CN108062770B - Method for accurately positioning center of micropore in picture of micropore plate by natural photographing - Google Patents
Method for accurately positioning center of micropore in picture of micropore plate by natural photographing Download PDFInfo
- Publication number
- CN108062770B CN108062770B CN201711007652.8A CN201711007652A CN108062770B CN 108062770 B CN108062770 B CN 108062770B CN 201711007652 A CN201711007652 A CN 201711007652A CN 108062770 B CN108062770 B CN 108062770B
- Authority
- CN
- China
- Prior art keywords
- center
- image
- microplate
- positioning
- straight line
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012360 testing method Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 239000011148 porous material Substances 0.000 abstract 2
- 238000001514 detection method Methods 0.000 description 19
- 238000002474 experimental method Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- DEYFWGXTPWNADC-UHFFFAOYSA-N 6-[2-phenylethyl(propyl)amino]-5,6,7,8-tetrahydronaphthalen-1-ol Chemical compound C1CC2=C(O)C=CC=C2CC1N(CCC)CCC1=CC=CC=C1 DEYFWGXTPWNADC-UHFFFAOYSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
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
-
- G06T5/70—
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Abstract
The invention relates to a method for accurately positioning the centers of micropores in a microplate picture by natural photographing, which decomposes the accurate positioning of the centers of the pores of the microplate into the accurate positioning of the rectangular boundary of the microplate and the accurate positioning of the centers of the pores of the microplate according to the well-positioned rectangular boundary. The invention utilizes the fitting of the image and the straight line to position the rectangular boundary, not only has high efficiency and accuracy, but also plays a vital role in positioning the hole center of the microporous plate and provides a guarantee of accuracy for positioning the hole center of the microporous plate. But also greatly improves the working efficiency of hospital and laboratory workers.
Description
Technical Field
The invention relates to the technical field of image positioning, in particular to a method for accurately positioning the center of a micropore in a microplate picture by natural photographing.
Background
The microporous plate is a multipurpose detection test plate and has wide application in clinical experiments, chemical experiments, veterinary reagent detection and the like.
With the development of artificial intelligence, the clinical experiment staff have higher and higher requirements for intelligent and automatic experiments. The intelligent identification of the microporous plate can accelerate the artificial intelligence of clinical experiments, greatly liberate the labor force of experiment workers and promote the development of the society. Furthermore, the experimental reagent in the round hole can be quickly extracted by accurately positioning the hole center of the microporous plate, the experiment is digitalized, the machine learning and the intelligent identification are convenient, and the intelligent automation of the clinical experiment becomes possible.
Therefore, how to accurately position the center of the micropore plate is very important.
Known detection and localization methods include:
the patent No. 201110223911.7 fast rectangle detection method of high resolution large order image: the method comprises the following steps of preprocessing to obtain a cross point set, improving a PPHT detection straight line, searching and deleting the cross point set where all boundary point pixels on the straight line are located along the straight line, searching for accurately matched parallel lines, determining coordinates of rectangular end points and the like. The magnitude of reduced coordinates is realized in the preprocessing of the first step, and the pixel values of n four adjacent pixel coordinate pixels of each boundary point are set as a first numerical value to obtain a cross point set, so that the detection under the high-resolution large-magnitude image is solved. And in the second step, detecting the Hough peak value by using a progressive probability Hough transform algorithm to obtain each straight line corresponding to the boundary point pixel set. The third step is to search the number of non-zero pixel points included in the query on the straight line in a circulating manner, and the largest straight line is obtained. Then, the Euclidean length and the slope of the straight line obtained in the third step are calculated, a pair of parallel straight lines with equal length is searched, and the straight lines are reasonably considered as the boundaries of a rectangle. And finding whether there is a pair of parallel lines starting from the end points that are relatively vertical, forming a complete rectangle. The method can solve the detection problem of the high-resolution large-data-level image; the accuracy is high, and the method is suitable for unknown rectangular size and direction; however, in the preprocessing, the cross point set needs to be calculated in advance, so that the efficiency is low; the detection method needs to accurately find a pair of parallel lines with the same Euclidean length and slope, has limitation on the application range of the rectangle in the actual image, and has large calculation amount.
