CN103177449B - Based on mobile foursquare image boundary extraction method - Google Patents
Based on mobile foursquare image boundary extraction method Download PDFInfo
- Publication number
- CN103177449B CN103177449B CN201310109713.7A CN201310109713A CN103177449B CN 103177449 B CN103177449 B CN 103177449B CN 201310109713 A CN201310109713 A CN 201310109713A CN 103177449 B CN103177449 B CN 103177449B
- Authority
- CN
- China
- Prior art keywords
- square
- image
- line segment
- intersection point
- mobile
- 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.)
- Expired - Fee Related
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- IYLGZMTXKJYONK-ACLXAEORSA-N (12s,15r)-15-hydroxy-11,16-dioxo-15,20-dihydrosenecionan-12-yl acetate Chemical compound O1C(=O)[C@](CC)(O)C[C@@H](C)[C@](C)(OC(C)=O)C(=O)OCC2=CCN3[C@H]2[C@H]1CC3 IYLGZMTXKJYONK-ACLXAEORSA-N 0.000 description 2
- IYLGZMTXKJYONK-UHFFFAOYSA-N ruwenine Natural products O1C(=O)C(CC)(O)CC(C)C(C)(OC(C)=O)C(=O)OCC2=CCN3C2C1CC3 IYLGZMTXKJYONK-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of based on mobile foursquare image boundary extraction method, comprise the following steps: 1) image is transformed into Lab color space, for L component, color data scope is divided into n region, and give each region and number accordingly, each pixel number of image is converted into the numbering in region corresponding to this pixel native color numerical value; 2) for described L component, all four pixels of mutually adjoining are configured to square, utilize division line segment to split each square, make in square, to number identical summit and be in the same area, and the end points of described division line segment is in the mid point of square side; 3) to any two squares that are connected, will the division line segment of intersection point be had to be interconnected to form cut-off rule, the outward flange of this cut-off rule and image forms described image boundary jointly.The disposable Boundary Extraction completing image of the present invention, efficiency is higher, and speed is faster.
Description
Technical field
The present invention relates to computer image processing technology field, particularly relate to one in image boundary extraction based on mobile foursquare image boundary extraction method.
Background technology
The edge of object refers to occur in image the part of light intensity sudden change, namely object edge pixel and adjacent area pixel in gray level compared with there is the characteristic of jump, this is the foundation of general edge detection algorithm.Border is the essential characteristic of image, contains the useful information of the image overwhelming majority.The rim detection of digital picture is the basis of the art of image analysis such as Iamge Segmentation, target area identification, region shape extraction, first usual image understanding and analysis are rim detection, and the rim detection of current digital image has become one of most active problem of machine vision research field.
So-called image boundary, refer to the border of objects in images, general pattern monochrome information changes the border that obvious place is considered to image object, boundary information has very important in image processing field, all have great significance in fields such as comprising Iamge Segmentation, image vector, image abstraction, decide the accuracy of the result of its process.
In image, one of method of object characteristic parameter diagnosis is the border of extracting image, determines the shape of target to be measured, area, mean radius and center-of-mass coordinate etc. again by data boundary.The extraction on border is generally divided into two steps: the first step, adopts edge detection operator to obtain edge image; Second step, the object edge in edge image carries out frontier tracing.When edge feature is comparatively complicated and when there is the interference of other intersect edge, the automatic extraction on border is often very difficult.
The edge of image refers to the part that image local area brightness is changed significantly, and the gray scale section in this region generally can be regarded as a step, both changes to the larger gray-scale value of another gray scale difference from the play of having to go to the toilet in very little buffer area of a gray-scale value.The most information of image has been concentrated in the marginal portion of image, the determination of image border is very important with the Understanding and reasoning extracted for whole image scene, also be the key character that Iamge Segmentation relies on simultaneously, tolerance, the detection and positioning of the rim detection mainly grey scale change of image, since 1959 propose rim detection, through the development of five more than ten years, existing many middle different edge detection methods.
At present, the various Boundary Extraction technology proposed, such as, based on the boundary extraction method etc. of Canny rim detection, consider brightness of image to be changed obvious position as image border, then connect adjacent marginal point as border, but do not consider whether image boundary is closed.Such algorithm is only considered the Information locating at edge and is not considered the globality of the object representated by border; In addition, the Boundary Extraction based on the square algorithm of traditional movement for black white image, once can only carry out division isoline according to a demarcation threshold, can not disposablely extract multistage gray scale.
