CN109741334A - A method of image segmentation is carried out by piecemeal threshold value - Google Patents
A method of image segmentation is carried out by piecemeal threshold value Download PDFInfo
- Publication number
- CN109741334A CN109741334A CN201811433315.XA CN201811433315A CN109741334A CN 109741334 A CN109741334 A CN 109741334A CN 201811433315 A CN201811433315 A CN 201811433315A CN 109741334 A CN109741334 A CN 109741334A
- Authority
- CN
- China
- Prior art keywords
- image
- image block
- segmentation
- threshold value
- block
- 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- Withdrawn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
Landscapes
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of method for carrying out image segmentation by piecemeal threshold value, comprising: by image segmentation to be processed at multiple images block；Gray scale difference between each image block threshold value and class is calculated using otsu method, is separated promising image block with the image block only having powerful connections using such gray scale difference；Otsu method is respectively adopted to each image block and carries out binaryzation；The image of the binaryzation is split.The present invention is used through image segmentation to be processed into multiple images block, then gray scale difference between each image block threshold value and class is calculated with otsu method, promising image block is separated with the image block only having powerful connections using such gray scale difference, later again to each image block be respectively adopted otsu method carry out binaryzation divide again, it is able to achieve the preferable segmentation to image, prevents illumination or reflective to influence caused by image segmentation.
Description
Technical field
The present invention relates to technical field of image segmentation, more particularly to a kind of side for carrying out image segmentation by piecemeal threshold value
Method.
Background technique
Image segmentation is exactly to divide the image into several regions specific, with unique properties and propose interesting target
Technology and process, be committed step of the image procossing to image analysis.When picture quality is fine, when illumination is well-proportioned
It only needs that image segmentation task can be ideally accomplished using the method for global threshold, but can sometimes encounter uneven illumination
Even phenomenon, such as shadow occlusion, local bloom, so as to cause relatively good segmentation effect cannot be reached.
As shown in Figs 1-4, wherein Fig. 1 and Fig. 3 is to do coin denominations identification shooting, it can be seen that due to coin surface
Reflective and polishing angle the reason of, there are serious uneven illumination phenomenons for picture.
If two images are directly carried out with the processing of otsu global thresholdization, available Fig. 2 and Fig. 4's as a result, can be with
See the poor effect of segmentation, for example the first width is then that left-hand component illumination is too strong, the coin segmentation effect on the left side is very poor.Second
The illumination of width, the upper right corner is eager to excel, and the coin in the upper right corner has centainly reflective, and gray value is integrally higher, causes most
Segmentation effect is very poor afterwards.
Summary of the invention
In view of the technical drawbacks of the prior art, it is an object of the present invention to provide a kind of coins for identification
The method for carrying out image segmentation by piecemeal threshold value.
The technical solution adopted to achieve the purpose of the present invention is:
A method of image segmentation is carried out by piecemeal threshold value, comprising the following steps:
S1, by image segmentation to be processed at multiple images block；
S2 calculates gray scale difference between each image block threshold value and class using otsu method, before having using such gray scale difference
The image block of scape is separated with the image block only having powerful connections；
S3 is respectively adopted otsu method to each image block and carries out binaryzation；
S4 is split the image of the binaryzation.
The illumination of the image block formed after segmentation is uniform.
The image block being divided to form is uniform.
The present invention is used through image segmentation to be processed into multiple images block, then calculates each image block threshold with otsu method
Gray scale difference between value and class, is separated promising image block with the image block only having powerful connections using such gray scale difference, later
Again to each image block be respectively adopted otsu method carry out binaryzation divide again, be able to achieve the preferable segmentation to image, prevent
Illumination is reflective to influence caused by image segmentation.
Detailed description of the invention
Fig. 1-2 show to be processed two image of shooting；
Fig. 3-4, which is shown, directly carries out the result after otsu global threshold segmentation to the two images of Fig. 1-2；
Fig. 5 is the image block schematic diagram of segmented image process of the present invention；
Fig. 6 is the effect picture after the image segmentation of the invention to Fig. 1；
Fig. 7 is the flow chart of image segmentation of the invention.
Specific embodiment
The present invention is described in further detail below in conjunction with the drawings and specific embodiments.It should be appreciated that described herein
Specific embodiment be only used to explain the present invention, be not intended to limit the present invention.
As illustrated in figs. 5-7, the method for the invention that image segmentation is carried out by piecemeal threshold value, comprising the following steps:
S1, by image segmentation to be processed at multiple images block；
S2 calculates gray scale difference between each image block threshold value and class using otsu method, before having using such gray scale difference
The image block of scape is separated with the image block only having powerful connections；
S3 is respectively adopted otsu method to each image block and carries out binaryzation；
S4 is split the image of binaryzation.
By dividing the image into several image blocks, Threshold segmentation is carried out respectively, can solve illumination to a certain extent
Or it is unevenly influenced caused by reflection.The image block of selection wants sufficiently small, so as to the illumination of each image block be it is uniform, this
It when sample automatic threshold, will be divided with high threshold in high gray areas, will be divided with Low threshold in low gray level areas.
Fig. 5 is the piecemeal of image to be processed as a result, the piecemeal in example is suitable with coin-size, and having divided piece later can be by
Block carries out Global thresholding otsu method and handles.
However, it is noted that only having powerful connections in some image blocks in the formed image block of segmentation, needing to carry out at this time
Judgement excludes the processing for the image block having powerful connections to this.
After the dissociable basis for calculating each image block, discovery differentiation effect is not fine, passes through and analyzes maximum kind
Between variance method, average gray difference judges the separability of image block between the class at discovery segmentation threshold, and better area may be implemented
Other effect.I.e. when only having powerful connections in image or when only object, relatively due to their gray values, then calculated with otsu method
" background " and " prospect " average gray poor (gray scale difference between class) meeting very little, on the contrary can be very big, by comparing, it can be achieved that fine area
Divide each image block.Wherein, the mathematic(al) representation of average gray difference is as follows between class:
Δ μ=| μ1(k)-μ2(k)|
If the gray value of image is 0~m-1 grades, usual image gray levels are 0 to 255, and the pixel number of gray value i is ni,
Sum of all pixels at this time:
Then two groups of C are divided into threshold value T1={ 0~T-1 }, C2={ T~m-1 }, the probability of each group are as follows:
ThereforeBe threshold value be k when background image average gray value,It is
Target image average gray value.
In Fig. 5, shown in the text of the mark of each image block, T is segmentation threshold, and d average gray between class is poor, it can be seen that
When only having powerful connections in each image block block, average gray difference with have object phase difference very big, selected characteristic distinguish effect it is fine.
In this example, select gray scale difference 20 that can distinguish well two different pieces.
The above is only a preferred embodiment of the present invention, it is noted that for the common skill of the art
For art personnel, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. a kind of method for carrying out image segmentation by piecemeal threshold value, which comprises the following steps:
S1, by image segmentation to be processed at multiple images block；
S2 calculates gray scale difference between each image block threshold value and class using otsu method, will be promising using such gray scale difference
Image block is separated with the image block only having powerful connections；
S3 is respectively adopted otsu method to each image block and carries out binaryzation；
S4 is split the image of the binaryzation.
2. the method for carrying out image segmentation by piecemeal threshold value as described in claim 1, which is characterized in that formed after segmentation
The illumination of the image block is uniform.
3. the method for carrying out image segmentation by piecemeal threshold value as described in claim 1, which is characterized in that be divided to form
The image block is uniform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433315.XA CN109741334A (en) | 2018-11-28 | 2018-11-28 | A method of image segmentation is carried out by piecemeal threshold value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433315.XA CN109741334A (en) | 2018-11-28 | 2018-11-28 | A method of image segmentation is carried out by piecemeal threshold value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109741334A true CN109741334A (en) | 2019-05-10 |
Family
ID=66358199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811433315.XA Withdrawn CN109741334A (en) | 2018-11-28 | 2018-11-28 | A method of image segmentation is carried out by piecemeal threshold value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741334A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400319A (en) * | 2019-07-16 | 2019-11-01 | 东华大学 | A kind of spinning cake greasy dirt partitioning algorithm based on domain division method |
| CN110473194A (en) * | 2019-08-12 | 2019-11-19 | 西南大学 | Fruit surface defect detection method based on more image block Threshold Segmentation Algorithms |
| CN110570445A (en) * | 2019-09-09 | 2019-12-13 | 上海联影医疗科技有限公司 | Image segmentation method, device, terminal and readable medium |
| CN112037161A (en) * | 2019-05-17 | 2020-12-04 | 上海贝特威自动化科技有限公司 | Gluing analysis method based on area automatic threshold analysis |
| CN112435232A (en) * | 2020-11-23 | 2021-03-02 | 南京信息工程大学 | Defect detection method based on haar wavelet combined image variance |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156868A (en) * | 2011-03-31 | 2011-08-17 | 汉王科技股份有限公司 | Image binaryzation method and device |
| CN102509077A (en) * | 2011-10-28 | 2012-06-20 | 江苏物联网研究发展中心 | Target identification method based on automatic illumination evaluation |
| CN106157323A (en) * | 2016-08-30 | 2016-11-23 | 西安工程大学 | The insulator division and extracting method that a kind of dynamic division threshold value and block search combine |
| CN106991753A (en) * | 2017-04-07 | 2017-07-28 | 深圳怡化电脑股份有限公司 | A kind of image binaryzation method and device |
| CN107610144A (en) * | 2017-07-21 | 2018-01-19 | 哈尔滨工程大学 | A kind of improved IR image segmentation method based on maximum variance between clusters |
| CN107945200A (en) * | 2017-12-14 | 2018-04-20 | 中南大学 | Image binaryzation dividing method |
-
2018
- 2018-11-28 CN CN201811433315.XA patent/CN109741334A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156868A (en) * | 2011-03-31 | 2011-08-17 | 汉王科技股份有限公司 | Image binaryzation method and device |
| CN102509077A (en) * | 2011-10-28 | 2012-06-20 | 江苏物联网研究发展中心 | Target identification method based on automatic illumination evaluation |
| CN106157323A (en) * | 2016-08-30 | 2016-11-23 | 西安工程大学 | The insulator division and extracting method that a kind of dynamic division threshold value and block search combine |
| CN106991753A (en) * | 2017-04-07 | 2017-07-28 | 深圳怡化电脑股份有限公司 | A kind of image binaryzation method and device |
| CN107610144A (en) * | 2017-07-21 | 2018-01-19 | 哈尔滨工程大学 | A kind of improved IR image segmentation method based on maximum variance between clusters |
| CN107945200A (en) * | 2017-12-14 | 2018-04-20 | 中南大学 | Image binaryzation dividing method |
Non-Patent Citations (1)
| Title |
|---|
| WIKIWEN: "光照不均匀图像分割技巧1——分块阈值", 《HTTP://BLOG.CSDN.NET/KK55GUANG2/ARTICLE/DETAILS/78475414》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037161A (en) * | 2019-05-17 | 2020-12-04 | 上海贝特威自动化科技有限公司 | Gluing analysis method based on area automatic threshold analysis |
| CN110400319A (en) * | 2019-07-16 | 2019-11-01 | 东华大学 | A kind of spinning cake greasy dirt partitioning algorithm based on domain division method |
| CN110473194A (en) * | 2019-08-12 | 2019-11-19 | 西南大学 | Fruit surface defect detection method based on more image block Threshold Segmentation Algorithms |
| CN110570445A (en) * | 2019-09-09 | 2019-12-13 | 上海联影医疗科技有限公司 | Image segmentation method, device, terminal and readable medium |
| CN110570445B (en) * | 2019-09-09 | 2022-03-25 | 上海联影医疗科技股份有限公司 | Image segmentation method, device, terminal and readable medium |
| CN112435232A (en) * | 2020-11-23 | 2021-03-02 | 南京信息工程大学 | Defect detection method based on haar wavelet combined image variance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741334A (en) | A method of image segmentation is carried out by piecemeal threshold value | |
| CN105160355B (en) | A kind of method for detecting change of remote sensing image based on region correlation and vision word | |
| US20070110309A1 (en) | Shadow detection in images | |
| CN105279772B (en) | A kind of trackability method of discrimination of infrared sequence image | |
| CN109242870A (en) | A kind of sea horizon detection method divided based on image with textural characteristics | |
| CN101170641A (en) | A method for image edge detection based on threshold sectioning | |
| CN105261021B (en) | Remove the method and device of foreground detection result shade | |
| US8983199B2 (en) | Apparatus and method for generating image feature data | |
| CN106127735B (en) | A kind of facilities vegetable edge clear class blade face scab dividing method and device | |
| CN105404868B (en) | The rapid detection method of text in a kind of complex background based on interaction platform | |
| CN111369570A (en) | Multi-target detection tracking method for video image | |
| CN109472770A (en) | A kind of image characteristic point Fast Match Algorithm in printed circuit board (PCB) detecting | |
| CN115131359A (en) | Method for detecting pitting defects on surface of metal workpiece | |
| Abdusalomov et al. | An improvement for the foreground recognition method using shadow removal technique for indoor environments | |
| CN109785356A (en) | A kind of background modeling method of video image | |
| CN108230334B (en) | High-concentration wind-blown sand image segmentation method based on gray threshold | |
| CN108717699B (en) | Ultrasonic image segmentation method based on continuous minimum segmentation | |
| Kim et al. | Object Modeling with Color Arrangement for Region‐Based Tracking | |
| US20020048402A1 (en) | Segmentation of digital images | |
| CN106446832B (en) | Video-based pedestrian real-time detection method | |
| CN108711139A (en) | One kind being based on defogging AI image analysis systems and quick response access control method | |
| CN115984863B (en) | Image processing method, device, equipment and storage medium | |
| CN105761237B (en) | Chip x-ray image Hierarchical Segmentation based on mean shift | |
| CN110276260B (en) | Commodity detection method based on depth camera | |
| Chandrakala et al. | Threshold based segmentation using block 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190510 |