network information security and social stability.Therefore, it is to provide under the new situation clearly to realize effective supervision to Quick Response Code in internet
The major issue that clean network environment and Logistics networks information security are faced.
Image content in internet is various, and shooting angle is different, and picture format, encryption algorithm are varied, in identification
The problems such as Quick Response Code also existence position in picture positions and posture is corrected, this all brings tired to the supervision of network Quick Response Code
It is difficult.
The content of the invention
The technical problems to be solved by the invention are the defects of overcoming prior art, there is provided a kind of QR codes framing side
Method.
The technical scheme is that a kind of internet QR code image monitoring methods, methods described comprise the following steps:
(1) image preprocessing, QR code pictures is pre-processed, specifically included,
A. image gray processing:Weighted mean method is taken, obtains gray level image;
B. image binaryzation:Binaryzation is carried out to image using big Tianjin law;
C. image denoising:Noise is filtered out using morphology noise filter;Opened first containing noisy image having
Computing, closed operation then is carried out to obtained image, the noise on image is removed;
(2) witness marker Graph Extraction, witness marker region is refined using morphologic method, excludes the interference of background;
(3) vacancy is filled
The hole in bianry image is filled line by line using constraint step length algorithm, so that Quick Response Code is in a connected domain
In;
(4) two-dimension code area is extracted, and after the completion of vacancy filling, deployment area growth algorithm obtains two-dimension code area company
Logical threshold;
By above step, Quick Response Code region is obtained.
The beneficial effects of the present invention are:The present invention can effectively realize the QR code image position methods in network, meet
Tight demand of the country to network multimedia information safety under the new situation.
Brief description of the drawings
Fig. 1 is QR codes positioning flow figure of the present invention
Embodiment
Below, carried out as described in detail below for the present invention with reference to accompanying drawing:
Online picture embraces a wide spectrum of ideas, rich and varied, there is many figures similar to QR code witness marker profiles, therefore algorithm
Need can effective filter false location information.In addition, after monitoring the witness marker figures of QR codes, it is also necessary to according to positioning mark
The size of will figure and apart from the position for determining whole QR codes, there is provided give subsequent module to use.Therefore QR code location algorithms are
The bottleneck of whole system performance.One good QR code figures location algorithm can not only detect all pictures for including QR codes, also
The position where it can accurately be oriented.
Picture pretreatment is carried out first, including:Image gray processing, image binaryzation, image denoising, obtain after removing noise
Picture;Then 1 is met according to horizontal vertical regional percentage:1:3:1:1 property, detect QR code witness markers;Finally, with
The center of one witness marker is seed point, and calmodulin binding domain CaM increases, and obtains Quick Response Code region.
2.1 image preprocessing
Image preprocessing includes three image gray processing, image binaryzation, image denoising steps.
Image gray processing:The calculating time and calculating space that image after gray processing processing needs are less, are greatly improved
Processing speed, therefore gray processing processing first is carried out to image.Take weighted mean method herein, due to human eye to green it is sensitive most
Height, [20-22] minimum to blue-sensitive, therefore average energy is weighted to RGB three-components as the following formula and obtains more rational gray scale
Image:
Gray=0.29900 × R+0.58700 × G+0.11400 × B
Image binaryzation:In order to obtain the image of high quality, grayscale image is converted into bianry image by us.Image two
Value is that the gray value of pixel on image is arranged into 0 or 255, and whole image is showed into obvious black and white effect.
Have more than 20 in individual thresholding algorithm, big Tianjin law performance is best, therefore selects big Tianjin law to come to image binaryzation herein.
Image denoising:Opening operation and closed operation are combined using morphology noise filter and can be used to filter out noise.
Contain noisy image progress opening operation to having first, optional structure salt matrices are bigger than the size of noise, the knot of opening operation
Fruit is by the noise remove in background;Followed by the image to obtaining carries out closed operation, and the noise on image is removed.The method is fitted
Image type is that the object size in image is larger, and does not have fine details, and the method can preferably keep image thin
Section.
2.2 witness marker Graph Extractions
In order to extract Quick Response Code region, we will find witness marker figure region.Because background is complicated,
Witness marker region also is refined with morphologic method after Quick Response Code candidate region is extracted, excludes the interference of background.
There are three witness markers on each Quick Response Code, find the key that position witness marker figure is Quick Response Code extraction.It is fixed
Bit flag figure is made up of three black, white, black concentric squares of different sizes.
It can be found that the black and white ratio all substantially 1 on every line:1:3:1:1, no matter marked from what scanning direction positioning
Will can meet black one white one black one white one black substantially 1:1:3:1:1 ratio, it is unrelated with scanning angle.
2.3 vacancies are filled
We want obtained simply Quick Response Code region, and other backgrounds are disturbing factors.Bianry image after processing,
Due to the presence of white hole, Quick Response Code is not in a connection threshold, in order to which two-dimension code area is taken out, is walked using constraint
Long algorithm fills the hole in bianry image line by line, so that Quick Response Code is in a connected domain.
2.4 two-dimension code areas are extracted
Two-dimension code area is substantially divided into a connection threshold by vacancy filling algorithm, next, to extract two
Tie up connection threshold corresponding to code.The center one of witness marker figure is scheduled in the connection threshold where Quick Response Code, can deployment area increase
Algorithm obtains connecting threshold.
By above step, Quick Response Code region is obtained.