Summary of the invention
The invention provides a kind of based on mobile foursquare image boundary extraction method, the method is used for extracting the border of multi-grey image, disposable complete extraction while ensure image boundary close with continuously.
A kind of based on mobile foursquare image boundary extraction method, comprise the following steps:
1) image is transformed into Lab color space, for L component, color data scope is divided into n region, and give each region and number accordingly, each pixel number of image is converted into the numbering in region corresponding to this pixel native color numerical value;
2) for described L component, all four pixels of mutually adjoining are configured to square, utilize division line segment to split each square, make in square, to number identical summit and be in the same area, and the end points of described division line segment is in the mid point of square side;
3) to any two squares that are connected, will the division line segment of intersection point be had to be interconnected to form cut-off rule, the outward flange of this cut-off rule and image forms described image boundary jointly.
As preferably, described n is the natural number of 2 ~ 256, and each zone number is from 0 to (n-1), and the span in each region is 256/n.Pixel number is 0-255, and meaningless when n is 1, and during n=2, image becomes bianry image, and 256 is the upper limit.
Further preferred, described n is 16 ~ 64, and this is an empirical value, according to be can not too little because too little colouring information after quantizing seldom, border has been lacked can not reflect image well, the too large too many data volume in border too redundancy.
As preferably, also comprise and the cut-off rule in step 3) is carried out smooth treatment, then obtain described image boundary.The advantage of smooth treatment is that the closed boundary entirety of image is more smooth, and the border of general object is all smooth, or even continuous curve shape, can be understood as more near the actual boundary of image object after smooth.
Preferred further, described described smooth treatment is:
Determine the intersection point of cut-off rule and each square side, if the division line segment of these intersection point both sides in respective square all without point of crossing, then this intersection point mobile, makes the angle between the division line segment of these intersection point both sides increase.
First the intersection point of cut-off rule and each square side is determined, judge the division line segment of these intersection point both sides again in respective square with or without point of crossing, this point of crossing is the intersection point dividing line segment in same square, if point of crossing exists, keep the position of intersecting point of current cut-off rule and each square side constant, if without corresponding point of crossing, current intersection point is moved in side, angle between the division line segment of these intersection point both sides is increased, namely completes the smooth treatment to cut-off rule.
Further preferred, during intersection point described in mobile, the square side along this intersection point place moves.Boundary intersection on side, must can not exceed side ranges, and the thought of skew is that the knuckle of line is as far as possible little, broken line angle is little mean more smooth.
Preferred further, the displacement of described intersection point and the ratio of the square length of side are 0 ~ 1:2.End points due to each division line segment is in the mid point of square side, namely the intersection point of cut-off rule and each square side is in the mid point of square side, in the process of intersection point movement, the position of intersection point can not offset whole square, because intersection point is exactly between the square that surrounds in pixel, depart from foursquare border just to mean and go to outside one other pixel, the current pixel wanting to surround can not be surrounded.
The present invention has following 2 beneficial effects:
1, the present invention is directed to abstracted image and extract image boundary, and make border become level and smooth by the position of the boundary line end points of adjustment local, the border of extracting has closure, and whole image becomes different regions by by these boundary segmentation;
2, boundary extraction method of the present invention disposablely by the Boundary Extraction of image out and can only extract isoline for a kind of threshold value unlike the square algorithm of traditional movement, and efficiency is higher, and speed is faster.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that the present invention is based on mobile foursquare image boundary extraction method.
Fig. 2 is the position view dividing line segment in square of the present invention.
The schematic diagram of intersection point adjustment when Fig. 3 is smooth treatment of the present invention.
Embodiment
As shown in Figure 1, a kind of based on mobile foursquare image boundary extraction method, implementation step is as follows:
(1) image is transformed into Lab color space, for L component, color data scope is divided into 16 regions, and give each region and number accordingly, each zone number is from 0 to 15, the span in each region is 16, then each pixel number of image is converted into the numbering in region corresponding to this pixel native color numerical value, namely each pixel number of image is converted into the numerical value in 0 ~ 15.
(2) for L component, all four pixels of mutually adjoining are configured to square, utilize division line segment to split each square, make in square, to number identical summit and be in the same area, and the end points dividing line segment is in the mid point of square side.
Four pixels are configured in square, and when there is different colors in square, wherein the boundary line of two kinds of colors is division line segment.
As shown in Figure 2, all four pixels of mutually adjoining are configured to square, when four pixels are same color (see a figure), in the square that these four pixels are built into, only there is a kind of color, illustrate that this square is not on the border of image, therefore, in this square, there is not division line segment.
As shown in b figure in Fig. 2, have eight squares in b figure, have two colors in each square, dividing line section is positioned on the boundary line of these two colors.
As shown in c figure in Fig. 2, have six squares in c figure, have three kinds of different colours in each square, dividing line section is positioned on the boundary line of arbitrary two kinds of colors, in part square, there is point of crossing in the division line segment between arbitrary two kinds of colors in this square.
As shown in d figure in Fig. 2, in the square in d figure, have four kinds of colors, divide the boundary line that line segment is four kinds of colors, and in square, there is point of crossing in division line segment.
Divide line segment in 2 in figure and will number identical vertex partition in square at the same area, and the end points that every bar divides line segment is in the mid point of square side.
(3) to any two squares that are connected, will the division line segment of intersection point be had to be interconnected to form cut-off rule, the common composing images border of outward flange of this cut-off rule and image.
After having the division line segment of intersection point to be interconnected to obtain cut-off rule, also need to carry out smooth treatment to cut-off rule, the method of smooth treatment is: the intersection point first determining cut-off rule and each square side, judge the division line segment of these intersection point both sides again in respective square with or without point of crossing, this point of crossing is the intersection point dividing line segment in same square, if point of crossing exists, keep the position of intersecting point of current cut-off rule and each square side constant, if without corresponding point of crossing, current intersection point is moved along the square side at this intersection point place in side, and the ratio of the displacement of intersection point and the square length of side is 0 ~ 1:2, angle between the division line segment of these intersection point both sides is increased.
As shown in Figure 3, in figure, 3 is the image after nine squares are communicated with, wherein in each square, the line of band arrow is division line segment, be respectively and divide line segment ab, divide line segment bc and divide line segment cd, above-mentioned three division line segments are linked to be cut-off rule abcd, are increase the angle dividing line segment ab and divide between line segment cd to the object of cut-off rule abcd smooth treatment.A dotted line ac is built between a point and c point, dotted line ac is crossing with square side obtains e point, e point is b point along the point after square side transverse shifting, in like manner, between b point and d point, a dotted line bd, dotted line bd are crossing with square side obtains f point, f point for c point vertically move along square side after point, connect the cut-off rule that aefd obtains, be the image boundary after smooth treatment.
Claims (5)
1., based on a mobile foursquare image boundary extraction method, it is characterized in that, comprise the following steps:
1) image is transformed into Lab color space, for L component, color data scope is divided into n region, and give each region and number accordingly, each pixel number of image is converted into the numbering in region corresponding to this pixel native color numerical value;
2) for described L component, all four pixels of mutually adjoining are configured to square, utilize division line segment to split each square, make in square, to number identical summit and be in the same area, and the end points of described division line segment is in the mid point of square side;
3) to any two squares that are connected, by there being the division line segment of intersection point to be interconnected to form cut-off rule, carry out smooth treatment process to secant, the outward flange of this cut-off rule and image forms described image boundary jointly;
Described described smooth treatment is:
Determine the intersection point of cut-off rule and each square side, if the division line segment of these intersection point both sides in respective square all without point of crossing, this point of crossing is the intersection point dividing line segment in same square, then this intersection point mobile, and the angle between the division line segment of these intersection point both sides is increased.
2., as claimed in claim 1 based on mobile foursquare image boundary extraction method, it is characterized in that, described n is the natural number of 2 ~ 256, and each zone number is from 0 to (n-1), and the span in each region is 256/n.
3., as claimed in claim 2 based on mobile foursquare image boundary extraction method, it is characterized in that, described n is 16 ~ 64.
4. as claimed in claim 1 based on mobile foursquare image boundary extraction method, it is characterized in that, during intersection point described in mobile, the square side along this intersection point place moves.
5., as claimed in claim 4 based on mobile foursquare image boundary extraction method, it is characterized in that, the displacement of described intersection point and the ratio of the square length of side are 0 ~ 1:2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310109713.7A CN103177449B (en) | 2013-03-29 | 2013-03-29 | Based on mobile foursquare image boundary extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310109713.7A CN103177449B (en) | 2013-03-29 | 2013-03-29 | Based on mobile foursquare image boundary extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103177449A CN103177449A (en) | 2013-06-26 |
| CN103177449B true CN103177449B (en) | 2015-08-26 |
Family
ID=48637279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310109713.7A Expired - Fee Related CN103177449B (en) | 2013-03-29 | 2013-03-29 | Based on mobile foursquare image boundary extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103177449B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977972B (en) * | 2017-12-01 | 2019-03-05 | 浙江科技学院 | A kind of image partition method |
| CN109752723B (en) * | 2019-01-07 | 2020-12-29 | 北京臻迪科技股份有限公司 | Underwater topographic map drawing method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251932A (en) * | 2008-03-18 | 2008-08-27 | 中国科学院软件研究所 | Plant leaf analogy method based on physics |
-
2013
- 2013-03-29 CN CN201310109713.7A patent/CN103177449B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251932A (en) * | 2008-03-18 | 2008-08-27 | 中国科学院软件研究所 | Plant leaf analogy method based on physics |
Non-Patent Citations (3)
| Title |
|---|
| Geometric Desing and Space Planning Using the Marching Squares and Marching Cube Algorithms;Carsten Maple;《Geometric Modeling and Graphics,2003》;20031231;全文 * |
| Matthias Müller等..Screen Space Meshes.《Proceeding of the 2007 ACM SIGGRAPH/Eurographics Symposium on Computer Animation》.2007, * |
| 虚拟植物叶片的可视化建模技术研究;王立臣;《中国优秀硕士学位论文全文数据库-信息科技辑》;20100115(第1期);正文20页第1段及21页4.2.2节，46页第1段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103177449A (en) | 2013-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wei et al. | Toward automatic building footprint delineation from aerial images using CNN and regularization | |
| CN107767382B (en) | The extraction method and system of static three-dimensional map contour of building line | |
| CN107704801B (en) | Curve lane line detection method based on segmented straight line and segmented Bezier curve | |
| CN104331689B (en) | The recognition methods of a kind of cooperation mark and how intelligent individual identity and pose | |
| CN102930561B (en) | Delaunay-triangulation-based grid map vectorizing method | |
| CN107578035A (en) | Human body contour outline extracting method based on super-pixel polychrome color space | |
| CN109859226B (en) | Detection method of checkerboard corner sub-pixels for graph segmentation | |
| CN107679436A (en) | A kind of image correcting method suitable for Bending Deformation Quick Response Code | |
| CN109816669A (en) | A kind of improvement Mask R-CNN image instance dividing method identifying power equipments defect | |
| CN105740860A (en) | Automatic detection method for Chinese character area of shop sign in natural scene | |
| CN106157323A (en) | The insulator division and extracting method that a kind of dynamic division threshold value and block search combine | |
| CN104200197A (en) | Three-dimensional human body behavior recognition method and device | |
| CN102881017B (en) | Cell separation method | |
| CN104899881A (en) | Shadow detection method for moving vehicle in video image | |
| CN103049731A (en) | Decoding method for point-distributed color coding marks | |
| CN103226829A (en) | Image edge detection method based on edge enhancement operator | |
| CN109754440A (en) | A kind of shadow region detection method based on full convolutional network and average drifting | |
| CN105068918A (en) | Page test method and device | |
| CN104778833A (en) | Traffic light recognition method | |
| CN107527343A (en) | A kind of agaricus bisporus stage division based on image procossing | |
| Feng et al. | A separating method of adjacent apples based on machine vision and chain code information | |
| CN104143096A (en) | Binary connected domain labeling method based on address event representation | |
| CN103500451B (en) | A kind of independent floating ice extracting method for satellite data | |
| CN103177449B (en) | Based on mobile foursquare image boundary extraction method | |
| CN105787912A (en) | Classification-based step type edge sub pixel localization 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 | ||
| C14 | Grant of patent or utility model | ||
| 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: 20150826 Termination date: 20210329 |