A rectangular target detection method of patent No. 201610514128.9: the method comprises the steps of extracting sample characteristics, obtaining a root filter, obtaining a component filter, detecting a model and carrying out gradient search calculation. The method relies on machine learning, and a picture without a target object is required to be used as a negative sample in advance to form a training set. Extracting sample characteristics: the pictures with and without rectangular objects are taken as positive samples and negative samples respectively, and are divided into a plurality of cell units, and a direction gradient histogram of each block is obtained. And the second step is to scan the sample picture, extract and combine the directional gradient histograms of all the blocks to form the final characteristic vector, and input the final characteristic vector into a support vector machine to obtain a root filter. And thirdly, searching the position of the component filter according to the position of the root filter, screening out the optimal position according to the score, and inputting the characteristics of the component filter into a hidden variable support vector machine for training. And finally, judging whether the detection frame is outside the edge of the target contour based on the searched edge gradient calculation algorithm, and then adjusting the position of the detection frame. Although the method has high detection accuracy, a large number of pictures are required to be taken as samples for training in advance, and various steps used in the method are more complicated compared with other detection methods.
In addition to the above two methods, there are an image processing apparatus and a rectangle detection method of patent No. 201210439013.X, an image processing apparatus and a straight line detection method of patent No. 201210439005.5, a tool wear detection method based on a minimum circumscribed rectangle of patent No. 201610944459.6, and the like. However, none of these detection methods has the expected effect.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide the method for accurately positioning the centers of the micropores in the picture of the microporous plate by natural photographing, which has high positioning accuracy and high detection efficiency.
In order to achieve the purpose, the technical scheme provided by the invention is as follows: the rectangular boundary of the microplate is positioned first, and then the hole center of the microplate is positioned according to the positioned rectangular boundary.
Wherein, the rectangular boundary of the positioning microplate comprises the following steps:
s1, shooting the image of the micropore plate under natural illumination;
and S2, carrying out graying image, Gaussian low-pass filtering and binary image processing on the image, highlighting the characteristic information of the image, and eliminating irrelevant information of the image, so as to more easily capture the characteristics of the image and more conveniently carry out the following operation and judgment. And, acquiring the number XMax of the horizontal pixel points and the number YMax of the longitudinal pixel points of the image in advance.
S3, deleting a small-area connected domain;
s4, deleting burrs of the main connected domain, eliminating irrelevant pixel points left in the steps S2 and S3, and simultaneously acquiring a reference point for straight line fitting so as to make a boundary line in the next step;
s5, fitting a straight line and correcting a rectangle;
positioning the well center of the microplate comprises the steps of:
s6, blurring the center of the positioning hole: determining the center position of each hole according to the rectangular area obtained in the step S5;
and S7, accurately positioning the hole center.
Further, the image preprocessing of step S2 includes graying out the image, gaussian low-pass filtering, and binarizing the image.
Further, the step S3 of deleting the small-area connected domain includes traversing and recording eight connected domains, calculating the area of each connected domain, sorting all the connected domains from small to large according to the areas, and deleting the small-area connected domains according to the corresponding proportion. The method comprises the following specific steps:
s3-1, traversing and recording the eight-connected region: calculating and recording the number of communication points of the small object region and the position corresponding to each communication point by using MATLAB self-contained functions (bwleaeln and regionprops);
s3-2, calculating the area of each connected domain: the area of one connected domain can be replaced by the total number of the connected points, so that the area of each connected domain is obtained by counting the number of the connected points of each connected domain;
s3-3, sorting all connected domains from small to large according to area;
and S3-4, deleting the small-area connected domain according to the proportion. According to specific conditions, small areas of 50% -80% of all connected domains are deleted, the connected areas of small object areas are eliminated, noise points are further eliminated, and irrelevant pixel points are eliminated.
