CN112489058A - Efficient and accurate stripe direction estimation method - Google Patents
Efficient and accurate stripe direction estimation method Download PDFInfo
- Publication number
- CN112489058A CN112489058A CN202011410592.6A CN202011410592A CN112489058A CN 112489058 A CN112489058 A CN 112489058A CN 202011410592 A CN202011410592 A CN 202011410592A CN 112489058 A CN112489058 A CN 112489058A
- Authority
- CN
- China
- Prior art keywords
- stripe
- efficient
- accurate
- estimation method
- marking
- 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 26
- 239000012634 fragment Substances 0.000 claims abstract description 7
- 238000012795 verification Methods 0.000 claims description 6
- 239000006185 dispersion Substances 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a high-efficiency and accurate fringe direction estimation method, which comprises the following steps: p1, carrying out exposure shooting on the surface of the stripe to obtain a real-time stripe image; p2, carrying out fragment interception on the real-time image to form a stripe unit; p3, overlapping and matching the units, finding out the units with the same shape, and removing edge patterns; p4, carrying out strong exposure on the same unit, distinguishing a stripe area from a background area, and marking a stripe boundary line; p5, marking inflection points of the stripe boundary lines to form marking points; p6, judging the stripe direction according to the distribution state of the mark points to form an estimation result, avoiding interference caused by adjacent stripes and background patterns, improving the stripe identification accuracy, and simultaneously identifying the stripe shape and the distribution state by combining a boundary line inflection point marking method, being beneficial to determining the stripe region, further judging the two directions, being capable of greatly improving the identification efficiency and the estimation accuracy, improving the use effect and being beneficial to popularization.
Description
Technical Field
The invention relates to the technical field of stripe directions, in particular to a high-efficiency and accurate stripe direction estimation method.
Background
In the current daily life and production, some graphs can be configured with stripe patterns, and direction identification and estimation are needed, so that stripe positioning and pavement directions are determined, and disorder is avoided.
However, most of the absorbed stripe directions are directly shot and identified through a camera, and most of the ordered stripes are continuous intensive patterns, so that the stripes are easy to mix with background patterns during shooting, the identification efficiency and accuracy are affected, and a new method needs to be provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides an efficient and accurate fringe direction estimation method.
In order to achieve the purpose, the invention adopts the following technical scheme:
an efficient and accurate fringe direction estimation method comprises the following steps:
p1, carrying out exposure shooting on the surface of the stripe to obtain a real-time stripe image;
p2, carrying out fragment interception on the real-time image to form a stripe unit;
p3, overlapping and matching the units, finding out the units with the same shape, and removing edge patterns;
p4, carrying out strong exposure on the same unit, distinguishing a stripe area from a background area, and marking a stripe boundary line;
p5, marking inflection points of the stripe boundary lines to form marking points;
and P6, judging the stripe direction according to the distribution state of the mark points to form an estimation result.
Preferably, the exposure shot of the step P1 uses two exposure beams, and forms an interference area on a fringe substrate.
Preferably, the fragment interception in the step P2 is in a picture format, and a primary picture set and a verification picture set are constructed.
Preferably, the primary picture set comprises a noisy histogram having a size of 512 × 512 and a density of 500ppi, where ppi denotes pixels per inch, and the verification picture set comprises a noiseless histogram having a size of 512 × 512 and a density of 1000 ppi.
Preferably, the overlap matching of the P3 step is stripe image stack matching, and the selected area maximizes the overlap area as a stripe region.
Preferably, the marker stripe boundary line in the step P4 is a light/dark boundary line position after the strong exposure, and a boundary pattern is drawn.
Preferably, the boundary line inflection point of the P5 step includes a convex point and a concave point.
Preferably, the method for determining the stripe direction in the step P6 includes the following steps:
s1, accurately marking the boundary inflection point, and recording the number and the corresponding position;
s2, identifying inflection point dispersion states, and removing the center position of the top stripe at the comprehensive intersection according to the central connecting line;
s3, identifying at least two areas with the most dense inflection point distribution, mutually connecting the areas to cross the center position, and determining a transverse central line and a longitudinal central line;
and S4, determining the distance from the most dense area to the central line, and estimating the stripe direction.
