CN110874821A - Image processing method for automatically filtering non-sperm components in semen - Google Patents
Image processing method for automatically filtering non-sperm components in semen Download PDFInfo
- Publication number
- CN110874821A CN110874821A CN201811009209.9A CN201811009209A CN110874821A CN 110874821 A CN110874821 A CN 110874821A CN 201811009209 A CN201811009209 A CN 201811009209A CN 110874821 A CN110874821 A CN 110874821A
- Authority
- CN
- China
- Prior art keywords
- image
- semen
- filtering
- difference
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 210000000582 semen Anatomy 0.000 title claims abstract description 58
- 238000001914 filtration Methods 0.000 title claims abstract description 38
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 239000012535 impurity Substances 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012935 Averaging Methods 0.000 claims abstract description 4
- 230000003321 amplification Effects 0.000 claims description 8
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 210000004027 cell Anatomy 0.000 description 24
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 210000002919 epithelial cell Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009027 insemination Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004899 motility Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
An image processing method for automatically filtering non-sperm components in semen, comprising the following steps: acquiring a semen image; filtering a round cell area in the semen image to generate a filtered image; carrying out averaging processing on the filtered image to obtain an average image; obtaining a difference image by subtracting the mean image and the semen image; superposing a grid template on the difference image; deleting bright spot areas which are not overlapped with the grid lines of the grid template in the difference image to generate an intermediate image; performing expansion processing on the intermediate image to generate an expanded image; filling a cavity area in the expansion image to generate a filling image; a final image is generated. On the basis of filtering the round cells, the arrangement of the grid template is matched with the expansion processing and the template filtering of the image, so that the filtering of impurities or bubbles in the semen image is realized, the sperm image in a discrete state in the semen is accurately detected, and the influence on the accuracy of counting the sperm cells due to the gathering of the sperm in the impurity or bubble area is avoided.
Description
Technical Field
The invention relates to the field of sperm detection, in particular to an image processing method for automatically filtering non-sperm components in semen.
Background
Computer-assisted analysis technology (CASA) based on sperm quality has evolved rapidly by the end of the last 80 th century. People find that the automatic measurement and evaluation of various data of sperms by using a computer image analysis technology has a plurality of advantages, and the method has the advantages of simple operation, high analysis speed, high calculation precision and good repeatability, provides accurate reference data for artificial insemination, improves the inspection level of inspection doctors, reduces the workload of the inspection doctors, and can overcome the defects of the traditional determination method, such as time consumption, poor measurement precision, strong manual subjectivity and the like.
In the prior art, most of the methods for analyzing semen images are as follows: the semen is amplified and imaged through a phase contrast microscope, and then a dynamic image under the microscope is amplified and collected through a camera system for the second time, so that the sperms in the image are counted or identified. However, the semen contains a large amount of non-sperm components including round cells, epithelial cells, air bubbles, impurities and the like, and the sperm in the semen can be concentrated at the position of the large impurity and the air bubbles, so that the aggregation phenomenon of the sperm is caused.
Since analysis of all sperm cells has a great influence on the results of the examination, it is common to use a calculation for clinically analyzing only sperm concentration and motility in discrete states. If only simple image enhancement and binarization analysis techniques are adopted, all bright parts in the semen image can be identified as sperms, and the result is several times different from the actual clinical result and is not reliable. If the conventional method is used to simply filter a large area of the object, instability occurs, which is not very reliable because the large area is not continuous in all cases.
Disclosure of Invention
The invention aims to provide an image processing method for automatically filtering non-sperm components in semen, which has the advantage that sperm images in a discrete state in the semen can be accurately detected.
The technical purpose of the invention is realized by the following technical scheme:
an image processing method for automatically filtering non-sperm components in semen, comprising the following steps:
step 1: acquiring a semen image, and acquiring the semen image by using an image amplification device;
step 2: filtering a round cell area in the semen image to generate a filtered image;
and step 3: generating a mean image, and carrying out averaging processing on the filtered image to obtain the mean image;
and 4, step 4: generating a difference image, and obtaining the difference image by making a difference between the mean image and the semen image;
and 5: setting a grid template, and overlapping the grid template on the difference image;
step 6: generating an intermediate image, deleting bright spot areas which are not overlapped with the grid lines of the grid template in the difference image, and generating the intermediate image;
and 7: generating an expansion image, and performing expansion processing on the intermediate image to generate an expansion image;
and 8: generating a filling image, filling a cavity area in the expansion image, and generating the filling image;
and step 9: and generating a final image, selecting an image region with a single area exceeding a preset area in the filling image as an impurity template, and deleting an image region corresponding to the impurity template in the filtering image to generate the final image.
By adopting the technical scheme, most of round cells in the semen are the same in shape, and the round cell filtering area is a simple filtering method in the image processing process, but the shapes of impurities and bubbles are irregular, and meanwhile, a large number of sperm cells are collected at the positions of the impurities and the bubbles, and the collected sperm cells cannot be used as an object for researching the quality of the semen. After the difference image is generated, bright spot areas in the semen image can be completely highlighted, then the bright spot areas are deleted through the grid template, only large-block impurities or bubbles are located to collect a large number of cells to form the dense bright spot areas, the dense bright spot areas form a whole area in an image expansion mode, the whole area serves as the template to filter corresponding areas in the semen image, filtering of the cell collection areas formed by the impurities or the bubbles in the semen can be achieved, only free sperm cells remain in the semen image, and the sperm image in a discrete state in the semen is accurately detected.
As a refinement of the invention, the image magnification device is arranged as a phase contrast microscope.
As a refinement of the present invention, said step 8 comprises:
step 8-1: carrying out distinguishing marking on different areas in the expansion image;
step 8-2: filling the hollow area of a single image area in the expansion image to generate a filling image.
As a refinement of the invention, the distinguishing mark is provided as a color mark.
As a refinement of the present invention, said step 4 comprises: and after the average image and the semen image are subjected to difference, carrying out brightness amplification to generate the difference image.
As an improvement of the present invention, a calculation method for generating a gray scale value in the difference image comprises:
g’=(g1-g2)*Mult+Add
wherein g1 is the gray value of the coordinate point in the semen image, g2 is the gray value of the corresponding coordinate point in the mean image, Mult is the amplification factor, Add is the offset, and g' is the gray value of the corresponding point in the difference image.
In conclusion, the invention has the following beneficial effects:
as round cells, impurities and bubbles are filtered, only sperm cells remain in the obtained final image, and the sperm image in a discrete state in the semen can be accurately detected through small-area sample collection in the actual research process.
Drawings
FIG. 1 is a flow diagram of an image processing method for automatically filtering non-sperm components of semen;
FIG. 2 is a schematic diagram of a filtered image;
FIG. 3 is a schematic diagram of a mean image;
FIG. 4 is a schematic diagram of a difference image;
FIG. 5 is a difference image after adding a grid template;
FIG. 6 is a schematic illustration of an intermediate image;
FIG. 7 is a schematic view of a dilated image;
FIG. 8 is a schematic view of a fill image;
fig. 9 is a schematic diagram of the final image.
Detailed Description
The present invention will be described in further detail with reference to the attached drawings, wherein like parts are designated by like reference numerals. It should be noted that as used in the following description, the terms "front," "rear," "left," "right," "upper" and "lower," "bottom" and "top" refer to directions in the drawings, and the terms "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
An image processing method for automatically filtering non-sperm components in semen, as shown in fig. 1, comprises the following steps:
step 1: a semen image is acquired, the semen image being acquired by means of an image magnification device, here preferably a phase contrast microscope.
Step 2: and filtering the circular cell region, and filtering the circular cell region in the semen image to generate a filtered image as shown in figure 2.
Step 2-1: intercepting an image region corresponding to a round cell in the semen image by using image processing software such as Photoshop, and generating a corresponding round cell filtering template; in the Delphi development environment, the OPEN CV development kit was used to convert the round cell filter template into a template file. When round cell filtering needs to be carried out on the semen image, an OPEN CV development kit and a corresponding template file are used for filtering an image area with the same shape as the template file in the semen image, and therefore a filtering image is generated.
Because the round cells are the same in shape and are all round, after the round cell filtering template is generated through image processing software, template files generated according to the round cell filtering template can be compared with all regions in the semen image one by one, and the round image regions in the semen image are filtered by utilizing the inherent image processing technology of the OPEN CV development kit, so that the filtering of the round cell image regions is realized.
And step 3: averaging, which is to average the filtered image to generate an average image as shown in fig. 3.
And 4, step 4: and generating a difference image, and performing brightness amplification after the difference is performed between the mean image and the semen image to generate the difference image shown in fig. 4.
The calculation method for generating the gray value in the difference image comprises the following steps:
g’=(g1-g2)*Mult+Add
wherein g1 is the gray value of the coordinate point in the semen image, g2 is the gray value of the corresponding coordinate point in the mean image, Mult is the amplification factor of brightness, Add is the offset, and g' is the gray value of the corresponding point in the difference image.
And 5: as shown in fig. 5, a grid template is set, and the grid template is superimposed on the difference image, and the grid template is preferably composed of a 3 × 3 pixel grid.
Step 6: an intermediate image is generated, and the bright spot regions in the difference image that do not overlap the grid lines of the grid template are deleted, thereby generating an intermediate image as shown in fig. 6.
And 7: the expansion process performs expansion processing on the intermediate image to generate an expanded image as shown in fig. 7.
And 8: and (5) filling the image, namely filling the hollow area in the expanded image to generate a filled image.
Step 8-1: different regions in the dilated image are marked differently. Wherein the distinctive marks include, but are not limited to, color marks or depth marks, preferably color marks here, marking adjacent regions in mutually different colors to facilitate a researcher to clearly view the layout of the dilated image.
Step 8-2: the hole regions of the individual image regions in the dilated image are filled to produce a filled image as shown in fig. 8.
And step 9: and (3) template filtering, namely selecting an image area with a single area exceeding a preset area in the filled image as an impurity template, and deleting an image area corresponding to the impurity template in the filtered image to generate a final image as shown in fig. 9.
In conclusion, on the basis of filtering the round cells, the arrangement of the grid template is matched with the expansion processing and the template filtering of the image, so that the filtering of impurities or bubbles in the semen image is realized, the semen image in a discrete state in the semen is accurately detected, and the influence on the accuracy of counting the sperm cells due to the fact that the sperm are gathered in the impurity or bubble area is avoided.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
Claims (6)
1. An image processing method for automatically filtering non-sperm components in semen, comprising the steps of:
step 1: acquiring a semen image, and acquiring the semen image by using an image amplification device;
step 2: filtering a round cell area in the semen image to generate a filtered image;
and step 3: generating a mean image, and carrying out averaging processing on the filtered image to obtain the mean image;
and 4, step 4: generating a difference image, and obtaining the difference image by making a difference between the mean image and the semen image;
and 5: setting a grid template, and overlapping the grid template on the difference image;
step 6: generating an intermediate image, deleting bright spot areas which are not overlapped with the grid lines of the grid template in the difference image, and generating the intermediate image;
and 7: generating an expansion image, and performing expansion processing on the intermediate image to generate an expansion image;
and 8: generating a filling image, filling a cavity area in the expansion image, and generating the filling image;
and step 9: and generating a final image, selecting an image region with a single area exceeding a preset area in the filling image as an impurity template, and deleting an image region corresponding to the impurity template in the filtering image to generate the final image.
2. The image processing method for automatically filtering non-sperm components of semen as recited in claim 1, wherein: the image magnification device is arranged as a phase contrast microscope.
3. An image processing method for the automatic filtering of non-sperm components of semen as claimed in claim 2, wherein said step 8 comprises:
step 8-1: carrying out distinguishing marking on different areas in the expansion image;
step 8-2: filling the hollow area of a single image area in the expansion image to generate a filling image.
4. An image processing method for the automatic filtering of non-sperm components of semen as claimed in claim 3, characterized in that: the distinctive marks are provided as color marks.
5. An image processing method for the automatic filtering of non-sperm components of semen as claimed in claim 4, wherein said step 4 comprises: and after the average image and the semen image are subjected to difference, carrying out brightness amplification to generate the difference image.
6. An image processing method for the automatic filtering of non-sperm components of semen as claimed in claim 5, wherein: the calculation method for generating the gray value in the difference image comprises the following steps:
g’=(g1-g2)*Mult+Add
wherein g1 is the gray value of the coordinate point in the semen image, g2 is the gray value of the corresponding coordinate point in the mean image, Mult is the amplification factor, Add is the offset, and g' is the gray value of the corresponding point in the difference image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009209.9A CN110874821B (en) | 2018-08-31 | 2018-08-31 | Image processing method for automatically filtering non-sperm components in semen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009209.9A CN110874821B (en) | 2018-08-31 | 2018-08-31 | Image processing method for automatically filtering non-sperm components in semen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110874821A true CN110874821A (en) | 2020-03-10 |
| CN110874821B CN110874821B (en) | 2023-05-30 |
Family
ID=69715755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811009209.9A Active CN110874821B (en) | 2018-08-31 | 2018-08-31 | Image processing method for automatically filtering non-sperm components in semen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110874821B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202075277U (en) * | 2011-05-10 | 2011-12-14 | 北京华方神火科技有限公司 | Sperm detecting room |
| CN102800101A (en) * | 2012-08-09 | 2012-11-28 | 西北工业大学 | Satellite-borne infrared remote sensing image airport ROI rapid detection method |
| US20130095499A1 (en) * | 2011-10-07 | 2013-04-18 | Brown University | Methods, compositions and kits for imaging cells and tissues using nanoparticles and spatial frequency heterodyne imaging |
| US20130273524A1 (en) * | 2012-04-17 | 2013-10-17 | Joel R. L. Ehrenkranz | Device for performing a blood, cell, and/or pathogen count and methods for use thereof |
| CN104933679A (en) * | 2015-07-06 | 2015-09-23 | 福州瑞芯微电子有限公司 | A method for enlarging an image and a system corresponding to the method |
| CN105960463A (en) * | 2013-11-20 | 2016-09-21 | 布里格姆女子医院有限公司 | System and method for sperm sorting |
| CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
| US20170301093A1 (en) * | 2016-04-13 | 2017-10-19 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
| CN107545557A (en) * | 2016-06-23 | 2018-01-05 | 爱威科技股份有限公司 | Egg detecting method and device in excrement image |
| CN108229098A (en) * | 2016-12-09 | 2018-06-29 | 深圳市瀚海基因生物科技有限公司 | Monomolecular identification, method of counting and device |
| CN108428214A (en) * | 2017-02-13 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of image processing method and device |
-
2018
- 2018-08-31 CN CN201811009209.9A patent/CN110874821B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202075277U (en) * | 2011-05-10 | 2011-12-14 | 北京华方神火科技有限公司 | Sperm detecting room |
| US20130095499A1 (en) * | 2011-10-07 | 2013-04-18 | Brown University | Methods, compositions and kits for imaging cells and tissues using nanoparticles and spatial frequency heterodyne imaging |
| US20130273524A1 (en) * | 2012-04-17 | 2013-10-17 | Joel R. L. Ehrenkranz | Device for performing a blood, cell, and/or pathogen count and methods for use thereof |
| CN102800101A (en) * | 2012-08-09 | 2012-11-28 | 西北工业大学 | Satellite-borne infrared remote sensing image airport ROI rapid detection method |
| CN105960463A (en) * | 2013-11-20 | 2016-09-21 | 布里格姆女子医院有限公司 | System and method for sperm sorting |
| CN104933679A (en) * | 2015-07-06 | 2015-09-23 | 福州瑞芯微电子有限公司 | A method for enlarging an image and a system corresponding to the method |
| US20170301093A1 (en) * | 2016-04-13 | 2017-10-19 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
| CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
| CN107545557A (en) * | 2016-06-23 | 2018-01-05 | 爱威科技股份有限公司 | Egg detecting method and device in excrement image |
| CN108229098A (en) * | 2016-12-09 | 2018-06-29 | 深圳市瀚海基因生物科技有限公司 | Monomolecular identification, method of counting and device |
| CN108428214A (en) * | 2017-02-13 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of image processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| 李红卫;苑伟政;叶芳;: "基于数学形态学的微阵列芯片荧光图像处理与分析", 传感技术学报 * |
| 柳建武: "***质量计算机辅助分析技术的研究" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110874821B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11506650B2 (en) | Method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials | |
| WO2020063461A1 (en) | Urban extent extraction method and apparatus based on random forest classification algorithm, and electronic device | |
| CN104535475B (en) | Method and device for determining microstructure of carbonate rock | |
| CN109903284B (en) | HER2 immunohistochemical image automatic discrimination method and system | |
| CN104751473B (en) | Method and device for determining characteristics of multi-scale holes of carbonatite | |
| CN109461188B (en) | A kind of two-dimensional x-ray cephalometry image anatomical features point automatic positioning method | |
| CN110796661B (en) | Fungal microscopic image segmentation detection method and system based on convolutional neural network | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN107239742A (en) | A kind of gauge pointer scale value calculating method | |
| CN108186051A (en) | A kind of image processing method and processing system of the automatic measurement fetus Double Tops electrical path length from ultrasonoscopy | |
| CN109035283A (en) | It is a kind of precisely to be detected and quantitative analysis method based on the pulmonary emphysema for randomly selecting subregion | |
| CN108389184A (en) | A kind of workpiece drilling number detection method based on machine vision | |
| CN103954334A (en) | Fully automatic image pickup type water meter verification system and operating method thereof | |
| CN110490971B (en) | Method for reconstructing cell dynamic characteristic three-dimensional image under biological microscope | |
| CN108320799A (en) | Image analysis and recognition method for lateral flow paper strip disease diagnosis | |
| CN116152697A (en) | Three-dimensional model measuring method and related device for concrete structure cracks | |
| CN109920002B (en) | Characteristic point positioning method in cephalometry image based on three-dimensional random forest model | |
| CN111008602A (en) | Two-dimensional and three-dimensional visual combined lineation feature extraction method for small-curvature thin-wall part | |
| CN111795967B (en) | Smear self-checking method of marrow cell morphology automatic checking system | |
| CN110930345A (en) | Sperm tail recognition method | |
| CN110874821A (en) | Image processing method for automatically filtering non-sperm components in semen | |
| CN106485728B (en) | A kind of automatic measure of bar shaped main transformer oil level indicator | |
| CN113421301B (en) | Method and system for positioning central area of field crop | |
| CN114219780A (en) | Deep learning-based method for detecting and segmenting nail fold microcirculation blood vessel | |
| CN104006767A (en) | High-throughput plant type measurement method based on image processing |
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 |