CN116189178A - Identification method, equipment and storage medium for microscopic cell image - Google Patents
Identification method, equipment and storage medium for microscopic cell image Download PDFInfo
- Publication number
- CN116189178A CN116189178A CN202211729291.9A CN202211729291A CN116189178A CN 116189178 A CN116189178 A CN 116189178A CN 202211729291 A CN202211729291 A CN 202211729291A CN 116189178 A CN116189178 A CN 116189178A
- Authority
- CN
- China
- Prior art keywords
- cell
- image
- contour
- signal
- microscopic
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the field of image processing in optical microscopic imaging, in particular to a microscopic cell image identification method, which comprises the following steps: extracting a cell background image, and calculating by using a cell original image and the cell background image to obtain a cell signal image; extracting a cell contour signal, amplifying the cell contour signal, and adding the amplified cell contour signal with an original cell image to obtain a contour-enhanced cell image; dividing the dense cell area to realize cell separation; and superposing the cell outline result image after cell separation and the cell original image to obtain a clear cell fusion image. The invention improves the contrast of cell outline, makes cell signals and the background easier to distinguish, effectively improves the accuracy and the integrity of cell identification, simultaneously improves the accuracy of cell positioning, area and counting, and rapidly displays detection and identification results, and brings better experience to practical application.
Description
Technical Field
The present invention relates to the field of image processing in optical microscopy imaging, and in particular, to a method, apparatus, and storage medium for identifying microscopic cell images.
Background
Common cell image types for microscopic imaging include bright field images and fluorescent images. Most of the bright field cells are hollow, incomplete in edges and irregular, so that great challenges are brought to recognition analysis, and the existing methods such as threshold segmentation, contour detection, edge detection and the like are difficult to relatively and completely locate cell positions and calculate cell areas. Most fluorescent cells are represented by uneven image brightness, uneven cell brightness, dense cell overlapping and the like, and the existing classical methods such as watershed still have a plurality of unreasonable errors although having certain advantages for the dense overlapping cell identification. Therefore, the existing microscopic imaging has the defects of poor image sharpness, cell identification accuracy and integrity no matter the identification of the bright field image or the fluorescent image.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a method, equipment and a storage medium for identifying microscopic cell images, which effectively improve the accuracy and the integrity of cell identification.
In order to achieve the above object, the present invention can be achieved by the following technical scheme:
a method of identifying a microscopic cell image, comprising the steps of:
extracting a cell background image, and calculating by using a cell original image and the cell background image to obtain a cell signal image;
extracting a cell contour signal, amplifying the cell contour signal, and adding the amplified cell contour signal with an original cell image to obtain a contour-enhanced cell image;
dividing the dense cell area to realize cell separation;
and superposing the cell outline result image after cell separation and the cell original image to obtain a clear cell fusion image.
Further, after the step of dividing the dense cell region to achieve cell separation,
and identifying each cell area and contour through connected domain analysis, calculating cell center points and counting, and aiming at the condition of large cell area, adopting average cell area to carry out integer division to obtain cell area and counting with relatively reasonable resolution.
Further, after the step of extracting the cell contour signal, amplifying the cell contour signal, adding the amplified cell contour signal to the original image of the cell to obtain the contour-enhanced cell image,
identifying a cell contour or an internal thread texture by a canny edge detection operator, and extracting cell characteristics;
the cell characteristics are fused through morphological dilation operation, so that the effective filling of the cell interior is realized.
Further, the step of extracting the cell contour signal comprises the following steps: removing the high-frequency signal through Gaussian filtering, remaining a result image of the low-frequency signal, and subtracting the result image from the original image of the cell to obtain a high-frequency signal, thereby obtaining the cell contour signal.
Further, the cell background image is extracted through Gaussian filtering, and division operation is carried out on the cell original image and the cell background image to obtain a cell signal image.
Further, the cell background image is extracted through Gaussian filtering, and subtraction operation is carried out on the cell original image and the cell background image to obtain a cell signal image.
Further, the dense cell area is divided by a watershed algorithm, so that cell separation is realized.
Further, before the cell contour result image after cell separation is overlapped with the cell original image, the cell contour is identified through a canny edge detection operator, and then the image is overlapped.
A computer device comprising a processor and a memory having stored therein at least one instruction, at least one program, code set or instruction set, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the method of identification of a microscopic cell image according to any of claims 1 to 8.
