CN105654097A - Method for detecting quadrangular marker in image - Google Patents
Method for detecting quadrangular marker in image Download PDFInfo
- Publication number
- CN105654097A CN105654097A CN201511008855.XA CN201511008855A CN105654097A CN 105654097 A CN105654097 A CN 105654097A CN 201511008855 A CN201511008855 A CN 201511008855A CN 105654097 A CN105654097 A CN 105654097A
- Authority
- CN
- China
- Prior art keywords
- line segment
- image
- detection
- tetragon
- edge
- 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.)
- Granted
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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for detecting a quadrangular marker. The method comprises the steps of performing back projection processing on a to-be-detected image in a manner than color distribution in a quadrangular marker area in a to-be-detected image as a template, thereby obtaining a back projection result picture; performing edge detection on the back projection result picture for obtaining an edge detecting result picture; extracting four edge line segments which satisfy a condition of a preset threshold from the edge detecting result picture; calculating the intersection point between two straight lines in which two adjacent line segments in the four edge line segments exist; and obtaining four top points of the quadrangular marker according to the four obtained intersection points. According to the method for detecting the quadrangular marker, the extracted edge line segments are screened through presetting an accumulation threshold so that the number of lines which are used in subsequent calculation is reduced, thereby improving detection speed and detection precision. Furthermore back projection processing is performed on the to-be-detected image before edge detection, thereby reducing interference and influence of a background image to the detected area, and improving detection precision.
Description
Technical field
The present invention relates to technical field of image processing, particularly relate to the detection method of tetragon label in a kind of image.
Background technology
In machine vision and image processing field, adopt the label of advantages of simple that extraction and the detection of image information are had highly important meaning, be favorably improved the accuracy and speed to image procossing. Rectangle marked thing owing to himself shape design is simple, be prone to be extracted the feature of characteristic point and be widely used, in actual applications, rectangle marked thing is shown in the picture is shaped as irregular quadrilateral, therefore, the identification to rectangle marked object area is exactly to trapeziform detection this in image.
In recent years, existing a few studies personnel start the detection of quadrilateral area in image is expanded research, it is that CN103198444A, name are called in the patent documentation of " detection method of image processing apparatus and rectangle " at published application publication number, multiple candidate rectangle is constituted by extracting four straight lines of pairwise orthogonal from a plurality of straight line detected, further according near each angle of each candidate rectangle edge pixel be distributed try to achieve each angle like angular travel degree, finally determine detection rectangle.
But above-mentioned detection method has a disadvantage in that owing to it extracts a plurality of straight line, the straight line number and the intersection point number that participate in calculating are more, therefore there is the detection shortcoming that speed is slow, precision is low.
Summary of the invention
The present invention provides the detection method of tetragon label in a kind of image, compared to prior art, can improve detection speed and accuracy of detection.
For achieving the above object, the present invention provides following technical scheme:
The detection method of tetragon label in a kind of image, including:
In image to be detected, described image to be detected is done back projection process for template by the distribution of color in tetragon label region, obtains back projection result figure;
Described back projection result figure is made rim detection, obtains edge detection results figure;
With predetermined threshold value for condition, from described edge detection results figure, extract the four edges edge line segment satisfied condition;
Calculate the intersection point of any two adjacent segments place straight lines in described four edges edge line segment;
Four summits of described tetragon label are obtained according to four intersection points obtained.
Alternatively, described image to be detected is made back projection for template and is processed by described distribution of color in tetragon label region in image to be detected, also includes before:
Described image application gaussian filtering to be detected is made noise reduction process, and carries out gradation conversion process.
Alternatively, described image to be detected is made back projection for template and is processed by described distribution of color in tetragon label region in image to be detected, including:
For template described image to be detected made backprojection operations with the distribution of color in described tetragon label region, and carry out binary conversion treatment and repeatedly closed operation process.
Alternatively, described with predetermined threshold value for condition, from described edge detection results figure, extract the four edges edge line segment satisfied condition, including:
To preset accumulative threshold value for condition, described edge detection results figure is made accumulated probability type straight line Hough transformation and processes, extract four described edge line segments of the condition that is met.
