CN113781515A - Cell image segmentation method, device and computer readable storage medium - Google Patents
Cell image segmentation method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN113781515A CN113781515A CN202111085684.6A CN202111085684A CN113781515A CN 113781515 A CN113781515 A CN 113781515A CN 202111085684 A CN202111085684 A CN 202111085684A CN 113781515 A CN113781515 A CN 113781515A
- Authority
- CN
- China
- Prior art keywords
- image
- seed point
- diagram
- ridge line
- segmentation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000003709 image segmentation Methods 0.000 title claims abstract description 50
- 238000010586 diagram Methods 0.000 claims abstract description 106
- 238000005260 corrosion Methods 0.000 claims abstract description 45
- 230000007797 corrosion Effects 0.000 claims abstract description 45
- 230000011218 segmentation Effects 0.000 claims abstract description 39
- 238000012937 correction Methods 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 34
- 238000009499 grossing Methods 0.000 claims description 9
- 238000005530 etching Methods 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 230000001413 cellular effect Effects 0.000 claims description 2
- 230000001464 adherent effect Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a cell image segmentation method, a cell image segmentation device and a computer readable storage medium, wherein the cell image segmentation method comprises the following steps: acquiring a target gray level image to be processed, and acquiring a target binary image according to the target gray level image; performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, and performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram; performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram; and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray level image. According to the scheme provided by the embodiment of the invention, the image segmentation precision can be improved, and the image segmentation capability of the adherent cells is greatly improved, so that more accurate image data can be obtained.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a cell image segmentation method, a cell image segmentation apparatus, and a computer-readable storage medium.
Background
Image segmentation refers to a process of dividing an image into a series of sub-regions that do not overlap with each other and have the same characteristics, so as to extract an object of interest from a background. With the rapid progress of computer science and technology, image segmentation technology has been widely applied and deeply expanded in a plurality of subject research fields. The existing image segmentation technology still faces huge challenges in terms of segmentation precision, calculation speed, algorithm universality and evaluation standard uniformity, wherein the segmentation precision is one of the most important optimization directions in the image segmentation technology.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a cell image segmentation method, a cell image segmentation device and a computer readable storage medium, which can improve the segmentation precision of images, greatly improve the image segmentation capability of adherent cells, and obtain more accurate image data.
In a first aspect, an embodiment of the present invention provides a cell image segmentation method, including: acquiring a target gray level image to be processed, and acquiring a target binary image according to the target gray level image; performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, and performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram; performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram; and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray level image.
According to some embodiments of the first aspect of the present invention, the obtaining a target binary image from the target grayscale image comprises: and executing preprocessing operation on the target gray level image to obtain a target binary image, wherein the preprocessing operation comprises contrast enhancement processing, denoising smoothing processing, wavelet transformation processing and binarization processing.
According to some embodiments of the first aspect of the present invention, the contrast enhancement processing comprises: and carrying out nonlinear stretching on the brightness of each pixel point of the target gray level image by using a nonlinear enhancement method to obtain a contrast enhancement image, wherein the nonlinear enhancement method is a weighting distribution-based adaptive Gamma correction method.
According to some embodiments of the first aspect of the present invention, the denoising smoothing process comprises: and carrying out weighted average on the gray value of each pixel point of the contrast enhanced image by using a Gaussian filtering method to obtain a de-noised smooth image.
According to some embodiments of the first aspect of the present invention, the performing an iterative erosion operation on the target binarized image to obtain an initial seed point map includes: dividing the target binary image into a to-be-corroded area and a protected area according to a preset minimum corroded area, wherein the area of the to-be-corroded area is larger than the minimum corroded area, and the area of the protected area is smaller than or equal to the minimum corroded area; performing iterative etching operation on the area to be etched according to a morphological method; and obtaining an initial seed point diagram according to the protected area.
According to some embodiments of the first aspect of the present invention, performing a distance transformation operation on the initial seed point map to obtain an initial ridge line map; and adding a ridge line on the boundary of the initial ridge line graph to obtain a background ridge line graph.
