CN114494318A - Method for extracting cornea contour from cornea dynamic deformation video based on Otsu algorithm - Google Patents
Method for extracting cornea contour from cornea dynamic deformation video based on Otsu algorithm Download PDFInfo
- Publication number
- CN114494318A CN114494318A CN202210145560.0A CN202210145560A CN114494318A CN 114494318 A CN114494318 A CN 114494318A CN 202210145560 A CN202210145560 A CN 202210145560A CN 114494318 A CN114494318 A CN 114494318A
- Authority
- CN
- China
- Prior art keywords
- image
- cornea
- dynamic deformation
- extracting
- otsu
- 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
- 210000004087 cornea Anatomy 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 26
- 238000003709 image segmentation Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000009467 reduction Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims description 6
- 239000012535 impurity Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 16
- 238000000605 extraction Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 4
- 238000009432 framing Methods 0.000 description 3
- 230000001575 pathological effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 201000002287 Keratoconus Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 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
- G06T7/13—Edge detection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30041—Eye; Retina; Ophthalmic
Abstract
The invention relates to a method for extracting a cornea profile from a cornea dynamic deformation video based on an Otsu algorithm, which comprises the following steps: step 1, preprocessing a cornea outline image; step 2, carrying out image segmentation on the image preprocessed in the step 1 by adopting an Otsu algorithm, and introducing mathematical morphology operation to reduce the possibility of occurrence of holes and fine noise; and 3, calculating the image gradient by using a Gaussian function, and detecting the edge of the image by setting a double threshold. The invention can greatly improve the accuracy and the integrity of the extracted cornea contour.
Description
Technical Field
The invention belongs to the technical field of image processing, relates to a method for extracting a cornea profile from a cornea dynamic deformation video, and particularly relates to a method for extracting a cornea profile from a cornea dynamic deformation video based on an Otsu algorithm.
Background
At present, the contour extraction technology is widely applied to image processing. After a large amount of image data is acquired, the specific object in the image needs to be characterized, and the specific object is detected, identified and classified according to the contour characteristic information of the image. Therefore, how to extract the contour of a certain kind of specific object from an image is a problem to be solved urgently at present.
In the past few years, a large number of researchers have devised various solutions to the problem of object contour extraction. Saber M S et al propose a new scheme for designing a computer-aided system based on OTSU to detect abnormalities in breast images, helping radiologists to more easily find abnormalities on mammograms. The image segmentation algorithm for improving the Otsu algorithm and the artificial bee colony optimization is provided by Huangcui et al aiming at the characteristics of high image processing calculation complexity, poor real-time performance and the like in the image segmentation process, and an ideal segmentation effect can be achieved. Liupei jin et al have designed an infrared image multi-threshold segmentation method by using two-dimensional OTSU, which improves the real-time and accuracy of electrical equipment infrared image multi-threshold segmentation. However, when the algorithms are applied to the cornea dynamic deformation video cornea contour extraction process, the accuracy requirement cannot be met.
Through searching, the published patent documents which are the same as or similar to the invention are not found.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a cornea contour extraction method based on a cornea dynamic deformation video of Otsu algorithm, which has reasonable design and high accuracy and can meet the requirement of contour extraction integrity.
The invention solves the practical problem by adopting the following technical scheme:
a method for extracting a cornea contour from a cornea dynamic deformation video based on an Otsu algorithm comprises the following steps:
step 1, preprocessing a cornea outline image;
step 2, carrying out image segmentation on the image preprocessed in the step 1 by adopting an Otsu algorithm, and introducing mathematical morphology operation to reduce the possibility of occurrence of holes and fine noise;
and 3, calculating the image gradient by using a Gaussian function, and detecting the edge of the image by setting a double threshold.
Moreover, the specific method of step 1 is: performing frame processing on the cornea dynamic deformation video, and then performing image preprocessing such as impurity removal, graying, image noise reduction and the like on the cornea contour image:
H=0.299R+0.587G+0.144B (1)
adding Gaussian filtering to perform image noise reduction, and using a two-dimensional Gaussian function:
wherein x and y are the abscissa and the ordinate of the image center point.
Further, the specific steps of step 2 include:
(1) dividing the images into two classes according to the gray characteristic of the images by adopting a maximum inter-class difference method, calculating the inter-class variance of each classification result, and selecting the maximum value as an optimal threshold value:
ω=αω1+βω2 (3)
σ2=α(ω-ω1)2+β(ω-ω2)2 (4)
T=max{σ2(k)},k∈[0,N-1] (5)
wherein, N is the gray value of the gray image, alpha and beta are the ratio of the number of two kinds of pixels in the whole image, omega1And ω2Is the mean value of two types of gray scales.
(2) The image processing process introduces the open operation and the close operation in mathematical morphology:
opening operation: the image is corroded and then expanded, so that the noise on the image can be eliminated;
and (3) closed operation: the expansion is carried out firstly, then the corrosion is carried out, fine holes can be filled, and images are communicated;
and (3) expansion operation: the result of the expansion of the set P by the structuring element Q is a mapping of Q with respect to the originIs not a set of origin positions of the space-time Q:
and (3) corrosion operation: the set P is a set of the origin positions of Q when Q is contained in all P as a result of erosion by the structural element Q.
Further, the specific steps of step 3 include:
calculating image gradients by a gaussian function, detecting edges of the image by setting a dual threshold:
calculating the gradient g of the Sobel operator in the horizontal directionx(x, y) and gradient g in the vertical directiony(x,y):
gx(x,y)=gσ(x,y)*soblex(x,y) (11)
gy(x,y)=gσ(x,y)*sobley(x,y) (12)
The combined gradient G (x, y) and direction θ can be calculated by the following formula:
the invention has the advantages and beneficial effects that:
1. the invention provides a cornea dynamic deformation video cornea contour extraction method based on an Otsu algorithm, which is characterized in that a weighted average gray algorithm is used for graying an image, and Gaussian filtering is added through a sliding window for image noise reduction; determining an image segmentation threshold by adopting an Otsu algorithm; calculating an optimal threshold value; the purposes of removing noise, filling holes and optimizing image boundaries are achieved by adopting mathematical morphology operation; and calculating the image gradient by using a Gaussian function, and setting a double threshold value to extract the edge of the cornea image.
2. The method is based on the Otsu algorithm to automatically calculate the threshold value, can accurately calculate the biomechanical parameters of the cornea and analyze the biomechanical characteristic change of the cornea, and can realize the intelligent detection of the keratoconus.
3. In the process of extracting the cornea contour, the image gradient is calculated by utilizing the Gaussian function, the edge property of the image is detected by setting double thresholds, the edge of the cornea image is extracted, and the characteristics of the edge property determine that the extraction result of the object contour which is approximate to an ellipsoid is more advantageous. The invention applies the method to the extraction of the cornea contour of the dynamic deformation video of the cornea, and greatly improves the accuracy and the integrity of the contour.
Drawings
FIG. 1 is a process flow diagram of the present invention;
FIG. 2 is an image of step 1 of the present invention after impurity removal;
FIG. 3 is a grayed image of step 1 of the present invention;
FIG. 4 is a denoised image of step 1 of the present invention;
fig. 5 is an image of the final corneal profile extraction of step 3 of the present invention.
Detailed Description
The embodiments of the invention are further described in the following with reference to the drawings:
a method for extracting a corneal profile from a corneal dynamic deformation video based on the greater fluid algorithm, as shown in fig. 1 to 5, includes the following steps:
step 1, preprocessing a cornea outline image;
the specific method of the step 1 comprises the following steps: performing framing processing on the cornea dynamic deformation video, and then performing image preprocessing such as impurity removal, graying, image noise reduction and the like on the cornea contour image;
in the embodiment, the color image is converted into the gray image, so that the color variation range is greatly reduced, the subsequent operation amount on the image is greatly reduced, and the distribution of the color and the brightness level of the whole image can be still represented.
H=0.299R+0.587G+0.144B (1)
Adding Gaussian filtering to perform image noise reduction, and using a two-dimensional Gaussian function:
wherein x and y are the abscissa and the ordinate of the image center point.
Step 2, carrying out image segmentation on the image preprocessed in the step 1 by adopting an Otsu algorithm, and introducing mathematical morphology operation to reduce the possibility of occurrence of holes and fine noise;
the specific steps of the step 2 comprise:
(1) dividing the images into two classes according to the gray characteristic of the images by adopting a maximum inter-class difference method, calculating the inter-class variance of each classification result, and selecting the maximum value as an optimal threshold value:
ω=αω1+βω2 (3)
σ2=α(ω-ω1)2+β(ω-ω2)2 (4)
T=max{σ2(k)},k∈[0,N-1] (5)
wherein, N is the gray value of the gray image, alpha and beta are the ratio of the number of two kinds of pixels in the whole image, omega1And ω2Is the mean value of two types of gray scales.
(2) The image processing process introduces the open operation and the close operation in mathematical morphology:
opening operation: the image is corroded and then expanded, so that the noise on the image can be eliminated;
and (3) closed operation: the expansion is carried out firstly, then the corrosion is carried out, fine holes can be filled, and images are communicated;
and (3) expansion operation: the result of the expansion of the set P by the structuring element Q is a mapping of Q with respect to the originIs not a set of null Q origin positions at times P intersect:
and (3) corrosion operation: the set P is a set of the origin positions of Q when Q is contained in all P as a result of erosion by the structural element Q.
And 3, calculating the image gradient by using a Gaussian function, and detecting the edge of the image by setting a double threshold.
The specific steps of the step 3 comprise:
the image gradient is calculated by a gaussian function, and the edge of the image is detected by setting a dual threshold.
Calculating the gradient g of the Sobel operator in the horizontal directionx(x, y) and gradient g in the vertical directiony(x,y)。
gx(x,y)=gσ(x,y)*soblex(x,y) (11)
gy(x,y)=gσ(x,y)*sobley(x,y) (12)
The combined gradient G (x, y) and direction θ can be calculated by the following formula:
the invention can also be applied to the field of cell detection, can utilize the outline of the cell to identify and screen the pathological cells, can quickly analyze the representation of the pathological cells while ensuring the identification accuracy, and can calculate the number of the pathological cells after comparison.
The working principle of the invention is as follows:
a method for extracting a cornea contour from a cornea dynamic deformation video based on an Otsu algorithm comprises the following steps: step 1, framing a cornea dynamic deformation video, and then carrying out image preprocessing such as impurity removal, graying, image noise reduction, image binarization and the like on a cornea contour image; 2, performing region segmentation on the preprocessed image by adopting an Otsu algorithm, and simultaneously introducing mathematical morphology operation to reduce the possibility of occurrence of holes and fine noise; and 3, calculating the image gradient by using a Gaussian function, and detecting the edge of the image by setting a double threshold. And judging the points which are more than the high threshold value as real edges, and simultaneously checking the 8-connected region pixels of the pixel points which are less than the high threshold value and more than the low threshold value, and considering the 8-connected region pixels as the real edges as long as the high threshold value points exist. The contour extraction result of the invention can meet the requirements of completeness and accuracy, and can completely and accurately obtain the corneal contour information.
The invention adopts the Otsu algorithm to calculate the optimal threshold value to carry out image segmentation, simultaneously introduces mathematical morphology operation to reduce the possibility of generating holes and fine noise, calculates the image gradient by introducing a Gaussian function, sets double threshold values to detect the edge of the cornea, and comprises the following steps in order to complete the purpose: firstly, framing a cornea dynamic deformation video, and then, carrying out impurity removal, graying, image noise reduction and other processing on a cornea contour image; then binarizing the denoised image, then segmenting the image by adopting an Otsu algorithm, and simultaneously introducing mathematical morphology operation to reduce the possibility of generating holes and fine noise; and finally, calculating the image gradient by using a Gaussian function, and detecting the edge of the cornea by setting a double threshold.
The core of the invention is to calculate the image gradient through a Gaussian function and then set a double threshold value to detect the edge of the cornea.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (4)
1. A method for extracting a cornea contour from a cornea dynamic deformation video based on an Otsu algorithm is characterized by comprising the following steps: the method comprises the following steps:
step 1, preprocessing a cornea outline image;
step 2, carrying out image segmentation on the image preprocessed in the step 1 by adopting an Otsu algorithm, and introducing mathematical morphology operation to reduce the possibility of occurrence of holes and fine noise;
and 3, calculating the image gradient by using a Gaussian function, and detecting the edge of the image by setting a double threshold.
2. The method for extracting the corneal profile based on the corneal dynamic deformation video of Otsu's algorithm as claimed in claim 1, wherein: the specific method of the step 1 comprises the following steps: performing frame processing on the cornea dynamic deformation video, and then performing image preprocessing such as impurity removal, graying, image noise reduction and the like on the cornea contour image:
H=0.299R+0.587G+0.144B (1)
adding Gaussian filtering to perform image noise reduction, and using a two-dimensional Gaussian function:
wherein x and y are the abscissa and the ordinate of the image center point.
3. The method for extracting the corneal profile based on the corneal dynamic deformation video of Otsu's algorithm as claimed in claim 1, wherein: the specific steps of the step 2 comprise:
(1) dividing the images into two classes according to the gray characteristic of the images by adopting a maximum inter-class difference method, calculating the inter-class variance of each classification result, and selecting the maximum value as an optimal threshold value:
ω=αω1+βω2 (3)
σ2=α(ω-ω1)2+β(ω-ω2)2 (4)
T=max{σ2(k)},k∈[0,N-1] (5)
wherein, N is the gray value of the gray image, alpha and beta are the ratio of the number of two kinds of pixels in the whole image, omega1And ω2The mean value of two types of gray scales;
(2) the method is characterized in that an opening operation and a closing operation in mathematical morphology are introduced in the image processing process:
opening operation: the image is corroded and then expanded, so that the noise on the image can be eliminated;
and (3) closed operation: the expansion is carried out firstly, then the corrosion is carried out, fine holes can be filled, and images are communicated;
and (3) expansion operation: the result of the expansion of the set P by the structuring element Q is a mapping of Q with respect to the originIs not a set of origin positions of the space-time Q:
and (3) corrosion operation: the set P is a set of origin positions of Q when Q is contained in all P as a result of erosion by the structural element Q:
4. the method for extracting the corneal profile based on the corneal dynamic deformation video of Otsu's algorithm as claimed in claim 1, wherein: the specific steps of the step 3 comprise:
calculating image gradients by a gaussian function, detecting edges of the image by setting a dual threshold:
calculating the gradient gx (x, y) in the horizontal direction and the gradient g in the vertical direction by using a Sobel operatory(x,y):
gx(x,y)=gσ(x,y)*soblex(x,y) (11)
gy(x,y)=gσ(x,y)*sobley(x,y) (12)
The combined gradient G (x, y) and direction θ can be calculated by the following formula:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210145560.0A CN114494318B (en) | 2022-02-17 | 2022-02-17 | Cornea contour extraction method based on cornea dynamic deformation video of Ojin algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210145560.0A CN114494318B (en) | 2022-02-17 | 2022-02-17 | Cornea contour extraction method based on cornea dynamic deformation video of Ojin algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114494318A true CN114494318A (en) | 2022-05-13 |
CN114494318B CN114494318B (en) | 2023-05-23 |
Family
ID=81481453
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210145560.0A Active CN114494318B (en) | 2022-02-17 | 2022-02-17 | Cornea contour extraction method based on cornea dynamic deformation video of Ojin algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114494318B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114943707A (en) * | 2022-05-26 | 2022-08-26 | 天津市眼科医院 | Fine cornea deformation identification method and device based on pixel-level cornea biomechanical parameters |
CN115272321A (en) * | 2022-09-28 | 2022-11-01 | 山东军冠纺织有限公司 | Textile defect detection method based on machine vision |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102800089A (en) * | 2012-06-28 | 2012-11-28 | 华中科技大学 | Main carotid artery blood vessel extraction and thickness measuring method based on neck ultrasound images |
CN103927526A (en) * | 2014-04-30 | 2014-07-16 | 长安大学 | Vehicle detecting method based on Gauss difference multi-scale edge fusion |
CN106228138A (en) * | 2016-07-26 | 2016-12-14 | 国网重庆市电力公司电力科学研究院 | A kind of Road Detection algorithm of integration region and marginal information |
US20180018767A1 (en) * | 2016-07-12 | 2018-01-18 | National Tsing Hua University | Method of segmenting single neuron images with high-dynamic-range thresholds and computer readable storage medium thereof |
CN107909590A (en) * | 2017-11-15 | 2018-04-13 | 北京工业大学 | A kind of IVUS image outer membrane edge fate segmentation methods based on Snake innovatory algorithms |
CN109146860A (en) * | 2018-08-03 | 2019-01-04 | 北京工商大学 | Full-automatic mechanical equipment installs leakage detection method and device |
CN109584240A (en) * | 2018-12-20 | 2019-04-05 | 成都理工大学 | Come down rear crack displacement image-recognizing method |
CN110473222A (en) * | 2019-07-02 | 2019-11-19 | 清华大学 | Image-element extracting method and device |
CN111429462A (en) * | 2020-02-26 | 2020-07-17 | 重庆邮电大学 | License plate positioning method based on edge detection and mathematical morphology |
CN111724319A (en) * | 2020-06-19 | 2020-09-29 | 马鞍山职业技术学院 | Image processing method in video monitoring system |
CN112132153A (en) * | 2020-09-22 | 2020-12-25 | 山东大学 | Tomato fruit identification method and system based on clustering and morphological processing |
CN112669295A (en) * | 2020-12-30 | 2021-04-16 | 上海电机学院 | Lithium battery pole piece defect detection method based on secondary threshold segmentation theory |
-
2022
- 2022-02-17 CN CN202210145560.0A patent/CN114494318B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102800089A (en) * | 2012-06-28 | 2012-11-28 | 华中科技大学 | Main carotid artery blood vessel extraction and thickness measuring method based on neck ultrasound images |
CN103927526A (en) * | 2014-04-30 | 2014-07-16 | 长安大学 | Vehicle detecting method based on Gauss difference multi-scale edge fusion |
US20180018767A1 (en) * | 2016-07-12 | 2018-01-18 | National Tsing Hua University | Method of segmenting single neuron images with high-dynamic-range thresholds and computer readable storage medium thereof |
CN106228138A (en) * | 2016-07-26 | 2016-12-14 | 国网重庆市电力公司电力科学研究院 | A kind of Road Detection algorithm of integration region and marginal information |
CN107909590A (en) * | 2017-11-15 | 2018-04-13 | 北京工业大学 | A kind of IVUS image outer membrane edge fate segmentation methods based on Snake innovatory algorithms |
CN109146860A (en) * | 2018-08-03 | 2019-01-04 | 北京工商大学 | Full-automatic mechanical equipment installs leakage detection method and device |
CN109584240A (en) * | 2018-12-20 | 2019-04-05 | 成都理工大学 | Come down rear crack displacement image-recognizing method |
CN110473222A (en) * | 2019-07-02 | 2019-11-19 | 清华大学 | Image-element extracting method and device |
CN111429462A (en) * | 2020-02-26 | 2020-07-17 | 重庆邮电大学 | License plate positioning method based on edge detection and mathematical morphology |
CN111724319A (en) * | 2020-06-19 | 2020-09-29 | 马鞍山职业技术学院 | Image processing method in video monitoring system |
CN112132153A (en) * | 2020-09-22 | 2020-12-25 | 山东大学 | Tomato fruit identification method and system based on clustering and morphological processing |
CN112669295A (en) * | 2020-12-30 | 2021-04-16 | 上海电机学院 | Lithium battery pole piece defect detection method based on secondary threshold segmentation theory |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114943707A (en) * | 2022-05-26 | 2022-08-26 | 天津市眼科医院 | Fine cornea deformation identification method and device based on pixel-level cornea biomechanical parameters |
CN114943707B (en) * | 2022-05-26 | 2023-06-30 | 天津市眼科医院 | Fine cornea deformation identification method and device based on pixel-level cornea biomechanics parameters |
CN115272321A (en) * | 2022-09-28 | 2022-11-01 | 山东军冠纺织有限公司 | Textile defect detection method based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN114494318B (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114494318B (en) | Cornea contour extraction method based on cornea dynamic deformation video of Ojin algorithm | |
WO2021109697A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
CN111754538B (en) | Threshold segmentation method for USB surface defect detection | |
CN111340824A (en) | Image feature segmentation method based on data mining | |
CN111598897B (en) | Infrared image segmentation method based on Otsu and improved Bernsen | |
CN110544262B (en) | Cervical cell image segmentation method based on machine vision | |
CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
CN114943744A (en) | Edge detection method based on local Otsu thresholding | |
Soni et al. | CT scan based brain tumor recognition and extraction using Prewitt and morphological dilation | |
CN112258449A (en) | Rapid nodule matching method based on nodule characteristics | |
CN113643290B (en) | Straw counting method and device based on image processing and storage medium | |
CN109615630A (en) | Semi-continuous casting alusil alloy Analysis on Microstructure method based on image processing techniques | |
Yu et al. | A breast region extraction scheme for digital mammograms using gradient vector flow Snake | |
CN113850792A (en) | Cell classification counting method and system based on computer vision | |
CN110276260B (en) | Commodity detection method based on depth camera | |
CN113763404A (en) | Foam image segmentation method based on optimization mark and edge constraint watershed algorithm | |
CN113870299A (en) | 3D printing fault detection method based on edge detection and morphological image processing | |
Tomasila | Sand Soil Image Processing Using the Watershed Transform and Otsu Thresholding Based on Gaussian Noise | |
CN112784922A (en) | Extraction and classification method of intelligent cloud medical images | |
CN112785589A (en) | Method for acquiring digital medical abnormal image through cloud network | |
CN101789127A (en) | Method for extracting target from video image | |
CN112801963A (en) | Video image occlusion detection method and system | |
Yang et al. | Image processing and identification of lumber surface knots | |
Zhang | Highway Crack Material Detection Algorithm Based on Digital Image Processing Technology | |
CN114240988A (en) | Image segmentation method based on nonlinear scale space |
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 |