Further, step S4 deletes the main connected domain burrs to approach the actual boundary line with the test points sequentially from the upper, lower, left, and right directions of the image; the specific steps for approaching the actual boundary line in a single direction are as follows:
s4-1, obtaining a test point: randomly acquiring the number of the transverse test points XMax alpha percent according to the proportion of alpha percent (alpha percent is the proportion of the number of the test points to be supposed to be extracted and the size of the pixels of the length or the width of the image) by using the parameters (XMax and YMax) transmitted from the preprocessing step according to the characteristics of the image, and recording the coordinate value (x, 0) of each test point by using a data structure;
s4-2, judging whether the current test point is a filling point (whether the pixel point value is '1'), and if the pixel point value is '1', defining the current test point as a collision; otherwise, defining the test point as a non-collision state, and enabling the transverse test point to advance towards the center direction of the image;
s4-3, if the current test points collide, a rectangular area with the length of XMax beta% and the width of YMax beta% is made by taking the current test points as the center, and then the number N of filling pixel points in the area is calculated; if the number of N is larger than or equal to M (M is a critical value for judging whether the number of N is a burr), the test point is considered to be very close to the actual boundary line, the forward movement is stopped, and the step S4-4 is carried out; on the contrary, when N is smaller than M, the collision area is considered as an irrelevant pixel point, the pixel point is eliminated, the area is skipped, the process is continued to advance, the next test point is entered, and the step S4-2 is returned; if the current test point does not collide, continuing to move towards the center direction of the image, entering the next test point, changing all pixel points in the area to be 0, changing the coordinate of the test point to be (x, y + YMax x beta%), and returning to the step S4-2;
and S4-4, recording coordinates of the test points, and incorporating the coordinates into a point set for making a boundary line.
Further, the step S5 is a concrete step of fitting a straight line to find the intersection point, as follows:
s5-1, acquiring four groups of reference points: acquiring the point set obtained in step S4;
s5-2, performing dot separation connection on each group of reference points: because the deviation of the straight line made by two adjacent points is overlarge, two points are taken by adopting a rule of separating one point, and then a straight line is calculated;
s5-3, counting the filling points on each fitting straight line of each group:
s5-4, selecting a straight line with the largest filling point number according to the counted filling point numbers by each group, and taking the straight line as a boundary line of the group direction;
and S5-5, obtaining four end points of the rectangular frame according to the four straight line simultaneous straight line equation sets obtained in the step S5-4, and recording the four end points.
S5-6, performing perspective transformation by using a rectangular rectification function getPerpectiontransform () and warpPeractive () of opencv according to the four vertexes obtained in the step S5-5, rectifying and extracting the microplate picture.
Further, the step S6 is to blur the center of the positioning hole as follows:
s6-1, confirming the length and width of the rectangular area in the image: using the coordinate difference between the four end points obtained in step S5 to obtain the side length of the rectangular region in the image, and determining the length and width of the rectangular region;
s6-2, cutting boundary lines of all edges of the image rectangle in equal proportion according to the length proportion relation between the frame of the micropore plate and the boundary of the micropore plate which is measured in advance, and recording the seats of cutting points;
s6-3, performing straight line fitting according to the two cutting points which correspond up and down or left and right, solving the intersection point of the two straight lines in the left and right direction and the up and down direction, namely the circle center, and solving the radius according to the proportional relation between the side length of the microporous plate and the radius of the circular hole;
and S6-4, respectively recording the coordinate values of the centers of the holes in the central area of the image and the corresponding radiuses one by one.
Further, the specific step of precisely positioning the hole center in step S7 is as follows:
s7-1, extracting the round holes one by one according to the radius and the position of the circle center to be used as a target area for processing;
s7-2, performing circular recognition of the corresponding radius of the target region by using Hough function houghbridge ();
s7-3, removing the circle with the newly positioned circle center deviating from the original circle center by more than 10% of pixel value through the average value and all circles identified in the step S7-2 of screening the known radius and circle center coordinates, and carrying out average value calculation on the X, Y coordinates and the radius of the circle center;
and S7-4, adding the adjusted hole center coordinates to the relative position of the target area in the image to obtain the hole center coordinates and the corresponding radius value of each circular hole in the image, namely the position of each hole center in the image.
The principle of the scheme is as follows:
how to accurately position the center of each hole of the microporous plate is decomposed into how to position the rectangular boundary of the microporous plate and how to accurately position the center of the hole of the microporous plate according to the positioned rectangular boundary.
When the rectangular boundary of the microporous plate is positioned, the image processing technology is adopted to simplify the image, noise and burrs in the image are deleted, then the rectangular boundary is obtained through a method of straight line fitting detection, rectangular perspective transformation is carried out on the positioned rectangular region, and a standard rectangular region picture of the microporous plate is extracted.
When the hole center of the micropore plate is accurately positioned, because the rectangular area of the micropore plate is standard, the actual proportion can not be changed, the equal proportion point of each edge boundary line is solved according to the proportion of the frame and the edge of the micropore plate, the equal proportion straight line intersection point is calculated on the positioned and corrected rectangle, namely, the hole center position of each hole, thereby realizing the fuzzy positioning of the micropore plate, and then the Hough function houghCrick () is utilized to correspondingly adjust the position of each hole, thereby reducing the dependence of the round hole positioning on the rectangular boundary positioning, and ensuring that the positioning of the circle center is more flexible and the position is more accurate, thereby solving the problem of the accurate positioning of the hole center of the micropore plate.
Compared with the prior art, utilize image and sharp fitting, fix a position rectangle boundary, it is not only high-efficient accurate, still to the hole center location of micropore board play crucial effect, provide the assurance of accuracy for the hole center of location micropore board. But also greatly improves the working efficiency of hospital and laboratory workers.
Drawings
FIG. 1 is a flow chart of a method for accurately positioning the centers of micro-holes in a microplate picture photographed by nature according to the present invention;
FIG. 2 is a schematic view of a mold for a microplate;
FIG. 3 is a flow chart of deleting small-area connected domains in the present invention;
FIG. 4 is a flowchart of the present invention for removing a primary connected domain spur;
FIG. 5 is a flow chart of the present invention for finding the intersection point by straight line fitting;
FIG. 6 is a flow chart of the present invention for blurring the center of the positioning holes;
FIG. 7 is a flow chart of the present invention for precisely locating the center of a hole.
Detailed Description
The invention will be further illustrated with reference to specific examples:
referring to fig. 1, in the method for accurately positioning the center of a micropore in a microplate picture obtained by natural photography according to the embodiment, a rectangular boundary of a microplate is positioned first, and then the center of the micropore of the microplate is positioned according to the positioned rectangular boundary;
wherein, the rectangular boundary of the positioning microplate comprises the following steps:
s1, shooting the image of the micropore plate under natural illumination;
s2, carrying out graying, Gaussian low-pass filtering and binarization processing on the image;
s3, deleting a small-area connected domain; as shown in fig. 3, the specific steps are as follows:
s3-1, traversing and recording the eight-connected region: calculating and recording the number of communication points of the small object region and the position corresponding to each communication point by using MATLAB self-contained functions (bwleaeln and regionprops);
s3-2, calculating the area of each connected domain;
s3-3, sorting all connected domains from small to large according to area;
and S3-4, deleting the small-area connected domain according to the proportion.
S4, deleting the burrs of the main connected domain; test points are required to be adopted to approach the actual boundary line from the upper direction, the lower direction, the left direction and the right direction of the image respectively, as shown in fig. 4, the specific steps of approaching the actual boundary line in a single direction are as follows:
s4-1, obtaining a test point;
s4-2, judging whether the current test point collides;
s4-3, if the current test points collide, a rectangular area with the length of XMax beta% and the width of YMax beta% is made by taking the current test points as the center, and then the number N of filling pixel points in the area is calculated; if the number of N is more than or equal to M, stopping advancing, and proceeding to step S4-4; on the contrary, when N is smaller than M, the collision area is considered as an irrelevant pixel point, the pixel point is eliminated, the area is skipped, the process is continued to advance, the next test point is entered, and the step S4-2 is returned; if the current test point does not collide, continuing to move forward towards the center of the image, entering the next test point, and returning to the step S4-2;
and S4-4, recording coordinates of the test points, and incorporating the coordinates into a point set for making a boundary line.
S5, fitting a straight line to solve an intersection point; as shown in fig. 5, the specific steps are as follows:
s5-1, acquiring four groups of reference points, namely an upper group, a lower group, a left group and a right group;
s5-2, performing point separation connection on each group of reference points to avoid overlarge straight line deviation between two adjacent points;
s5-3, counting the number of filling points on each fitting straight line of each group;
s5-4, according to the counted filling points, then calculating a straight line with the largest filling points, and taking the straight line as a boundary line of the group direction;
and S5-5, obtaining four end points of the rectangular frame according to the four straight line simultaneous straight line equation sets obtained in the step S5-4, and recording the four end points.
S5-6, performing perspective transformation by using a rectangular rectification function getPerpectiontransform () and warpPeractive () of opencv according to the four vertexes obtained in the step S5-5, rectifying and extracting the microplate picture.
Positioning the well center of the microplate comprises the steps of:
s6, blurring the center of the positioning hole; as shown in fig. 6, the specific steps are as follows:
s6-1, confirming the length and width of the rectangular area in the image;
s6-2, cutting boundary lines of all edges of the image rectangle in equal proportion according to the length proportion relation between the frame of the micropore plate and the boundary of the micropore plate which is measured in advance, and recording the seats of cutting points;
s6-3, performing straight line fitting according to the two cutting points which correspond up and down or left and right, solving the intersection point of the two straight lines in the left and right direction and the up and down direction, namely the circle center, and solving the radius according to the proportional relation between the side length of the microporous plate and the radius of the circular hole;
and S6-4, respectively recording the coordinate values of the centers of the holes of the image target area and the corresponding radiuses one by one.
S7, accurately positioning the center of the hole; as shown in fig. 7, the specific steps are as follows:
s7-1, extracting the round holes one by one according to the radius and the position of the circle center to be used as a target area for processing;
s7-2, performing circle recognition on the target area by utilizing a Hough function;
s7-3, removing the circle with the newly positioned circle center deviating from the original circle center by more than 10% of pixel value through the average value and all circles identified in the step S7-2 of screening the known radius and circle center coordinates, and carrying out average value calculation on the X, Y coordinates and the radius of the circle center;
and S7-4, adding the adjusted hole center coordinates to the relative position of the target area in the image to obtain the hole center coordinates and the corresponding radius values of all the round holes in the image.
The embodiment utilizes image and straight line fitting to fix a position rectangle boundary, and is not only high-efficient accurate, still plays crucial effect to the hole center location of micropore board, provides the assurance of accuracy for the hole center of location micropore board. But also greatly improves the working efficiency of hospital and laboratory workers.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that variations based on the shape and principle of the present invention should be covered within the scope of the present invention.
Claims (6)
1. A method for accurately positioning the center of a micropore in a microplate picture by natural photographing is characterized in that: firstly, positioning a rectangular boundary of a microporous plate, and then positioning the hole center of the microporous plate according to the positioned rectangular boundary;
wherein, the rectangular boundary of the positioning microplate comprises the following steps:
s1, shooting the image of the micropore plate under natural illumination;
s2, preprocessing the image;
s3, deleting a small-area connected domain;
s4, deleting the burrs of the main connected domain;
s5, fitting a straight line and correcting a rectangle;
positioning the well center of the microplate comprises the steps of:
s6, blurring the center of the positioning hole;
s7, accurately positioning the center of the hole;
the specific steps of linearly fitting and correcting the rectangle in step S5 are as follows:
s5-1, acquiring four groups of reference points, namely an upper group, a lower group, a left group and a right group;
s5-2, performing point separation connection on each group of reference points;
s5-3, counting the number of filling points on each fitting straight line of each group;
s5-4, selecting a straight line with the largest filling point number according to the counted filling point numbers by each group, and taking the straight line as a boundary line of the group direction;
s5-5, obtaining four end points of the rectangular frame according to the four straight line simultaneous straight line equation sets obtained in the step S5-4, and recording the end points;
s5-6, performing perspective transformation by using a rectangular rectification function getPerpectiontransform () and warpPeractive () of opencv according to the four vertexes obtained in the step S5-5, rectifying and extracting the microplate picture.
2. The method of claim 1 for accurately locating the center of a microwell in a microplate picture of a natural photograph, wherein: the preprocessing of the image in step S2 includes graying, gaussian low-pass filtering, and binarization processing of the image.
3. The method of claim 1 for accurately locating the center of a microwell in a microplate picture of a natural photograph, wherein: the specific steps of step S3 are as follows:
s3-1, traversing and recording the eight connected domains;
s3-2, calculating the area of each connected domain;
s3-3, sorting all connected domains from small to large according to area;
and S3-4, deleting the small-area connected domain according to the proportion.
4. The method of claim 1 for accurately locating the center of a microwell in a microplate picture of a natural photograph, wherein: the step S4 is to approach the actual boundary line with the test points from the upper, lower, left, and right directions of the image in sequence.
5. The method of claim 1 for accurately locating the center of a microwell in a microplate picture of a natural photograph, wherein: the step S6 of blurring the center of the positioning hole includes the following steps:
s6-1, confirming the length and width of the rectangular area in the image;
s6-2, cutting boundary lines of each edge of the image rectangle in equal proportion according to the length proportion relation between the frame of the micropore plate and the boundary of the micropore plate which is measured in advance, and recording coordinates of a cutting point;
s6-3, performing straight line fitting according to the two cutting points which correspond up and down or left and right, solving the intersection point of the two straight lines in the left and right direction and the up and down direction, namely the circle center, and solving the radius according to the proportional relation between the side length of the microporous plate and the radius of the circular hole;
and S6-4, respectively recording the coordinate values of the centers of the holes of the image target area and the corresponding radiuses one by one.
6. The method of claim 1 for accurately locating the center of a microwell in a microplate picture of a natural photograph, wherein: the specific step of accurately positioning the hole center in the step S7 is as follows:
s7-1, extracting the round holes one by one according to the radius and the position of the circle center to be used as a target area for processing;
s7-2, performing circle recognition on the target area by utilizing a Hough function;
s7-3, removing the circle with the newly positioned circle center deviating from the original circle center by more than 10% of pixel value through the average value and all circles identified in the step S7-2 of screening the known radius and circle center coordinates, and carrying out average value calculation on the X, Y coordinates and the radius of the circle center;
and S7-4, adding the adjusted hole center coordinates to the relative position of the target area in the image to obtain the hole center coordinates and the corresponding radius values of all the round holes in the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711007652.8A CN108062770B (en) | 2017-10-25 | 2017-10-25 | Method for accurately positioning center of micropore in picture of micropore plate by natural photographing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711007652.8A CN108062770B (en) | 2017-10-25 | 2017-10-25 | Method for accurately positioning center of micropore in picture of micropore plate by natural photographing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108062770A CN108062770A (en) | 2018-05-22 |
| CN108062770B true CN108062770B (en) | 2021-08-17 |
Family
ID=62137030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711007652.8A Active CN108062770B (en) | 2017-10-25 | 2017-10-25 | Method for accurately positioning center of micropore in picture of micropore plate by natural photographing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108062770B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723734B (en) * | 2020-06-19 | 2022-02-18 | 哈尔滨理工大学 | Hole site identification method based on machine vision |
| CN115540746B (en) * | 2022-01-06 | 2023-06-20 | 深圳荣耀智能机器有限公司 | Structural member side hole position detection method |
| CN116298241A (en) * | 2023-01-09 | 2023-06-23 | 浙江宝太智能科技有限公司 | Hole site positioning method for chemiluminescent immunoassay analyzer detection system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463159A (en) * | 2014-12-31 | 2015-03-25 | 北京释码大华科技有限公司 | Image processing method and device of iris positioning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206116B (en) * | 2007-12-07 | 2010-08-18 | 北京机械工业学院 | Goal spot global automatic positioning method |
| JP6547903B2 (en) * | 2015-09-30 | 2019-07-24 | 日本電気株式会社 | Image processing apparatus, image processing method and storage medium |
| CN105469084A (en) * | 2015-11-20 | 2016-04-06 | 中国科学院苏州生物医学工程技术研究所 | Rapid extraction method and system for target central point |
-
2017
- 2017-10-25 CN CN201711007652.8A patent/CN108062770B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463159A (en) * | 2014-12-31 | 2015-03-25 | 北京释码大华科技有限公司 | Image processing method and device of iris positioning |
Non-Patent Citations (2)
| Title |
|---|
| 基于圆拟合的非完整圆激光光斑中心检测算法;王拯洲 等;《激光与红外》;20130630;第43卷(第6期);第708-711页 * |
| 基于灰度信息和支持向量机的人眼检测方法;于明鑫 等;《工程科学学报》;20150630;第37卷(第6期);第804-811页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108062770A (en) | 2018-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109801337B (en) | 6D pose estimation method based on instance segmentation network and iterative optimization | |
| CN110148196B (en) | Image processing method and device and related equipment | |
| CN108062770B (en) | Method for accurately positioning center of micropore in picture of micropore plate by natural photographing | |
| CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
| CN105046197B (en) | Multi-template pedestrian detection method based on cluster | |
| CN109726717B (en) | Vehicle comprehensive information detection system | |
| Gomez et al. | Traffic lights detection and state estimation using hidden markov models | |
| CN107506760A (en) | Traffic signals detection method and system based on GPS location and visual pattern processing | |
| CN106407981A (en) | License plate recognition method, device and system | |
| CN105913093A (en) | Template matching method for character recognizing and processing | |
| CN108564114B (en) | Human body fecal leucocyte automatic identification method based on machine learning | |
| CN105989334B (en) | Road detection method based on monocular vision | |
| CN110443791B (en) | Workpiece detection method and device based on deep learning network | |
| CN111881790A (en) | Automatic extraction method and device for road crosswalk in high-precision map making | |
| CN106778779A (en) | A kind of electric injection molding machine mould detection method | |
| CN103258201A (en) | Form line extraction method integrating global information and local information | |
| CN102999886A (en) | Image edge detector and ruler raster grid line precision detection system | |
| CN109741325B (en) | Intelligent detection method for wiring verticality | |
| CN107452035B (en) | Method and apparatus for analyzing lane line image and computer readable medium thereof | |
| Ji et al. | Integrating visual selective attention model with HOG features for traffic light detection and recognition | |
| CN106709524A (en) | Component symbol detection and identification method in electrical engineering drawing | |
| Zhang et al. | Edge detection based on improved sobel operator | |
| CN104915678A (en) | Detection method and apparatus of target object in power transmission line | |
| CN111257329A (en) | Smartphone camera defect detection method and detection system | |
| CN104966047A (en) | Method and device for identifying vehicle license |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |