CN102831424A - Method for extracting visible component by microscope system - Google Patents
Method for extracting visible component by microscope system Download PDFInfo
- Publication number
- CN102831424A CN102831424A CN2012102683441A CN201210268344A CN102831424A CN 102831424 A CN102831424 A CN 102831424A CN 2012102683441 A CN2012102683441 A CN 2012102683441A CN 201210268344 A CN201210268344 A CN 201210268344A CN 102831424 A CN102831424 A CN 102831424A
- Authority
- CN
- China
- Prior art keywords
- visible component
- pixel
- image
- convex polygon
- operator
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a method for extracting visible components by a microscope system, and belongs to the field of image processing of the microscope system. The method comprises the following steps: first, filming to obtain a digital image including a visible component area, then, obtaining a pixel collection of boundaries of the visible component area through image analysis, increasing or decreasing elements in the collection through calculation and arranging the elements to make the elements in the pixel collection connect in sequence to form a closed convex polygon which completely contains the whole area of the visible component. The convex polygon is a minimal convex polygon including the visible component area. Thus, the visible component area can be completely obtained. The method is advantaged by good extracting effect aimed at boundary vague, a certain extent out-of-focus, low-scale contrast, and broken visible components.
Description
Technical field
The present invention relates to microscopic system visible component method for distilling, relate in particular to the location in visible component zone in a kind of microscopic system visual field and the method for complete extraction.
Background technology
Method based on the microscopic system visible component is extracted is well-known.Like the disclosed method and system of the patent of application number 200380108664.X and 201010568805.Coming the segmented extraction target area based on background and visible component gray scale difference value is the method that generally adopts at present.Regrettably; To obscurity boundary, to a certain degree out of focus, low contrast and broken visible component extraction effect are often not good; Can not intactly extract the target area, even can not obtain visible component quantity accurately, and this is related to follow-up all operations to visible component; Like Classification and Identification etc., with the mistake that directly causes net result.
Summary of the invention
The present invention provides a kind of microscopic system visible component method for distilling; With solve to obscurity boundary, to a certain degree out of focus, low contrast and broken visible component extraction effect are not good; The target area can not be intactly extracted, even the problem of visible component quantity accurately can not be obtained.
The technical scheme that the present invention takes is: may further comprise the steps:
(1), take to obtain to include and form subregional digital picture f, wherein digital picture is made up of pixel, includes to form subregion pixel and background pixel, each pixel has the pixel value of oneself;
(2), calculate the image gradient of digital picture f;
wherein G is the image gradient of digital picture f; S is the gradient operator template, and S can select Sobel operator, Robert operator, Prewitt operator;
(3), to the G binary conversion treatment, binarization method can be selected the maximum between-cluster variance method on the one dimension histogram that fixed threshold binarization method or Otsu propose;
(4), bianry image carried out the border follow the tracks of, obtain the orderly two-dimensional coordinate set of the boundary pixel P{p in a visible component zone
1, p
2..., p
n, n is the plain number of boundary pixel element of set, each element of P is made up of x component and y component, like p
1=(p
1.x, p
1.y);
(5), calculating includes the subregional minimum area convex polygon of formation:
1), sort the set of the pixel that obtains in the step (2) from small to large by polar angle, obtains new set P ' { p
1, p
2..., p
n, n is the plain number of boundary pixel element of set;
2), order reads 3 element p from P '
1, p
2, p
3, form two vectors in twos
Calculate the cross product ψ of two vectors, if ψ greater than 0, reads p from P '
4, p
2, p
3, p
4Form two vectors in twos and continue to calculate cross product; Otherwise, deletion p from P '
3, read p
4, p
1, p
2, p
4Calculate cross product; Calculate the element of deleting in the set as stated above; All travel through once up to the middle all elements of P ', obtain the sub-set P of P ' ", " the interior element head and the tail link to each other in order with P; Can obtain comprising the minimal convex polygon in particle zone, i.e. P " interior element is the summit of minimal convex polygon;
(6), the convex polygon that obtains with step (5) is as mask, in digital picture f, obtains the visible component zone.