According to some embodiments of the first aspect of the present invention, the performing a correction operation on the initial seed point map according to the background ridge line map to obtain a foreground seed point map comprises: performing expansion operation on the background ridge line graph to obtain a ridge line expansion graph; carrying out inversion operation on the ridge expansion diagram to obtain a ridge inversion diagram; and performing intersection treatment on the ridge line reverse graph and the initial seed point graph to obtain a foreground seed point graph.
According to some embodiments of the first aspect of the present invention, the performing a watershed segmentation operation on the foreground seed point map and the background ridge line map to obtain a segmentation result of the target gray scale image comprises: carrying out gradient processing on the de-noised smooth image to obtain a gradient image; merging the foreground seed point diagram and the background ridge line diagram to obtain a foreground background diagram; mapping the gradient image according to the foreground background image to obtain a corrected gradient image; and performing watershed segmentation operation on the corrected gradient image to obtain a segmentation result of the target gray level image.
In a second aspect, an embodiment of the present invention provides a cell image segmentation apparatus, including: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for cell image segmentation according to any one of the embodiments of the first aspect.
In a third aspect, the present invention also provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to execute the cell image segmentation method according to the first aspect.
One or more technical schemes provided in the embodiment of the application have at least the following beneficial effects: the method comprises the steps of obtaining a target gray image to be processed, obtaining a target binary image according to the target gray image, performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram, performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram, and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray image. According to the scheme provided by the embodiment of the invention, the foreground seed point diagram is obtained in an iterative corrosion mode, and the subsequent watershed segmentation operation is executed according to the foreground seed point diagram, so that the image segmentation effect of the adherent cells by the watershed segmentation operation is better, the segmentation precision of the image is improved, and more accurate image data is obtained.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart illustrating steps of a cell image segmentation method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a method for segmenting a cell image according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of a method for segmenting a cell image according to another embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps of a method for segmenting a cell image according to another embodiment of the present invention;
FIG. 5 is a flowchart illustrating steps of a method for segmenting a cell image according to another embodiment of the present invention;
FIG. 6 is a flowchart illustrating the steps of a cell image segmentation method according to another embodiment of the present invention;
FIG. 7 is a flowchart illustrating steps of a method for segmenting a cell image according to another embodiment of the present invention;
FIG. 8 is a flowchart illustrating steps of a method for segmenting a cellular image according to another embodiment of the present invention;
FIG. 9 is a schematic diagram of a target gray scale image according to an embodiment of the invention;
FIG. 10 is a diagram of a contrast enhanced image according to another embodiment of the present invention;
FIG. 11 is a schematic diagram of a denoised smooth image according to another embodiment of the present invention;
FIG. 12 is a diagram illustrating a wavelet transform image according to another embodiment of the present invention;
FIG. 13 is a schematic diagram of a target binary image according to another embodiment of the present invention;
FIG. 14 is a schematic diagram of an initial seed point map according to another embodiment of the present invention;
FIG. 15 is a background ridge line illustration of another embodiment of the present invention;
FIG. 16 is a schematic diagram of a foreground seed point diagram according to another embodiment of the present invention;
FIG. 17 is a diagram illustrating segmentation results according to another embodiment of the present invention;
fig. 18 is a schematic structural diagram of a cell image segmentation apparatus according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms "first," "second," and the like in the description, in the claims, or in the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The embodiment of the invention provides a cell image segmentation method, a cell image segmentation device and a computer readable storage medium, wherein the cell image segmentation method specifically comprises the following steps of but is not limited to: the method comprises the steps of obtaining a target gray image to be processed, obtaining a target binary image according to the target gray image, performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram, performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram, and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray image. According to the scheme provided by the embodiment of the invention, the foreground seed point diagram is obtained in an iterative corrosion mode, and the subsequent watershed segmentation operation is executed according to the foreground seed point diagram, so that the image segmentation effect of the adherent cells by the watershed segmentation operation is better, the segmentation precision of the image is improved, and more accurate image data is obtained.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In a first aspect, an embodiment of the present invention provides a cell image segmentation method.
Referring to fig. 1, the cell image segmentation method includes, but is not limited to, step S100, step S200, step S300, and step S400.
