CN107169979A - A kind of method for detecting image edge of improvement Canny operators - Google Patents
A kind of method for detecting image edge of improvement Canny operators Download PDFInfo
- Publication number
- CN107169979A CN107169979A CN201710328101.5A CN201710328101A CN107169979A CN 107169979 A CN107169979 A CN 107169979A CN 201710328101 A CN201710328101 A CN 201710328101A CN 107169979 A CN107169979 A CN 107169979A
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- threshold value
- gradient
- detecting
- 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.)
- Withdrawn
Links
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
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method for detecting image edge of improvement Canny operators, comprise the following steps：S1：Image is smoothed, noise is suppressed with Gaussian filter；S2：Image gradient amplitude and direction after calculating smoothly；S3：Non-maxima suppression is carried out to gradient；S4：Optimal high-low threshold value is sought with iterative algorithm；S5：Edge is detected and connected with dual threashold value-based algorithm；S6：Edge is refined with Mathematical Morphology method.The present invention can effectively suppress noise, obtain optimal segmenting threshold, it is adaptable to the detection of medical cell image.
Description
Technical field
Present invention relates particularly to a kind of method for detecting image edge of improvement Canny operators.
Background technology
With the development of computer vision and digital image processing techniques, edge detecting technology is increasingly being applied to respectively
In individual field, the effect of performance is also increasing.Cell is the base unit of vital movement, all biologies in addition to virus
Constituted by cell.The edge of cell image has the spies such as area, circularity and the number of object boundary information, especially cell
Levy, morphological analysis and later condition-inference of its testing result for cell provide important evidence.
Traditional edge detection operator is the change of gray value in each neighborhood of pixels according to image, using mathematical method
In single order or the change of Second order directional detect edge.These Operator structures are simple, realize speed, but to making an uproar
Sound shadow rings larger, will cell image edge is discontinuous, interference edge occur if be applied in cell image rim detection
The shortcomings of edge or cell image loss in detail.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of method for detecting image edge of improvement Canny operators.
A kind of method for detecting image edge of improvement Canny operators, comprises the following steps：
S1：Image is smoothed, noise is suppressed with Gaussian filter；
S2：Image gradient amplitude and direction after calculating smoothly；
S3：Non-maxima suppression is carried out to gradient；
S4：Optimal high-low threshold value is sought with iterative algorithm；
S5：Edge is detected and connected with dual threashold value-based algorithm；
S6：Edge is refined with Mathematical Morphology method.
Further, step S1 specific method is as follows：
From one-dimensional Gaussian functionWave filter is constructed, respectively in rows and columns to original imageConvolution operation is carried out, is obtained
To smoothed image：
,
,
Wherein,It is the standard deviation of Gaussian function.
Further, step S2 specific method is as follows：
UsingImage after the finite difference formulations of neighborhood single order local derviation are smoothGradient magnitudeAnd gradient
Direction：
,
,
,；
Wherein,WithIt is original image respectivelyBy wave filterWithAlong the result of row and column or so.
Further, step S4 specific method is as follows：
1）Initial threshold is obtained by counting grey level histogram：
；
；
Wherein, K is iterations；、It is minimum and maximum gray value in image respectively；
2）Use threshold valueSegment the image into two partsWith, wherein：
；
；
3）Calculate respectivelyWithGray averageWith, wherein：
,；
F (i, j) is image（i,j）Point gray value；、Meet respectively：
；
；
4）Calculate new threshold value：
；
5）IfOr the requirement that satisfaction is specified then terminates, otherwise K=K+1, goes to step 2）；
6）Iteration terminates, and takes finalWithThe optimal high and low threshold value split as image.
The beneficial effects of the invention are as follows：
The present invention can effectively suppress noise, obtain optimal segmenting threshold, it is adaptable to the detection of medical cell image.
Embodiment
The present invention is further elaborated for specific examples below, but not as a limitation of the invention.
A kind of method for detecting image edge of improvement Canny operators, comprises the following steps：
S1：Image is smoothed, noise is suppressed with Gaussian filter；
S2：Image gradient amplitude and direction after calculating smoothly；
S3：Non-maxima suppression is carried out to gradient；
S4：Optimal high-low threshold value is sought with iterative algorithm；
S5：Edge is detected and connected with dual threashold value-based algorithm；
S6：Edge is refined with Mathematical Morphology method.
Step S1 specific method is as follows：
From one-dimensional Gaussian functionWave filter is constructed, respectively in rows and columns to original imageConvolution operation is carried out, is obtained
To smoothed image：
,
,
Wherein,It is the standard deviation of Gaussian function.
Step S2 specific method is as follows：
UsingImage after the finite difference formulations of neighborhood single order local derviation are smoothGradient magnitudeAnd gradient
Direction：
,
,
,；
Wherein,WithIt is original image respectivelyBy wave filterWithAlong the result of row and column or so.
Step S4 specific method is as follows：
1）Initial threshold is obtained by counting grey level histogram：
；
；
Wherein, K is iterations；、It is minimum and maximum gray value in image respectively；
2）Use threshold valueSegment the image into two partsWith, wherein：
；
；
3）Calculate respectivelyWithGray averageWith, wherein：
,；
F (i, j) is image（i,j）Point gray value；、Meet respectively：
；
；
4）Calculate new threshold value：
；
5）IfOr the requirement that satisfaction is specified then terminates, otherwise K=K+1, goes to step 2）；
6）Iteration terminates, and takes finalWithThe optimal high and low threshold value split as image.
Claims (4)
1. a kind of method for detecting image edge of improvement Canny operators, it is characterised in that comprise the following steps：
S1：Image is smoothed, noise is suppressed with Gaussian filter；
S2：Image gradient amplitude and direction after calculating smoothly；
S3：Non-maxima suppression is carried out to gradient；
S4：Optimal high-low threshold value is sought with iterative algorithm；
S5：Edge is detected and connected with dual threashold value-based algorithm；
S6：Edge is refined with Mathematical Morphology method.
2. method for detecting image edge according to claim 1, it is characterised in that step S1 specific method is as follows：
From one-dimensional Gaussian functionWave filter is constructed, respectively in rows and columns to original imageConvolution operation is carried out, is obtained
To smoothed image：
,
,
Wherein,It is the standard deviation of Gaussian function.
3. method for detecting image edge according to claim 1, it is characterised in that step S2 specific method is as follows：
UsingImage after the finite difference formulations of neighborhood single order local derviation are smoothGradient magnitudeWith gradient side
To：
,
,
,；
Wherein,WithIt is original image respectivelyBy wave filterWithAlong the result of row and column or so.
4. method for detecting image edge according to claim 1, it is characterised in that step S4 specific method is as follows：
1）Initial threshold is obtained by counting grey level histogram：
；
；
Wherein, K is iterations；、It is minimum and maximum gray value in image respectively；
2）Use threshold valueSegment the image into two partsWith, wherein：
；
；
3）Calculate respectivelyWithGray averageWith, wherein：
,；
F (i, j) is image（i,j）Point gray value；、Meet respectively：
；
；
4）Calculate new threshold value：
；
5）IfOr the requirement that satisfaction is specified then terminates, otherwise K=K+1, goes to step 2）；
6）Iteration terminates, and takes finalWithThe optimal high and low threshold value split as image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328101.5A CN107169979A (en) | 2017-05-11 | 2017-05-11 | A kind of method for detecting image edge of improvement Canny operators |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328101.5A CN107169979A (en) | 2017-05-11 | 2017-05-11 | A kind of method for detecting image edge of improvement Canny operators |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107169979A true CN107169979A (en) | 2017-09-15 |
Family
ID=59814953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710328101.5A Withdrawn CN107169979A (en) | 2017-05-11 | 2017-05-11 | A kind of method for detecting image edge of improvement Canny operators |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169979A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108109208A (en) * | 2017-12-01 | 2018-06-01 | 同济大学 | A kind of marine wind electric field augmented reality method |
| CN108280838A (en) * | 2018-01-31 | 2018-07-13 | 桂林电子科技大学 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
| CN108489469A (en) * | 2018-03-20 | 2018-09-04 | 重庆交通大学 | A kind of monocular distance measuring device and method |
| CN108596844A (en) * | 2018-04-12 | 2018-09-28 | 中国人民解放军陆军装甲兵学院 | Background suppression method for playing big gun Remote Control Weapon Station |
| CN108717069A (en) * | 2018-05-29 | 2018-10-30 | 电子科技大学 | A kind of high-pressure bottle thermal imaging imperfection detection method based on the segmentation of row variable step |
| CN109146905A (en) * | 2018-08-30 | 2019-01-04 | 南京理工大学 | For the CANNY operator edge detection algorithm of low-light level environment |
| CN109409190A (en) * | 2018-08-21 | 2019-03-01 | 南京理工大学 | Pedestrian detection method based on histogram of gradients and Canny edge detector |
| CN109658429A (en) * | 2018-12-21 | 2019-04-19 | 电子科技大学 | A kind of infrared image cirrus detection method based on boundary fractal dimension |
| CN109919929A (en) * | 2019-03-06 | 2019-06-21 | 电子科技大学 | A kind of fissuring of tongue feature extracting method based on wavelet transformation |
| CN110428433A (en) * | 2019-07-02 | 2019-11-08 | 西华师范大学 | A kind of Canny edge detection algorithm based on local threshold |
| CN110689016A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
| CN110782437A (en) * | 2019-10-18 | 2020-02-11 | 国网电力科学研究院武汉南瑞有限责任公司 | Improved PCNN power failure image space positioning method based on boundary characteristics |
| CN112819739A (en) * | 2021-01-28 | 2021-05-18 | 浙江祺跃科技有限公司 | Scanning electron microscope image processing method and system |
| CN113256551A (en) * | 2021-01-21 | 2021-08-13 | 中国煤炭科工集团太原研究院有限公司 | Roadway roof rigid belt drilling identification and positioning system and method based on machine vision |
| CN117876361A (en) * | 2024-03-11 | 2024-04-12 | 烟台海上航天科技有限公司 | Image processing method and system for high-risk operation of gas pipeline |
-
2017
- 2017-05-11 CN CN201710328101.5A patent/CN107169979A/en not_active Withdrawn
Non-Patent Citations (1)
| Title |
|---|
| 王小俊 等: ""基于改进Canny算子的图像边缘检测算法"", 《计算机工程》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108109208A (en) * | 2017-12-01 | 2018-06-01 | 同济大学 | A kind of marine wind electric field augmented reality method |
| CN108109208B (en) * | 2017-12-01 | 2022-02-08 | 同济大学 | Augmented reality method for offshore wind farm |
| CN108280838A (en) * | 2018-01-31 | 2018-07-13 | 桂林电子科技大学 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
| CN108489469A (en) * | 2018-03-20 | 2018-09-04 | 重庆交通大学 | A kind of monocular distance measuring device and method |
| CN108596844A (en) * | 2018-04-12 | 2018-09-28 | 中国人民解放军陆军装甲兵学院 | Background suppression method for playing big gun Remote Control Weapon Station |
| CN108717069A (en) * | 2018-05-29 | 2018-10-30 | 电子科技大学 | A kind of high-pressure bottle thermal imaging imperfection detection method based on the segmentation of row variable step |
| CN108717069B (en) * | 2018-05-29 | 2020-08-11 | 电子科技大学 | High-pressure container thermal imaging defect detection method based on line variable step length segmentation |
| CN110689016A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
| CN110689016B (en) * | 2018-07-05 | 2023-04-18 | 山东华软金盾软件股份有限公司 | License plate image coarse positioning method |
| CN109409190A (en) * | 2018-08-21 | 2019-03-01 | 南京理工大学 | Pedestrian detection method based on histogram of gradients and Canny edge detector |
| CN109146905A (en) * | 2018-08-30 | 2019-01-04 | 南京理工大学 | For the CANNY operator edge detection algorithm of low-light level environment |
| CN109658429A (en) * | 2018-12-21 | 2019-04-19 | 电子科技大学 | A kind of infrared image cirrus detection method based on boundary fractal dimension |
| CN109919929A (en) * | 2019-03-06 | 2019-06-21 | 电子科技大学 | A kind of fissuring of tongue feature extracting method based on wavelet transformation |
| CN110428433A (en) * | 2019-07-02 | 2019-11-08 | 西华师范大学 | A kind of Canny edge detection algorithm based on local threshold |
| CN110428433B (en) * | 2019-07-02 | 2023-05-09 | 西华师范大学 | Canny edge detection algorithm based on local threshold |
| CN110782437A (en) * | 2019-10-18 | 2020-02-11 | 国网电力科学研究院武汉南瑞有限责任公司 | Improved PCNN power failure image space positioning method based on boundary characteristics |
| CN110782437B (en) * | 2019-10-18 | 2022-05-06 | 国网电力科学研究院武汉南瑞有限责任公司 | Improved PCNN power failure image space positioning method based on boundary characteristics |
| CN113256551A (en) * | 2021-01-21 | 2021-08-13 | 中国煤炭科工集团太原研究院有限公司 | Roadway roof rigid belt drilling identification and positioning system and method based on machine vision |
| CN113256551B (en) * | 2021-01-21 | 2023-03-14 | 中国煤炭科工集团太原研究院有限公司 | Roadway roof rigid belt drilling identification and positioning system and method based on machine vision |
| CN112819739A (en) * | 2021-01-28 | 2021-05-18 | 浙江祺跃科技有限公司 | Scanning electron microscope image processing method and system |
| CN112819739B (en) * | 2021-01-28 | 2024-03-01 | 浙江祺跃科技有限公司 | Image processing method and system for scanning electron microscope |
| CN117876361A (en) * | 2024-03-11 | 2024-04-12 | 烟台海上航天科技有限公司 | Image processing method and system for high-risk operation of gas pipeline |
| CN117876361B (en) * | 2024-03-11 | 2024-05-10 | 烟台海上航天科技有限公司 | Image processing method and system for high-risk operation of gas pipeline |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169979A (en) | A kind of method for detecting image edge of improvement Canny operators | |
| CN110428433B (en) | Canny edge detection algorithm based on local threshold | |
| CN102156996B (en) | Image edge detection method | |
| Li et al. | Modified directional weighted filter for removal of salt & pepper noise | |
| CN107067382A (en) | A kind of improved method for detecting image edge | |
| Zhang et al. | Method of famous tea sprout identification and segmentation based on improved watershed algorithm | |
| CN111833366A (en) | Edge detection method based on Canny algorithm | |
| CN105590319A (en) | Method for detecting image saliency region for deep learning | |
| CN114399522A (en) | High-low threshold-based Canny operator edge detection method | |
| CN104036521A (en) | Novel retina eye fundus image segmenting method | |
| CN109003233B (en) | Image denoising method based on self-adaptive weight total variation model | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| Xu et al. | Edge detection algorithm of medical image based on Canny operator | |
| Li et al. | A salt & pepper noise filter based on local and global image information | |
| WO2023078285A1 (en) | Moire pattern removal method and apparatus for text image, and electronic device | |
| CN106023160B (en) | Blast furnace charge level method for detecting image edge and device | |
| CN110909631A (en) | Finger vein image ROI extraction and enhancement method | |
| CN105225243B (en) | One kind can antimierophonic method for detecting image edge | |
| CN111489389A (en) | Light spot center detection method | |
| CN104408432B (en) | Infrared image target detection method based on histogram modification | |
| CN105930811A (en) | Palm texture feature detection method based on image processing | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| US8693769B2 (en) | Image classification methods and systems | |
| CN110929574A (en) | Infrared weak and small target rapid detection method | |
| CN106780529B (en) | Conference video mosaic detection method based on external rectangle |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170915 |
|
| WW01 | Invention patent application withdrawn after publication |