One embodiment of the present invention is in step (2);
uses gradient operator S that gray level image is carried out neighborhood territory pixel value weighted sum operation, and operator S is as weighting weights foundation.
One embodiment of the present invention is in the step (4); The method that adopts chain code or neighborhood to judge is carried out the border and is followed the tracks of; The chain code method adopts four or eight neighborhood coding and sorting orders of clockwise or counterclockwise traversal time ordered pair pixel: find a frontier point as initial point; According to the traversal order, travel through and get back to initial point after a week as the traversal end condition, during the frontier point of traversal all deposit among the set P; The neighborhood determining method judges that based on the binaryzation result whether each pixel four or eight neighborhoods all are the visible component pixel, if promptly this is the visible component internal point, do not process; Otherwise this is the visible component frontier point, deposits in the frontier point set.
One embodiment of the present invention is in the step (5) 1) in; The polar angle ordering is based on polar coordinates; Polar initial point can be chosen four angles of image; Like the lower left corner, polar angle scope
One embodiment of the present invention is in the step (5) 2) in, vector is calculated by set P ' interior element and gets,
Vector
With
Cross product be expressed as (p
2.x-p
1.x) * (p
3.y-p
2.y)-(p
3.x-p
2.x) * (p
2.y-p
1.y).
The microscopic system that the present invention adopts comprises: imaging system, visible component container, light source, image processing system.Light source has strengthened the brightness and contrast of visible component in its container, and imaging system is taken visible component and formed Digital Image Transmission to the image processing system analysis; Wherein said visible component container is transparent, and light source and imaging system can be positioned at the homonymy or the heteropleural of visible component container.
The feature of image that microscopic system obtains be little in the object lens depth of field, receive under pathology and the medicine factor affecting, local unintelligible and damage boundary very easily takes place in visible component, is difficult to the complete visible component zone of segmented extraction with conventional method.
Advantage of the present invention is: a kind of visible component of microscopic system more accurately method for distilling is provided, to obscurity boundary, to a certain degree out of focus, low contrast and broken visible component also have good extraction effect.The present invention adopts the border salient point to connect to come the segmented extraction visible component, can connect damaged boundary, when accurately extracting the visible component zone, for follow-up shape information extraction and content analysis are laid a good foundation.
Description of drawings
Fig. 1 is the microscopic system structural representation that the present invention adopts, and wherein light source can be placed on position shown in current location or the frame of broken lines;
Fig. 2 a is the urine particle source images of being taken by microscopic system, is specially single squamous cell image;
Fig. 2 b is the urine particle source images of being taken by microscopic system, is specially single squamous cell image;
Fig. 2 c is the urine particle source images of being taken by microscopic system, is specially the leucocyte picture of cliquing graph;
Fig. 2 d is the urine particle source images of being taken by microscopic system, is specially the leucocyte picture of cliquing graph;
Fig. 3 a is depicted as the image gradient synoptic diagram after source images and the sobel operator convolution, and the image among the figure is corresponding with image among Fig. 2 a;
Fig. 3 b is depicted as the image gradient synoptic diagram after source images and the sobel operator convolution, and the image among the figure is corresponding with image among Fig. 2 b;
Fig. 3 c is depicted as the image gradient synoptic diagram after source images and the sobel operator convolution, and the image among the figure is corresponding with image among Fig. 2 c;
Fig. 3 d is depicted as the image gradient synoptic diagram after source images and the sobel operator convolution, and the image among the figure is corresponding with image among Fig. 2 d;
Fig. 4 a is depicted as the minimum area convex polygon apex coordinate synoptic diagram in visible component zone, and the image among the figure is corresponding with image among Fig. 3 a;
Fig. 4 b is depicted as the minimum area convex polygon apex coordinate synoptic diagram in visible component zone, and the image among the figure is corresponding with image among Fig. 3 b;
Fig. 4 c is depicted as the minimum area convex polygon apex coordinate synoptic diagram in visible component zone, and the image among the figure is corresponding with image among Fig. 3 c;
Fig. 4 d is depicted as the minimum area convex polygon apex coordinate synoptic diagram in visible component zone, and the image among the figure is corresponding with image among Fig. 3 d;
Fig. 5 a is depicted as the visible component that obtains according to the inventive method and extracts synoptic diagram as a result, and the image among the figure is corresponding with image among Fig. 4 a;
Fig. 5 b is depicted as the visible component that obtains according to the inventive method and extracts synoptic diagram as a result, and the image among the figure is corresponding with image among Fig. 4 b;
Fig. 5 c is depicted as the visible component that obtains according to the inventive method and extracts synoptic diagram as a result, and the image among the figure is corresponding with image among Fig. 4 c;
Fig. 5 d is depicted as the visible component that obtains according to the inventive method and extracts synoptic diagram as a result, and the image among the figure is corresponding with image among Fig. 4 d.
Embodiment
(1), microscopic system structural representation as shown in Figure 1, wherein light source can be placed on position shown in current location or the frame of broken lines.Imaging system is taken the visible component container and is obtained to include the subregional digital picture f of formation, and wherein digital picture is made up of some pixels, includes and forms subregion pixel and background pixel, and each pixel has the pixel value of oneself.
(2), calculate the image gradient of digital picture f;
wherein; G is the image gradient of digital picture f; S is the gradient operator template, and S can select Sobel operator or Robert operator or Prewitt operator;
When S chooses Sobel operator, G
x, G
yRespectively presentation video f in the horizontal direction with vertical direction on separately gradient statistics;
Horizontal direction Sobel operator:
Vertical direction Sobel operator:
Result of calculation G is shown in Fig. 3 a, Fig. 3 b, Fig. 3 c, Fig. 3 d.
This step of the present invention or employing:
The Robert operator:
With
The Prewitt operator:
With
(3), to the G binary conversion treatment, this instance adopts fixed threshold binaryzation dividing method, binary-state threshold is 40; Or to adopt Otsu method calculated threshold be 41, and the two difference does not have influence to net result;
(4), adopt the chain code method to carry out the border to follow the tracks of, the chain code method adopts the clockwise traversal order encoding ordering of pixel eight neighborhoods, coding rule:
0 | 1 | 2 |
7 | p | 3 |
6 | 5 | 4 |
Wherein, p is a frontier point, and its 8 neighborhood is encoded to 0-7 successively, and 0 direction is the initial traverse direction, and according to clockwise traversal order, 7 directions travel through at last;
When beginning to travel through; At first find in the bianry image left side bottom boundary's point then according to the traversal order, continue traversal as initial point up to returning initial point as the traversal end condition; The point that record traveled through, the orderly two-dimensional coordinate of boundary pixel that obtains a visible component zone is gathered P{p
1, p
2..., p
n, n is the plain number of boundary pixel element of set, each element of P is made up of x component and y component, i.e. p
1=(p
1.x, p
1.y);
(5), calculating includes the subregional minimum area convex polygon of formation:
1), to establish the image lower left corner be true origin, sorts the element in the pixel set P from small to large by polar angle, obtains new set P ' { p
1, p
2..., p
n, n is the plain number of boundary pixel element of set;
2), order reads 3 element p from P '
1, p
2, p
3, form two vectors in twos
Calculate the cross product ψ of two vectors, if ψ greater than 0, reads p from P '
4, p
2, p
3, p
4Form two vectors in twos and continue to calculate cross product; Otherwise, deletion p from P '
3, read p
4, p
1, p
2, p
4Calculate cross product; Calculate the element of deleting in the set as stated above; All travel through once up to the middle all elements of P ', obtain the sub-set P of P ' ", " the interior element head and the tail link to each other in order with P; Can obtain comprising the minimal convex polygon in particle zone, promptly the interior element of P ' is the summit of minimal convex polygon;
Be depicted as P like Fig. 4 a, Fig. 4 b, Fig. 4 c, Fig. 4 d " in the coordinate synoptic diagram of point on image;
(6), P is linked in sequence, and " interior point obtains including and forms subregional minimum area convex polygon, as mask, in digital picture f, obtains the visible component zone with the convex polygon interior zone, like Fig. 5 a, Fig. 5 b, Fig. 5 c, Fig. 5 d.
