CN106127738A - Agglutination test interpretation method - Google Patents
Agglutination test interpretation method Download PDFInfo
- Publication number
- CN106127738A CN106127738A CN201610427645.2A CN201610427645A CN106127738A CN 106127738 A CN106127738 A CN 106127738A CN 201610427645 A CN201610427645 A CN 201610427645A CN 106127738 A CN106127738 A CN 106127738A
- Authority
- CN
- China
- Prior art keywords
- sample
- agglutination test
- agglutination
- picture
- image
- 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
- 230000004520 agglutination Effects 0.000 title claims abstract description 82
- 238000012360 testing method Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000000284 extract Substances 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 239000000203 mixture Substances 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 13
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 13
- 238000003556 assay Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000015271 coagulation Effects 0.000 description 5
- 238000005345 coagulation Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 239000000427 antigen Substances 0.000 description 3
- 102000036639 antigens Human genes 0.000 description 3
- 108091007433 antigens Proteins 0.000 description 3
- ZLFVRXUOSPRRKQ-UHFFFAOYSA-N chembl2138372 Chemical compound [O-][N+](=O)C1=CC(C)=CC=C1N=NC1=C(O)C=CC2=CC=CC=C12 ZLFVRXUOSPRRKQ-UHFFFAOYSA-N 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000030452 Transient pseudohypoaldosteronism Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000009589 serological test Methods 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 208000006379 syphilis Diseases 0.000 description 2
- RZZPDXZPRHQOCG-OJAKKHQRSA-O CDP-choline(1+) Chemical compound O[C@@H]1[C@H](O)[C@@H](COP(O)(=O)OP(O)(=O)OCC[N+](C)(C)C)O[C@H]1N1C(=O)N=C(N)C=C1 RZZPDXZPRHQOCG-OJAKKHQRSA-O 0.000 description 1
- 238000002965 ELISA Methods 0.000 description 1
- 241000589884 Treponema pallidum Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000023555 blood coagulation Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012128 rapid plasma reagin Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000008672 reprogramming Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000002966 serum Anatomy 0.000 description 1
- 150000004992 toluidines Chemical class 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A kind of agglutination test interpretation method, first carries out Image semantic classification, obtains the digitized image of agglutination test result, and lightness and contrast level parameter to picture simultaneously processes；Then use " Hough transformation " extraction algorithm, the border in the agglutination test region of picture is detected by Computer Vision Platform, after extracting border, carry out the extraction on border further according to COLOR COMPOSITION THROUGH DISTRIBUTION, it is thus achieved that extract the rectangular histogram of picture；Extract the sample in the border in agglutination test region；Sample picture is extracted according to gained threshold value；The picture noise of filtered sample picture, it is thus achieved that Sample Image；Extract agglutination speckle in Sample Image, calculate agglutination speckle number and area；Finally, agglutination speckle number and area according to obtaining provide the rank belonging to sample.The agglutination test interpretation method that the present invention provides, using iconography and Computer Image Processing is means, substantially increases the reliability of agglutination test interpretation, reduces the randomness of eye-observation.
Description
Technical field
The present invention relates to a kind of video data processing method, particularly relate to a kind of digitized image to agglutination test result
Process and distinguish, and the method that interpretation provides conclusion (of pressure testing) accordingly, to realize the automatization of agglutination test detection.
Background technology
The serological test of coagulation is there is with corresponding antibodies in coagulation experiment particulate antigen after being combined.Antigen is combined with antibody
Thing is under electrolyte effect, through certain time, forms macroscopic coagulation agglomerate.Test can be carried out in glass plate, is referred to as
Glass plate agglutination test, test can be carried out on card, and referred to as card agglutination test can be used for the qualification of antibacterial and the qualitative of antibody
Detection；Also can carry out in test tube, claim tube agglutination test, be mainly used in antiserum titre and measure.
Serological test is the most widely used technological means of current Lues Assay, and it is divided into again rapid plasma reagin to try
Test (RPR), toluidine red not heat run (TRUST), TPHA (TPHA), treponema pallidum ELISA in fact
Test and fluorescent treponemal antibody-absorption test (FTA-ABS) etc..Wherein, TRUST test is to use VDRL antigen in toluidines
Red solution detects reagin present in syphilitic's serum, macroscopic pink coagulation block occurs, can sentence
Fixed, combining the extension rate of sample, semiquantitative purpose can reached.The method is due to spy quick, directly perceived, easy and simple to handle
Property is applied in most of hospitals.
The automatization level of agglutination test is relatively low, is carrying out reaction time of blood coagulation, generally detects paper enterprising pedestrian work at one
Operation and interpretation, thereby increase work and the time of medical worker.
Summary of the invention
It is an object of the present invention to provide a kind of agglutination test interpretation method, the numeral to agglutination test result gained
Change image to process, and carry out computer interpretation accordingly, to realize the automatization of agglutination test detection.
A kind of agglutination test interpretation method of offer, the number to agglutination test result gained are provided
Word image processes, and carries out computer interpretation and the method providing conclusion (of pressure testing) accordingly, it is achieved agglutination test detection
Automatization.
A kind of agglutination test interpretation method that the present invention provides, its step includes:
First carry out Image semantic classification, obtain the digitized image of agglutination test result (such as: use digital camera that coagulation is tried
Test plate to shoot), lightness (Brightness) and contrast (Contrast) parameter to picture simultaneously processes, with
Strengthening picture effective information；
Then, extract the border (such as: black circle) in agglutination test region, use " Hough transformation " extraction algorithm, at computer
On vision platform (such as: OpenCV platform), the border to the agglutination test region of picture is detected, after extracting border, further
The extraction on border is carried out, it is thus achieved that extract the rectangular histogram of picture according to COLOR COMPOSITION THROUGH DISTRIBUTION.
Then, the sample in the border in agglutination test region is extracted；
Afterwards, sample picture is extracted according to gained threshold value；
Then, the picture noise of filtered sample picture, it is thus achieved that Sample Image；
Afterwards, extract agglutination speckle in Sample Image, calculate agglutination speckle number and area；
Finally, agglutination speckle number and area according to obtaining provide the rank belonging to sample, such as: 2+、3+With 4+
Deng.
The beneficial effect that technical solution of the present invention realizes:
The present invention provide agglutination test interpretation method, it is adaptable to agglutination test detector, and by sample sampling, detection,
Image capturing and result judgement etc. are integrated in one so that the acquisition of sample, the addition of reagent, agglutination and result judge automatically
Complete.
The agglutination test interpretation method that the present invention provides, using iconography and Computer Image Processing is means, significantly carries
The high reliability of agglutination test interpretation, reduces the randomness of eye-observation.
The agglutination test interpretation method that the present invention provides, further increases the automatization level of agglutination test so that number
According to collection, store, read and the whole process of the link such as transmission realizes automatization.
The agglutination test interpretation method that the present invention provides, uses digitized means, can realize agglutination test further
Detection by quantitative, and the short range of test data and remotely transmission, reduce artificial participation, reduce labor intensity.
Accompanying drawing explanation
Fig. 1 is the structural representation of agglutination test analyser one embodiment of the present invention；
Fig. 2 is the structural representation of agglutination test analyser case one embodiment of the present invention；
Fig. 3 is the green channel grey level histogram obtained on Computer Vision Platform；
Fig. 4 is black circle Detection and Extraction design sketch；
Fig. 5 is the sample 1 assay maps after black circle extracts；
Fig. 6 be sample 1 Otsu algorithm adaptive threshold and segmentation after picture；
Fig. 7 is that sample 1 extracts image information according to Otsu threshold value；
Fig. 8 is that sample 1 filters image section noise；
Fig. 9 is the sample 2 assay maps after black circle extracts；
Figure 10 be sample 2 Otsu algorithm adaptive threshold and segmentation after picture；
Figure 11 is that sample 2 extracts image information according to Otsu threshold value；
Figure 12 is that sample 2 filters image section noise；
Figure 13 is the sample 3 assay maps after black circle extracts；
Figure 14 be sample 3 Otsu algorithm adaptive threshold and segmentation after picture；
Figure 15 is that sample 3 extracts image information according to Otsu threshold value；
Figure 16 is that sample 3 filters image section noise；
Figure 17 is the sample 4 assay maps after black circle extracts；
Figure 18 be sample 4 Otsu algorithm adaptive threshold and segmentation after picture；
Figure 19 is that sample 4 extracts image information according to Otsu threshold value；
Figure 20 is that sample 4 filters image section noise.
Detailed description of the invention
Technical scheme is described in detail below in conjunction with accompanying drawing.The embodiment of the present invention is only in order to illustrate the skill of the present invention
Art scheme and unrestricted, although the present invention being described in detail with reference to preferred embodiment, those of ordinary skill in the art
Should be appreciated that and the technical scheme of invention can be modified or equivalent, without deviating from the essence of technical solution of the present invention
God and scope, it all should be contained in scope of the presently claimed invention.
Interpretation method, as a example by toluidine red not heat run, is illustrated and illustrates by the present invention.
First various syphilis positive samples are entered on testing inspection paper by the working specification of toluidine red not heat run
Row agglutination.
The result of the test of gained is carried out Image semantic classification, obtains the digitized image of agglutination test result (such as: use number
Agglutination test plate is shot by code-phase machine), lightness (Brightness) and the contrast (Contrast) to picture simultaneously
Parameter processes.
The strengthening of picture effective information is realized by image being carried out the mode such as gray scale translation and gray scale stretching.Gray scale translates
It is that the overall gray value of image is carried out linear translation, can be used to adjust the brightness of image.Gray scale stretching is the gray scale to image
Rectangular histogram carries out linear or nonlinear conversion, contributes to improving the gray scale dynamic range of image, by original low contrast
Image stretch is the image of high-contrast.Image before and after process is the most as depicted in figs. 1 and 2.
" Hough transformation " with detection of straight lines and line segment, can use the combination of straight line or line segment for the detection of rectangle
Complete.For the OpenCV platform of image detection, do not have direct function library (Hough transformation) to support rectangle, need to call
Hough transformation straight line or Hough transformation line segment reprogramming complete hough transform.Hough transform is the application of Hough transformation detection.
In the present embodiment, the region in black circle is as completing the region of agglutination test, and black circle is agglutination test region
Border.Use " Hough transformation-circle " extraction algorithm, the black circle in picture is examined by OpenCV Computer Vision Platform
Survey, after extracting circular boundary, carry out the extraction of black circles further according to COLOR COMPOSITION THROUGH DISTRIBUTION, extract the green channel gray scale of picture
Rectangular histogram (sees Fig. 3).In Fig. 3, rectangular histogram presents three peaks, and leftmost side height is relatively low, and the crest that width is bigger is black circle
Branch, and just screen black circle information in this branch further.As shown in Figure 4, in figure, blue portion is black circle Detection and Extraction effect
The black circle detected, remaining RED sector is residual image part.
As a example by sample 1, then, the sample (seeing Fig. 5) in the border in agglutination test region is extracted.As shown in Figure 6, its
First row is respectively " original noisy image ", " rectangular histogram " and " global threshold " from left to right, and second row is respectively from left to right
" original noisy image ", " rectangular histogram " and " OTSU threshold value ", the 3rd row is respectively " image after gaussian filtering ", " straight from left to right
Side's figure " and " OTSU threshold value ".Having these figures visible, after gaussian filtering, the OTSU algorithm threshold value of image is more excellent (eliminates different
Constant value is disturbed).When not using OTSU algorithm, when picture signal edge or feature are enough strong, global threshold can obtain reason
Think interesting image regions (ROI), but when picture signal edge or feature are insufficient to strong, global threshold cannot obtain reason
Think interesting image regions.And OTSU algorithm the most all can obtain enough preferably interesting image regions.It addition,
For our practical situations, the edge interference of noisy image is excessive (visible burr in rectangular histogram), to OTSU
Threshold calculations is not accurate enough, comprises too much annular side information.Therefore, calculate according to Otsu algorithm (having carried out gaussian filtering)
After the grey level histogram differential threshold of sample, according to gained threshold value, the image of sample is carried out binary conversion treatment；
Then, sample picture (seeing Fig. 7) is extracted according to gained threshold value,
Afterwards, by image space filtering (such as: gaussian filtering) and morphologic filtering (such as: the two-value erosion algorithm of image)
Picture noise etc. mode filtered sample picture, it is thus achieved that Sample Image (sees Fig. 8)；
Then, extract agglutination speckle in Sample Image, calculate agglutination speckle number and area；
Finally, agglutination speckle number (numerical value is 121.98) and area (numerical value is 425) according to obtaining provide examination
The rank tested is 4+。
The gaussian filtering that the present embodiment uses is a kind of linear smoothing filtering, it is adaptable to eliminates Gaussian noise, extensively applies
Noise abatement process in image procossing.Gaussian filtering is exactly the average process that is weighted entire image, each pixel
Value, obtains after being all weighted averagely by other pixel values in itself and field.It is mainly used to eliminate the additivity on image
Random noise.
The two-value erosion algorithm of the image that the present embodiment uses is a kind of elimination boundary point, makes the mistake that border is internally shunk
Journey.Can be used to eliminate little and insignificant object, be mainly used to eliminate edge interference and Discrete Stochastic grain noise etc..
The rank that the present embodiment uses judges that the number according to the size and speckle of extracting " speckle " on image is how many
Carry out grade classification.For 4+, the sample of 3+, 2+, it is believed that the strongest positive sample, its speckle is the biggest and number is relatively fewer.
But at the sample of more than 2+, the number of Main Basis speckle distribution determines rank, because still having tiny on strong positive sample image
Red, the calculating for spot size is the most consistent regular, and spatial distribution number and dispersion degree credibility thereof are higher.For
Negative sample and positive sample, first divide according to the number size of speckle.The numerical range that rank judges derives from calculation
The result of method training set, when rank judges, the direct result with this Algorithm for Training collection is compared.Along with detection sample size
Improving, the result of Algorithm for Training collection the most more levels off to real testing result, and the result that rank judges is the most accurate.
By above-mentioned identical method, sample 2 is carried out interpretation.The result of the test of gained is carried out the steps such as Image semantic classification
After, extracting the sample (seeing Fig. 9) in the border in agglutination test region, the grey level histogram calculating sample according to Otsu algorithm is poor
After dividing threshold value, according to gained threshold value, the image of sample is carried out binary conversion treatment (seeing Figure 10).Examination is extracted according to gained threshold value
Master drawing sheet (sees Figure 11), the picture noise of filtered sample picture, it is thus achieved that Sample Image (seeing Figure 12) extracts in Sample Image
Agglutination speckle, calculates agglutination speckle number and area.Finally, according to the agglutination speckle number (numerical value obtained
Be 64.95) and area (numerical value is 558) to provide the rank of test be 3+。
By above-mentioned identical method, sample 3 is carried out interpretation.The result of the test of gained is carried out the steps such as Image semantic classification
After, extract the sample (seeing Figure 13) in the border in agglutination test region, calculate the grey level histogram of sample according to Otsu algorithm
After differential threshold, according to gained threshold value, the image of sample is carried out binary conversion treatment (seeing Figure 14).Extract according to gained threshold value
Sample picture (sees Figure 15), the picture noise of filtered sample picture, it is thus achieved that Sample Image (seeing Figure 16) extracts Sample Image
Middle agglutination speckle, calculates agglutination speckle number and area.Finally, according to the agglutination speckle number (number obtained
Value is 87.087) and area (numerical value is 583) to provide the rank of test be 2+。
By above-mentioned identical method, sample 4 is carried out interpretation.The result of the test of gained is carried out the steps such as Image semantic classification
After, extract the sample (seeing Figure 17) in the border in agglutination test region, calculate the grey level histogram of sample according to Otsu algorithm
After differential threshold, according to gained threshold value, the image of sample is carried out binary conversion treatment (seeing Figure 18).Extract according to gained threshold value
Sample picture (sees Figure 19), the picture noise of filtered sample picture, it is thus achieved that Sample Image (seeing Figure 20) extracts Sample Image
Middle agglutination speckle, calculates agglutination speckle number and area.Finally, according to the agglutination speckle number (number obtained
Value is 6.926) and area (numerical value is 982) to provide the rank of test be 1+。
Claims (10)
1. an agglutination test interpretation method, it is characterised in that including:
First carry out Image semantic classification, obtain the digitized image of agglutination test result, lightness and the contrast to picture simultaneously
Parameter processes, to strengthen picture effective information；
Then, extract the border in agglutination test region, use " Hough transformation " extraction algorithm, to figure on Computer Vision Platform
The border in the agglutination test region of sheet is detected, and after extracting border, carries out the extraction on border further according to COLOR COMPOSITION THROUGH DISTRIBUTION, obtains
The rectangular histogram of picture must be extracted.
Then, the sample in the border in agglutination test region is extracted；
Afterwards, sample picture is extracted according to gained threshold value；
Then, the picture noise of filtered sample picture, it is thus achieved that Sample Image；
Afterwards, extract agglutination speckle in Sample Image, calculate agglutination speckle number and area；
Finally, agglutination speckle number and area according to obtaining provide the rank belonging to sample.
Agglutination test interpretation method the most according to claim 1, it is characterised in that the acquisition methods of described digitized image
For using digital camera that agglutination test plate is shot.
Agglutination test interpretation method the most according to claim 1, it is characterised in that use black circle to illustrate agglutination test region
Border.
Agglutination test interpretation method the most according to claim 1, it is characterised in that described " Hough transformation " is that " Hough becomes
Change-circular ".
Agglutination test interpretation method the most according to claim 1, it is characterised in that described Computer Vision Platform is
OpenCV platform.
Agglutination test interpretation method the most according to claim 1, it is characterised in that use gray scale translation and gray scale to stretch
Mode strengthens picture effective information.
Agglutination test interpretation method the most according to claim 1, it is characterised in that use OTSU algorithm gained threshold value to extract
During sample picture, image is carried out gaussian filtering.
Agglutination test interpretation method the most according to claim 1, it is characterised in that filtered by image space and morphology
The picture noise of the filtered sample picture described in filtering enforcement.
Agglutination test interpretation method the most according to claim 8, it is characterised in that described image space is filtered into Gauss
Filtering.
Agglutination test interpretation method the most according to claim 8, it is characterised in that described morphologic filtering is image
Two-value erosion algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610427645.2A CN106127738B (en) | 2016-06-16 | 2016-06-16 | agglutination test interpretation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610427645.2A CN106127738B (en) | 2016-06-16 | 2016-06-16 | agglutination test interpretation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106127738A true CN106127738A (en) | 2016-11-16 |
| CN106127738B CN106127738B (en) | 2018-12-11 |
Family
ID=57469510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610427645.2A Active CN106127738B (en) | 2016-06-16 | 2016-06-16 | agglutination test interpretation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127738B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980860A (en) * | 2017-04-07 | 2017-07-25 | 广州誉康医药有限公司 | A kind of result automatic interpretation method for liquid medium cross matching |
| CN107064503A (en) * | 2017-05-16 | 2017-08-18 | 上海兰卫医学检验所股份有限公司 | The determination methods and device of a kind of syphilis helicoid antibody testing result |
| CN107992851A (en) * | 2017-12-20 | 2018-05-04 | 闫鸿远 | A kind of recognition methods of agglutination test |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1450796A (en) * | 2002-04-08 | 2003-10-22 | 三菱电机株式会社 | Method and apparatus for detecting and/or tracking image or color area of image sequence |
| CN1543572A (en) * | 2001-05-25 | 2004-11-03 | ������ķϵͳ֪ʶ��Ȩ����˾ | Imaging means for excisions apparatus |
| CN1849514A (en) * | 2003-07-08 | 2006-10-18 | 因韦尔尼斯医药瑞士股份有限公司 | Particle agglutination detection method and device |
| CN101390129A (en) * | 2006-02-28 | 2009-03-18 | 仁爱米拉索莱有限公司 | Method and apparatus for analyzing clusters of objects |
| CN101980785A (en) * | 2008-01-30 | 2011-02-23 | 奥索临床诊断有限公司 | Immunodiagnostic test cards having indicating indicia |
| CN102243171A (en) * | 2011-04-13 | 2011-11-16 | 北京农产品质量检测与农田环境监测技术研究中心 | Method for detecting lime substances in flour with near-infrared micro-imaging technology |
| CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
| CN102446353A (en) * | 2010-09-30 | 2012-05-09 | 广州阳普医疗科技股份有限公司 | Machine vision interpretation method and device for blood type analysis |
| CN103424555A (en) * | 2012-05-18 | 2013-12-04 | 林妈利 | Reagent group for matching test before blood transfusion and test method thereof |
| CN103673872A (en) * | 2012-09-10 | 2014-03-26 | 中国科学院空间科学与应用研究中心 | Measurement method and measurement system of liquid drop volume |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| US8953855B2 (en) * | 2008-03-05 | 2015-02-10 | Hitachi High-Technologies Corporation | Edge detection technique and charged particle radiation equipment |
-
2016
- 2016-06-16 CN CN201610427645.2A patent/CN106127738B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1543572A (en) * | 2001-05-25 | 2004-11-03 | ������ķϵͳ֪ʶ��Ȩ����˾ | Imaging means for excisions apparatus |
| CN1450796A (en) * | 2002-04-08 | 2003-10-22 | 三菱电机株式会社 | Method and apparatus for detecting and/or tracking image or color area of image sequence |
| CN1849514A (en) * | 2003-07-08 | 2006-10-18 | 因韦尔尼斯医药瑞士股份有限公司 | Particle agglutination detection method and device |
| CN101390129A (en) * | 2006-02-28 | 2009-03-18 | 仁爱米拉索莱有限公司 | Method and apparatus for analyzing clusters of objects |
| CN101980785A (en) * | 2008-01-30 | 2011-02-23 | 奥索临床诊断有限公司 | Immunodiagnostic test cards having indicating indicia |
| US8953855B2 (en) * | 2008-03-05 | 2015-02-10 | Hitachi High-Technologies Corporation | Edge detection technique and charged particle radiation equipment |
| CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
| CN102446353A (en) * | 2010-09-30 | 2012-05-09 | 广州阳普医疗科技股份有限公司 | Machine vision interpretation method and device for blood type analysis |
| CN102243171A (en) * | 2011-04-13 | 2011-11-16 | 北京农产品质量检测与农田环境监测技术研究中心 | Method for detecting lime substances in flour with near-infrared micro-imaging technology |
| CN103424555A (en) * | 2012-05-18 | 2013-12-04 | 林妈利 | Reagent group for matching test before blood transfusion and test method thereof |
| CN103673872A (en) * | 2012-09-10 | 2014-03-26 | 中国科学院空间科学与应用研究中心 | Measurement method and measurement system of liquid drop volume |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980860A (en) * | 2017-04-07 | 2017-07-25 | 广州誉康医药有限公司 | A kind of result automatic interpretation method for liquid medium cross matching |
| CN107064503A (en) * | 2017-05-16 | 2017-08-18 | 上海兰卫医学检验所股份有限公司 | The determination methods and device of a kind of syphilis helicoid antibody testing result |
| CN107992851A (en) * | 2017-12-20 | 2018-05-04 | 闫鸿远 | A kind of recognition methods of agglutination test |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106127738B (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108682008B (en) | A kind of Leukocyte Image clarity evaluation method and device | |
| Nasir et al. | Unsupervised colour segmentation of white blood cell for acute leukaemia images | |
| CN111079620B (en) | White blood cell image detection and identification model construction method and application based on transfer learning | |
| Kayal et al. | A new dynamic thresholding based technique for detection of hard exudates in digital retinal fundus image | |
| Ghazali et al. | Automated system for diagnosis intestinal parasites by computerized image analysis | |
| CN105825516A (en) | DICOM image blood flow analysis system | |
| CN105973904A (en) | Edible oil impurity detection method based on image background probability graph | |
| CN106914428A (en) | A kind of New Algorithm of the steel ball surface defect Differential Detection based on machine vision | |
| CN106127738A (en) | Agglutination test interpretation method | |
| CN112001920A (en) | Fundus image recognition method, device and equipment | |
| US8824768B1 (en) | Fertilization test method and apparatus | |
| Wollmann et al. | Multi-channel deep transfer learning for nuclei segmentation in glioblastoma cell tissue images | |
| CN110148125A (en) | Adaptive skin oil and fat detection method based on color detection | |
| CN103279960B (en) | A kind of image partition method of human body cache based on X-ray backscatter images | |
| Kotyk et al. | Apoptosis analysis in classification paradigm: a neural network based approach | |
| Costa Filho et al. | Sputum smear microscopy for tuberculosis: Evaluation of autofocus functions and automatic identification of tuberculosis mycobacterium | |
| CN111242880B (en) | Multi-depth-of-field image superposition method, equipment and medium for microscope | |
| Roy et al. | Detection of retinal microaneurysms using fractal analysis and feature extraction technique | |
| Wilm et al. | Multi-scanner canine cutaneous squamous cell carcinoma histopathology dataset | |
| WO2020178931A1 (en) | Testing apparatus and testing method | |
| Saini et al. | A comparative study of different auto-focus methods for mycobacterium tuberculosis detection from brightfield microscopic images | |
| CN109448012A (en) | A kind of method for detecting image edge and device | |
| CN113128511B (en) | Coke tissue identification method and device | |
| CN110543802A (en) | Method and device for identifying left and right eyes in fundus images | |
| CN116524496A (en) | Parasite auxiliary detection system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201108 No. 888 Xiangyang Road, Shanghai, Minhang District Patentee after: Shanghai Rongsheng Biological Pharmaceutical Co.,Ltd. Address before: 201108 No. 888 Xiangyang Road, Shanghai, Minhang District Patentee before: SHANGHAI RONGSHENG BIOTECH CO.,LTD. |