CN108122241A - A kind of binary conversion treatment device and method of image - Google Patents
A kind of binary conversion treatment device and method of image Download PDFInfo
- Publication number
- CN108122241A CN108122241A CN201611069862.5A CN201611069862A CN108122241A CN 108122241 A CN108122241 A CN 108122241A CN 201611069862 A CN201611069862 A CN 201611069862A CN 108122241 A CN108122241 A CN 108122241A
- Authority
- CN
- China
- Prior art keywords
- image
- gray level
- conversion treatment
- point cloud
- under different
- 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
Abstract
The invention discloses a kind of binary conversion treatment device and methods of image.This method includes:Shoot gray level image of at least two same objects under different illumination conditions;By greyscale image transitions into three-dimensional compound point cloud chart picture;Whether judge the characteristic boundary of three-dimensional compound point cloud chart picture and object can form the curved surface of Threshold segmentation;When the result judged is is, foundation of the curved surface as binarization segmentation is preserved.Through the above way, therefore, the present invention be capable of quick visualization to gray level image carry out binary conversion treatment, and it can be inferred which situation is not suitable for the binary conversion treatment of image, scheme is simple, effect of visualization is extremely strong, improves the correctness and stability of method, shortens exploitation and the debugging cycle of Digital Image Processing.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of binary conversion treatment device and method of image.
Background technology
In Digital Image Processing, binary conversion treatment occupies very important status.Briefly, at the binaryzation of image
Reason is exactly that the gray scale of the point on image is set to 0 or 255, i.e., the gray level image of 256 brightness degrees is passed through appropriate threshold value
It chooses, still can reflect the whole binary image with local feature of image so as to obtain.
Preferable binary image in order to obtain, the region that the general boundary definition using closing, connection does not overlap.It is all
The pixel that gray scale is greater than or equal to threshold value is judged as belonging to certain objects, and gray value is represented with 255, otherwise these pixels
It is excluded beyond object area, gray value 0, represents the object area of background or exception.If including certain certain objects
There is uniform gray value in portion, and it is in a homogeneous background with other level gray values, uses threshold method
It can be obtained by more satisfactory segmentation effect.
However, traditional Binarization methods are suitable only for still image, and it is more sensitive to illumination condition variation, in reality
It is subject to many limitations in engineer application.
The content of the invention
The invention mainly solves the technical problem of providing a kind of binary conversion treatment device and methods of image, can be quick
Binary conversion treatment visually is carried out to gray level image, and can be inferred which situation is not suitable for the binary conversion treatment of image,
Scheme is simple, and effect of visualization is extremely strong, improves the correctness and stability of method, shorten Digital Image Processing exploitation and
Debugging cycle.
In order to solve the above technical problems, one aspect of the present invention is:It provides at a kind of binaryzation of image
Reason method, this method include:Shoot gray level image of at least two same objects under different illumination conditions;By the gray-scale map
As being converted into three-dimensional compound point cloud chart picture;Judge that the characteristic boundary of the compound point cloud chart picture of the three-dimensional and the object whether can
Form the curved surface of Threshold segmentation;When the result judged is is, foundation of the curved surface as binarization segmentation is preserved.
Wherein, this method further includes:
The result judged as it is no when, judge under the illumination condition be not suitable for carry out image binary conversion treatment.
Wherein, the step of shooting gray level image of at least two same objects under different illumination conditions includes:
Gray level image of at least two same objects under different illumination conditions is shot from same angle and distance.
Wherein, from same angle and distance shooting gray level image of at least two same objects under different illumination conditions
Step includes:
Gray scale of at least two same objects under different illumination conditions under different time is shot from same angle and distance
Image.
Wherein, by the greyscale image transitions into three-dimensional compound point cloud chart as the step of include:
The gray level image is spliced to form three-dimensional compound point cloud chart picture, and the compound point cloud chart picture of the three-dimensional is visualized
Show.
In order to solve the above technical problems, another technical solution used in the present invention is:A kind of binaryzation of image is provided
Processing unit, the device include:
Taking module, for shooting gray level image of at least two same objects under different illumination conditions;
Form module, for by the greyscale image transitions into three-dimensional compound point cloud chart picture;
Whether judgment module, the characteristic boundary for judging the compound point cloud chart picture of the three-dimensional and the object can form
The curved surface of Threshold segmentation;
Control module and memory module, the control module control institute when the result that the judgment module judges is is
It states memory module and preserves foundation of the curved surface as binarization segmentation.
Wherein, control module the result that the judgment module judges as it is no when, judge under the illumination condition uncomfortable
Close the binary conversion treatment for carrying out image.
Wherein, taking module is specially to shoot at least two same objects in different illumination conditions from same angle and distance
Under gray level image.
Wherein, taking module be specially from same angle and distance shoot at least two same objects under different time not
With the gray level image under the conditions of illumination.
Wherein, it is specially that the gray level image is spliced to form three-dimensional compound point cloud chart picture to form module;
The binary conversion treatment device further includes:
Display module, for the compound point cloud chart picture of the three-dimensional visually to be shown.
The beneficial effects of the invention are as follows:The situation of the prior art is different from, the present invention is provided at a kind of binaryzation of image
Device and method is managed, this method comprises the following steps:Ash of at least two same objects under different illumination conditions is shot first
Spend image, then by greyscale image transitions into three-dimensional compound point cloud chart picture, and then judge three-dimensional compound point cloud chart as and object
Whether characteristic boundary can form the curved surface of Threshold segmentation, and when the result judged is is, preserve curved surface as binaryzation point
The foundation cut.Therefore, what the present invention was capable of quick visualization carries out binary conversion treatment to gray level image, and which can be inferred that
Situation is not suitable for the binary conversion treatment of image, and scheme is simple, and effect of visualization is extremely strong, improves the correctness and stabilization of method
Property shortens exploitation and the debugging cycle of Digital Image Processing.
Description of the drawings
Fig. 1 is a kind of flow chart of the binary processing method of image provided in an embodiment of the present invention;
Fig. 2 is a kind of structure diagram of the binary conversion treatment device of image provided in an embodiment of the present invention.
Specific embodiment
Referring to Fig. 1, Fig. 1 is a kind of flow chart of the binary processing method of image provided in an embodiment of the present invention.Such as
Shown in Fig. 1, the method for the present embodiment comprises the following steps:
Step S1:Shoot gray level image of at least two same objects under different illumination conditions.Wherein, the gray level image
For 2-D gray image.
Specifically, shoot gray-scale map of at least two same objects under different illumination conditions from same angle and distance
Picture.More specifically, at least two same objects are shot under different illumination conditions under different time from same angle and distance
Gray level image.Wherein, same angle and distance refers respectively to capture apparatus, such as the angle and distance between video camera and object.
In other embodiments, can also be directly by manually producing different illumination conditions, such as people can be passed through
Work simulates the illumination condition in morning, noon and these three periods in the afternoon, then in same specific position, same specific angle
Degree shoots gray level image of the same object under different illumination conditions.The method for manually producing different illumination conditions is not required to
The different time that the natural law is waited to be formed, can save the time, improve efficiency.
In this step, the quantity of the image preferably shot by camera for three and more than, it is subsequent three-dimensional multiple to facilitate
The formation of chalaza cloud atlas picture and the curved surface for forming more accurately Threshold segmentation, to improve the accuracy of image procossing.
Step S2:By greyscale image transitions into three-dimensional compound point cloud chart picture.2-D gray image is converted into three-dimensional multiple
Chalaza cloud atlas picture.
This step is specifically that gray level image is spliced to form three-dimensional compound point cloud chart picture, and can by three-dimensional compound point cloud chart picture
Depending on showing for change.
Step S3:Whether judge the characteristic boundary of three-dimensional compound point cloud chart picture and object can form the song of Threshold segmentation
Face.In this step, if the result judged is yes, step S4 is jumped to, if the result judged is no, jumps to step
S5。
Step S4:Preserve foundation of the curved surface as binarization segmentation.
Step S5:Judge to be not suitable for the binary conversion treatment for carrying out image under the illumination condition.
Therefore, what the present invention was capable of quick visualization carries out binary conversion treatment to gray level image, and which can be inferred that
Situation is not suitable for the binary conversion treatment of image, and scheme is simple, and effect of visualization is extremely strong, improves the correctness and stabilization of method
Property shortens exploitation and the debugging cycle of Digital Image Processing.
The present invention also provides a kind of binary conversion treatment device of image, which is applied in previously described method,
Referring specifically to Fig. 2.
As shown in Fig. 2, the device 20 of the present embodiment includes taking module 21, forms module 22, memory module 23, judges mould
Block 24, control module 25 and display module 26.
Wherein, taking module 21 is for shooting gray level image of at least two same objects under different illumination conditions.Tool
Body, shoot gray level image of at least two same objects under different illumination conditions from same angle and distance.More specifically,
Gray level image of at least two same objects under different illumination conditions under different time is shot from same angle and distance.
In other embodiments, can also be directly by manually producing different illumination conditions, such as people can be passed through
Work simulates the illumination condition in morning, noon and these three periods in the afternoon, then in same specific position, same specific angle
Gray level image of the degree shooting object under different illumination conditions.Manually producing the method for different illumination conditions need not wait
It treats the different time that the natural law is formed, the time can be saved, improve efficiency.
In the present embodiment, the quantity of the image preferably shot for three and more than, to facilitate subsequent three-dimensional spot cloud
The formation of image and the curved surface for forming more accurately Threshold segmentation, to improve the accuracy of image procossing.
Module 22 is formed to be used for greyscale image transitions into three-dimensional compound point cloud chart picture.Specifically, for gray level image is spelled
It connects to form three-dimensional compound point cloud chart picture.Further, three-dimensional compound point cloud chart picture is visually shown by display module 26
Out.
Judgment module 24 is used to judge whether the characteristic boundary of three-dimensional compound point cloud chart picture and object can form threshold value point
The curved surface cut.
Control module 25 is used for when the result that judgment module 24 judges is is, control memory module 23 preserves curved surface conduct
The foundation of binarization segmentation, the result that judgment module 24 judges as it is no when, judge under those illumination conditions be not suitable for progress
The binary conversion treatment of image.
Therefore, what the present invention was capable of quick visualization carries out binary conversion treatment to gray level image, and which can be inferred that
Situation is not suitable for the binary conversion treatment of image, and scheme is simple, and effect of visualization is extremely strong, improves the correctness and stabilization of method
Property shortens exploitation and the debugging cycle of Digital Image Processing.
The foregoing is merely the embodiment of the present invention, are not intended to limit the scope of the invention, every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made directly or indirectly is used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of binary processing method of image, which is characterized in that the described method includes:
Shoot gray level image of at least two same objects under different illumination conditions;
By the greyscale image transitions into three-dimensional compound point cloud chart picture;
Whether judge the characteristic boundary of the compound point cloud chart picture of the three-dimensional and the object can form the curved surface of Threshold segmentation;
When the result judged is is, foundation of the curved surface as binarization segmentation is preserved.
2. binary processing method according to claim 1, which is characterized in that the method further includes:
The result judged as it is no when, judge under the illumination condition be not suitable for carry out image binary conversion treatment.
3. binary processing method according to claim 1, which is characterized in that shooting at least two same objects exist
The step of gray level image under different illumination conditions, includes:
Gray level image of at least two same objects under different illumination conditions is shot from same angle and distance.
4. binary processing method according to claim 3, which is characterized in that it is described from same angle and distance shoot to
The step of lacking gray level image of two same objects under different illumination conditions includes:
Gray level image of at least two same objects under different illumination conditions under different time is shot from same angle and distance.
5. binary processing method according to claim 1, which is characterized in that it is described by the greyscale image transitions into three
Tie up compound point cloud chart as the step of include:
The gray level image is spliced to form three-dimensional compound point cloud chart picture, and the compound point cloud chart picture of the three-dimensional is visually shown
It shows to come.
6. the binary conversion treatment device of a kind of image, which is characterized in that described device includes:
Taking module, for shooting gray level image of at least two same objects under different illumination conditions;
Form module, for by the greyscale image transitions into three-dimensional compound point cloud chart picture;
Whether judgment module, the characteristic boundary for judging the compound point cloud chart picture of the three-dimensional and the object can form threshold value
The curved surface of segmentation;
Control module and memory module, the control module are deposited when the result that the judgment module judges is is described in control
It stores up module and preserves foundation of the curved surface as binarization segmentation.
7. binary conversion treatment device according to claim 6, which is characterized in that the control module is in the judgment module
The result judged as it is no when, judge under the illumination condition be not suitable for carry out image binary conversion treatment.
8. binary conversion treatment device according to claim 6, which is characterized in that the taking module is specially from same angle
It spends and apart from shooting gray level image of at least two same objects under different illumination conditions.
9. binary conversion treatment device according to claim 7, which is characterized in that the taking module is specially from same angle
It spends and apart from shooting gray level image of at least two same objects under different illumination conditions under different time.
10. binary conversion treatment device according to claim 6, which is characterized in that the formation module is specially by described in
Gray level image is spliced to form three-dimensional compound point cloud chart picture;
The binary conversion treatment device further includes:
Display module, for the compound point cloud chart picture of the three-dimensional visually to be shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611069862.5A CN108122241B (en) | 2016-11-29 | 2016-11-29 | Image binarization processing device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611069862.5A CN108122241B (en) | 2016-11-29 | 2016-11-29 | Image binarization processing device and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108122241A true CN108122241A (en) | 2018-06-05 |
CN108122241B CN108122241B (en) | 2021-10-15 |
Family
ID=62224444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611069862.5A Active CN108122241B (en) | 2016-11-29 | 2016-11-29 | Image binarization processing device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108122241B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739559A (en) * | 2008-11-18 | 2010-06-16 | 哈尔滨理工大学 | Threshold zone-based image binarization method |
US8542252B2 (en) * | 2009-05-29 | 2013-09-24 | Microsoft Corporation | Target digitization, extraction, and tracking |
CN103366170A (en) * | 2012-04-02 | 2013-10-23 | 鸿富锦精密工业(深圳)有限公司 | Image binarization processing device and method thereof |
-
2016
- 2016-11-29 CN CN201611069862.5A patent/CN108122241B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739559A (en) * | 2008-11-18 | 2010-06-16 | 哈尔滨理工大学 | Threshold zone-based image binarization method |
US8542252B2 (en) * | 2009-05-29 | 2013-09-24 | Microsoft Corporation | Target digitization, extraction, and tracking |
CN103366170A (en) * | 2012-04-02 | 2013-10-23 | 鸿富锦精密工业(深圳)有限公司 | Image binarization processing device and method thereof |
Non-Patent Citations (2)
Title |
---|
YING WANG ET AL.: "Edge extraction by merging 3D point cloud and 2D image data", 《2013 10TH INTERNATIONAL CONFERENCE AND EXPO ON EMERGING TECHNOLOGIES FOR A SMARTER WORLD (CEWIT)》 * |
田涌涛: "基于二维三阶多项式拟合的阈值曲面分割法", 《计算机工程》 * |
Also Published As
Publication number | Publication date |
---|---|
CN108122241B (en) | 2021-10-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107690672B (en) | Training data generation method and device and image semantic segmentation method thereof | |
CN110163246B (en) | Monocular light field image unsupervised depth estimation method based on convolutional neural network | |
CN106548455B (en) | Apparatus and method for adjusting brightness of image | |
US9773302B2 (en) | Three-dimensional object model tagging | |
CN109142366A (en) | Spherical housing defect inspection method, device and computer readable storage medium | |
CN107590791B (en) | Image enhancement method and image processing apparatus | |
CN110189714A (en) | The display methods and device, electronic equipment, medium of backlight are adjusted with region | |
CN109951635A (en) | It takes pictures processing method, device, mobile terminal and storage medium | |
CN109829868B (en) | Lightweight deep learning model image defogging method, electronic equipment and medium | |
CN107004266A (en) | The method for detecting defect on surface of tyre | |
CN109241964A (en) | The acquisition methods and equipment of the crawl point of mechanical arm | |
JP2010191968A (en) | Image enhancement method and image enhancement device | |
CN109003271A (en) | A kind of Wiring harness connector winding displacement quality determining method based on deep learning YOLO algorithm | |
CN105093289A (en) | Seismic horizon identification method based on image processing | |
CN102270335A (en) | Method for embedding additional information into image | |
CN114627554A (en) | Automatic aquaculture feeding centralized management method and system for aquatic products | |
CN104952089B (en) | A kind of image processing method and system | |
CN105531743A (en) | Rendering device | |
US20120169759A1 (en) | Method and apparatus for creating a live artistic sketch of an image | |
CN107452019B (en) | Target detection method, device and system based on model switching and storage medium | |
CN108122241A (en) | A kind of binary conversion treatment device and method of image | |
CN105809128A (en) | Eye pupil positioning method and system for eye part image and shooting terminal | |
CN105635807A (en) | Video editing method and apparatus | |
US20220122244A1 (en) | Defect image generation method for deep learning and system therefor | |
CN104700378A (en) | Genetic algorithm based low-illumination video image processing method |
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 |