Step S100: acquiring a target gray level image to be processed, and acquiring a target binary image according to the target gray level image;
specifically, the obtained target gray level image is subjected to contrast enhancement processing, denoising smoothing processing, wavelet transformation processing and binarization processing in sequence to obtain a target binarization image.
It should be noted that the Otsu algorithm may be used to perform the binarization operation on the target grayscale image, and other algorithms may also be used to perform the binarization operation, which is not limited in this embodiment.
Step S200: performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, and performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram;
referring to fig. 9 to 17, it can be understood that the segmentation result of the image can be corrected by using the erosion in morphology, and a more accurate initial seed point diagram can be obtained by performing an iterative erosion operation on the target binary image, so as to determine the connected domain in the image; the background ridge line map can be used for correcting the initial seed point map, so that the distance transformation operation can be performed on the initial seed point map to obtain the background ridge line map.
It should be noted that, in the distance transformation operation, the value of the foreground pixel may be converted into the distance from the point to the nearest background point, and the value of the background pixel may also be converted into the distance from the point to the nearest foreground point, which is not limited in this embodiment.
Step S300: performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram;
specifically, the background ridge line graph is sequentially subjected to expansion processing and negation processing, and then is subjected to intersection processing with the initial seed point graph, so that a foreground seed point graph can be obtained.
Step S400: and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray level image.
Specifically, gradient processing is carried out on the target gray level image, then a corrected gradient image is obtained on the target gray level image after the gradient processing according to a foreground background image obtained by a foreground seed point diagram and a background ridge line diagram, and then watershed segmentation operation is carried out on the corrected gradient image.
Through the steps S100 to S400, a target gray image to be processed is obtained, then the target binary image is obtained according to the target gray image, then iterative corrosion operation is carried out on the target binary image to obtain an initial seed point diagram, then distance transformation operation is carried out on the initial seed point diagram to obtain a background ridge line diagram, correction operation is carried out on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram, and then watershed segmentation operation is carried out on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray image. It can be understood that according to the scheme provided by the embodiment of the present invention, the foreground seed point diagram is obtained through iterative erosion, and then the subsequent watershed segmentation operation is performed according to the foreground seed point diagram, so that the watershed segmentation operation has a better effect on segmenting the image of the adherent cells, thereby improving the segmentation precision of the image and obtaining more accurate image data.
Referring to fig. 2, the step 100 includes, but is not limited to, the following step S110.
Step S110: and executing preprocessing operation on the target gray level image to obtain a target binary image, wherein the preprocessing operation comprises contrast enhancement processing, denoising smoothing processing, wavelet transformation processing and binarization processing.
It should be noted that, in an embodiment, the preprocessing operation preferably sequentially performs the contrast enhancement processing, the denoising smoothing processing, the wavelet transform processing, and the binarization processing.
Referring to fig. 3, specifically, regarding the above step 110, the contrast enhancement process specifically includes, but is not limited to, the following step S111.
Step S111: and carrying out nonlinear stretching on the brightness of each pixel point of the target gray level image by using a nonlinear enhancement method to obtain a contrast enhancement image, wherein the nonlinear enhancement method is a weighting distribution-based adaptive Gamma correction method.
It should be noted that the correction enhancement formula of the adaptive Gamma correction method is as follows:
pdf(l)＝nl/(M*N)；
γ＝1-cdf(l)；
T(l)＝lmax(l/lmax)γ＝lmax(l/lmax)1-cdf(l)；
wherein lmaxIs the maximum pixel value of the target gray level image, l is the pixel of any pixel point in the target gray level image, Gamma is the Gamma correction parameter, nlThe number of pixels with the gray level of l in the target gray image is M, N is the number of all pixels in the target gray image.
It should be noted that, in the related art, the enhancement formula based on Gamma correction is as follows:
T(l)＝lmax(l/lmax)γ
it will be appreciated that when contrast is enhanced by the conventional Gamma corrected enhancement formula, different images will exhibit the same intensity variation when contrast is directly modified, since Gamma is a fixed parameter. In order to solve the problem, the embodiment adopts the probability density functions of different gray levels of the image to process, so that the influence of different gray levels is reduced when the contrast of the image is enhanced.