Preferably, the estimated stripe directions of step S4 are divided into two, where two symmetric farthest distance dense areas are taken as the extending directions of the stripes, and two closest home dense areas that are the densest are taken as the tiling directions of the stripes.
According to the efficient and accurate stripe direction estimation method provided by the invention, through adopting double-path light beam exposure for shooting, the image definition can be effectively improved, the segmentation interception and the strong exposure irradiation are combined, the interference caused by adjacent stripes and background patterns is avoided, the stripe identification accuracy is improved, meanwhile, the stripe shape and the distribution state are identified by combining a boundary line inflection point marking method, the stripe area is favorably determined, the two directions of the stripe area are further judged, the identification efficiency and the estimation accuracy can be greatly improved, the use effect is improved, and the popularization is facilitated.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
An efficient and accurate fringe direction estimation method comprises the following steps:
p1, carrying out exposure shooting on the surface of the stripe to obtain a real-time stripe image;
p2, carrying out fragment interception on the real-time image to form a stripe unit;
p3, overlapping and matching the units, finding out the units with the same shape, and removing edge patterns;
p4, carrying out strong exposure on the same unit, distinguishing a stripe area from a background area, and marking a stripe boundary line;
p5, marking inflection points of the stripe boundary lines to form marking points;
and P6, judging the stripe direction according to the distribution state of the mark points to form an estimation result.
Preferably, the exposure shot of the step P1 uses two exposure beams, and forms an interference area on a fringe substrate.
Preferably, the fragment truncation of step P2 is in a picture format, and a primary picture set and a verification picture set are constructed.
Preferably, the primary picture set comprises noisy fringe patterns, the size of the fringe patterns is 512 x 512, the density is 500ppi, ppi represents the number of pixels per inch, and the verification picture set comprises noiseless fringe patterns, the size of the fringe patterns is 512 x 512, and the density is 1000 ppi.
Preferably, the overlap matching of the P3 step is a stripe image stack matching, and the region is selected to maximize the overlap area as a stripe region.
Preferably, the marker stripe boundary line in the step P4 is a light/dark boundary line position after the strong exposure, and a boundary pattern is drawn.
Preferably, the boundary line inflection point of the P5 step includes a convex point and a concave point.
Preferably, the method for determining the stripe direction in the step P6 includes the steps of:
s1, accurately marking the boundary inflection point, and recording the number and the corresponding position;
s2, identifying inflection point dispersion states, and removing the center position of the top stripe at the comprehensive intersection according to the central connecting line;
s3, identifying at least two areas with the most dense inflection point distribution, mutually connecting the areas to cross the center position, and determining a transverse central line and a longitudinal central line;
and S4, determining the distance from the most dense area to the central line, and estimating the stripe direction.
Preferably, the estimated stripe directions in step S4 are divided into two, where two symmetric farthest distance dense areas are taken as extending directions of the stripes, and two closest home dense areas that are the densest are taken as tiling directions of the stripes.
According to the efficient and accurate stripe direction estimation method provided by the invention, through adopting double-path light beam exposure for shooting, the image definition can be effectively improved, the segmentation interception and the strong exposure irradiation are combined, the interference caused by adjacent stripes and background patterns is avoided, the stripe identification accuracy is improved, meanwhile, the stripe shape and the distribution state are identified by combining a boundary line inflection point marking method, the stripe area is favorably determined, the two directions of the stripe area are further judged, the identification efficiency and the estimation accuracy can be greatly improved, the use effect is improved, and the popularization is facilitated.
Claims (9)
1. An efficient and accurate fringe direction estimation method is characterized by comprising the following steps: the estimation method comprises the following steps:
p1, carrying out exposure shooting on the surface of the stripe to obtain a real-time stripe image;
p2, carrying out fragment interception on the real-time image to form a stripe unit;
p3, overlapping and matching the units, finding out the units with the same shape, and removing edge patterns;
p4, carrying out strong exposure on the same unit, distinguishing a stripe area from a background area, and marking a stripe boundary line;
p5, marking inflection points of the stripe boundary lines to form marking points;
and P6, judging the stripe direction according to the distribution state of the mark points to form an estimation result.
2. An efficient and accurate streak direction estimation method according to claim 1, wherein: the exposure shooting of the step P1 adopts two exposure beams, and forms an interference area on a fringe substrate.
3. An efficient and accurate streak direction estimation method according to claim 1, wherein: and the fragment interception in the step P2 adopts a picture format, and an initial picture set and a verification picture set are constructed.
4. A method for efficient and accurate streak direction estimation according to claim 3, wherein: the primary picture set comprises noisy fringe patterns, the size of the fringe patterns is 512 x 512, the density is 500ppi, the ppi represents the number of pixels per inch, the verification picture set comprises noiseless fringe patterns, the size of the fringe patterns is 512 x 512, and the density is 1000 ppi.
5. An efficient and accurate streak direction estimation method according to claim 1, wherein: the overlap matching of the P3 step is a stripe image stack matching, and the selected area maximizes the overlap area as a stripe region.
6. An efficient and accurate streak direction estimation method according to claim 1, wherein: the marker stripe boundary line in the step P4 is a light and dark boundary line position after strong exposure, and a boundary graph is drawn.
7. An efficient and accurate streak direction estimation method according to claim 1, wherein: the boundary line inflection point of the P5 step includes a convex point and a concave point.
8. An efficient and accurate streak direction estimation method according to claim 1, wherein: the method for judging the stripe direction in the step P6 comprises the following steps:
s1, accurately marking the boundary inflection point, and recording the number and the corresponding position;
s2, identifying inflection point dispersion states, and removing the center position of the top stripe at the comprehensive intersection according to the central connecting line;
s3, identifying at least two areas with the most dense inflection point distribution, mutually connecting the areas to cross the center position, and determining a transverse central line and a longitudinal central line;
and S4, determining the distance from the most dense area to the central line, and estimating the stripe direction.
9. An efficient and accurate streak direction estimation method according to claim 8, wherein: the estimated stripe directions in the step S4 are divided into two, where two symmetric farthest distance dense areas are taken as the extending directions of the stripes, and two closest home dense areas that are the densest are taken as the tiling directions of the stripes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011410592.6A CN112489058A (en) | 2020-12-03 | 2020-12-03 | Efficient and accurate stripe direction estimation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011410592.6A CN112489058A (en) | 2020-12-03 | 2020-12-03 | Efficient and accurate stripe direction estimation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112489058A true CN112489058A (en) | 2021-03-12 |
Family
ID=74938125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011410592.6A Pending CN112489058A (en) | 2020-12-03 | 2020-12-03 | Efficient and accurate stripe direction estimation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489058A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000132685A (en) * | 1998-10-23 | 2000-05-12 | Matsushita Electric Works Ltd | Method for inspecting external appearance |
| US20020126295A1 (en) * | 2000-11-20 | 2002-09-12 | Gilbert Dudkiewicz | Automatic installation and process for taking measurements and acquiring shapes |
| WO2015189174A2 (en) * | 2014-06-10 | 2015-12-17 | Carl Zeiss Meditec, Inc. | Improved frequency-domain interferometric based imaging systems and methods |
| CN106091978A (en) * | 2016-06-01 | 2016-11-09 | 西安工程大学 | The joining method of interference fringe image in inclined in type measurements by laser interferometry |
| CN107917676A (en) * | 2017-10-24 | 2018-04-17 | 南京理工大学 | A kind of interferometric method based on stripe pattern spectrum analysis |
| CN109889696A (en) * | 2019-03-18 | 2019-06-14 | 上海顺久电子科技有限公司 | Antinoise for automatic geometric correction shoots image-recognizing method and system |
| CN110298811A (en) * | 2018-03-21 | 2019-10-01 | 北京大学 | Preprocess method, device, terminal and the computer readable storage medium of image |
| CN111402149A (en) * | 2020-03-06 | 2020-07-10 | 四川大学 | Fringe pattern restoration method based on convolutional neural network denoising regularization |
-
2020
- 2020-12-03 CN CN202011410592.6A patent/CN112489058A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000132685A (en) * | 1998-10-23 | 2000-05-12 | Matsushita Electric Works Ltd | Method for inspecting external appearance |
| US20020126295A1 (en) * | 2000-11-20 | 2002-09-12 | Gilbert Dudkiewicz | Automatic installation and process for taking measurements and acquiring shapes |
| WO2015189174A2 (en) * | 2014-06-10 | 2015-12-17 | Carl Zeiss Meditec, Inc. | Improved frequency-domain interferometric based imaging systems and methods |
| CN106091978A (en) * | 2016-06-01 | 2016-11-09 | 西安工程大学 | The joining method of interference fringe image in inclined in type measurements by laser interferometry |
| CN107917676A (en) * | 2017-10-24 | 2018-04-17 | 南京理工大学 | A kind of interferometric method based on stripe pattern spectrum analysis |
| CN110298811A (en) * | 2018-03-21 | 2019-10-01 | 北京大学 | Preprocess method, device, terminal and the computer readable storage medium of image |
| CN109889696A (en) * | 2019-03-18 | 2019-06-14 | 上海顺久电子科技有限公司 | Antinoise for automatic geometric correction shoots image-recognizing method and system |
| CN111402149A (en) * | 2020-03-06 | 2020-07-10 | 四川大学 | Fringe pattern restoration method based on convolutional neural network denoising regularization |
Non-Patent Citations (1)
| Title |
|---|
| 杨鹏程;刘洋;朱新栋;胥光申;肖渊;: "基于物体像的干涉条纹图像中散斑噪声的识别方法", 应用光学, no. 02, 15 March 2017 (2017-03-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145915B (en) | Rapid distortion correction method for license plate under complex scene | |
| CN111207695A (en) | Hot-rolled strip steel end three-dimensional contour measuring method based on double-line structured light | |
| KR20200087184A (en) | Method for manufacturing metal plate and metal plate for manufacturing deposition mask, and method for manufacturing deposition mask and deposition mask | |
| CN101339601B (en) | License plate Chinese character recognition method based on SIFT algorithm | |
| CN105718870A (en) | Road marking line extracting method based on forward camera head in automatic driving | |
| CN102673106A (en) | Silk screen print positioning equipment and method for photovoltaic solar silicon chip | |
| CN112224590B (en) | Billet labeling method and system based on three-dimensional point cloud | |
| CN110390256B (en) | Asphalt pavement crack extraction method | |
| CN113390605B (en) | Full-field measurement method for wing deformation of wind tunnel test airplane | |
| CN107389693A (en) | A kind of printed matter defect automatic testing method based on machine vision | |
| CN105551046A (en) | Vehicle face location method and device | |
| CN109870458B (en) | Pavement crack detection and classification method based on three-dimensional laser sensor and bounding box | |
| CN105225229A (en) | Fish based on vision signal cross dam movement locus locating device and method | |
| CN112489058A (en) | Efficient and accurate stripe direction estimation method | |
| CN111739006B (en) | Elliptical image detection algorithm and system based on enclosed road integral | |
| CN113313116A (en) | Vision-based accurate detection and positioning method for underwater artificial target | |
| CN112862898A (en) | Flow velocity measuring method based on computer vision | |
| JP3589293B2 (en) | Road white line detection method | |
| CN109015632A (en) | A kind of robot hand end localization method | |
| CN111462214A (en) | Line structure light stripe central line extraction method based on Hough transformation | |
| CN111968079A (en) | Three-dimensional pavement crack extraction method based on section local extreme value and segmentation sparsity | |
| CN117689717B (en) | Ground badminton pose detection method for robot pickup | |
| CN111318815A (en) | Laser marking system | |
| CN112184820B (en) | Laser double-sided shot blasting spot positioning method and system and computer readable storage medium | |
| CN114565745A (en) | Laser additive manufacturing scanning path regional planning method considering suspension feature recognition |
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 |