CN108122241B - Image binarization processing device and method - Google Patents
Image binarization processing device and method Download PDFInfo
- Publication number
- CN108122241B CN108122241B CN201611069862.5A CN201611069862A CN108122241B CN 108122241 B CN108122241 B CN 108122241B CN 201611069862 A CN201611069862 A CN 201611069862A CN 108122241 B CN108122241 B CN 108122241B
- Authority
- CN
- China
- Prior art keywords
- image
- binarization processing
- gray level
- point cloud
- dimensional composite
- 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.)
- Active
Links
Images
Abstract
The invention discloses a binarization processing device and a binarization processing method for an image. The method comprises the following steps: shooting at least two gray level images of the same object under different illumination conditions; converting the gray level image into a three-dimensional composite point cloud image; judging whether the characteristic boundaries of the three-dimensional composite point cloud image and the object can form a curved surface of threshold segmentation; and when the judgment result is yes, saving the curved surface as the basis of the binary segmentation. By the method, the gray-scale image can be rapidly and visually binarized, situations which are not suitable for the binarization of the image can be deduced, the scheme is simple, the visualization effect is extremely strong, the correctness and the stability of the method are improved, and the development and debugging period of digital image processing is shortened.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a binarization processing device and method for an image.
Background
In digital image processing, binarization processing plays a very important role. In brief, the binarization processing of the image is to set the gray scale of a point on the image to 0 or 255, that is, select a gray scale image with 256 brightness levels by using an appropriate threshold value, so as to obtain a binarized image which can still reflect the overall and local features of the image.
In order to obtain an ideal binary image, a non-overlapping region is generally defined by closed and connected boundaries. All pixels with the gray levels larger than or equal to the threshold are judged to belong to the specific object, the gray level value of the pixels is represented by 255, otherwise, the pixels are excluded from the object area, the gray level value is 0, and the pixels represent the background or the exceptional object area. If a specific object has uniform gray values inside and is in a uniform background with gray values of other levels, a more ideal segmentation effect can be obtained by using a threshold method.
However, the conventional binarization algorithm is only suitable for static images, is sensitive to illumination condition changes, and is limited in practical engineering application.
Disclosure of Invention
The invention mainly solves the technical problem of providing the image binarization processing device and method, can rapidly and visually carry out binarization processing on the gray level image, can deduce which conditions are not suitable for the binarization processing of the image, has simple scheme and strong visualization effect, improves the correctness and stability of the method, and shortens the development and debugging period of digital image processing.
In order to solve the technical problems, the invention adopts a technical scheme that: provided is a binarization processing method of an image, the method comprising: shooting at least two gray level images of the same object under different illumination conditions; converting the gray level image into a three-dimensional composite point cloud image; judging whether the three-dimensional composite point cloud image and the characteristic boundary of the object can form a curved surface of threshold segmentation; and when the judgment result is yes, saving the curved surface as the basis of binarization segmentation.
Wherein, the method also comprises:
and if the judgment result is negative, judging that the image is not suitable for binarization processing under the illumination condition.
The step of shooting at least two gray level images of the same object under different illumination conditions comprises the following steps:
at least two gray level images of the same object under different lighting conditions are shot from the same angle and distance.
The method comprises the following steps of shooting at least two gray level images of the same object under different lighting conditions from the same angle and distance, wherein the steps comprise:
at least two gray level images of the same object under different illumination conditions at different times are shot from the same angle and distance.
Wherein the step of converting the grayscale image into a three-dimensional composite point cloud image comprises:
and splicing the gray level images to form a three-dimensional composite point cloud image, and displaying the three-dimensional composite point cloud image in a visualized manner.
In order to solve the technical problem, the invention adopts another technical scheme that: provided is an image binarization processing device, comprising:
the shooting module is used for shooting at least two gray level images of the same object under different illumination conditions;
a forming module for converting the gray level image into a three-dimensional composite point cloud image;
the judging module is used for judging whether the three-dimensional composite point cloud image and the characteristic boundary of the object can form a curved surface for threshold segmentation;
the control module controls the storage module to store the curved surface as a basis for binarization segmentation when the judgment result of the judgment module is yes.
And the control module judges that the image is not suitable for binarization processing under the illumination condition when the judgment result of the judgment module is negative.
The shooting module is used for shooting at least two gray level images of the same object under different illumination conditions from the same angle and distance.
The shooting module is used for shooting at least two gray level images of the same object under different illumination conditions at different time from the same angle and distance.
The forming module specifically splices the gray level images to form a three-dimensional composite point cloud image;
the binarization processing device further includes:
and the display module is used for displaying the three-dimensional composite point cloud image in a visual mode.