Claims (5)
1. microscopic system visible component method for distilling is characterized in that may further comprise the steps:
(1), take to obtain to include and form subregional digital picture f, wherein digital picture is made up of pixel, includes to form subregion pixel and background pixel, each pixel has the pixel value of oneself;
(2), calculate the image gradient of digital picture f;
wherein G is the image gradient of digital picture f; S is the gradient operator template, and S can select Sobel operator, Robert operator, Prewitt operator;
(3), to the G binary conversion treatment, binarization method can be selected the maximum between-cluster variance method on the one dimension histogram that fixed threshold binarization method or Otsu propose;
(4), bianry image carried out the border follow the tracks of, obtain the orderly two-dimensional coordinate set of the boundary pixel P{p in a visible component zone
1, p
2..., p
n, n is the plain number of boundary pixel element of set, each element of P is made up of x component and y component, like p
1=(p
1.x, p
1.y);
(5), calculating includes the subregional minimum area convex polygon of formation:
1), sort the set of the pixel that obtains in the step (2) from small to large by polar angle, obtains new set P ' { p
1, p
2..., p
n, n is the plain number of boundary pixel element of set;
2), order reads 3 element p from P '
1, p
2, p
3, form two vectors in twos
Calculate the cross product ψ of two vectors, if ψ greater than 0, reads p from P '
4, p
2, p
3, p
4Form two vectors in twos and continue to calculate cross product; Otherwise, deletion p from P '
3, read p
4, p
1, p
2, p
4Calculate cross product; Calculate the element of deleting in the set as stated above; All travel through once up to the middle all elements of P ', obtain the sub-set P of P ' ", " the interior element head and the tail link to each other in order with P; Can obtain comprising the minimal convex polygon in particle zone, i.e. P " interior element is the summit of minimal convex polygon;
(6), the convex polygon that obtains with step (5) is as mask, in digital picture f, obtains the visible component zone.
2. a kind of microscopic system visible component method for distilling as claimed in claim 1; It is characterized in that: in the step (2);
uses gradient operator S that gray level image is carried out neighborhood territory pixel value weighted sum operation, and operator S is as weighting weights foundation.
3. a kind of microscopic system visible component method for distilling as claimed in claim 1; It is characterized in that: in the step (4), the method that adopts chain code or neighborhood to judge is carried out the border and is followed the tracks of four or eight neighborhood coding and sorting orders of the traversal that the employing of chain code method is clockwise or counterclockwise time ordered pair pixel: find a frontier point as initial point; According to the traversal order; Travel through and get back to initial point after a week as the traversal end condition, during the frontier point of traversal all deposit among the set P, the neighborhood determining method judges whether each pixel four or eight neighborhoods all are the visible component pixel; If promptly this is the visible component internal point, do not process; Otherwise this is the visible component frontier point, deposits in the frontier point set.
4. a kind of microscopic system visible component method for distilling as claimed in claim 1 is characterized in that: step (5) 1) in, polar angle sorts based on polar coordinates, polar initial point is chosen four angles of image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210268344.1A CN102831424B (en) | 2012-07-31 | 2012-07-31 | Method for extracting visible component by microscope system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210268344.1A CN102831424B (en) | 2012-07-31 | 2012-07-31 | Method for extracting visible component by microscope system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102831424A true CN102831424A (en) | 2012-12-19 |
CN102831424B CN102831424B (en) | 2015-01-14 |
Family
ID=47334552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210268344.1A Active CN102831424B (en) | 2012-07-31 | 2012-07-31 | Method for extracting visible component by microscope system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102831424B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107305181A (en) * | 2016-04-18 | 2017-10-31 | 重庆大学 | A kind of method for studying percutaneous dosing solvent penetration |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1380543A (en) * | 2001-04-12 | 2002-11-20 | 清华大学 | Image segmentation and identification method in industrial radiation imaging system |