A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by a processor to implement the method of identification of a microscopic cell image according to any of claims 1 to 8.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, by enhancing the cell outline signal, the separation of dense cells is effectively realized, and the cell outline result image after cell separation and the cell original image are overlapped to obtain a clear cell fusion image. The defect that the sharpness of an original image obtained by processing a common microscope is poor is overcome, the contrast of cell contours is improved, cell signals and a background are more easily distinguished, the accuracy and the integrity of cell identification are effectively improved, the accuracy of cell positioning, area and counting are improved, and the detection and identification result is rapidly displayed, so that better experience is brought to practical application.
Drawings
FIG. 1 is a flow chart of identification of microscopic cell images of the present invention;
FIG. 2 is a schematic diagram of a final display of a well-defined cell fusion according to an embodiment of the present invention;
FIG. 3 is a well-defined cell fusion map of a second final display of an embodiment of the invention.
Detailed Description
The invention will be further described with reference to the drawings and detailed description. The terms such as "upper", "inner", "middle", "left", "right" and "a" and the like recited in the present specification are also for convenience of description only and are not intended to limit the scope of the present invention, but rather to change or adjust the relative relationship thereof, without substantially changing the technical content, and are considered to be within the scope of the present invention.
As shown in fig. 1, the identification method of microscopic cell image according to the present invention mainly comprises the following steps:
s1, extracting a cell background image, and performing operation by using a cell original image and the cell background image to obtain a cell signal image;
s2, extracting a cell contour signal, amplifying the cell contour signal, and adding the amplified cell contour signal and an original cell image to obtain a contour-enhanced cell image;
s3, dividing the dense cell area to realize cell separation;
and S4, superposing the cell outline result image after cell separation and the cell original image to obtain a clear cell fusion image.
According to the invention, the cell signal image is obtained through extraction and operation, so that the cell outline signal is extracted and enhanced, the dense cells are effectively and easily segmented, and finally, the cell outline result image after cell separation and the cell original image are overlapped to obtain a clear cell fusion image, so that the detection and identification results of the microscopic cell image are effectively, accurately and rapidly displayed.
Example 1
For bright field cell images, identification of microscopic cell images is achieved by:
s11, acquiring an initial image of cell scanning as an initial image of the cell. And extracting a cell background image through Gaussian filtering, and carrying out division operation on the cell original image and the cell background image to realize homogenization of the background image brightness, wherein the filtering scale parameters are adjustable and are used for realizing different homogenization effects. Gaussian filtering is a spatial filter, and can effectively remove a 'sharp' part (high-frequency signal) in an image, so that an image blurring effect is realized, namely only a low-frequency signal is reserved. The uneven background of the image is usually corresponding to low-frequency signals, the foreground signal is usually corresponding to high-frequency signals, so that the foreground signal can be well removed by adopting a larger convolution kernel (50-200), and the low-frequency brightness change field is reserved, namely the extraction of the uneven background distribution field of the cells is realized. Because the whole bright field cell is brighter, the cell uneven background distribution field can be eliminated by dividing the cell original image and the cell background image, and a result image with even background brightness is obtained, wherein a sharp foreground signal, namely a cell signal to be analyzed, is effectively reserved.
S12, removing the high-frequency signals obtained in the step S11 through Gaussian filtering, remaining a result image of the low-frequency signals, subtracting the result image from a cell original image to obtain high-frequency signals, obtaining cell outline signals, amplifying the cell outline signals by a certain multiple, and then overlapping the cell outline signals with the cell original image to realize enhanced sharpening of cell edge outlines. The magnification parameter is adjustable, is used for realizing the reinforcing effect of different degree. The Gaussian filter adopts a larger convolution kernel, effectively extracts a low-frequency signal, subtracts the low-frequency signal from the original image of the cell, and can extract a high-frequency signal of interest, namely the contour of the cell. And amplifying the cell contour signal by a certain multiple to enhance the cell contour intensity. And finally, adding the enhanced cell contour signal with the cell original image to obtain a contour enhanced result image, wherein the contour enhanced result image is expressed as that the contrast of the cell contour is greatly improved.
S13, identifying cell outlines or internal filiform textures through a canny edge detection operator, wherein an edge strength threshold parameter is adjustable and is used for extracting the characteristics of cells as abundant as possible. The canny operator can effectively detect as much edge information as possible, which is close to the actual cell edge, and can reduce the interference of noise on edge detection as much as possible. The detection effect is strongly dependent on the edge intensity threshold, and by controlling the edge intensity threshold, the feature information such as the cell outline and the like which are as rich as possible can be obtained. The presence of a filiform signal within the bright field cell is aimed at detecting the presence of a filiform signal within the cell, which facilitates filling of the cell interior.
S14, fusing cell characteristics through morphological expansion operation to obtain a region which covers cells as completely as possible, wherein expansion scale parameters are adjustable and are used for realizing a proper cell region coverage effect. Morphological expansion is an operation of obtaining local space maximum value, and by means of convolution of a convolution kernel and a graph, calculating the maximum value of pixel points in a certain neighborhood coverage area and assigning the maximum value to pixels designated by reference points, so that the highlight area in the image is gradually expanded, and the effective filling of irregular gaps, cavities and the like in cells can be realized. The inside of the cell in the illumination field is filled, so that the interference of the filiform signals in the cell is eliminated, and the filiform signals in the cell are prevented from being regarded as outline signals of the cell.
S15, dividing the dense cell area through distance transformation and a watershed algorithm based on seed points, so as to realize cell separation. The distance transformation can be performed by assigning each foreground pixel as a distance value (generally Euclidean distance) between the nearest background pixel point and the background pixel point aiming at the binarized image, and circularly processing to obtain a distance matrix, so that the farther from the boundary, the brighter the point is; then traversing the whole image to find all brightness maximum points to be used as seed starting points of a watershed algorithm, so that cells which are mutually overlapped and adhered can always obtain one seed starting point respectively; then, starting from each seed point through a watershed algorithm, expanding gradually, and when the areas of 2 seed points are intersected, taking the position as a dividing line of 2 cells, so that dense cells can be separated. The dense cells are separated, so that the cell outline can be accurately identified, and the cell positioning, area and counting accuracy of the microscopic image can be effectively improved.
S16, after the cells are separated in the step S15, a plurality of cell blocks may still be aggregated, each cell area and contour are identified through connected domain analysis, and cell center points and areas are calculated. Aiming at the condition that the area is too large, the average cell area is adopted for integer division, and the cell area with relatively reasonable resolution is obtained. Based on the watershed result, the areas with the same gray values are separated one by one through connected domain analysis, the area of each area is calculated, if the area exceeds the average cell area by more than 2 times, the total area and the average area are divided, the estimation result of the number of cells contained in the total area and the average area is obtained, and meanwhile, the clear outline of each cell is obtained.
S17, superposing the transparent cell outline result image with outline lines, which is obtained by processing the connected domain in the step S16, on the cell original image according to the initial coordinate position of the cell to carry out drawing display, so as to obtain a cell fusion diagram with clear outline, and as shown in fig. 2, the rapid display of the cell detection and identification result is realized, and the practical application is convenient. In the step, the cell outline can be identified by a canny edge detection operator and then the image superposition is carried out, so that the cell outline is clearer and more accurate.
Example two
For fluorescent cell images, identification of microscopic cell images is achieved by:
s21, acquiring an initial image of cell scanning as an initial image of cells. And extracting a cell background image through Gaussian filtering, and carrying out division operation on the cell original image and the cell background image to realize homogenization of the background image brightness, wherein the filtering scale parameters are adjustable and are used for realizing different homogenization effects. Gaussian filtering is a spatial filter, and can effectively remove a 'sharp' part (high-frequency signal) in an image, so that an image blurring effect is realized, namely only a low-frequency signal is reserved. The uneven background of the image is usually corresponding to low-frequency signals, the foreground signal is usually corresponding to high-frequency signals, so that the foreground signal can be well removed by adopting a larger convolution kernel (50-200), and the low-frequency brightness change field is reserved, namely the extraction of the uneven background distribution field of the cells is realized. Because the fluorescent cell background is darker, the cell uneven background distribution field can be eliminated by subtracting the cell original image and the cell background image, and a result image with uniform background brightness is obtained, wherein a sharp foreground signal, namely a cell signal to be analyzed, is effectively reserved.
S22, removing the high-frequency signals obtained in the step S21 through Gaussian filtering, remaining a result image of the low-frequency signals, subtracting the result image from a cell original image to obtain high-frequency signals, obtaining cell outline signals, amplifying the cell outline signals by a certain multiple, and then overlapping the cell outline signals with the cell original image to realize enhanced sharpening of cell edge outlines. The magnification parameter is adjustable, is used for realizing the reinforcing effect of different degree. The Gaussian filter adopts a larger convolution kernel, effectively extracts a low-frequency signal, subtracts the low-frequency signal from the original image of the cell, and can extract a high-frequency signal of interest, namely the contour of the cell. And amplifying the cell contour signal by a certain multiple to enhance the cell contour intensity. And finally, adding the enhanced cell contour signal with the cell original image to obtain a contour enhanced result image, wherein the contour enhanced result image is expressed as that the contrast of the cell contour is greatly improved.
S23, dividing the dense cell area through a watershed algorithm to realize cell separation. The distance transformation can be performed by assigning each foreground pixel as a distance value (generally Euclidean distance) between the nearest background pixel point and the background pixel point aiming at the binarized image, and circularly processing to obtain a distance matrix, so that the farther from the boundary, the brighter the point is; then traversing the whole image to find all brightness maximum points to be used as seed starting points of a watershed algorithm, so that cells which are mutually overlapped and adhered can always obtain one seed starting point respectively; then, starting from each seed point through a watershed algorithm, expanding gradually, and when the areas of 2 seed points are intersected, taking the position as a dividing line of 2 cells, so that dense cells can be separated. The dense cells are separated, so that the cell outline can be accurately identified, and the cell positioning, area and counting accuracy of the microscopic image can be effectively improved.
S24, after the cells are separated in the step S23, a plurality of cell blocks may still be aggregated, each cell area and outline are identified through connected domain analysis, and cell center points and counts are calculated. Aiming at the condition that the area is too large, the average cell area is adopted for integer division, so that the cell area and the count which are relatively reasonable in resolution are obtained. Based on the watershed result, the areas with the same gray values are separated one by one through connected domain analysis, the area of each area is calculated, if the area exceeds the average cell area by more than 2 times, the total area and the average area are divided, the estimation result of the number of cells contained in the total area and the average area is obtained, and meanwhile, the clear outline of each cell is obtained.
S25, recognizing the outline of the cell obtained in the step S24 through a canny edge detection operator, and superposing the outline of the cell on an original image of the cell according to the initial coordinate position of the cell to carry out drawing display, so as to obtain a cell fusion diagram with a clear outline, and realizing rapid display of a cell detection recognition result as shown in FIG. 3. The canny operator can effectively detect as much edge information as possible, which is close to the actual cell edge, and can reduce the interference of noise on edge detection as much as possible. The detection effect is strongly dependent on the edge intensity threshold. By controlling the edge intensity threshold, as accurate cell profile information as possible can be obtained. And the cell outline result image and the original image are fused and overlapped according to the colors, so that a fusion diagram corresponding to the detection result and the original image can be obtained quickly, and the practical application is convenient.
A computer device comprising a processor and a memory, wherein at least one instruction, at least one program, code set or instruction set is stored in the memory, said at least one instruction, said at least one program, said code set or instruction set being loaded and executed by the processor to implement the method of identifying a microscopic cell image as described above.
A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set, said at least one instruction, said at least one program, said code set, or instruction set being loaded and executed by a processor to implement a method of identifying a microscopic cell image as described above.
The embodiments of the present invention are not limited thereto, and the present invention may be modified, substituted or combined in various other forms without departing from the basic technical spirit of the present invention, which falls within the scope of the claims, according to the above-described aspects of the present invention, using the general knowledge and conventional means of the art.
Claims (10)
1. A method for identifying a microscopic cell image, comprising the steps of:
extracting a cell background image, and calculating by using a cell original image and the cell background image to obtain a cell signal image;
extracting a cell contour signal, amplifying the cell contour signal, and adding the amplified cell contour signal with an original cell image to obtain a contour-enhanced cell image;
dividing the dense cell area to realize cell separation;
and superposing the cell outline result image after cell separation and the cell original image to obtain a clear cell fusion image.
2. The method for recognizing a microscopic cell image according to claim 1, wherein after the step of dividing the dense cell region to separate cells,
and identifying each cell area and contour through connected domain analysis, calculating cell center points and counting, and aiming at the condition of large cell area, adopting average cell area to carry out integer division to obtain cell area and counting with relatively reasonable resolution.
3. The method for recognizing microscopic cell image according to claim 2, wherein after the step of extracting the cell contour signal, amplifying the cell contour signal, adding the amplified cell contour signal to the original image of the cell to obtain the contour-enhanced cell image,
identifying a cell contour or an internal thread texture by a canny edge detection operator, and extracting cell characteristics;
the cell characteristics are fused through morphological dilation operation, so that the effective filling of the cell interior is realized.
4. The method of claim 1, wherein the step of extracting the cell contour signal comprises: removing the high-frequency signal through Gaussian filtering, remaining a result image of the low-frequency signal, and subtracting the result image from the original image of the cell to obtain a high-frequency signal, thereby obtaining the cell contour signal.
5. The method for recognizing microscopic cell images according to claim 1, wherein the extracted cell background image is extracted by gaussian filtering, and the cell signal image is obtained by dividing the cell original image and the cell background image.
6. The method of claim 1, wherein the extracting the cell background image is performed by gaussian filtering, and the cell signal image is obtained by subtracting the cell original image and the cell background image.
7. The method of claim 1, wherein the cell separation is achieved by segmenting the dense cell region by a watershed algorithm.
8. The method for identifying microscopic cell images according to claim 1, wherein the cell contours are identified by a canny edge detection operator before the cell contour result image after cell separation and the cell original image are superimposed.
9. A computer device comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a set of codes, or a set of instructions, the at least one instruction, the at least one program, the set of codes, or the set of instructions being loaded and executed by the processor to implement the method of identifying a microscopic cell image according to any of claims 1 to 8.
10. A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by a processor to implement the method of identification of a microscopic cell image according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211729291.9A CN116189178A (en) | 2022-12-30 | 2022-12-30 | Identification method, equipment and storage medium for microscopic cell image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211729291.9A CN116189178A (en) | 2022-12-30 | 2022-12-30 | Identification method, equipment and storage medium for microscopic cell image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116189178A true CN116189178A (en) | 2023-05-30 |
Family
ID=86448152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211729291.9A Pending CN116189178A (en) | 2022-12-30 | 2022-12-30 | Identification method, equipment and storage medium for microscopic cell image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116189178A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005568A (en) * | 2006-01-16 | 2007-07-25 | 索尼株式会社 | Apparatus, method, and computer program for processing image, and recording medium storing the computer program |
| CN107316077A (en) * | 2017-06-21 | 2017-11-03 | 上海交通大学 | A kind of fat cell automatic counting method based on image segmentation and rim detection |
| CN110838126A (en) * | 2019-10-30 | 2020-02-25 | 东莞太力生物工程有限公司 | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium |
| CN110910367A (en) * | 2019-11-19 | 2020-03-24 | 长春理工大学 | Bioreactor cell culture quality evaluation method |
| CN110956612A (en) * | 2019-10-31 | 2020-04-03 | 华侨大学 | Cell rapid counting method, computer equipment and readable storage medium |
| CN111583178A (en) * | 2020-04-02 | 2020-08-25 | 电子科技大学 | Method for segmenting adhesive algae cells in algae cell microscopic image |
| CN111583227A (en) * | 2020-05-08 | 2020-08-25 | 华侨大学 | Method, device, equipment and medium for automatically counting fluorescent cells |
| CN112257729A (en) * | 2020-11-13 | 2021-01-22 | 腾讯科技（深圳）有限公司 | Image recognition method, device, equipment and storage medium |
| CN112991213A (en) * | 2021-03-12 | 2021-06-18 | 宁波大学 | Cell counting method |
| CN112991306A (en) * | 2021-03-25 | 2021-06-18 | 华南理工大学 | Cleavage stage embryo cell position segmentation and counting method based on image processing |
| 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 |
| CN113888540A (en) * | 2021-12-06 | 2022-01-04 | 深圳市海谱纳米光学科技有限公司 | Separation method and system for human face skin component image |
| CN114004774A (en) * | 2021-10-29 | 2022-02-01 | 中南大学 | Rapid color sketch image generation algorithm |
