CN106875413B - A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming - Google Patents
A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming Download PDFInfo
- Publication number
- CN106875413B CN106875413B CN201710076460.6A CN201710076460A CN106875413B CN 106875413 B CN106875413 B CN 106875413B CN 201710076460 A CN201710076460 A CN 201710076460A CN 106875413 B CN106875413 B CN 106875413B
- Authority
- CN
- China
- Prior art keywords
- image
- cytoplasm
- bianry image
- connected domain
- end member
- 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
Classifications
-
- 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
- G06T2207/30242—Counting objects in image
Abstract
The invention discloses a kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming, the following steps are included: reading in the hyperspectral image data of blood film and being compressed, compressed high-spectral data is decomposed using continuous maximum angular convex cone method, obtains the abundance figure of blood film preset number end member；Binary conversion treatment is carried out in conjunction with abundance figure of the Da-Jin algorithm to each end member, and tiny noise spot is removed using Mathematical Morphology Method erosion operation；Holes filling is carried out to each end member bianry image, cytoplasm bianry image is selected according to the size of connected domain number and largest connected domain；The cytoplasm connected domain of cytoplasm bianry image is marked and area statistics, chooses the intermediate value of cytoplasm connected domain area as reference valueR；All cytoplasm connected domains are identified and counted.The present invention takes full advantage of spectrum and image information, solves the enumeration problem of adhesion red blood cell, improves the accuracy of the automatic count results of red blood cell.
Description
Technical field
The present invention relates to digital image processing techniques field, in particular to a kind of adhesion red blood cell based on high light spectrum image-forming
Automatic counting method.
Background technique
Red blood cell carries oxygen transportation and immune function as one of the most common type haemocyte.Red blood cell count(RBC) is blood
The important indicator of routine inspection has important reference value in terms of disease prevention and diagnosis.Currently, automatic blood cell point
Analyzer effectively improves analysis rate, but it analyzes result there are higher false negative rate, and there is still a need for examine for part sample
Member carries out microscope reinspection again to reduce rate of missed diagnosis and misdiagnosis rate.Blood film microexamination, which is used as, clinically judges haemocyte
The goldstandard of pathological change is still essential analysis means.And blood cell differential and knowledge of the tradition based on analysis of digital microscopy images
Other method can free reviewer from the work of the microscopy of cumbersome time-consuming, reduce erroneous judgement caused by human factor, mention
High discrimination.But it due to cellular morphology diversity, the interference of cytoadherence and certain ingredients, still fails to look for so far
Meet the method for clinical requirement to a kind of pair of arbitrary cell image procossing precision.
Micro- high light spectrum image-forming technology combines traditional optical imagery and spectral technique, is obtaining sample space information
While, dozens of also is provided to hundreds of narrow-band spectrum information for each pixel in image, and it is thin can not only to analyze blood
The morphosis of born of the same parents, additionally it is possible to cell component content relevant information is analyzed, to realize that more accurate specimen discerning, biochemical parameter mention
It takes etc. and to provide possibility, be expected to solve the above-mentioned bottleneck problem based on image method.But how to make full use of acquired figure
Picture and spectral information, the accuracy for improving quantification and qualification is still the key of high light spectrum image-forming technology application.
Summary of the invention
The purpose of the present invention is to provide a kind of the adhesion red blood cell automatic counting method based on high light spectrum image-forming, this method
It can make full use of spectrum and image information, efficiently identify adhesion red blood cell, improve the accuracy rate of red blood cell count(RBC).
Realizing the specific technical solution of the object of the invention is:
A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming, the described method comprises the following steps:
(1) it reads in the hyperspectral image data of blood film and is compressed, using continuous maximum angular convex cone method to process
The hyperspectral image data of compression processing is decomposed, and the abundance figure of blood film preset number end member is obtained；
(2) binary conversion treatment is carried out respectively in conjunction with abundance figure of the Da-Jin algorithm to the blood film preset number end member, and adopt
Tiny noise spot is removed with Mathematical Morphology Method erosion operation, obtains the bianry image of preset number end member abundance figure；
(3) holes filling operation is carried out respectively to the bianry image of the preset number end member abundance figure, and according to process
The number of connected domain and the size in largest connected domain select cytoplasm bianry image in each end member bianry image after holes filling；
(4) the cytoplasm connected domain of the cytoplasm bianry image is marked and area statistics, selection cytoplasm connects
The intermediate value of logical domain area is as reference value R；
(5) all cytoplasm connected domains are identified and is counted.