CN101713776A (en) * | 2009-11-13 | 2010-05-26 | 长春迪瑞实业有限公司 | Neural network-based method for identifying and classifying visible components in urine |
CN101826209A (en) * | 2010-04-29 | 2010-09-08 | 电子科技大学 | Canny model-based method for segmenting three-dimensional medical image |
CN102073876A (en) * | 2011-01-10 | 2011-05-25 | 中国科学院光电技术研究所 | Biochip sampling point identification method based on edge detection |
CN102270233A (en) * | 2011-07-29 | 2011-12-07 | 中国航天科技集团公司第五研究院第五一三研究所 | Searching method for convex hull |
-
2012
- 2012-07-31 CN CN201210268344.1A patent/CN102831424B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1380543A (en) * | 2001-04-12 | 2002-11-20 | 清华大学 | Image segmentation and identification method in industrial radiation imaging system |
CN101713776A (en) * | 2009-11-13 | 2010-05-26 | 长春迪瑞实业有限公司 | Neural network-based method for identifying and classifying visible components in urine |
CN101826209A (en) * | 2010-04-29 | 2010-09-08 | 电子科技大学 | Canny model-based method for segmenting three-dimensional medical image |
CN102073876A (en) * | 2011-01-10 | 2011-05-25 | 中国科学院光电技术研究所 | Biochip sampling point identification method based on edge detection |
CN102270233A (en) * | 2011-07-29 | 2011-12-07 | 中国航天科技集团公司第五研究院第五一三研究所 | Searching method for convex hull |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107305181A (en) * | 2016-04-18 | 2017-10-31 | 重庆大学 | A kind of method for studying percutaneous dosing solvent penetration |
Also Published As
Publication number | Publication date |
---|---|
CN102831424B (en) | 2015-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105261017B (en) | The method that image segmentation based on road surface constraint extracts pedestrian's area-of-interest | |
CN108280450B (en) | Expressway pavement detection method based on lane lines | |
CN102132323B (en) | System and method for automatic image straightening | |
CN102708351B (en) | Method for fast identifying Data Matrix two-dimensional bar code under complicated working condition background | |
CN105100640A (en) | Local registration parallel video stitching method and local registration parallel video stitching system | |
Kierdorf et al. | Behind the leaves: Estimation of occluded grapevine berries with conditional generative adversarial networks | |
CN110414385A (en) | A kind of method for detecting lane lines and system based on homography conversion and characteristic window | |
CN112580447B (en) | Edge second-order statistics and fusion-based power line detection method | |
CN111199195A (en) | Pond state full-automatic monitoring method and device based on remote sensing image | |
CN117197686A (en) | Satellite image-based high-standard farmland plot boundary automatic identification method | |
Xu et al. | Pixel-level pavement crack detection using enhanced high-resolution semantic network | |
CN114494283A (en) | Automatic farmland dividing method and system | |
Chu et al. | Fine‐grained crack segmentation for high‐resolution images via a multiscale cascaded network | |
Kok et al. | Obscured tree branches segmentation and 3D reconstruction using deep learning and geometrical constraints | |
Deng et al. | Cascade refinement extraction network with active boundary loss for segmentation of concrete cracks from high-resolution images | |
CN113920147A (en) | Remote sensing image building extraction method and device based on deep learning | |
CN116935296A (en) | Orchard environment scene detection method and terminal based on multitask deep learning | |
CN102831424B (en) | Method for extracting visible component by microscope system | |
Vukadinov et al. | An algorithm for coastline extraction from satellite imagery | |
Rampriya et al. | RSNet: Rail semantic segmentation network for extracting aerial railroad images | |
CN116311218A (en) | Noise plant point cloud semantic segmentation method and system based on self-attention feature fusion | |
CN107145887B (en) | A kind of seam cutting framing evidence collecting method deleted for object | |
CN108875565A (en) | The recognition methods of railway column, storage medium, electronic equipment, system | |
Tian et al. | Robust text segmentation using graph cut | |
CN108171771A (en) | The line drawing in a kind of combination external margin information and interior polymeric road draws generating algorithm |
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 | ||
CP01 | Change in the name or title of a patent holder |
Address after: 130012 Changchun province high tech Zone, the River Street, No. 95, No. Patentee after: Medical Polytron Technologies Inc Address before: 130012 Changchun province high tech Zone, the River Street, No. 95, No. Patentee before: Changchun Dirui Medical Technology Co., Ltd. |
|
CP01 | Change in the name or title of a patent holder |