Alternatively, the intersection point of any two adjacent segments place straight lines in described calculating described four edges edge line segment, including:
When judging that four described edge line segments all exist slope, calculate the slope of edge line segment described in bar;
Four described edge line segments are sorted successively according to the size of slope absolute value, for L1, L2, L3, L4;
Calculate the intersection point of line segment L1 place straight line and line segment L3, L4 place straight line and the intersection point of line segment L2 place straight line and line segment L3, L4 place straight line, it is thus achieved that described four intersection points.
Alternatively, the intersection point of any two adjacent segments place straight lines in described calculating described four edges edge line segment, also include:
When one judged in four described edge line segments or two lines section are absent from slope, calculate its excess-three bar or the slope of two edge line segments that there is slope;
The described edge line segment that there is slope by three or two sorts successively according to the size of slope absolute value, for L1, L2, L3 or L1, L2;
When a line segment is absent from slope, calculate the intersection point of this line segment place straight line and line segment L2, L3 place straight line and the intersection point of line segment L1 place straight line and line segment L2, L3 place straight line, it is thus achieved that described four intersection points;
When two lines section is absent from slope, calculate this two lines section place straight line respectively with the intersection point of line segment L1, L2 place straight line, it is thus achieved that described four intersection points.
Alternatively, four intersection points that described basis obtains obtain four summits of described tetragon label, including:
Calculate the distance that in described four intersection points, any two intersection point is fastened in image coordinate, it is thus achieved that lowest distance value;
Respectively centered by four described intersection points, four square detection regions are set with 1/2nd of described lowest distance value for the length of side;
In four described square detection regions, detection has the harris angle point of eigenvalue of maximum respectively, it is determined that for four summits of described tetragon label.
Alternatively, described in four described square detection regions respectively detection there is the harris angle point of eigenvalue of maximum, it is determined that for four summits of described tetragon label, including:
Four the harris angle points detected are made sub-pixization process, using the result described four summits as described tetragon label.
Alternatively, the distance that in described four intersection points of described calculating, any two intersection point is fastened in image coordinate, it is thus achieved that lowest distance value, including:
Calculated distance value is formed distance set;
Travel through the described distance value in described distance set, it is thus achieved that lowest distance value.
Alternatively, the longest edge of tetragon label described in described image to be detected and the lenth ratio of most minor face are not more than 2.
As shown from the above technical solution, the detection method of tetragon label in image provided by the present invention, including: in image to be detected, described image to be detected is done back projection process for template by the distribution of color in tetragon label region, obtains back projection result figure; Described back projection result figure is made rim detection, obtains edge detection results figure; With predetermined threshold value for condition, from described edge detection results figure, extract the four edges edge line segment satisfied condition; Calculate the intersection point of any two adjacent segments place straight lines in described four edges edge line segment; Four summits of described tetragon label are obtained according to four intersection points obtained.
The detection method of tetragon label in image of the present invention, when extracting edge line segment from edge detection results figure, by arranging predetermined threshold value, the four edges edge line segment satisfied condition is extracted for condition with predetermined threshold value, with based on extracting four the line segments calculating obtained and four summits determining tetragon label, detection speed and accuracy of detection compared with prior art, make the straight line number that participation calculates few, thus can be improved; Further, figure to be detected makees back projection before carrying out rim detection process, it is possible to reduce the background image interference on detecting region and impact, accuracy of detection can be improved.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The flow chart of the detection method of tetragon label in a kind of image that Fig. 1 provides for the embodiment of the present invention;
Fig. 2 is the flow chart of step S103 in the embodiment of the present invention;
Fig. 3 is the flow chart of step S104 in the embodiment of the present invention.
Detailed description of the invention
In order to make those skilled in the art be more fully understood that the technical scheme in the present invention, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only a part of embodiment of the present invention, rather than whole embodiments. Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, all should belong to the scope of protection of the invention.
Refer to the flow chart of the detection method of tetragon label in a kind of image that Fig. 1, Fig. 1 provide for the embodiment of the present invention.
The detection method of tetragon label in the image that the present embodiment provides, need to meet the following conditions when application: the color of the color in (1) tetragon label region and background image has obvious differentiation; (2) distribution of color in tetragon label region is comparatively uniform; (3) longest edge of tetragon label and the lenth ratio of most minor face are not more than 2; (4) tetragon label area ratio/occupancy ratio in whole image to be detected can not be too small.
Detection method described in the present embodiment comprises the following steps:
S100: described image to be detected is done back projection process for template by the distribution of color in tetragon label region in image to be detected, obtains back projection result figure.
Before carrying out this step, first the image to be detected gathered is done pretreatment, specifically include: image to be detected is made noise reduction process by application gaussian filtering, then it is carried out gradation conversion process and be converted to gray level image. The present embodiment can adopt industrial camera gather image, require that when gathering image gathering camera has certain distance from rectangle marked thing.
After image to be detected has been carried out pretreatment, for template image to be detected made backprojection operations with the distribution of color in tetragon label region, and result is carried out binary conversion treatment and repeatedly closed operation process, obtain back projection result figure.
S101: described back projection result figure is made rim detection, obtains edge detection results figure.
S102: with predetermined threshold value for condition, extracts the four edges edge line segment satisfied condition from described edge detection results figure.
Concrete, the edge detection results figure obtained makees accumulated probability type straight line Hough transformation process, wherein, accumulative threshold value is preset by rationally arranging, to preset accumulative threshold value for condition, extracting the four edges edge line segment being met threshold condition, each edge of correspondence markings thing only extracts an edge line segment satisfied condition.
Therefore compared to detection method of the prior art, method described in the present embodiment is by presetting accumulative threshold value, the edge line segment extracted is screened, only extract four edge line segments meeting threshold condition, make the line segment decreased number of participation subsequent calculations, amount of calculation can be reduced, improve detection speed.
S103: calculate the intersection point of any two adjacent segments place straight lines in described four edges edge line segment.
In this step, refer to Fig. 2, before calculating the intersection point obtaining line segment place, edge straight line, first determine whether whether the four edges edge line segment detected exists slope, and its judged result includes following two situation: (1) four edges edge line segment all exists slope; (2) four edges edge line segment there is one or two be absent from slope.
When being judged as the first situation, when namely four edges edge line segment all exists slope, its detailed process calculating intersection point is as follows:
S200: calculate the slope of edge line segment described in bar;
Concrete, the slope k of i-th line sectioniBy the starting point coordinate (x of this line segmenti��yi) and terminal point coordinate (xi�䡢yi'), according to computing formulaCalculating obtains, and wherein starting point coordinate and terminal point coordinate are obtained by edge detection results figure does in previous step the process of accumulated probability type straight line Hough transformation.
S201: four described edge line segments are sorted successively according to the size of slope absolute value, for L1, L2, L3, L4;
S202: calculate the intersection point of line segment L1 place straight line and line segment L3, L4 place straight line and the intersection point of line segment L2 place straight line and line segment L3, L4 place straight line, it is thus achieved that described four intersection points A1, A2, A3, A4.
When being judged as the second situation, namely having one in four edges edge line segment or when two lines section is absent from slope, it is specific as follows that it calculates process:
S300: calculate its excess-three bar or the slope of two edge line segments that there is slope;
The computational methods of slope ibid, particularly as follows: the slope k of i-th line sectioniBy the starting point coordinate (x of this line segmenti��yi) and terminal point coordinate (xi�䡢yi'), according to computing formulaCalculating obtains, and wherein starting point coordinate and terminal point coordinate are obtained by edge detection results figure does in previous step the process of accumulated probability type straight line Hough transformation.
S301: the described edge line segment that there is slope by three or two sorts successively according to the size of slope absolute value, for L1, L2, L3 or L1, L2;
S302: when a line segment is absent from slope, calculates the intersection point of this line segment place straight line and line segment L2, L3 place straight line and the intersection point of line segment L1 place straight line and line segment L2, L3 place straight line, it is thus achieved that described four intersection points A1, A2, A3, A4; When two lines section is absent from slope, calculate this two lines section place straight line respectively with the intersection point of line segment L1, L2 place straight line, it is thus achieved that described four intersection points A1, A2, A3, A4.