Further, step (1) specifically includes:
Read in the hyperspectral image data Data (2x, 2y, λ) of blood film；
It is compressed using image of the quadratic linear interpolation method to each wave band in the hyperspectral image data, obtains pressure
Hyperspectral image data Data ' (x, y, λ) after contracting；
The compressed hyperspectral image data Data ' (x, y, λ) is divided using continuous maximum angular convex cone method
Solution, obtains the abundance figure I of n end member of blood filmj(x, y) (j=1,2 ..., n).
Further, step (2) specifically includes:
Adaptively obtain the abundance figure I of n end member of the blood film respectively using Da-Jin algorithmj(x, y) (j=1,
2 ..., segmentation threshold T n)j(j=1,2 .., n)；
According to the segmentation threshold Tj(j=1,2 .., n) is respectively to the abundance figure I of the n end memberj(x, y) (j=1,
2 .., n) binary conversion treatment is carried out, and it is tiny using the progress mathematical morphology erosion operation removal of the structural element of 3 × 3 sizes
Noise spot obtains the abundance figure I of the n end memberj(x, y) (j=1,2 .., n) corresponding bianry image Bj(x, y) (j=1,
2 .., n).
Further, step (3) specifically includes:
To the bianry image Bj(x, y) (j=1,2 .., n) carries out inversion operation respectively, obtains inverse bianry image Rj
(x, y) (j=1,2 .., n)；
Respectively by the inverse bianry image RjThe pixel value in largest connected domain negates in (x, y) (j=1,2 .., n),
He remains unchanged the pixel value of connected domain, obtains image Rj' (x, y) (j=1,2 .., n), to the bianry image Bj(x, y) (j
=1,2 .., n) and corresponding described image Rj' (x, y) (j=1,2 .., n) progress xor operation, after obtaining holes filling
Bianry image Bj' (x, y) (j=1,2 .., n)；
The filled bianry image B of described hole is obtained respectivelyj' the number N of connected domain in (x, y) (j=1,2 .., n)j
(j=1,2 .., n) and the area S in largest connected domainj(j=1,2 .., n), and judged respectively, if NjGreater than 100 with
And SjGreater than 1000 and less than 4000, then the filled bianry image B of described holej' (x, y) be cytoplasm bianry image Bc(x,
y)。
Further, step (4) specifically includes:
To the cytoplasm bianry image BcCytoplasm connected domain in (x, y) is marked, and is counted respectively according to label
The size in each respective markers region, and using the intermediate value of size as reference value R.
Further, step (5) specifically includes:
Successively to the cytoplasm bianry image BcThe area of the cytoplasm connected domain of each label carries out in (x, y)
Judgement；
If the area of the cytoplasm connected domain is less than 0.5 × R, without counting；If more than 0.5 × R and less than 1.9
× R, is denoted as individual cells；It if more than 1.9 × R, is fitted using Least Chimb shape, if fitting convex-edge shape area is greater than 2.5
× R is then denoted as two adhesion cells, is otherwise denoted as individual cells.
The beneficial effect of the technical scheme provided by the present invention is that: proposed by the invention is a kind of viscous based on high light spectrum image-forming
Even red blood cell automatic counting method decomposes the abundance figure for obtaining main end member, different ends by carrying out to hyperspectral image data
Member is related to different component in blood, assists in removing the information unrelated with counting, further carries out at binaryzation to abundance figure
Reason and holes filling operation by cytoplasmic identification and are sentenced cytoplasm size to automatically extract cytoplasm bianry image
Not, it solves influence of the adhesion cells to count results, improves the accuracy rate of the automatic count results of red blood cell.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the adhesion red blood cell automatic counting method based on high light spectrum image-forming provided by the invention；
Fig. 2 is holes filling operational flowchart provided by the invention；
Fig. 3 is that cytoplasm bianry image provided by the invention chooses flow chart；
Fig. 4 is adhesion Erythrocyte Recognition flow chart provided by the invention；
Fig. 5 is the abundance image of 5 end members of the embodiment of the present invention；
Fig. 6 is the bianry image of 5 end members of the embodiment of the present invention；
Fig. 7 is the bianry image of 5 end members by holes filling of the embodiment of the present invention；
Fig. 8 is the cytoplasm bianry image (a) and adhesion Erythrocyte Recognition result figure of the embodiment of the present invention.
Specific embodiment
Illustrate technological means, technological improvement and beneficial effect of the present invention in order to be more clearly understood, ties below
Closing attached drawing, the present invention will be described in detail.
A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming provided by the present invention, referring to Fig. 1, Fig. 2,
Fig. 3 and Fig. 4, including the following steps:
S101: reading in the hyperspectral image data of blood film and compressed, using continuous maximum angular convex cone method to warp
The hyperspectral image data of overcompression processing is decomposed, and the abundance figure of blood film preset number end member is obtained.
The step specifically:
Read in the hyperspectral image data Data (2x, 2y, λ) of blood film；
Successively the row, column number of band image each in the hyperspectral image data is compressed using quadratic linear interpolation method
For original half, compressed hyperspectral image data Data ' (x, y, λ) is obtained；
The compressed hyperspectral image data Data ' (x, y, λ) is divided using continuous maximum angular convex cone method
Solution, obtains the abundance figure I of 5 end members of blood filmj(x, y) (j=1,2 ..., 5)；
Wherein, the selection of preset number n is configured according to the needs in practical application, and the embodiment of the present invention does not do this
Limitation, this is illustrated for sentencing n=5.
S102: carrying out binary conversion treatment in conjunction with abundance figure of the Da-Jin algorithm to the blood film preset number end member respectively, and
Tiny noise spot is removed using Mathematical Morphology Method erosion operation, obtains the bianry image of preset number end member abundance figure.
The step specifically:
Adaptively obtain the abundance figure I of 5 end members of the blood film respectively using Da-Jin algorithmj(x, y) (j=1,
2 ..., segmentation threshold T 5)j(j=1,2 ..., 5)；
By 5 end members abundance figure Ij(x, y) (j=1,2 ..., 5) in each pixel pixel value and segmentation threshold
Value Tj(5) j=1,2 ..., is compared, if the pixel value of pixel is greater than Tj(j=1,2 ..., 5), then by the pixel
Pixel value is set to 1, and the pixel value of the pixel is otherwise set to 0, obtains the abundance figure I of 5 end members respectivelyj(x, y) (j=1,
2 ..., 5) corresponding initial binary image Oj(x, y) (j=1,2 ..., 5)；
Using the square structure element of 3 × 3 sizes respectively to the initial binary image Oj(x, y) (j=1,2 ...,
5) it carries out mathematical morphology erosion operation and removes tiny noise spot, obtain the abundance figure I of 5 end membersj(x, y) (j=1,2 ...,
5) corresponding bianry image Bj(x, y) (j=1,2 ..., 5).
S103: holes filling operation is carried out respectively to the bianry image of the preset number end member abundance figure, and according to warp
It crosses the number of connected domain and the size in largest connected domain in the filled each end member bianry image of hole and selects cytoplasm binary map
Picture.