Further, in an embodiment, the enhancement formula based on Gamma correction further utilizes a weighted distribution function to perform fine tuning on the statistical histogram, so as to smooth fluctuation phenomena among data and reduce adverse reactions, wherein the weighted distribution function is as follows:
where α is a tunable parameter, pdfmaxIs the maximum value in the probability density function, pdfminIs the minimum of the probability density function. The updated cdf function is formulated as follows:
thus, the updated enhancement formula based on Gamma correction is as follows:
referring to fig. 4, specifically, regarding the above step 110, the denoising smoothing process specifically includes, but is not limited to, the following step S112.
Step S112: and carrying out weighted average on the gray value of each pixel point of the contrast enhanced image according to a Gaussian filtering method to obtain a de-noised smooth image.
It will be appreciated that gaussian filtering is a linear smoothing filter suitable for eliminating gaussian noise. Most of noise of the image belongs to Gaussian noise, so that the Gaussian noise can be eliminated by using a Gaussian filtering method, the image denoising is better completed, and a denoised smooth image is obtained.
Referring to fig. 5, the step 200 includes, but is not limited to, the following steps S210, S220, and S230.
Step S210: dividing the target binary image into a to-be-corroded area and a protected area according to a preset minimum corroded area, wherein the area of the to-be-corroded area is larger than the minimum corroded area, and the area of the protected area is smaller than or equal to the minimum corroded area;
step S220: performing iterative etching operation on the area to be etched according to a morphological method;
step S230: and obtaining an initial seed point diagram according to the protected area.
In one embodiment, the specific operations in step S220 are as follows:
for the first iteration: firstly, dividing a binary image into two regions according to a set minimum corrosion area; then, determining a region with an area larger than the minimum corrosion area in the binary image to obtain a region to be corroded for 1 time; meanwhile, determining a region with an area smaller than or equal to the minimum corrosion area in the binary image to obtain a protected region for 1 time; and then, carrying out 1-time corrosion operation on the 1-time to-be-corroded area according to a morphological method to obtain a 1-time corrosion image.
For the second iteration: firstly, dividing a 1-time corrosion image into two areas according to the minimum corrosion area; then, determining the area of the 1-time corrosion image larger than the minimum corrosion area to obtain 2-time to-be-corroded areas; meanwhile, determining the area of the area less than or equal to the minimum corrosion area in the 1-time corrosion image to obtain a 2-time protected area; and then, carrying out 2 times of corrosion operations on the 2 times of to-be-corroded areas according to a morphological method to obtain 2 times of corrosion images.
For the third iteration: firstly, dividing a 2-time corrosion image into two areas according to the minimum corrosion area; then, determining the area of the 2-time corrosion image larger than the minimum corrosion area to obtain 3-time to-be-corroded areas; meanwhile, determining the area of the area less than or equal to the minimum corrosion area in the 2-time corrosion image to obtain a 3-time protected area; and then, carrying out 3 times of corrosion operations on the 3 times of to-be-corroded areas according to a morphological method to obtain 3 times of corrosion images.
For the fourth iteration: firstly, dividing a 3-time corrosion image into two areas according to the minimum corrosion area; then, determining the area of the 3-time corrosion image which is larger than the minimum corrosion area to obtain 4-time to-be-corroded areas; meanwhile, determining the area of the area less than or equal to the minimum corrosion area in the 3 times corrosion image to obtain a 4 times protected area; and then, carrying out 4 times of corrosion operations on the 4 times of areas to be corroded according to a morphological method to obtain 4 times of corrosion images.
For the fifth iteration: firstly, dividing a 4-time corrosion image into two areas according to the minimum corrosion area; then, determining the area of the 4-time corrosion image larger than the minimum corrosion area to obtain 5-time to-be-corroded areas; meanwhile, determining the area of the area less than or equal to the minimum corrosion area in the 4 times corrosion image to obtain a 5 times protected area; and then, carrying out 5 times of etching operation on the 5 times of to-be-etched areas according to a morphological method to obtain 5 times of etching images.
In one embodiment, regarding step S230, the specific operations are as follows:
and carrying out union operation on the protected area for 1 time, the protected area for 2 times, the protected area for 3 times, the protected area for 4 times and the corrosion image for 5 times to obtain an initial seed point diagram.
In an embodiment, it is preferable to perform the nth etching on the nth obtained region to be etched.
It should be noted that the number of times of etching the to-be-etched region obtained by each iterative etching may be 1 time, 2 times, and the like, and this embodiment does not limit this.
Referring to fig. 6, the above step 200 specifically includes, but is not limited to, the following steps S240 and S250.
Step S240: performing distance transformation operation on the initial seed point diagram to obtain an initial ridge line diagram;
step S250: and adding ridge lines on the boundary of the initial ridge line graph to obtain a background ridge line graph.
Specifically, after the initial ridge line map is obtained by processing the initial seed point map through the distance transformation operation, in order to process an object at the image boundary, a background ridge line map may be obtained by adding ridge lines on the peripheral boundary of the initial ridge line map.
Referring to fig. 7, the step 300 specifically includes, but is not limited to, the following steps S310, S320, and S330.
Step S310: performing expansion operation on the background ridge line image to obtain a ridge line expansion image;
step S320: carrying out inversion operation on the ridge expansion diagram to obtain a ridge inversion diagram;
step S330: and performing intersection treatment on the ridge line inverse image and the initial seed point image to obtain a foreground seed point image.
Specifically, firstly, performing expansion operation on the background ridge diagram to obtain a ridge expansion diagram, then performing negation operation on the ridge expansion diagram to obtain a ridge negation diagram, and then performing intersection processing on the ridge negation diagram and the initial seed point diagram to obtain a foreground seed point diagram.
Referring to fig. 8, the step 400 includes, but is not limited to, the following steps S410, S420, S430, and S440.
Step S410: carrying out gradient processing on the denoised smooth image to obtain a gradient image;
step S420: merging the foreground seed point diagram and the background ridge line diagram to obtain a foreground background diagram;
step S430: mapping the gradient image according to the foreground background image to obtain a corrected gradient image;
step S440: and performing watershed segmentation operation on the corrected gradient image to obtain a segmentation result of the target gray level image.
It should be noted that, in step S430, specifically, a pixel position with a value different from zero in the foreground-background image is mapped to a corresponding pixel position of the gradient image, and a minimum value is assigned to the corresponding pixel position of the gradient image, so that the modified gradient image can be obtained.
Based on the cell image segmentation method according to the embodiment of the first aspect, the following provides various embodiments of the cell image segmentation apparatus according to the second aspect of the present invention.
Referring to fig. 18, specifically, the cell image segmentation apparatus includes: memory 100, processor 200, and a computer program stored on memory 100 and executable on processor 200.
The processor 200 and the memory 100 may be connected by a bus or other means.
Non-transitory software programs and instructions necessary to implement the image processing method of the above-described embodiment are stored in the memory 100, and when executed by the processor 200, perform the cell image segmentation method of the above-described embodiment, for example, performing the above-described method steps S100 to S400 in fig. 1, the method step S110 in fig. 2, the method step S111 in fig. 3, the method step S112 in fig. 4, the method steps S210 to S230 in fig. 5, the method steps S240 to S250 in fig. 6, the method steps S310 to S330 in fig. 7, and the method steps S410 to S440 in fig. 8.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Referring to fig. 9 to 17, it can be understood that, since the cell image segmentation apparatus according to the second aspect of the present invention and the cell image segmentation method according to any one of the above-mentioned first aspects belong to the same inventive concept, specific embodiments and technical effects of the cell image segmentation apparatus according to the second aspect of the present invention may refer to specific embodiments and technical effects of the cell image segmentation method according to any one of the above-mentioned first aspects, and are not described herein again.
Based on the cell image segmentation method of the embodiment of the first aspect, various embodiments of the computer-readable storage medium of the third aspect of the present invention are set forth below.
The computer-readable storage medium stores computer-executable instructions, which are executed by a processor 200 or controller, for example, by a processor 200 in the above-mentioned embodiment of the image processing apparatus, and can cause the above-mentioned processor 200 to execute the image processing method in the above-mentioned embodiment, for example, to execute the above-mentioned method steps S100 to S500 in fig. 1, method steps S110 to S140 in fig. 2, method steps S131 to S132 in fig. 3, method steps S210 to S240 in fig. 4, method steps S310 to S320 in fig. 5, and method steps S510 to S520 in fig. 6.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor 200, such as a central processing unit 200, digital signal processor 200, or microprocessor 200, or as hardware, or as integrated circuits, such as application specific integrated circuits. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory 100 technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A method of cell image segmentation, comprising:
acquiring a target gray level image to be processed, and acquiring a target binary image according to the target gray level image;
performing iterative corrosion operation on the target binary image to obtain an initial seed point diagram, and performing distance transformation operation on the initial seed point diagram to obtain a background ridge line diagram;
performing correction operation on the initial seed point diagram according to the background ridge line diagram to obtain a foreground seed point diagram;
and performing watershed segmentation operation on the foreground seed point diagram and the background ridge line diagram to obtain a segmentation result of the target gray level image.
2. The cell image segmentation method according to claim 1, wherein the obtaining of the target binary image from the target gray-scale image comprises:
and executing preprocessing operation on the target gray level image to obtain a target binary image, wherein the preprocessing operation comprises contrast enhancement processing, denoising smoothing processing, wavelet transformation processing and binarization processing.
3. The cell image segmentation method according to claim 2, wherein the contrast enhancement process includes:
and carrying out nonlinear stretching on the brightness of each pixel point of the target gray level image by using a nonlinear enhancement method to obtain a contrast enhancement image, wherein the nonlinear enhancement method is a weighting distribution-based adaptive Gamma correction method.
4. The cell image segmentation method according to claim 3, wherein the denoising smoothing process includes:
and carrying out weighted average on the gray value of each pixel point of the contrast enhanced image by using a Gaussian filtering method to obtain a de-noised smooth image.
5. The cell image segmentation method according to claim 1, wherein the performing an iterative erosion operation on the target binarized image to obtain an initial seed point map comprises:
dividing the target binary image into a to-be-corroded area and a protected area according to a preset minimum corroded area, wherein the area of the to-be-corroded area is larger than the minimum corroded area, and the area of the protected area is smaller than or equal to the minimum corroded area;
performing iterative etching operation on the area to be etched according to a morphological method;
and obtaining an initial seed point diagram according to the protected area.
6. The cellular image segmentation method according to claim 1, wherein the performing a distance transform operation on the initial seed point map results in a background ridge line map, comprising:
performing distance transformation operation on the initial seed point diagram to obtain an initial ridge line diagram;
and adding a ridge line on the boundary of the initial ridge line graph to obtain a background ridge line graph.
7. The cell image segmentation method according to claim 1, wherein the performing a correction operation on the initial seed point map according to the background ridge line map to obtain a foreground seed point map comprises:
performing expansion operation on the background ridge line graph to obtain a ridge line expansion graph;
carrying out inversion operation on the ridge expansion diagram to obtain a ridge inversion diagram;
and performing intersection treatment on the ridge line reverse graph and the initial seed point graph to obtain a foreground seed point graph.
8. The cell image segmentation method according to claim 4, wherein the performing a watershed segmentation operation on the foreground seed point map and the background ridge line map to obtain a segmentation result of the target gray scale image comprises:
carrying out gradient processing on the de-noised smooth image to obtain a gradient image;
merging the foreground seed point diagram and the background ridge line diagram to obtain a foreground background diagram;
mapping the gradient image according to the foreground background image to obtain a corrected gradient image;
and performing watershed segmentation operation on the corrected gradient image to obtain a segmentation result of the target gray level image.
9. A cell image segmentation apparatus, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of cell image segmentation according to any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when executed by a processor, implements the cell image segmentation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111085684.6A CN113781515A (en) | 2021-09-16 | 2021-09-16 | Cell image segmentation method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111085684.6A CN113781515A (en) | 2021-09-16 | 2021-09-16 | Cell image segmentation method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781515A true CN113781515A (en) | 2021-12-10 |
Family
ID=78844471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111085684.6A Pending CN113781515A (en) | 2021-09-16 | 2021-09-16 | Cell image segmentation method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113781515A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240978A (en) * | 2022-03-01 | 2022-03-25 | 珠海横琴圣澳云智科技有限公司 | Cell edge segmentation method and device based on adaptive morphology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160668A (en) * | 2015-08-26 | 2015-12-16 | 爱威科技股份有限公司 | Image segmentation method and system, and cell image segmentation method and system |
| CN108280821A (en) * | 2017-12-15 | 2018-07-13 | 上海市第六人民医院 | Sections of Bone Marrow fluorescent marker quantified system analysis based on intelligent image analysis |
| CN110223305A (en) * | 2019-06-12 | 2019-09-10 | 志诺维思（北京）基因科技有限公司 | Cell segmentation method, apparatus and readable storage medium storing program for executing |
| CN112907558A (en) * | 2021-03-15 | 2021-06-04 | 南京农业大学 | Full-automatic image determination method for thousand grain weight of rape seeds |
-
2021
- 2021-09-16 CN CN202111085684.6A patent/CN113781515A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160668A (en) * | 2015-08-26 | 2015-12-16 | 爱威科技股份有限公司 | Image segmentation method and system, and cell image segmentation method and system |
| CN108280821A (en) * | 2017-12-15 | 2018-07-13 | 上海市第六人民医院 | Sections of Bone Marrow fluorescent marker quantified system analysis based on intelligent image analysis |
| CN110223305A (en) * | 2019-06-12 | 2019-09-10 | 志诺维思（北京）基因科技有限公司 | Cell segmentation method, apparatus and readable storage medium storing program for executing |
| CN112907558A (en) * | 2021-03-15 | 2021-06-04 | 南京农业大学 | Full-automatic image determination method for thousand grain weight of rape seeds |
Non-Patent Citations (1)
| Title |
|---|
| 季玉瑶: ""基于图像处理的虾苗计数研究"", 《农业科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240978A (en) * | 2022-03-01 | 2022-03-25 | 珠海横琴圣澳云智科技有限公司 | Cell edge segmentation method and device based on adaptive morphology |
| CN114240978B (en) * | 2022-03-01 | 2022-05-13 | 珠海横琴圣澳云智科技有限公司 | Cell edge segmentation method and device based on adaptive morphology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970844B2 (en) | Image segmentation method and device, computer device and non-volatile storage medium | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN112419271B (en) | Image segmentation method, device and computer readable storage medium | |
| CN108364297B (en) | Blood vessel image segmentation method, terminal and storage medium | |
| CN109416749B (en) | Image gray scale classification method and device and readable storage medium | |
| CN111429372A (en) | Method for enhancing edge detection effect of low-contrast image | |
| CN111882565B (en) | Image binarization method, device, equipment and storage medium | |
| CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
| Khan et al. | Image de-noising using noise ratio estimation, K-means clustering and non-local means-based estimator | |
| CN108510478B (en) | Lung airway image segmentation method, terminal and storage medium | |
| CN116703754A (en) | Image enhancement method for detecting cracks of building water supply pipeline | |
| CN113781515A (en) | Cell image segmentation method, device and computer readable storage medium | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN117173201B (en) | Second order differential image segmentation method, system, medium and device | |
| CN116385446B (en) | Crystal impurity detection method for boehmite production | |
| CN114240990B (en) | SAR image point target segmentation method | |
| CN115984312A (en) | Image segmentation method, electronic device and computer-readable storage medium | |
| CN108447066B (en) | Biliary tract image segmentation method, terminal and storage medium | |
| CN112329674B (en) | Icing lake detection method and device based on multi-texture feature fusion | |
| CN114998186A (en) | Image processing-based method and system for detecting surface scab defect of copper starting sheet | |
| CN114581423A (en) | Twin crystal boundary identification method, device and equipment and readable storage medium | |
| He et al. | Multilevel thresholding based on fuzzy masi entropy | |
| Haseyama et al. | A genetic algorithm based image segmentation for image analysis | |
| CN114677525B (en) | Edge detection method based on binary image processing | |
| Fouad et al. | Automaticand accurate segmentation of gridded cDNA microarray images using different methods |
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 |