| CN115393375A (en) * | 2022-08-17 | 2022-11-25 | 华侨大学 | Bright field cell image segmentation method and device in fluorescence microscopic imaging |
-
2022
- 2022-12-30 CN CN202211729291.9A patent/CN116189178A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005568A (en) * | 2006-01-16 | 2007-07-25 | 索尼株式会社 | Apparatus, method, and computer program for processing image, and recording medium storing the computer program |
| CN107316077A (en) * | 2017-06-21 | 2017-11-03 | 上海交通大学 | A kind of fat cell automatic counting method based on image segmentation and rim detection |
| CN110838126A (en) * | 2019-10-30 | 2020-02-25 | 东莞太力生物工程有限公司 | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium |
| CN110956612A (en) * | 2019-10-31 | 2020-04-03 | 华侨大学 | Cell rapid counting method, computer equipment and readable storage medium |
| CN110910367A (en) * | 2019-11-19 | 2020-03-24 | 长春理工大学 | Bioreactor cell culture quality evaluation method |
| CN111583178A (en) * | 2020-04-02 | 2020-08-25 | 电子科技大学 | Method for segmenting adhesive algae cells in algae cell microscopic image |
| CN111583227A (en) * | 2020-05-08 | 2020-08-25 | 华侨大学 | Method, device, equipment and medium for automatically counting fluorescent cells |
| CN112257729A (en) * | 2020-11-13 | 2021-01-22 | 腾讯科技（深圳）有限公司 | Image recognition method, device, equipment and storage medium |
| CN112991213A (en) * | 2021-03-12 | 2021-06-18 | 宁波大学 | Cell counting method |
| CN112991306A (en) * | 2021-03-25 | 2021-06-18 | 华南理工大学 | Cleavage stage embryo cell position segmentation and counting method based on image processing |
| 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 |
| CN114004774A (en) * | 2021-10-29 | 2022-02-01 | 中南大学 | Rapid color sketch image generation algorithm |
| CN113888540A (en) * | 2021-12-06 | 2022-01-04 | 深圳市海谱纳米光学科技有限公司 | Separation method and system for human face skin component image |
| CN115393375A (en) * | 2022-08-17 | 2022-11-25 | 华侨大学 | Bright field cell image segmentation method and device in fluorescence microscopic imaging |
Non-Patent Citations (1)
| Title |
|---|
| 康世英 等: "基于MATLAB的牛乳体细胞快速计数方法", 《电脑知识与技术》, vol. 14, no. 26, pages 216 - 217 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145161B (en) | Pavement crack digital image processing and identifying method | |
| CN111310558B (en) | Intelligent pavement disease extraction method based on deep learning and image processing method | |
| CN112419250B (en) | Pavement crack digital image extraction, crack repair and crack parameter calculation method | |
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN108765402B (en) | Non-woven fabric defect detection and classification method | |
| US11538261B2 (en) | Systems and methods for automated cell segmentation and labeling in immunofluorescence microscopy | |
| CN115908269A (en) | Visual defect detection method and device, storage medium and computer equipment | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN112734761B (en) | Industrial product image boundary contour extraction method | |
| CN106096491B (en) | Automatic identification method for microaneurysms in fundus color photographic image | |
| CN112365448B (en) | Method for detecting fabric defects in warp knitting process | |
| KR20200082746A (en) | Cell-zone labeling apparatus and cell-zone detecting system including the same apparatus | |
| CN114037691A (en) | Carbon fiber plate crack detection method based on image processing | |
| CN113537037A (en) | Pavement disease identification method, system, electronic device and storage medium | |
| CN113505702A (en) | Pavement disease identification method and system based on double neural network optimization | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN110246139B (en) | Method for rapidly extracting plankton in-situ image ROI (region of interest) based on double thresholds | |
| CN117351011B (en) | Screen defect detection method, apparatus, and readable storage medium | |
| CN109063564B (en) | Target change detection method | |
| JPH0961138A (en) | Crack extraction apparatus | |
| CN116596899A (en) | Method, device, terminal and medium for identifying circulating tumor cells based on fluorescence image | |
| CN116189178A (en) | Identification method, equipment and storage medium for microscopic cell image | |
| CN116363097A (en) | Defect detection method and system for photovoltaic panel | |
| CN112270683B (en) | IHC digital preview image identification and organization foreground segmentation method and system | |
| CN114862889A (en) | Road edge extraction method and device based on remote sensing image |
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 |