The step specifically:
To the bianry image Bj(x, y) (5) j=1,2 ..., carries out inversion operation respectively, obtain inverse bianry image Rj
(x, y) (j=1,2 ..., 5)；
Using connected component labeling algorithm to the inverse bianry image Rj(x, y) (j=1,2 ..., 5) in connected domain point
It is not marked, obtains the inverse bianry image L of labelj(x, y) (j=1,2 ..., 5), then bianry image Lj(x, y) (j=1,
2 ..., 5) in mjThe pixel value of pixel is just m in a connected domainj, wherein mj=1,2 ..., Mj；
The inverse bianry image L of the label is counted respectivelyj(x, y) (j=1,2 ..., 5) in pixel value be mjPixel
The number of point, is denoted as Num (mj)(mj=1,2 ..., Mj), and find out Num (mj)(mj=1,2 ..., Mj) in maximum value institute
The pixel value of corresponding pixel is denoted as pj；
By the inverse bianry image L of the labelj(x, y) (j=1,2 ..., 5) in pixel value be pjPixel picture
Plain value is set to 0, and the pixel value of rest of pixels point remains unchanged, and obtains bianry image Rj' (x, y) (j=1,2 ..., 5)；
To the bianry image Bj(x, y) (j=1,5) and corresponding bianry image R 2 ...,j' (x, y) (j=1,
2 ..., 5) carry out xor operation, obtain holes filling after bianry image Bj' (x, y) (j=1,2 ..., 5)；
Using connected component labeling algorithm to the bianry image Bj' (x, y) (and j=1,2 ..., connected domain 5) marked
Note, obtains the bianry image L of labelj' (x, y) (j=1,2 ..., 5), then the bianry image L of the labelj' (x, y) (j=1,
2 ..., 5) in kthjThe pixel value of pixel is just k in a connected domainj, wherein kj=1,2 ..., Nj, Nj(j=1,2 ...,
It 5) is the bianry image Bj' (x, y) (and j=1,2 ..., 5) in connected domain number；The two-value of the label is counted respectively
Image Lj' (x, y) (and j=1,2 ..., 5) in pixel value be kjPixel number, be denoted as Num (kj)(kj=1,2 ...,
Nj), Num (kj)(kj=1,2 ..., Nj) in maximum value be the bianry image Bj' (x, y) (and j=1,2 ..., 5) in most
The area of big connected domain, is denoted as Sj；
If meeting NjGreater than 100 and SjGreater than 1000 and less than 4000, then the filled bianry image B of described holej’
(x, y) (j=1,2 ..., 5) be cytoplasm bianry image Bc(x, y).
S104: being marked the cytoplasm connected domain of the cytoplasm bianry image and area statistics, chooses cytoplasm
The intermediate value of connected domain area is as reference value R.
The step specifically:
Using connected component labeling algorithm to the cytoplasm bianry image BcEach cytoplasm connected domain in (x, y) carries out
Label, obtains the cytoplasm bianry image L of labelc(x, y), then LcM in (x, y)cPixel in a cytoplasm connected domain
Pixel value is mc, wherein mc=1,2 ..., Mc；
Count the cytoplasm bianry image L of the labelcPixel value is m in (x, y)cPixel number Num (mc)
(mc=1,2 ..., Mc)；
The pixel value for taking the statistics is mcPixel number Num (mc)(mc=1,2 ..., Mc) intermediate value, as
The reference value R of cytoplasm area.
S105: all cytoplasm connected domains are identified and is counted.
The step specifically:
It is successively m by the pixel value of the statisticscPixel number Num (mc)(mc=1,2 ..., Mc) with it is described
The reference value R of cytoplasm area is compared；
If the number Num (m of the pixelc) (m=1,2 ..., M ') less than 0.5 × R, then without count；If big
In 0.5 × R and less than 1.9 × R, it is denoted as individual cells；
If the number Num (m of the pixelc)(mc=1,2 ..., Mc) it is greater than 1.9 × R, it is handled using morphological images
In convex hull algorithm to Num (mc)(mc=1,2 ..., Mc) corresponding cytoplasm connected domain carries out the fitting of Least Chimb shape, and unites
Count the area S of the fitting convex-edge shapecIf Sc2.5 × R of > is denoted as two cells, is otherwise denoted as a cell.
Fig. 5 is the abundance figure of 5 end members of the embodiment of the present invention, respectively corresponds white space (a), stain (b), other
(c), cell wall (d) and cytoplasm (e).
Fig. 6 is the bianry image of 5 end members of the embodiment of the present invention.
Fig. 7 is the bianry image of 5 end members after the holes filling of the embodiment of the present invention.
Fig. 8 is the cytoplasm bianry image (a) and corresponding cytoplasm identification knot after the holes filling of the embodiment of the present invention
Fruit (b)-(d), wherein connected domain in (b) is the cytoplasm without counting, (c) in connected domain be identified as it is one red thin
The cytoplasm of born of the same parents, (d) in connected domain be the cytoplasm for being identified as two red blood cells, it can be seen that Erythrocyte Recognition effect compared with
It is good.
In conclusion the beneficial effect of the technical scheme provided by the present invention is that: one kind proposed by the invention is based on bloom
The adhesion red blood cell automatic counting method for composing imaging decomposes the abundance for obtaining main end member by carrying out to hyperspectral image data
Figure, since different end members are related to different component in blood, assists in removing the information unrelated with counting, further to abundance figure
Binary conversion treatment and holes filling operation are carried out to automatically extract cytoplasm bianry image, passes through of statistics cytoplasm connected domain
Number, cytoplasm size, and operation is carried out to statistical value and is reached to cytoplasmic indirect identification, solve adhesion cells to counting
As a result influence improves the accuracy rate of the automatic count results of red blood cell.According to different application backgrounds, the present invention is by appropriate
Modification be equally applicable to other associated picture process fields.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming, which is characterized in that the method includes following
Step:
(1) it reads in the hyperspectral image data of blood film and is compressed, using continuous maximum angular convex cone method to through overcompression
The hyperspectral image data of processing is decomposed, and the abundance figure of blood film preset number end member is obtained；
(2) binary conversion treatment is carried out respectively in conjunction with abundance figure of the Da-Jin algorithm to the blood film preset number end member, and use number
It learns morphological method erosion operation and removes tiny noise spot, obtain the bianry image of preset number end member abundance figure；
(3) holes filling operation is carried out respectively to the bianry image of the preset number end member abundance figure, and according to by hole
The number of connected domain and the size in largest connected domain select cytoplasm bianry image in filled each end member bianry image；
(4) the cytoplasm connected domain of the cytoplasm bianry image is marked and area statistics, chooses cytoplasm connected domain
The intermediate value of area is as reference value R；
(5) all cytoplasm connected domains are identified and is counted.
2. the adhesion red blood cell automatic counting method according to claim 1 based on high light spectrum image-forming, which is characterized in that institute
The detailed process of the step of stating (1) are as follows:
Read in the hyperspectral image data Data (2x, 2y, λ) of blood film；
It is compressed using image of the quadratic linear interpolation method to each wave band in the hyperspectral image data, after obtaining compression
Hyperspectral image data Data ' (x, y, λ)；
The compressed hyperspectral image data Data ' (x, y, λ) is decomposed using continuous maximum angular convex cone method, is obtained
Take the abundance figure I of n end member of blood filmj(x, y) (j=1,2 ..., n).
3. the adhesion red blood cell automatic counting method according to claim 1 based on high light spectrum image-forming, which is characterized in that institute
The detailed process of the step of stating (2) are as follows:
Adaptively obtain the abundance figure I of n end member of the blood film respectively using Da-Jin algorithmj(x, y) (j=1,2 ..., n)
Segmentation threshold Tj(j=1,2 .., n)；
According to the segmentation threshold Tj(j=1,2 .., n) is respectively to the abundance figure I of the n end memberj(x, y) (j=1,2 ..,
N) binary conversion treatment is carried out, and mathematical morphology erosion operation is carried out using the structural element of 3 × 3 sizes and removes tiny noise
Point obtains the abundance figure I of the n end memberj(x, y) (j=1,2 .., n) corresponding bianry image Bj(x, y) (j=1,2 ..,
n)。
4. the adhesion red blood cell automatic counting method according to claim 1 based on high light spectrum image-forming, which is characterized in that institute
The detailed process of the step of stating (3) are as follows:
To the bianry image Bj(x, y) (j=1,2 .., n) carries out inversion operation respectively, obtains inverse bianry image Rj(x, y)
(j=1,2 .., n)；
Respectively by the inverse bianry image RjThe pixel value in largest connected domain negates in (x, y) (j=1,2 .., n), other companies
The pixel value in logical domain remains unchanged, and obtains image Rj' (x, y) (j=1,2 .., n), to the bianry image Bj(x, y) (j=1,
2 .., n) and corresponding described image Rj' (x, y) (j=1,2 .., n) progress xor operation, the two-value after obtaining holes filling
Image Bj' (x, y) (j=1,2 .., n)；
The filled bianry image B of described hole is obtained respectivelyj' the number N of connected domain in (x, y) (j=1,2 .., n)j(j=
1,2 .., n) and largest connected domain area Sj(j=1,2 .., n), and judged respectively, if NjGreater than 100 and Sj
Greater than 1000 and less than 4000, then the filled bianry image B of described holej' (x, y) be cytoplasm bianry image Bc(x, y).
5. the adhesion red blood cell automatic counting method according to claim 1 based on high light spectrum image-forming, which is characterized in that institute
The detailed process of the step of stating (4) are as follows:
To the cytoplasm bianry image BcCytoplasm connected domain in (x, y) is marked, and counts each phase respectively according to label
The size of marked region is answered, and using the intermediate value of size as reference value R.
6. the adhesion red blood cell automatic counting method according to claim 1 based on high light spectrum image-forming, which is characterized in that institute
The detailed process of the step of stating (5) are as follows:
Successively to the cytoplasm bianry image BcThe area of the cytoplasm connected domain of each label is judged in (x, y)；
If the area of the cytoplasm connected domain is less than 0.5 × R, without counting；If more than 0.5 × R and less than 1.9 × R,
It is denoted as individual cells；If more than 1.9 × R, it is fitted using Least Chimb shape, if fitting convex-edge shape area is greater than 2.5 × R,
Two adhesion cells are then denoted as, individual cells are otherwise denoted as.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710076460.6A CN106875413B (en) | 2017-02-13 | 2017-02-13 | A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710076460.6A CN106875413B (en) | 2017-02-13 | 2017-02-13 | A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106875413A CN106875413A (en) | 2017-06-20 |
| CN106875413B true CN106875413B (en) | 2019-05-17 |
Family
ID=59165887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710076460.6A Active CN106875413B (en) | 2017-02-13 | 2017-02-13 | A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106875413B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110956612B (en) * | 2019-10-31 | 2023-03-31 | 华侨大学 | Cell rapid counting method, computer equipment and readable storage medium |
| CN113269745A (en) * | 2021-05-21 | 2021-08-17 | 燕山大学 | Aerial photography automobile counting method based on OpenCv |
| CN113222969A (en) * | 2021-05-28 | 2021-08-06 | 大连海事大学 | Imaging flow cytometry adhesion counting and activity detection method and device based on bidirectional background difference method |
| CN116309497B (en) * | 2023-03-26 | 2023-10-03 | 湖南医药学院 | Image recognition-based auxiliary analysis method for cancer cell counting and prognosis prediction |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692125A (en) * | 2009-09-10 | 2010-04-07 | 复旦大学 | Fisher judged null space based method for decomposing mixed pixels of high-spectrum remote sensing image |
| CN101866424A (en) * | 2010-05-20 | 2010-10-20 | 复旦大学 | Hyperspectral remote sensing image mixed pixel decomposition method based on independent component analysis |
| CN102193090A (en) * | 2010-03-19 | 2011-09-21 | 复旦大学 | Mixed pixel decomposition method for remote sensing images |
| CN103604737A (en) * | 2013-12-10 | 2014-02-26 | 山东大学 | Automatic blood cell recognition device and operating method thereof |
| CN103985119A (en) * | 2014-05-08 | 2014-08-13 | 山东大学 | Method for partitioning cytoplasm and cell nucleuses of white blood cells in color blood cell image |
| CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
| EP3089074A1 (en) * | 2015-04-22 | 2016-11-02 | The Boeing Company | Hyperspectral demixing using foveated compressive projections |
-
2017
- 2017-02-13 CN CN201710076460.6A patent/CN106875413B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692125A (en) * | 2009-09-10 | 2010-04-07 | 复旦大学 | Fisher judged null space based method for decomposing mixed pixels of high-spectrum remote sensing image |
| CN102193090A (en) * | 2010-03-19 | 2011-09-21 | 复旦大学 | Mixed pixel decomposition method for remote sensing images |
| CN101866424A (en) * | 2010-05-20 | 2010-10-20 | 复旦大学 | Hyperspectral remote sensing image mixed pixel decomposition method based on independent component analysis |
| CN103604737A (en) * | 2013-12-10 | 2014-02-26 | 山东大学 | Automatic blood cell recognition device and operating method thereof |
| CN103985119A (en) * | 2014-05-08 | 2014-08-13 | 山东大学 | Method for partitioning cytoplasm and cell nucleuses of white blood cells in color blood cell image |
| EP3089074A1 (en) * | 2015-04-22 | 2016-11-02 | The Boeing Company | Hyperspectral demixing using foveated compressive projections |
| CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106875413A (en) | 2017-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875413B (en) | A kind of adhesion red blood cell automatic counting method based on high light spectrum image-forming | |
| KR101989202B1 (en) | Method and software for analysing microbial growth | |
| CN110084150B (en) | Automatic white blood cell classification method and system based on deep learning | |
| JP4607100B2 (en) | Image pattern recognition system and method | |
| Quinn et al. | Automated blood smear analysis for mobile malaria diagnosis | |
| Zhang et al. | Automated semantic segmentation of red blood cells for sickle cell disease | |
| Wang et al. | Assisted diagnosis of cervical intraepithelial neoplasia (CIN) | |
| NL2024774B1 (en) | Blood leukocyte segmentation method based on adaptive histogram thresholding and contour detection | |
| WO2014087689A1 (en) | Image processing device, image processing system, and program | |
| WO2009125678A1 (en) | Method and device for dividing area of image of particle in urine | |
| CN112215790A (en) | KI67 index analysis method based on deep learning | |
| CN115082451A (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN113609984A (en) | Pointer instrument reading identification method and device and electronic equipment | |
| CN116012291A (en) | Industrial part image defect detection method and system, electronic equipment and storage medium | |
| Lee et al. | Image analysis using machine learning for automated detection of hemoglobin H inclusions in blood smears-a method for morphologic detection of rare cells | |
| CN101799920A (en) | Tongue picture analysis method based on colour feature and application thereof | |
| CN115266732A (en) | Carbon fiber tow defect detection method based on machine vision | |
| Shaw et al. | Optical mesoscopy, machine learning, and computational microscopy enable high information content diagnostic imaging of blood films | |
| CN110807754B (en) | Fungus microscopic image segmentation detection method and system based on deep semantic segmentation | |
| Haryanto et al. | A fast and accurate detection of Schizont plasmodium falciparum using channel color space segmentation method | |
| Poornima et al. | Detection of dengue fever with platelets count using image processing techniques | |
| Momenzadeh et al. | Automatic diagnosis of vulvovaginal candidiasis from pap smear images | |
| JP3653804B2 (en) | Particle image region segmentation method and apparatus | |
| CN113763384B (en) | Defect detection method and defect detection device in industrial quality inspection | |
| CN115457012A (en) | Pathological image segmentation method, system, storage medium, equipment and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210823 Address after: 215332 room 9, No. 18, Jinxing Road, Huaqiao Town, Kunshan City, Suzhou City, Jiangsu Province Patentee after: JIANGSU HUACHUANG HIGH-TECH MEDICAL TECHNOLOGY Co.,Ltd. Address before: 200241 No. 500, Dongchuan Road, Shanghai, Minhang District Patentee before: EAST CHINA NORMAL University |