When a line segment is absent from slope, calculate the intersection point of this line segment place straight line and line segment L2, L3 place straight line and the intersection point of line segment L1 place straight line and line segment L2, L3 place straight line, it is thus achieved that four intersection points; When two lines section is absent from slope, calculate this two lines section place straight line respectively with the intersection point of line segment L1, L2 place straight line, it is thus achieved that described four intersection points
Therefore detection method described in the present embodiment, when calculating the intersection point of its place straight line according to the edge line segment extracted, by comparing the slope size between each edge line segment, to prejudge position relationship between each line segment (opposite side or face frontier juncture system), then only calculate the intersection point faced between the section of sideline and obtain four intersection points, so that participating in the intersection point decreased number of subsequent calculations. And detection method of the prior art needs to calculate the intersection point between all line segments extracted, the intersection point number participating in subsequent calculations is many, can cause that workload is big, speed is slow, therefore compared with prior art, detection method described in the present embodiment can make amount of calculation be substantially reduced, and can improve detection speed.
S104: obtain four summits of described tetragon label according to four intersection points obtained.
In previous step, four intersection points are obtained by calculating the intersection point of line segment place, any two edges straight line, four intersecting point coordinates obtained are the rough estimate values on four summits to tetragon label, and four summits of tetragon label are accurately measured by four intersection points obtained based on upper step in this step.
Refer to Fig. 3, specifically include following steps:
S400: calculate the distance that in described four intersection points, any two intersection point is fastened in image coordinate, it is thus achieved that lowest distance value.
This step specifically includes: calculate the distance that in four intersection points A1, A2, A3, A4, any two intersection point is fastened in image coordinate, calculated distance value is formed distance set D; Travel through the distance value in described distance set D, it is thus achieved that lowest distance value, be designated as min{D}.
S401: respectively centered by four described intersection points, arranges four square detection regions with 1/2nd of described lowest distance value for the length of side. Namely, respectively centered by four intersection points A1, A2, A3, A4, four square detection regions are set with min{D}/2 for the length of side.
S402: detection has the harris angle point of eigenvalue of maximum respectively in four described square detection regions, it is determined that for four summits of described tetragon label.
This step specifically includes: in four square detection regions, detection has the harris angle point of eigenvalue of maximum respectively, four the harris angle points detected are made sub-pixization process, using the result described four summits as described tetragon label, obtain the fine estimation on four summits of tetragon label, thus completing the detection to tetragon label.
Therefore detection method described in the present embodiment, when detecting harris angle point, it is possible to reasonably arrange harris Corner Detection region according to four intersection points that rough estimate obtains, to reduce detection range, exclusive PCR harris angle point.Compared to the more existing method needing and manually arranging detection region, possesses certain intelligent and convenience. In detection region, detection harris angle point ensure that accuracy of detection simultaneously.
Therefore, the detection method of tetragon label in a kind of image that the present embodiment provides, by the detection to four summits of label, it is possible to preferably the shape facility of label is obtained, summit is detected as harris angle point, it is possible to ensure accuracy of detection.
When extracting edge line segment, by rationally arranging accumulative threshold value, the line segment extracted is screened, the each edge of correspondence markings thing only extracts an edge line segment satisfied condition, make the line segment number that participation calculates less, reduce amount of calculation, detection speed can be improved.
When four summits of rough estimate label, the position relationship between line segment (opposite side or face frontier juncture system) can be judged in advance, only calculating the intersection point facing between the straight line of section place, sideline, the intersection point number making participation subsequent calculations is few, is favorably improved detection speed.
When accurately estimating four summits of label, it is possible to the rough estimate position according to four summits, detection region is rationally set, reduces the detection range of harris angle point, make accuracy of detection improve further.
It addition, detection method described in the present embodiment, process image to be detected by ingenious utilization back projection, the background of substantially differentiation will be had with label field color to filter, therefore make detection process only small by the interference of complex background.
Above the detection method of tetragon label in a kind of image provided by the present invention is described in detail. Principles of the invention and embodiment are set forth by specific case used herein, and the explanation of above example is only intended to help to understand method and the core concept thereof of the present invention. It should be pointed out that, for those skilled in the art, under the premise without departing from the principles of the invention, it is also possible to the present invention carries out some improvement and modification, these improve and modify in the protection domain also falling into the claims in the present invention.
Claims (10)
1. the detection method of tetragon label in an image, it is characterised in that including:
In image to be detected, described image to be detected is done back projection process for template by the distribution of color in tetragon label region, obtains back projection result figure;
Described back projection result figure is made rim detection, obtains edge detection results figure;
With predetermined threshold value for condition, from described edge detection results figure, extract the four edges edge line segment satisfied condition;
Calculate the intersection point of any two adjacent segments place straight lines in described four edges edge line segment;
Four summits of described tetragon label are obtained according to four intersection points obtained.
2. detection method as claimed in claim 1, it is characterised in that described image to be detected is made back projection for template and processed by described distribution of color in tetragon label region in image to be detected, also includes before:
Described image application gaussian filtering to be detected is made noise reduction process, and carries out gradation conversion process.
3. detection method as claimed in claim 1, it is characterised in that described image to be detected is made back projection for template and processed by described distribution of color in tetragon label region in image to be detected, including:
For template described image to be detected made backprojection operations with the distribution of color in described tetragon label region, and carry out binary conversion treatment and repeatedly closed operation process.
4. detection method as claimed in claim 1, it is characterised in that described with predetermined threshold value for condition, extracts the four edges edge line segment satisfied condition from described edge detection results figure, including:
To preset accumulative threshold value for condition, described edge detection results figure is made accumulated probability type straight line Hough transformation and processes, extract four described edge line segments of the condition that is met.
5. detection method as claimed in claim 1, it is characterised in that the intersection point of any two adjacent segments place straight lines in described calculating described four edges edge line segment, including:
When judging that four described edge line segments all exist slope, calculate the slope of edge line segment described in bar;
Four described edge line segments are sorted successively according to the size of slope absolute value, for L1, L2, L3, L4;
Calculate the intersection point of line segment L1 place straight line and line segment L3, L4 place straight line and the intersection point of line segment L2 place straight line and line segment L3, L4 place straight line, it is thus achieved that described four intersection points.
6. detection method as claimed in claim 5, it is characterised in that the intersection point of any two adjacent segments place straight lines in described calculating described four edges edge line segment, also includes:
When one judged in four described edge line segments or two lines section are absent from slope, calculate its excess-three bar or the slope of two edge line segments that there is slope;
The described edge line segment that there is slope by three or two sorts successively according to the size of slope absolute value, for L1, L2, L3 or L1, L2;
When a line segment is absent from slope, calculate the intersection point of this line segment place straight line and line segment L2, L3 place straight line and the intersection point of line segment L1 place straight line and line segment L2, L3 place straight line, it is thus achieved that described four intersection points;
When two lines section is absent from slope, calculate this two lines section place straight line respectively with the intersection point of line segment L1, L2 place straight line, it is thus achieved that described four intersection points.
7. detection method as claimed in claim 1, it is characterised in that four intersection points that described basis obtains obtain four summits of described tetragon label, including:
Calculate the distance that in described four intersection points, any two intersection point is fastened in image coordinate, it is thus achieved that lowest distance value;
Respectively centered by four described intersection points, four square detection regions are set with 1/2nd of described lowest distance value for the length of side;
In four described square detection regions, detection has the harris angle point of eigenvalue of maximum respectively, it is determined that for four summits of described tetragon label.
8. detection method as claimed in claim 7, it is characterised in that described in four described square detection regions respectively detection there is the harris angle point of eigenvalue of maximum, it is determined that for four summits of described tetragon label, including:
Four the harris angle points detected are made sub-pixization process, using the result described four summits as described tetragon label.
9. detection method as claimed in claim 7, it is characterised in that the distance that in described four intersection points of described calculating, any two intersection point is fastened in image coordinate, it is thus achieved that lowest distance value, including:
Calculated distance value is formed distance set;
Travel through the described distance value in described distance set, it is thus achieved that lowest distance value.
10. the detection method as described in any one of claim 1-9, it is characterised in that the longest edge of tetragon label described in described image to be detected and the lenth ratio of most minor face are not more than 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511008855.XA CN105654097B (en) | 2015-12-29 | 2015-12-29 | The detection method of quadrangle marker in image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511008855.XA CN105654097B (en) | 2015-12-29 | 2015-12-29 | The detection method of quadrangle marker in image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105654097A true CN105654097A (en) | 2016-06-08 |
| CN105654097B CN105654097B (en) | 2019-04-16 |
Family
ID=56477280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511008855.XA Expired - Fee Related CN105654097B (en) | 2015-12-29 | 2015-12-29 | The detection method of quadrangle marker in image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105654097B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127778A (en) * | 2016-06-27 | 2016-11-16 | 安徽慧视金瞳科技有限公司 | A kind of line detection method for projecting interactive system |
| CN108109169A (en) * | 2017-12-12 | 2018-06-01 | 深圳市神州云海智能科技有限公司 | A kind of position and orientation estimation method, device and robot based on rectangle mark |
| CN108304840A (en) * | 2017-08-31 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
| CN108665495A (en) * | 2017-03-30 | 2018-10-16 | 展讯通信（上海）有限公司 | Image processing method and device, mobile terminal |
| CN108734743A (en) * | 2018-04-13 | 2018-11-02 | 深圳市商汤科技有限公司 | Method, apparatus, medium and electronic equipment for demarcating photographic device |
| CN108805124A (en) * | 2018-04-18 | 2018-11-13 | 北京嘀嘀无限科技发展有限公司 | Image processing method and device, computer readable storage medium |
| CN109214396A (en) * | 2018-08-24 | 2019-01-15 | 国网安徽省电力有限公司阜阳供电公司 | A kind of industrial equipment image characteristic extracting method and equipment |
| CN109949211A (en) * | 2019-03-07 | 2019-06-28 | 北京麦哲科技有限公司 | A kind of rectangle file and picture cutting method and device |
| CN110097065A (en) * | 2019-05-07 | 2019-08-06 | 厦门商集网络科技有限责任公司 | A kind of line detection method and terminal based on FreeMan chain code |
| CN110136156A (en) * | 2018-02-02 | 2019-08-16 | 北京三快在线科技有限公司 | A kind of polygonal region detection method and device |
| CN110751631A (en) * | 2019-10-10 | 2020-02-04 | 郑州大学 | Rapid high-precision rectangle detection method |
| CN112132163A (en) * | 2020-09-21 | 2020-12-25 | 杭州睿琪软件有限公司 | Method, system and computer readable storage medium for identifying edges of objects |
| CN113588667A (en) * | 2019-05-22 | 2021-11-02 | 合肥联宝信息技术有限公司 | Method and device for detecting object appearance |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080075392A1 (en) * | 2006-09-27 | 2008-03-27 | Fujitsu Limited | Image region detection method, recording medium, and device therefor |
| CN101727581A (en) * | 2009-12-10 | 2010-06-09 | 上海名图软件有限公司 | Plate number tilt correcting method based on character pre-cut |
-
2015
- 2015-12-29 CN CN201511008855.XA patent/CN105654097B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080075392A1 (en) * | 2006-09-27 | 2008-03-27 | Fujitsu Limited | Image region detection method, recording medium, and device therefor |
| CN101727581A (en) * | 2009-12-10 | 2010-06-09 | 上海名图软件有限公司 | Plate number tilt correcting method based on character pre-cut |
Non-Patent Citations (3)
| Title |
|---|
| 刘智: "基于Hough变换的四边形分类识别算法研究", 《广西计算机学会2010年学术年会论文集》 * |
| 张辰 等: "直方图反向投影多目标检测优化算法", 《计算机系统应用》 * |
| 黄柳: "四边形分类识别算法", 《信息技术》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127778A (en) * | 2016-06-27 | 2016-11-16 | 安徽慧视金瞳科技有限公司 | A kind of line detection method for projecting interactive system |
| CN106127778B (en) * | 2016-06-27 | 2019-01-04 | 安徽慧视金瞳科技有限公司 | It is a kind of for projecting the line detection method of interactive system |
| CN108665495A (en) * | 2017-03-30 | 2018-10-16 | 展讯通信（上海）有限公司 | Image processing method and device, mobile terminal |
| CN108665495B (en) * | 2017-03-30 | 2021-11-26 | 展讯通信（上海）有限公司 | Image processing method and device and mobile terminal |
| CN108304840A (en) * | 2017-08-31 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
| CN108109169A (en) * | 2017-12-12 | 2018-06-01 | 深圳市神州云海智能科技有限公司 | A kind of position and orientation estimation method, device and robot based on rectangle mark |
| CN108109169B (en) * | 2017-12-12 | 2021-12-14 | 深圳市神州云海智能科技有限公司 | Pose estimation method and device based on rectangular identifier and robot |
| CN110136156A (en) * | 2018-02-02 | 2019-08-16 | 北京三快在线科技有限公司 | A kind of polygonal region detection method and device |
| US11308710B2 (en) | 2018-02-02 | 2022-04-19 | Beijing Sankuai Online Technology Co., Ltd | Polygonal region detection |
| CN108734743A (en) * | 2018-04-13 | 2018-11-02 | 深圳市商汤科技有限公司 | Method, apparatus, medium and electronic equipment for demarcating photographic device |
| CN108805124A (en) * | 2018-04-18 | 2018-11-13 | 北京嘀嘀无限科技发展有限公司 | Image processing method and device, computer readable storage medium |
| CN109214396A (en) * | 2018-08-24 | 2019-01-15 | 国网安徽省电力有限公司阜阳供电公司 | A kind of industrial equipment image characteristic extracting method and equipment |
| CN109949211A (en) * | 2019-03-07 | 2019-06-28 | 北京麦哲科技有限公司 | A kind of rectangle file and picture cutting method and device |
| CN110097065A (en) * | 2019-05-07 | 2019-08-06 | 厦门商集网络科技有限责任公司 | A kind of line detection method and terminal based on FreeMan chain code |
| CN110097065B (en) * | 2019-05-07 | 2021-09-10 | 厦门商集网络科技有限责任公司 | Freeman chain code-based line detection method and terminal |
| CN113588667A (en) * | 2019-05-22 | 2021-11-02 | 合肥联宝信息技术有限公司 | Method and device for detecting object appearance |
| CN113588667B (en) * | 2019-05-22 | 2024-06-14 | 合肥联宝信息技术有限公司 | Method and device for detecting appearance of object |
| CN110751631A (en) * | 2019-10-10 | 2020-02-04 | 郑州大学 | Rapid high-precision rectangle detection method |
| CN110751631B (en) * | 2019-10-10 | 2023-04-07 | 郑州大学 | Quick and high-precision rectangle detection method |
| CN112132163A (en) * | 2020-09-21 | 2020-12-25 | 杭州睿琪软件有限公司 | Method, system and computer readable storage medium for identifying edges of objects |
| CN112132163B (en) * | 2020-09-21 | 2024-04-02 | 杭州睿琪软件有限公司 | Method, system and computer readable storage medium for identifying object edges |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105654097B (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654097A (en) | Method for detecting quadrangular marker in image | |
| CN107704801B (en) | Curve lane line detection method based on segmented straight line and segmented Bezier curve | |
| US20180122083A1 (en) | Method and device for straight line detection and image processing | |
| CN108986094B (en) | Automatic data updating method for training image library for face recognition | |
| CN106251353A (en) | Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof | |
| CN110619333B (en) | Text line segmentation method, text line segmentation device and electronic equipment | |
| CN105069799A (en) | Angular point positioning method and apparatus | |
| CN108009522B (en) | Road detection method, device and terminal | |
| CN112052782B (en) | Method, device, equipment and storage medium for recognizing parking space based on looking around | |
| CN105678768A (en) | Machine vision-based tire tread detection method | |
| CN111291603A (en) | Lane line detection method, device, system and storage medium | |
| CN109800619B (en) | Image recognition method for citrus fruits in mature period | |
| CN105023265A (en) | Checkerboard angular point automatic detection method under fish-eye lens | |
| CN102999886A (en) | Image edge detector and ruler raster grid line precision detection system | |
| CN109685827B (en) | Target detection and tracking method based on DSP | |
| CN102842039B (en) | Road image detection method based on Sobel operator | |
| CN104715487A (en) | Method for sub-pixel edge detection based on pseudo Zernike moments | |
| CN105260720A (en) | Fingerprint identification method and device | |
| CN102034254A (en) | Method for recognizing geometric figure | |
| CN107909083A (en) | A kind of hough transform extracting method based on outline optimization | |
| CN107909573B (en) | Method and device for detecting knife lines on annular surface of metal workpiece | |
| CN113177941B (en) | Steel coil edge crack identification method, system, medium and terminal | |
| CN103679724B (en) | Slope approximant straight line detection method | |
| CN106815810B (en) | Method and device for determining fitting boundary | |
| CN108734054A (en) | Unobstructed citrusfruit image-recognizing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190416 Termination date: 20191229 |