Described is only the instantiation of the present invention, any equivalent transformation based on the inventive method basis, belongs to this hair
Within bright protection domain.
Claims (1)
1. a kind of internet QR code image monitoring methods, it is characterised in that methods described comprises the following steps:
(1) image preprocessing, QR code pictures is pre-processed, specifically included,
A. image gray processing:Weighted mean method is taken, obtains gray level image;
B. image binaryzation:Binaryzation is carried out to image using big Tianjin law;
C. image denoising:Noise is filtered out using morphology noise filter;Contain noisy image progress opening operation to having first,
Then closed operation is carried out to obtained image, the noise on image is removed;
(2) witness marker Graph Extraction, witness marker region is refined using morphologic method, excludes the interference of background;
(3) vacancy is filled
The hole in bianry image is filled line by line using constraint step length algorithm, so that Quick Response Code is in a connected domain;
(4) two-dimension code area is extracted, and after the completion of vacancy filling, deployment area growth algorithm obtains two-dimension code area connection
Threshold;
By above step, Quick Response Code region is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610383793.9A CN107423651A (en) | 2016-06-01 | 2016-06-01 | A kind of QR codes image position method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610383793.9A CN107423651A (en) | 2016-06-01 | 2016-06-01 | A kind of QR codes image position method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107423651A true CN107423651A (en) | 2017-12-01 |
Family
ID=60422862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610383793.9A Pending CN107423651A (en) | 2016-06-01 | 2016-06-01 | A kind of QR codes image position method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107423651A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108109120A (en) * | 2017-12-18 | 2018-06-01 | 凌云光技术集团有限责任公司 | A kind of illumination compensation method and device of dot matrix Quick Response Code |
CN108876851A (en) * | 2018-07-16 | 2018-11-23 | 哈尔滨理工大学 | A kind of foil gauge image position method |
CN110009615A (en) * | 2019-03-31 | 2019-07-12 | 深圳大学 | The detection method and detection device of image angle point |
CN110874733A (en) * | 2018-08-31 | 2020-03-10 | 北京意锐新创科技有限公司 | Passive code scanning payment method and device supporting external equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424457A (en) * | 2013-08-20 | 2015-03-18 | 复旦大学 | Method for identifying two-dimensional code under the condition of nonlinear distortion |
CN104809422A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | QR code recognizing method based on image processing |
-
2016
- 2016-06-01 CN CN201610383793.9A patent/CN107423651A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424457A (en) * | 2013-08-20 | 2015-03-18 | 复旦大学 | Method for identifying two-dimensional code under the condition of nonlinear distortion |
CN104809422A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | QR code recognizing method based on image processing |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108109120A (en) * | 2017-12-18 | 2018-06-01 | 凌云光技术集团有限责任公司 | A kind of illumination compensation method and device of dot matrix Quick Response Code |
CN108109120B (en) * | 2017-12-18 | 2020-09-08 | 凌云光技术集团有限责任公司 | Illumination compensation method and device for dot matrix two-dimensional code |
CN108876851A (en) * | 2018-07-16 | 2018-11-23 | 哈尔滨理工大学 | A kind of foil gauge image position method |
CN110874733A (en) * | 2018-08-31 | 2020-03-10 | 北京意锐新创科技有限公司 | Passive code scanning payment method and device supporting external equipment |
CN110009615A (en) * | 2019-03-31 | 2019-07-12 | 深圳大学 | The detection method and detection device of image angle point |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106485183B (en) | A kind of Quick Response Code localization method and system | |
CN102163284B (en) | Chinese environment-oriented complex scene text positioning method | |
CN102136058B (en) | Bar code image identification method | |
CN107423651A (en) | A kind of QR codes image position method | |
CN102542660A (en) | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics | |
CN106156684B (en) | A kind of two-dimensional code identification method and device | |
CN103974144B (en) | A kind of video digital watermark method of feature based change of scale invariant point and micro- scene detection | |
CN104168484A (en) | Video watermarking method based on visual attention mechanism | |
CN102136064A (en) | System for recognizing characters from image | |
CN104598933A (en) | Multi-feature fusion based image copying detection method | |
KR102104221B1 (en) | Method and device for recognizing digital object unique identifier (DOI) | |
CN105260694B (en) | A kind of two-dimension code area localization method based on multistage key extraction with analysis | |
CN108509870B (en) | A kind of Eriocheir sinensis uniqueness recognition methods based on images match | |
CN104537601B (en) | A kind of gray level image spatial domain steganography method based on nine grids | |
CN104424457A (en) | Method for identifying two-dimensional code under the condition of nonlinear distortion | |
CN103177281A (en) | Two-dimensional code compiling method | |
CN109712127A (en) | A kind of electric transmission line fault detection method for patrolling video flowing for machine | |
CN109766750A (en) | A kind of table line position finding and detection method of financial statement | |
CN103699895A (en) | Method for detecting and extracting text in video | |
CN108829711A (en) | A kind of image search method based on multi-feature fusion | |
CN105631405B (en) | Traffic video intelligent recognition background modeling method based on Multilevel Block | |
CN109858394A (en) | A kind of remote sensing images water area extracting method based on conspicuousness detection | |
CN108764419A (en) | A method of the antifalsification label of identification tool random grain | |
Fang et al. | An optimization model for aesthetic two-dimensional barcodes | |
Gaikwad et al. | Information hiding using image embedding in QR codes for color images: A review |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171201 |
|
WD01 | Invention patent application deemed withdrawn after publication |