The invention has the beneficial effects that: the present invention provides a binarization processing device and method for an image, which is different from the prior art, the method comprises the following steps: the method comprises the steps of firstly shooting at least two gray level images of the same object under different illumination conditions, then converting the gray level images into three-dimensional composite point cloud images, further judging whether the characteristic boundaries of the three-dimensional composite point cloud images and the object can form a curved surface for threshold segmentation, and if so, storing the curved surface as a basis for binary segmentation. Therefore, the method can rapidly and visually carry out binarization processing on the gray level image, can deduce which conditions are not suitable for the binarization processing of the image, has simple scheme and extremely strong visualization effect, improves the correctness and stability of the method, and shortens the development and debugging period of digital image processing.
Drawings
Fig. 1 is a flowchart of a binarization processing method for an image according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an image binarization processing device according to an embodiment of the present invention.
Detailed Description
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for binarizing an image according to an embodiment of the present invention. As shown in fig. 1, the method of the present embodiment includes the following steps:
step S1: at least two gray level images of the same object under different lighting conditions are shot. Wherein the gray scale image is a two-dimensional gray scale image.
Specifically, at least two gray level images of the same object under different lighting conditions are shot from the same angle and distance. More specifically, at least two gray-scale images of the same object under different lighting conditions at different times are taken from the same angle and distance. Wherein the same angle and distance refer to the angle and distance between the photographing apparatus, such as a camera, and the object, respectively.
In other embodiments, different lighting conditions may also be directly created by human engineering, for example, lighting conditions in three time periods of morning, noon and afternoon may be simulated manually, and then a grayscale image of the same object under different lighting conditions is taken at the same specific position and at the same specific angle. The method for artificially manufacturing different illumination conditions does not need to wait for different time formed by natural rules, so that the time can be saved and the efficiency can be improved.
In this step, the number of images shot by the camera is preferably three or more, so as to facilitate formation of a subsequent three-dimensional composite point cloud image and formation of a more accurate curved surface for threshold segmentation, thereby improving accuracy of image processing.
Step S2: and converting the gray level image into a three-dimensional composite point cloud image. Namely, converting the two-dimensional gray level image into a three-dimensional composite point cloud image.
The method specifically comprises the steps of splicing the gray level images to form a three-dimensional composite point cloud image, and displaying the three-dimensional composite point cloud image in a visual mode.
Step S3: and judging whether the characteristic boundaries of the three-dimensional composite point cloud image and the object can form a curved surface segmented by a threshold value. In this step, if the result of the determination is yes, the process proceeds to step S4, and if the result of the determination is no, the process proceeds to step S5.
Step S4: and saving the curved surface as the basis of binarization segmentation.
Step S5: it is determined that the binarization processing of the image is not appropriate under the illumination condition.
Therefore, the method can rapidly and visually carry out binarization processing on the gray level image, can deduce which conditions are not suitable for the binarization processing of the image, has simple scheme and extremely strong visualization effect, improves the correctness and stability of the method, and shortens the development and debugging period of digital image processing.
The invention also provides a binarization processing device for the image, which is applied to the method described above, and particularly refers to fig. 2.
As shown in fig. 2, the apparatus 20 of the present embodiment includes a photographing module 21, a forming module 22, a storage module 23, a judging module 24, a control module 25, and a display module 26.
The shooting module 21 is configured to shoot at least two grayscale images of the same object under different lighting conditions. Specifically, at least two gray level images of the same object under different lighting conditions are shot from the same angle and distance. More specifically, at least two gray-scale images of the same object under different lighting conditions at different times are taken from the same angle and distance.
In other embodiments, different lighting conditions may also be directly created by human engineering, for example, lighting conditions in three time periods of morning, noon and afternoon may be simulated manually, and then a grayscale image of the object under different lighting conditions is taken at the same specific position and at the same specific angle. The method for artificially manufacturing different illumination conditions does not need to wait for different time formed by natural rules, so that the time can be saved and the efficiency can be improved.
In this embodiment, the number of the shot images is preferably three or more, so as to facilitate the formation of the subsequent three-dimensional composite point cloud image and the formation of a more accurate curved surface with threshold segmentation, and improve the accuracy of image processing.
The forming module 22 is used to convert the grayscale image into a three-dimensional composite point cloud image. Specifically, the gray level images are spliced to form a three-dimensional composite point cloud image. Further, the three-dimensional composite point cloud image is displayed in a visualized manner through the display module 26.
The judging module 24 is used for judging whether the three-dimensional composite point cloud image and the characteristic boundary of the object can form a curved surface of threshold segmentation.
The control module 25 is configured to control the storage module 23 to store the curved surface as a basis for binarization segmentation when the determination result of the determination module 24 is yes, and determine that the image is not suitable for binarization processing under the illumination conditions when the determination result of the determination module 24 is no.
Therefore, the method can rapidly and visually carry out binarization processing on the gray level image, can deduce which conditions are not suitable for the binarization processing of the image, has simple scheme and extremely strong visualization effect, improves the correctness and stability of the method, and shortens the development and debugging period of digital image processing.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A binarization processing method of an image is characterized by comprising the following steps:
shooting at least two gray level images of the same object under different illumination conditions;
converting the gray level image into a three-dimensional composite point cloud image;
judging whether the three-dimensional composite point cloud image and the characteristic boundary of the object can form a curved surface of threshold segmentation;
if the judgment result is yes, the curved surface is saved as the basis of binarization segmentation;
the step of shooting at least two gray level images of the same object under different illumination conditions comprises the following steps:
at least two gray level images of the same object under different lighting conditions are shot from the same angle and distance.
2. The binarization processing method according to claim 1, characterized in that the method further comprises:
and if the judgment result is negative, judging that the image is not suitable for binarization processing under the illumination condition.
3. The binarization processing method according to claim 1, wherein the step of photographing at least two gray scale images of the same object under different illumination conditions from the same angle and distance comprises:
at least two gray level images of the same object under different illumination conditions at different times are shot from the same angle and distance.
4. The binarization processing method according to claim 1, wherein the step of converting the grayscale image into a three-dimensional composite point cloud image comprises:
and splicing the gray level images to form a three-dimensional composite point cloud image, and displaying the three-dimensional composite point cloud image in a visualized manner.
5. An apparatus for binarization processing of an image, the apparatus comprising:
the shooting module is used for shooting at least two gray level images of the same object under different illumination conditions;
a forming module for converting the gray level image into a three-dimensional composite point cloud image;
the judging module is used for judging whether the three-dimensional composite point cloud image and the characteristic boundary of the object can form a curved surface for threshold segmentation;
the control module controls the storage module to store the curved surface as a basis for binarization segmentation when the judgment result of the judgment module is yes;
the shooting module is used for shooting at least two gray level images of the same object under different illumination conditions from the same angle and distance.
6. The binarization processing device according to claim 5, wherein the control module determines that it is not suitable for binarization processing of the image under the illumination condition when the result of the determination by the determination module is negative.
7. The binarization processing device according to claim 5, characterized in that the shooting module is specifically used for shooting at least two gray scale images of the same object under different illumination conditions at different times from the same angle and distance.
8. The binarization processing device according to claim 5, characterized in that the forming module is specifically configured to splice the grayscale images to form a three-dimensional composite point cloud image;
the binarization processing device further includes:
and the display module is used for displaying the three-dimensional composite point cloud image in a visual mode.
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 CN108122241A (en) | 2018-06-05 |
| CN108122241B true 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 |
|---|
| Edge extraction by merging 3D point cloud and 2D image data;Ying Wang et al.;《2013 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT)》;20140116;第1-6页 * |
| 基于二维三阶多项式拟合的阈值曲面分割法;田涌涛;《计算机工程》;20030331;第29卷(第4期);第127-129页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108122241A (en) | 2018-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3712841A1 (en) | Image processing method, image processing apparatus, and computer-readable recording medium | |
| CN111754538B (en) | Threshold segmentation method for USB surface defect detection | |
| CN113902641B (en) | Data center hot zone judging method and system based on infrared image | |
| CN105719250A (en) | Image inpainting method based on simple background, system and shooting camera | |
| CN103955906A (en) | Criminisi image restoration method based on bat algorithm | |
| Jing et al. | Pavement crack distress detection based on image analysis | |
| CN109801322A (en) | A kind of light leak test method and device | |
| JP5859749B2 (en) | Contrast improvement method using Bezier curve | |
| CN111311720B (en) | Texture image processing method and device | |
| CN109118494B (en) | Overlapping region segmentation method and device based on concave point matching | |
| CN108122241B (en) | Image binarization processing device and method | |
| CN111275642B (en) | Low-illumination image enhancement method based on significant foreground content | |
| CN110210401B (en) | Intelligent target detection method under weak light | |
| CN111985471A (en) | License plate positioning method and device and storage medium | |
| EP3930306A2 (en) | Method and apparatus for stabilizing image, roadside device and cloud control platform | |
| CN115170489A (en) | Method and device for identifying and measuring steel bars | |
| CN104021534A (en) | Shredded paper splicing method | |
| CN113469955A (en) | Photovoltaic module fault area image detection method and system | |
| CN114004771A (en) | HSV model-based brightness compensation method and detection method | |
| JP6354316B2 (en) | Image detection apparatus and program | |
| CN113034449A (en) | Target detection model training method and device and communication equipment | |
| CN112633065A (en) | Face detection method, system, storage medium and terminal based on data enhancement | |
| CN104240275A (en) | Image repairing method and device | |
| CN107452039B (en) | Method and device for compressing RGB color space | |
| WO2023134514A1 (en) | Systems and methods for image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |