CN103955937A - Microalgae automatic counting method based on digital image processing - Google Patents
Microalgae automatic counting method based on digital image processing Download PDFInfo
- Publication number
- CN103955937A CN103955937A CN201410205197.2A CN201410205197A CN103955937A CN 103955937 A CN103955937 A CN 103955937A CN 201410205197 A CN201410205197 A CN 201410205197A CN 103955937 A CN103955937 A CN 103955937A
- Authority
- CN
- China
- Prior art keywords
- image
- micro
- microalgae
- counting method
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a microalgae automatic counting method based on digital image processing. Digitalized processing is conducted on a preprocessed picture through a matlab image processing method to extract a binary image, morphological processing is conducted on the image, and the amount of microalgae is calculated. The problems of heavy labor and measurement errors caused by manual counting of microalgae microscopic images at present are solved. Meanwhile, the reliable counting method and the reliable counting steps are provided for the difficult problem that due to the fact that the microalgae microscopic images are easily affected by illumination impurity interference, light-background dark objects and cytoadherence, the microalgae can not be accurately counted, and the microalgae automatic counting method has important significance in microalgae growth monitoring.
Description
Technical field
The present invention relates to a kind of micro-algae automatic counting method based on Digital Image Processing, belong to microalgae culture system field.
Background technology
At present, micro-algae method of counting is mainly microscope manual observation counting method.Microscope manual observation counting method is with the micro-algae sample on microscopic examination microslide, then to micro-algae artificial counting, thereby drawing various parameters, result is more accurate, but inefficiency, speed is very slow.And micro-algae micro-image is easily subject to the interference of illumination, impurity etc., accurately cuts apart counting to image and bring difficulty.
Summary of the invention
The object of the invention is for overcoming the above-mentioned existing artificial micro-algae counting difficult problem such as waste time and energy, the present invention is directed to that micro-algae micro-image is subject to the interference of illumination impurity, the dark object of bright background, cytoadherence and the difficult problem that is difficult to accurate counting statistics provides reliable method of counting and step simultaneously.
The present invention adopts following scheme to realize: a kind of micro-algae automatic counting method based on Digital Image Processing, is characterized in that comprising the following steps:
(1) get microscope sample, make microslide, be placed under microscope and amplify, obtain coloured image;
(2) convert the coloured image of input to gray-scale map;
(3) gray-scale map is carried out to image median filter processing;
(4) image after medium filtering processing is done to end cap conversion, strengthen picture contrast;
(5) with the threshold method of the maximum equation difference, calculate the optimal threshold of the gray level image after step (4) is processed, with this optimal threshold, the gray level image after step (4) is processed is cut apart, and be converted into binary image;
(6) described binary image is carried out to morphological operation;
(7) remove the assorted point that area is less than a predetermined value;
(8) region that mark is communicated with, with each microalgae cell of color mark;
(9) area distributions in the microalgae cell region that statistics is labeled, shows microalgae cell sum.
In an embodiment of the present invention, in above-mentioned steps (2), the computing method of image ash value are Gray=0.29900*R+0.58700*G+0.11400*B; In formula, Gray represents the brightness of coloured image pixel, and R represents the pixel value of coloured image red component, and G represents the pixel value of coloured image green component, and B represents the pixel value of coloured image blue component.
In an embodiment of the present invention, medium filtering described in above-mentioned steps (3) is processed glide filter window used for [5 * 5].
In an embodiment of the present invention, the method in above-mentioned steps (4) is: the image after medium filtering is processed is with a structural element by closed operation Delete Objects from piece image, and then poor operation obtains a width and only retains the image of having deleted component; The structural element that end cap conversion is used for radius be the structural element of the disc-shape of 60 pixel sizes.
In an embodiment of the present invention, above-mentioned steps (6) concrete operation step is: first image after binaryzation is corroded, and negate, then image is carried out to morphological reconstruction, more once negate, and then image is closed to operation, then corrode; The structural element that above-mentioned morphological operation is used is the structural element that radius is the disc-shape of 10 pixel sizes.
In an embodiment of the present invention, the method in above-mentioned steps (7) is: in the bwareaopen function deleted image of use Matlab, area is less than the object of area threshold; Area threshold is 10, uses 8 neighborhoods.
Beneficial effect of the present invention: the present invention obtains year glass image of micro-algae with microscope, by data line, send into computing machine, by computing machine, samples pictures is carried out to figure identification, from digital photo, recognize and count out microalgae cell, the inventive method has adopted digital image processing techniques, has advantages of that cost is lower, work efficiency is high and accuracy is high.Artificial counting method inefficiency, slow-footed shortcoming have been overcome.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the micro-algae method of counting based on Digital Image Processing of the present invention.
Fig. 2 is the micro-algae original graph under microscope of the present invention.
Fig. 3 is the design sketch after image ash of the present invention value.
Fig. 4 is the design sketch after medium filtering of the present invention.
Fig. 5 is the design sketch after the end of the present invention cap conversion.
Fig. 6 is the design sketch after binary conversion treatment of the present invention.
Fig. 7 is the design sketch after morphology of the present invention is processed.
Fig. 8 is that removal area of the present invention is crossed the design sketch after wisp.
Fig. 9 is the figure after color mark of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.
With reference to process flow diagram 1, described a kind of micro-algae automatic counting method based on digital picture, comprises the following steps:
Step 101, gets microscope sample, makes microslide, is placed under microscope and amplifies, and obtains image, then is input to computing machine by data line.
Step 102, converts the coloured image of input to gray-scale map.
Step 103, carries out image pre-service to gray-scale map.
Step 104, does an end cap conversion to image, strengthens picture contrast.
Step 105, the optimal threshold with the threshold method of the maximum equation difference calculating gray level image, to Image Segmentation Using, is converted into binary image by image by this threshold value.
Step 106, carries out a series of morphological operation to the image after Threshold segmentation.
Step 107, remove area in image too small, the assorted point of microalgae cell certainly not.
Step 108, the region that mark is communicated with.
Step 109, with each microalgae cell of color mark.
Step 110, the area distributions in the microalgae cell region that statistics is labeled, shows microalgae cell sum.
Concrete, please continue referring to Fig. 1.
1. image acquisition
Get appropriate micro-algae sample on microslide, put under biological microscope (40x) and amplify, then connect computing machine by data line, obtain image.
2. image ash value
First convert the coloured image of input to gray-scale map.In the counting of micro-algae, mainly used the monochrome information of microalgae cell in image.The description of the gray level image colourity of whole and part and the distribution of brightness degree and the feature that have still reflected entire image the same as coloured image, and coloured image is converted into the calculated amount that gray level image can make follow-up image becomes few.
The method of the present invention's ash value is method of weighted mean.Its principle be take R, G, B and is set up rectangular coordinate system in space as axle, and the color of each pixel of RGB figure can represent with this three-dimensional point, and the color of each pixel of Gray figure can represent with a point on straight line R=G=B.So it is exactly to find a three dimensions to the mapping of the one-dimensional space that cromogram turns the essence of gray-scale map, what the most easily expect is exactly projection (point crossing rgb space is done vertical line to straight line R=G=B), and has Gray=0.29900*R+0.58700*G+0.11400*B.In formula, Gray represents the brightness of coloured image pixel, and R represents the pixel value of coloured image red component, and G represents the pixel value of coloured image green component, and B represents the pixel value of coloured image blue component.
3. medium filtering
Micro-algae gray level image is carried out to medium filtering processing, to remove the noise in gray level image.Medium filtering glide filter window used is [5 * 5].
4. end cap conversion
Image after medium filtering is carried out to end cap conversion, to proofread and correct the impact of uneven illumination.End cap conversion is by closed operation Delete Objects from piece image, and then poor operation obtains a width and only retains the image of having deleted component.
The structural element that end cap conversion is used for radius be the structural element of the disc-shape of 60 pixel sizes.
End cap transform definition is as follows:
Making original image is f, and the closed operation of f is (fb), and the image after the conversion of end cap is B
hat(f).
B
hat(f)=(f·b)-f (4-1)
5. Threshold segmentation
With maximum between-cluster variance threshold method, calculate the optimal threshold of gray level image, by this threshold value to Image Segmentation Using.Maximum between-cluster variance threshold method is to derive on the basis of principle of least square method, and its computing method are as follows: the gray-scale value of establishing piece image is m, and the pixel count that gray-scale value is i is n
i, obtain total pixel number and be:
The probability of each gray-scale value is:
Then by k value, be divided into two groups of C
0=[1 ... k] and C
1=[k+1 ... m], C
0the probability that group produces is:
C
1the probability that group produces is:
C
0the average gray value of group is:
C
1average gray value be:
Ensemble average gray-scale value is:
When threshold value is k, the mean value of gray scale is:
The average gray of sampling is μ=ω
0u
0+ ω
1u
1, the formula of variance between two groups is as follows:
d(k)=ω
0(u
0-u)
2+ω
1(u-u
1)
2 (5-9)
Overall intensity mean value is brought into formula (5-9) to be obtained:
d(k)=ω
0ω
1(u
1-u
2)
2 (5-10)
From changing k value between 1~m, ask k
*, make d (k
*)=max (d (k)); Then, with k
*for Threshold segmentation image, so just obtain best segmentation effect.
Image is converted into binary image, and what in image, pixel was greater than optimal threshold is set to 255, otherwise is 0.
Making former gray level image is f (x, y), and the image after binaryzation is g (x, y).
6. morphology is processed
Image after binaryzation needs morphology to process conventionally, to remove some stains, AC is cut apart simultaneously.Applicant, by lot of experiment validation, makes following morphology to micro-algae micro-image and processes, and can effectively remove the tiny stain in image, cuts apart AC.
Morphology treatment step is as follows: first image after binaryzation is corroded, image is negated, then image is carried out to morphological reconstruction, more once negate, and then image is closed to operation, then corrode.The structural element that above-mentioned morphological operation is used is the structural element that radius is the disc-shape of 10 pixel sizes.
(6.1) inversion operation method is as follows:
If the image after binaryzation is g (x, y), the image after inversion operation is h (x, y).
(6.2) morphological reconstruction method is as follows:
Morphological reconstruction refers to the morphological transformation of two width images and a structural element, and piece image is marking image, is the starting point of conversion; Another piece image is mask image, is used for retraining conversion process.
Morphological reconstruction can be understood as on probability carries out reexpansion to marking image, until the profile of marking image is applicable to mask image.
Make F expressive notation image, G represents template image,
represent that size is 1 marking image,
(F) expressive notation image F learns and rebuilds the expansion form of template image G.Marking image is carried out to reexpansion and be defined as F about the geodesic dilation of G, geodesic dilation is defined as:
Iterate until steady state (SS).
Iteration k time, until
(6-4)
(6.3) pass operational method is as follows:
Close computing and first piece image is corroded, and then use identical structural element to carry out expansive working.
Make A represent piece image, B represents structural elements, and AB represents the closed operation of structural elements B to image A, and it is defined as follows:
(6.4) erosion operation method is as follows:
Make A represent piece image, B represents structural elements, and c represents translation, and A Θ B represents the corrosion operation of structural elements B to image A, and it is defined as follows:
(6.5) dilation operation method is as follows:
Make A represent piece image, B represents structural elements, A
b represents the expansive working of structural elements B to image A, A
cthe supplementary set that represents A ,-B represents that B is about the symmetric set of true origin, it is defined as follows:
7. remove the too small object of object area
Remove area in image too small, the assorted point of micro-algae certainly not.Its area threshold is 10, uses 8 neighborhoods.
8. mark
The region that mark is communicated with, to add up chromosomal quantity and area.
White portion after image is cut apart, regard as a micro-phycobiont, according to BMP picture format from left to right, scan image from top to bottom, if find a white pixel point, be assumed to be A point, assign A point as Seed Points, by its mark value, be 1, and outwards find other white pixel point being connected with its 4 neighborhood, each the such some mark value finding is made as to 1, then take respectively each such point as Seed Points continuation searching, until can not find the connected white pixel point of unmarked mistake, such connected region is complete with regard to mark.
The white pixel point that continuation is found next unmarked mistake from A point according to scanning sequency is done Seed Points, and its mark value is made as to 2, finds the white pixel point of the unmarked mistake being connected with its 4 neighborhoods, so repeatedly, until entire image been scanned.With each micro-algae of color mark, to intuitively show.
9. add up
The area distributions in micro-phycobiont region that statistics is labeled, shows micro-algae sum.
The main points of technical scheme of the present invention have:
1. before Threshold segmentation, first image is done to end cap conversion, solve the difficult problem that the dark object of the bright background of micro-algae micro-image is difficult to accurately cut apart, to proofread and correct inhomogeneous illumination.
2. after Threshold segmentation, first image is made to a series of morphology and process, solve the problem that micro-algae micro-image impurity stain is many, cytoadherence is serious.
Embodiment 1
Figure 2 shows that micro-algae micro-image of the required counting of the present embodiment.
F=imread (' Fig. 2 .bmp'); % reads in image
I=rgb2gray (f); The value of % image ash
Image ash value effect as shown in Figure 3.
I=rgb2gray (f); The value of % image ash
I1=medfilt2 (I, [5,5]); % medium filtering
Image ash value effect as shown in Figure 4.
se=strel('disk',60);
J=imbothat (I1, se); Cap conversion at the bottom of %
End cap transform effect as shown in Figure 5.
level=graythresh(J);
BW=im2bw (J, level); % is converted into bianry image by image
Binaryzation effect as shown in Figure 6.
se1=strel('disk',10);
Ie=imerode (BW, se1); % corrodes image
Iobr=imreconstruct (Ie, BW); % morphological reconstruction
Iobrd=imdilate (Iobr, se1); % expands to image
Iobrcbr=imreconstruct (imcomplement (Iobrd) ... imcomplement (Iobr)); Morphological reconstruction
Iobrcbr=imcomplement (Iobrcbr); % image is negated
se2=strel('disk',10);
Iopen=imerode(Iobrcbr,se2);
Idilate=imdilate(Iopen,se2);
Morphology treatment effect as shown in Figure 7.
Ibw=bwareaopen (Idilate, 10); % removes the too small pixel of area
Remove area and cross wisp effect as shown in Figure 8.
[labeled, numObjects]=bwlabel (Ibw, 4); % mark connected region
RGB_label=label2rgb (labeled ,@spring, ' c', ' shuffle'); % mark connected region
Mark effect as shown in Figure 9.
chrdata=regionprops(labeled,'basic');
allchrs=[chrdata.Area];
Num=numObjects; % adds up micro-algae sum
Statistics is:
num=47;
Verification experimental verification:
With windows photo reader, open picture, naked eyes carry out artificial counting, and artificial counting result is: 48.
Make n
countingthe count results that represents this method, n
manuallyrepresent artificial counting result, accuracy rate η
accuratelyfor:
This example rate of accuracy reached 98%.
The micro-algae automatic counting method based on Digital Image Processing that applicant utilizes the present invention to propose, collects 540 micro-algae micro-images and verifies, total count rate of accuracy reached 92%.
The foregoing is only preferred embodiment of the present invention, all equalizations of doing according to the present patent application the scope of the claims change and modify, and all should belong to covering scope of the present invention.
Claims (6)
1. the micro-algae automatic counting method based on Digital Image Processing, is characterized in that comprising the following steps:
(1) get microscope sample, make microslide, be placed under microscope and amplify, obtain coloured image;
(2) convert the coloured image of input to gray-scale map;
(3) gray-scale map is carried out to image median filter processing;
(4) image after medium filtering processing is done to end cap conversion, strengthen picture contrast;
(5) with the threshold method of the maximum equation difference, calculate the optimal threshold of the gray level image after step (4) is processed, with this optimal threshold, the gray level image after step (4) is processed is cut apart, and be converted into binary image;
(6) described binary image is carried out to morphological operation;
(7) remove the assorted point that area is less than a predetermined value;
(8) region that mark is communicated with, with each microalgae cell of color mark;
(9) area distributions in the microalgae cell region that statistics is labeled, shows microalgae cell sum.
2. the micro-algae automatic counting method based on Digital Image Processing as claimed in claim 1, is characterized in that: in above-mentioned steps (2), the computing method of image ash value are * R+0.58700, Gray=0.29900 * G+0.11400 * B; In formula, Gray represents the brightness of coloured image pixel, and R represents the pixel value of coloured image red component, and G represents the pixel value of coloured image green component, and B represents the pixel value of coloured image blue component.
3. the micro-algae automatic counting method based on Digital Image Processing as claimed in claim 1, is characterized in that: medium filtering described in above-mentioned steps (3) is processed glide filter window used for [5 * 5].
4. the micro-algae automatic counting method based on Digital Image Processing as claimed in claim 1, it is characterized in that: the method in above-mentioned steps (4) is: the image after medium filtering is processed is with a structural element by closed operation Delete Objects from piece image, and then poor operation obtains a width and only retains the image of having deleted component; The structural element that end cap conversion is used for radius be the structural element of the disc-shape of 60 pixel sizes.
5. the micro-algae automatic counting method based on Digital Image Processing as claimed in claim 1, it is characterized in that: above-mentioned steps (6) concrete operation step is: first image after binaryzation is corroded, and negate, then image is carried out to morphological reconstruction, once negate again, and then image is closed to operation, then corrode; The structural element that above-mentioned morphological operation is used is the structural element that radius is the disc-shape of 10 pixel sizes.
6. the micro-algae automatic counting method based on Digital Image Processing as claimed in claim 1, is characterized in that: the method in above-mentioned steps (7) is: in the bwareaopen function deleted image of use Matlab, area is less than the object of area threshold; Area threshold is 10, uses 8 neighborhoods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410205197.2A CN103955937A (en) | 2014-05-15 | 2014-05-15 | Microalgae automatic counting method based on digital image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410205197.2A CN103955937A (en) | 2014-05-15 | 2014-05-15 | Microalgae automatic counting method based on digital image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103955937A true CN103955937A (en) | 2014-07-30 |
Family
ID=51333206
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410205197.2A Pending CN103955937A (en) | 2014-05-15 | 2014-05-15 | Microalgae automatic counting method based on digital image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103955937A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794710A (en) * | 2015-04-13 | 2015-07-22 | 上海泽煜实验设备有限公司 | Image processing method and device |
CN104794711A (en) * | 2015-04-13 | 2015-07-22 | 上海泽煜实验设备有限公司 | Image processing method and device |
CN104867159A (en) * | 2015-06-05 | 2015-08-26 | 北京大恒图像视觉有限公司 | Stain detection and classification method and device for sensor of digital camera |
CN106780522A (en) * | 2016-12-23 | 2017-05-31 | 杭州华卓信息科技有限公司 | A kind of bone marrow fluid cell segmentation method based on deep learning |
WO2017114439A1 (en) * | 2015-12-28 | 2017-07-06 | 清华大学深圳研究生院 | Image processing-based method and device for measuring growth degree of algae on silicone rubber surface |
CN107123102A (en) * | 2017-05-24 | 2017-09-01 | 天津工业大学 | A kind of adherent cell growth degrees of fusion automatic analysis method |
CN107767361A (en) * | 2017-08-28 | 2018-03-06 | 江苏理工学院 | A kind of carborundum line grain count method, storage device and terminal device |
CN107958459A (en) * | 2017-11-01 | 2018-04-24 | 浙江农林大学 | A kind of method and system for building phase contrast microscope cell image hierarchy structure information |
CN108171683A (en) * | 2017-12-12 | 2018-06-15 | 杭州键生物科技有限公司 | A kind of method for cell count using software automatic identification |
ES2685220R1 (en) * | 2017-03-30 | 2018-11-14 | Universidade De Vigo | Method for estimating microalgal growth |
CN108876752A (en) * | 2018-07-06 | 2018-11-23 | 武汉兰丁医学高科技有限公司 | The image recognition method of counting of blood cell |
CN109030488A (en) * | 2018-06-25 | 2018-12-18 | 中国海洋大学 | Algae bio quantity measuring method and device |
CN109447945A (en) * | 2018-09-21 | 2019-03-08 | 河南农业大学 | Wheat Basic Seedling rapid counting method based on machine vision and graphics process |
CN110110709A (en) * | 2019-05-27 | 2019-08-09 | 湖南开启时代智能科技有限公司 | A kind of red white corpuscle differential counting method, system and equipment based on image procossing |
CN110487705A (en) * | 2019-09-03 | 2019-11-22 | 中国科学院南京地理与湖泊研究所 | A kind of method of counting of Microcystis aeruginosa, system and device |
CN111795927A (en) * | 2020-06-05 | 2020-10-20 | 厦门大学 | Portable red tide algae density monitoring device based on image automatic counting |
CN112867782A (en) * | 2018-10-18 | 2021-05-28 | 阿克托里斯有限公司 | System and method for performing biological experiments using adaptive control theory control of program conditions |
CN114495098A (en) * | 2022-01-30 | 2022-05-13 | 南水北调中线干线工程建设管理局 | Diaxing algae cell statistical method and system based on microscope image |
CN114511851A (en) * | 2022-01-30 | 2022-05-17 | 南水北调中线干线工程建设管理局 | Hairspring algae cell statistical method based on microscope image |
CN114612333A (en) * | 2022-03-17 | 2022-06-10 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Microscopic image-based microencapsulated algae cell statistical method |
CN114612490A (en) * | 2022-03-17 | 2022-06-10 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Scenedesmus cell statistical method based on microscope image |
CN114627018A (en) * | 2022-03-17 | 2022-06-14 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Oscillating algae cell statistical method based on microscope images |
CN118033071A (en) * | 2024-01-24 | 2024-05-14 | 广东海洋大学 | Aquaculture water quality monitoring system based on artificial intelligence |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007018025A (en) * | 2004-06-30 | 2007-01-25 | Sharp Corp | Complexity measuring method, processing selection method, image processing method, its program and record medium, image processing device, and image processing system |
CN102663406A (en) * | 2012-04-12 | 2012-09-12 | 中国海洋大学 | Automatic chaetoceros and non-chaetoceros sorting method based on microscopic images |
CN103646380A (en) * | 2013-11-25 | 2014-03-19 | 大连海洋大学 | A method for removing small area noises in a binary image based on a stack theory |
-
2014
- 2014-05-15 CN CN201410205197.2A patent/CN103955937A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007018025A (en) * | 2004-06-30 | 2007-01-25 | Sharp Corp | Complexity measuring method, processing selection method, image processing method, its program and record medium, image processing device, and image processing system |
CN102663406A (en) * | 2012-04-12 | 2012-09-12 | 中国海洋大学 | Automatic chaetoceros and non-chaetoceros sorting method based on microscopic images |
CN103646380A (en) * | 2013-11-25 | 2014-03-19 | 大连海洋大学 | A method for removing small area noises in a binary image based on a stack theory |
Non-Patent Citations (3)
Title |
---|
OGE MARQUES: "《实用MATLAB图像和视频处理》", 12 December 2013, 清华大学出版社 * |
李金忠 等: "显微图像处理在藻类分类技术中的应用", 《贵州科学》 * |
郭显久 等: "基于图像处理技术的海洋微藻数量统计方法", 《大连海洋大学学报》 * |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794711A (en) * | 2015-04-13 | 2015-07-22 | 上海泽煜实验设备有限公司 | Image processing method and device |
CN104794710A (en) * | 2015-04-13 | 2015-07-22 | 上海泽煜实验设备有限公司 | Image processing method and device |
CN104867159A (en) * | 2015-06-05 | 2015-08-26 | 北京大恒图像视觉有限公司 | Stain detection and classification method and device for sensor of digital camera |
CN104867159B (en) * | 2015-06-05 | 2018-04-10 | 北京大恒图像视觉有限公司 | A kind of digital camera sensor dust detection and stage division and device |
WO2017114439A1 (en) * | 2015-12-28 | 2017-07-06 | 清华大学深圳研究生院 | Image processing-based method and device for measuring growth degree of algae on silicone rubber surface |
CN106780522B (en) * | 2016-12-23 | 2019-08-30 | 杭州华卓信息科技有限公司 | A kind of bone marrow fluid cell segmentation method based on deep learning |
CN106780522A (en) * | 2016-12-23 | 2017-05-31 | 杭州华卓信息科技有限公司 | A kind of bone marrow fluid cell segmentation method based on deep learning |
ES2685220R1 (en) * | 2017-03-30 | 2018-11-14 | Universidade De Vigo | Method for estimating microalgal growth |
CN107123102A (en) * | 2017-05-24 | 2017-09-01 | 天津工业大学 | A kind of adherent cell growth degrees of fusion automatic analysis method |
CN107767361A (en) * | 2017-08-28 | 2018-03-06 | 江苏理工学院 | A kind of carborundum line grain count method, storage device and terminal device |
CN107958459A (en) * | 2017-11-01 | 2018-04-24 | 浙江农林大学 | A kind of method and system for building phase contrast microscope cell image hierarchy structure information |
CN107958459B (en) * | 2017-11-01 | 2020-11-24 | 浙江农林大学 | Method and system for constructing hierarchical structure information of phase-contrast microscope cell image |
CN108171683B (en) * | 2017-12-12 | 2021-12-14 | 杭州键一生物科技有限公司 | Cell counting method adopting software for automatic identification |
CN108171683A (en) * | 2017-12-12 | 2018-06-15 | 杭州键生物科技有限公司 | A kind of method for cell count using software automatic identification |
CN109030488A (en) * | 2018-06-25 | 2018-12-18 | 中国海洋大学 | Algae bio quantity measuring method and device |
CN108876752A (en) * | 2018-07-06 | 2018-11-23 | 武汉兰丁医学高科技有限公司 | The image recognition method of counting of blood cell |
CN109447945A (en) * | 2018-09-21 | 2019-03-08 | 河南农业大学 | Wheat Basic Seedling rapid counting method based on machine vision and graphics process |
CN109447945B (en) * | 2018-09-21 | 2021-11-30 | 河南农业大学 | Quick counting method for basic wheat seedlings based on machine vision and graphic processing |
CN112867782B (en) * | 2018-10-18 | 2024-02-23 | 阿克托里斯有限公司 | System and method for performing biological experiments using adaptive controlled theory control of program conditions |
CN112867782A (en) * | 2018-10-18 | 2021-05-28 | 阿克托里斯有限公司 | System and method for performing biological experiments using adaptive control theory control of program conditions |
CN110110709A (en) * | 2019-05-27 | 2019-08-09 | 湖南开启时代智能科技有限公司 | A kind of red white corpuscle differential counting method, system and equipment based on image procossing |
CN110487705A (en) * | 2019-09-03 | 2019-11-22 | 中国科学院南京地理与湖泊研究所 | A kind of method of counting of Microcystis aeruginosa, system and device |
CN111795927A (en) * | 2020-06-05 | 2020-10-20 | 厦门大学 | Portable red tide algae density monitoring device based on image automatic counting |
CN114511851A (en) * | 2022-01-30 | 2022-05-17 | 南水北调中线干线工程建设管理局 | Hairspring algae cell statistical method based on microscope image |
CN114495098A (en) * | 2022-01-30 | 2022-05-13 | 南水北调中线干线工程建设管理局 | Diaxing algae cell statistical method and system based on microscope image |
CN114612333A (en) * | 2022-03-17 | 2022-06-10 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Microscopic image-based microencapsulated algae cell statistical method |
CN114612490A (en) * | 2022-03-17 | 2022-06-10 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Scenedesmus cell statistical method based on microscope image |
CN114627018A (en) * | 2022-03-17 | 2022-06-14 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Oscillating algae cell statistical method based on microscope images |
CN114612333B (en) * | 2022-03-17 | 2022-12-02 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Microscopic image-based micro-capsule algae cell statistical method |
CN114627018B (en) * | 2022-03-17 | 2023-01-13 | 生态环境部长江流域生态环境监督管理局生态环境监测与科学研究中心 | Oscillating algae cell statistical method based on microscope image |
CN118033071A (en) * | 2024-01-24 | 2024-05-14 | 广东海洋大学 | Aquaculture water quality monitoring system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103955937A (en) | Microalgae automatic counting method based on digital image processing | |
CN102096795B (en) | Method for recognizing worn two-dimensional barcode image | |
CN107292310B (en) | Visual positioning and automatic reading method for circular pointer type dial plate | |
CN102629322B (en) | Character feature extraction method based on stroke shape of boundary point and application thereof | |
CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
CN109182081B (en) | Single cell sorting system based on image processing model | |
CN107563379B (en) | Method for positioning text in natural scene image | |
CN102676633A (en) | Method for automatically counting bacterial colonies | |
CN104408449A (en) | Intelligent mobile terminal scene character processing method | |
CN104636706A (en) | Complicated background bar code image automatic partitioning method based on gradient direction consistency | |
CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
CN102637262B (en) | A kind of self-adaptation bacterial counting | |
CN102147867A (en) | Method for identifying traditional Chinese painting images and calligraphy images based on subject | |
CN112102232B (en) | Method and device for automatically evaluating colony quality of induced pluripotent stem cells | |
CN107818321A (en) | A kind of watermark date recognition method for vehicle annual test | |
CN108133216A (en) | The charactron Recognition of Reading method that achievable decimal point based on machine vision is read | |
CN108960100A (en) | A kind of recognition methods of the sugarcane sugarcane section based on image procossing | |
CN103793709A (en) | Cell recognition method and device, and urine analyzer | |
CN102750531A (en) | Method for detecting handwriting mark symbols for bill document positioning grids | |
CN112330561B (en) | Medical image segmentation method based on interactive foreground extraction and information entropy watershed | |
CN105426924A (en) | Scene classification method based on middle level features of images | |
CN117197686A (en) | Satellite image-based high-standard farmland plot boundary automatic identification method | |
CN106909881A (en) | The method and system of corn breeding base ridge number are extracted based on unmanned aerial vehicle remote sensing images | |
CN105528795B (en) | A kind of infrared face dividing method using annular shortest path | |
CN102737232B (en) | Cleavage cell recognition 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140730 |
|
RJ01 | Rejection of invention patent application after publication |