CN107818583A - Cross searching detection method and device - Google Patents
Cross searching detection method and device Download PDFInfo
- Publication number
- CN107818583A CN107818583A CN201711086611.2A CN201711086611A CN107818583A CN 107818583 A CN107818583 A CN 107818583A CN 201711086611 A CN201711086611 A CN 201711086611A CN 107818583 A CN107818583 A CN 107818583A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- roi
- cross
- straight lines
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000005260 corrosion Methods 0.000 claims abstract description 8
- 230000007797 corrosion Effects 0.000 claims abstract description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection 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
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of cross searching detection method and device, and method therein includes carrying out corrosion treatment to image to be detected, forms initial pictures；Wherein, cross mark to be detected at least one is provided with image to be detected；Self-adaption binaryzation processing is carried out to initial pictures, forms bianry image；Median filter process is carried out to bianry image, to eliminate the noise in bianry image；The closed contour of the image after median filter process, and the minimum enclosed rectangle corresponding to foundation outside the closed contour found are searched, as ROI；Two straight lines, and the central point using the intersection point of two straight lines as cross mark to be detected are fitted in ROI.The cross searching position of image can simply, be fast and effectively detected using foregoing invention.
Description
Technical field
The present invention relates to technical field of image processing, more specifically, be related to a kind of robust cross searching detection method and
Device.
Background technology
Image recognition, refer to handle image using computer, analyzed and understood, to identify various different modes
Target and the technology to picture.Typically in industrial application, first using industrial camera shoot picture, then recycle software according to
Picture ash jump does further identifying processing.Wherein, the identification to image cross searching has been widely used marks in characteristics of image
And calculate in two-dimensional image architectural characteristic, for example, cross searching identification technology is applied, to VR, (Virtual Reality are empty
Intend reality technology) horizontal parallax of equipment judged in scene.
But existing image cross searching lookup method is usually relatively complex, and speed is slow, the degree of accuracy is low in the presence of searching
Etc. various problems.
The content of the invention
In view of the above problems, it is current to solve it is an object of the invention to provide a kind of cross searching detection method and device
The problems such as process is cumbersome, detection efficiency and the degree of accuracy are low existing for the detection of picture centre cross.
Cross searching detection method provided by the invention, including corrosion treatment is carried out to image to be detected, form initial graph
Picture；Wherein, cross mark to be detected at least one is provided with image to be detected；Adaptive two-value is carried out to initial pictures
Change is handled, and forms bianry image；Median filter process is carried out to bianry image, to eliminate the noise in bianry image；Search warp
The closed contour of image after median filter process, and the minimum enclosed rectangle corresponding to foundation outside the closed contour found,
As ROI；Two straight lines, and the central point using the intersection point of two straight lines as cross mark to be detected are fitted in ROI.
Furthermore it is preferred that scheme be, in ROI be fitted two between during, two straight lines use least square method
It is fitted and is formed in ROI.
Furthermore it is preferred that scheme be that the number of the cross mark in image to be detected is corresponding with ROI number.
According to another aspect of the present invention, there is provided a kind of cross searching detection means, it is characterised in that single including pretreatment
Member, for carrying out corrosion treatment to image to be detected, form initial pictures；Wherein, at least one is provided with image to be detected
Locate cross mark；Arithmetic element, for carrying out self-adaption binaryzation computing to initial pictures, form bianry image；Filter unit,
For carrying out median filter process to bianry image, to eliminate the noise in bianry image；Area extracting unit, passed through for searching
The closed contour of image after median filter process, and the minimum enclosed rectangle corresponding to foundation outside the closed contour found,
As ROI；Recognition unit, for being fitted two straight lines in ROI, and using the intersection point of two straight lines as cross searching point.
Furthermore it is preferred that scheme be that in recognition unit, two straight lines are fitted formation using least square method in ROI.
Furthermore it is preferred that scheme be that the number of the cross mark in image to be detected is corresponding with ROI number.
Using above-mentioned cross searching detection method and device, burn into binaryzation is carried out to pending image successively, intermediate value is filtered
Ripple processing, the closed contour of the image after median filter process is obtained, and outside the closed contour found corresponding to foundation
Minimum enclosed rectangle, as ROI；Two straight lines are fitted in ROI, and using the intersection point of two straight lines as cross searching point, energy
Enough robusts calculate the position of image cross searching, simple and fast and degree of accuracy height.
In order to realize above-mentioned and related purpose, one or more aspects of the invention include the spy that will be explained in below
Sign.Some illustrative aspects of the present invention are described in detail in following explanation and accompanying drawing.However, these aspect instructions are only
It is some modes in the various modes for can be used the principle of the present invention.In addition, it is contemplated that including all these aspects with
And their equivalent.
Brief description of the drawings
By reference to the explanation below in conjunction with accompanying drawing, and with the present invention is more fully understood, of the invention is other
Purpose and result will be more apparent and should be readily appreciated that.In the accompanying drawings：
Fig. 1 is the cross searching detection method flow chart according to the embodiment of the present invention；
Fig. 2 is nephew's central detection device theory diagram according to the embodiment of the present invention.
Identical label indicates similar or corresponding feature or function in all of the figs.
Embodiment
In the following description, for purposes of illustration, in order to provide the comprehensive understanding to one or more embodiments, explain
Many details are stated.It may be evident, however, that these embodiments can also be realized in the case of these no details.
In other examples, for the ease of describing one or more embodiments, known structure and equipment are shown in block form an.
For the cross searching detection method of the present invention is described in detail, the specific embodiment below with reference to accompanying drawing to the present invention
It is described in detail.
Fig. 1 shows cross searching detection method flow according to embodiments of the present invention.
As shown in figure 1, the cross searching detection method of the embodiment of the present invention, comprises the following steps：
S110：Corrosion treatment is carried out to image to be detected, forms initial pictures；Wherein, it is provided with image to be detected
Cross mark to be detected at least one.
Wherein, treating the corrosion treatment of test image can be expressed as detecting image with structural element, find out figure
The region of the structural element can be put down as in, is that one kind eliminates boundary point, the process for making border internally shrink, beneficial to elimination
Small and insignificant object.
S120：Self-adaption binaryzation processing is carried out to initial pictures, forms bianry image.
Wherein, self-adaption binaryzation processing is carried out to initial pictures, mainly set the gray value of the pixel on image
0 or 255 is set to, whole image is showed the process of obvious black and white effect.Secretly have because the screen of VR products is bright
Difference, therefore self-adaption binaryzation is selected, compared to the integrality that global binary conversion treatment can ensure cross (mark).
S130：Median filter process is carried out to bianry image, to eliminate the noise in bianry image.
S140：The closed contour of the image after median filter process is searched, and is established outside the closed contour found
Corresponding minimum enclosed rectangle, as ROI (region of interest, area-of-interest).
Wherein it is possible to different seeking scopes is preset for different images to be tested, to median filter process
When image afterwards carries out closed contour lookup, can directly it be searched within a preset range.
S150：Two straight lines, and the center using the intersection point of two straight lines as cross mark to be detected are fitted in ROI
Point.
Wherein, because the cross mark on image to be tested is not necessarily standard cross, so as to cause ROI center not
Must be the practical center of cross mark, to realize the accurate lookup to image cross mark center, using minimum in each ROI
Square law is fitted two straight lines, and the intersection point of two straight lines is image to be detected or the cross searching of cross mark to be detected
(central point).
Understand, the number of the cross mark in image to be detected is corresponding with ROI number.
Corresponding with above-mentioned cross searching detection method, the present invention also provides a kind of cross searching detection means.
Fig. 2 shows cross searching detection means principle according to embodiments of the present invention.
As shown in Fig. 2 the cross searching detection means of the embodiment of the present invention, including pretreatment unit, for to be detected
Image carries out corrosion treatment, forms initial pictures；Wherein, cross to be detected at least one is provided with image to be detected
Note；Arithmetic element, for carrying out self-adaption binaryzation computing to initial pictures, form bianry image；Filter unit, for two
It is worth image and carries out median filter process, eliminates the noise in bianry image；Area extracting unit, for searching through medium filtering
The closed contour of image after processing, and minimum enclosed rectangle corresponding to establishing outside the closed contour found, as ROI,
The number of the ROI is corresponding with the number of the cross mark in image to be detected；Recognition unit, for being fitted two in ROI
Straight line, and the central point using the intersection point of two straight lines as cross mark to be detected.
Wherein, in recognition unit, two straight lines can be fitted formation using least square method in ROI.
By above-mentioned embodiment, cross searching detection method and device provided by the invention, it is capable of the inspection of robust
The cross searching of image is measured, simple and convenient and cross searching accuracy of detection is high, error is small.
Cross searching detection method and device according to the present invention are described in an illustrative manner above with reference to accompanying drawing.But
, can also be it will be appreciated by those skilled in the art that the cross searching detection method and device proposed for the invention described above
Do not depart from and make various improvement on the basis of present invention.Therefore, protection scope of the present invention should be wanted by appended right
The content of book is asked to determine.
Claims (6)
- A kind of 1. cross searching detection method, it is characterised in that including：Corrosion treatment is carried out to image to be detected, forms initial pictures；Wherein, at least one is provided with described image to be detected Locate cross mark to be detected；Self-adaption binaryzation processing is carried out to the initial pictures, forms bianry image；Median filter process is carried out to the bianry image, to eliminate the noise in the bianry image；The closed contour of the image after median filter process is searched, and it is minimum corresponding to foundation outside the closed contour found Boundary rectangle, as ROI；Two straight lines are fitted in the ROI, and using the intersection point of two straight lines as the cross mark to be detected Central point.
- 2. cross searching detection method as claimed in claim 1, it is characterised in that two straight lines of fitting in the ROI During,Two straight lines are fitted formation using least square method in the ROI.
- 3. cross searching detection method as claimed in claim 1, it is characterised in thatThe number of cross mark in described image to be detected is corresponding with the ROI number.
- A kind of 4. cross searching detection means, it is characterised in that including：Pretreatment unit, for carrying out corrosion treatment to image to be detected, form initial pictures；Wherein, in the mapping to be checked Cross mark to be detected at least one is provided with as in；Arithmetic element, for carrying out self-adaption binaryzation computing to the initial pictures, form bianry image；Filter unit, for carrying out median filter process to the bianry image, to eliminate the noise in the bianry image；Area extracting unit, for searching the closed contour of the image after median filter process, and in the closure wheel found Minimum enclosed rectangle corresponding to wide outer foundation, as ROI；Recognition unit, for being fitted two straight lines in the ROI, and using the intersection point of two straight lines as described to be detected Cross mark central point.
- 5. cross searching detection means as claimed in claim 4, it is characterised in that in the recognition unit, described two Straight line is fitted formation using least square method in the ROI.
- 6. cross searching detection means as claimed in claim 4, it is characterised in thatThe number of cross mark in described image to be detected is corresponding with the ROI number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711086611.2A CN107818583A (en) | 2017-11-07 | 2017-11-07 | Cross searching detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711086611.2A CN107818583A (en) | 2017-11-07 | 2017-11-07 | Cross searching detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107818583A true CN107818583A (en) | 2018-03-20 |
Family
ID=61603819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711086611.2A Pending CN107818583A (en) | 2017-11-07 | 2017-11-07 | Cross searching detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107818583A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108613630A (en) * | 2018-04-28 | 2018-10-02 | 中国计量大学 | The two linear pipe bubbles based on image processing techniques deviate measuring method |
| CN108876860A (en) * | 2018-04-28 | 2018-11-23 | 中国计量大学 | A kind of image calibration method for pipe bubble offset measurement |
| CN109741314A (en) * | 2018-12-29 | 2019-05-10 | 广州博通信息技术有限公司 | A kind of visible detection method and system of part |
| CN112362309A (en) * | 2020-10-27 | 2021-02-12 | 青岛歌尔声学科技有限公司 | Eccentric parallax testing method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015010451A1 (en) * | 2013-07-22 | 2015-01-29 | 浙江大学 | Method for road detection from one image |
| CN106355613A (en) * | 2016-08-31 | 2017-01-25 | 中国工程物理研究院激光聚变研究中心 | Method for automatically extracting cross pattern center on basis of least square fitting iteration |
-
2017
- 2017-11-07 CN CN201711086611.2A patent/CN107818583A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015010451A1 (en) * | 2013-07-22 | 2015-01-29 | 浙江大学 | Method for road detection from one image |
| CN106355613A (en) * | 2016-08-31 | 2017-01-25 | 中国工程物理研究院激光聚变研究中心 | Method for automatically extracting cross pattern center on basis of least square fitting iteration |
Non-Patent Citations (3)
| Title |
|---|
| 张竞丹 等: "十字激光图像的亚像素中心检测算法研究", 《深圳信息职业技术学院学报》 * |
| 董华冰: "一维图像条形码识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 马勇: "亚像素及模板匹配在十字形标记定位中的应用", 《信息通信》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108613630A (en) * | 2018-04-28 | 2018-10-02 | 中国计量大学 | The two linear pipe bubbles based on image processing techniques deviate measuring method |
| CN108876860A (en) * | 2018-04-28 | 2018-11-23 | 中国计量大学 | A kind of image calibration method for pipe bubble offset measurement |
| CN108613630B (en) * | 2018-04-28 | 2022-03-11 | 中国计量大学 | Two-wire tube level bubble offset measurement method based on image processing technology |
| CN108876860B (en) * | 2018-04-28 | 2023-06-20 | 中国计量大学 | Image calibration method for measuring bubble offset of tube level |
| CN109741314A (en) * | 2018-12-29 | 2019-05-10 | 广州博通信息技术有限公司 | A kind of visible detection method and system of part |
| CN112362309A (en) * | 2020-10-27 | 2021-02-12 | 青岛歌尔声学科技有限公司 | Eccentric parallax testing method and device |
| CN112362309B (en) * | 2020-10-27 | 2023-03-03 | 青岛歌尔声学科技有限公司 | Eccentric parallax testing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
| CN107818583A (en) | Cross searching detection method and device | |
| CN110956661B (en) | Method for calculating dynamic pose of visible light and infrared camera based on bidirectional homography matrix | |
| CN108288264B (en) | Wide-angle camera module contamination testing method | |
| CN105279772B (en) | A kind of trackability method of discrimination of infrared sequence image | |
| JP2012118698A (en) | Image processing system | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN107230212B (en) | Vision-based mobile phone size measuring method and system | |
| CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
| Kumar et al. | Vehicle speed detection using corner detection | |
| Bulugu | Algorithm for license plate localization and recognition for tanzania car plate numbers | |
| CN113205494B (en) | Infrared small target detection method and system based on adaptive scale image block weighting difference measurement | |
| CN108734123B (en) | Highway sign recognition method, electronic device, storage medium, and system | |
| CN105608674B (en) | A kind of image enchancing method based on image registration, interpolation and denoising | |
| CN105678731A (en) | Identification method of buckling of band steel | |
| CN114359149A (en) | Dam bank dangerous case video detection method and system based on real-time image edge enhancement | |
| CN109741306A (en) | Image processing method applied to hazardous chemical storehouse stacking | |
| CN105427276A (en) | Camera detection method based on image local edge characteristics | |
| CN111429437A (en) | Image non-reference definition quality detection method for target detection | |
| CN103473753A (en) | Target detection method based on multi-scale wavelet threshold denoising | |
| CN113284158B (en) | Image edge extraction method and system based on structural constraint clustering | |
| CN109448012A (en) | A kind of method for detecting image edge and device | |
| CN109359646A (en) | Liquid level type Meter recognition method based on crusing robot |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180320 |