CN111524143B - Foam adhesion image region segmentation processing method - Google Patents
Foam adhesion image region segmentation processing method Download PDFInfo
- Publication number
- CN111524143B CN111524143B CN202010227708.6A CN202010227708A CN111524143B CN 111524143 B CN111524143 B CN 111524143B CN 202010227708 A CN202010227708 A CN 202010227708A CN 111524143 B CN111524143 B CN 111524143B
- Authority
- CN
- China
- Prior art keywords
- foam
- image
- segmentation
- area
- pixel
- 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
- 239000006260 foam Substances 0.000 title claims abstract description 90
- 230000011218 segmentation Effects 0.000 title claims abstract description 28
- 238000003672 processing method Methods 0.000 title claims description 8
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000003709 image segmentation Methods 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 10
- 238000005188 flotation Methods 0.000 abstract description 7
- 239000010865 sewage Substances 0.000 abstract description 7
- 229910052500 inorganic mineral Inorganic materials 0.000 abstract description 6
- 239000011707 mineral Substances 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract 1
- 239000000284 extract Substances 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000000149 argon plasma sintering Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic 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
- G06T7/11—Region-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
- 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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a method for processing the regional segmentation of foam adhesion images, which analyzes the motion modes of the foams such as mineral flotation and sewage treatment, extracts the characteristic information such as bright spot, foam flooding edge and the like of the foam images, respectively uses the characteristic information as a target starting point and a boundary limiting point of image segmentation, well overcomes the defects of inaccurate boundary segmentation, easy over-segmentation or under-segmentation and the like of the traditional watershed segmentation algorithm, ensures that the segmentation among the adhesion foams is more accurate, improves the detection accuracy of the related information of the statistical diameters of the adhesion foams, greatly promotes the automation degree of the related process through the analysis and the treatment of the foam images in the mineral flotation and sewage treatment processes, improves the detection accuracy of the statistical diameters of the foams, further avoids the subjective factors of operators and improves the working environment of operators.
Description
Technical Field
The invention relates to the technical field of production detection in a flotation process, in particular to a processing method for partitioning foam adhesion image areas.
Background
In the process of generating a large amount of foam for mineral flotation, sewage treatment and the like, detecting the statistical diameter of the large amount of foam is an important parameter for measuring the process performance to control and regulate. However, the process still mainly depends on the naked eyes of experienced operators to observe and judge, the labor intensity is high, accurate detection is difficult to achieve, and no standard, standardized and measurable basis exists due to the difference of subjective judgment of the operators.
In the existing beneficiation and sewage treatment technology, because the detection method of manual observation is mainly adopted, time and labor are wasted, the detection result has large uncertainty and no unified measurement standard, and the working site environment is bad, so that adverse effects can be generated on the health and safety of operators.
Disclosure of Invention
The invention aims to provide a foam adhesion image region segmentation processing method, which can greatly promote the automation degree of related processes through analyzing and processing foam images in mineral flotation and sewage treatment processes, can improve the detection accuracy of foam statistical diameters, further avoids subjective factors of operators and improves the working environment of operators.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a processing method for segmentation of foam adhesion image areas comprises the following steps:
s1, carrying out threshold segmentation on each acquired frame of foam image, and segmenting a foam dark area and a foam highlight area to obtain a highlight foam facula image;
s2, defining a valley edge type pixel as a pixel point with a gray value smaller than the gray value of adjacent pixels at two sides along a certain direction, then comparing the pixel point with the gray value of the neighborhood of the pixel point by scanning the foam image, extracting the valley edge type pixel, taking the valley edge type pixel and the surrounding area thereof as an inter-foam edge area in the foam image, and generating an inter-foam edge area image;
s3, performing distance transformation on the obtained image of the edge area between the foams to generate a corresponding distance image;
s4, taking the obtained distance image as an image to be segmented, taking a foam facula image as a seed point image, and carrying out image segmentation by using a segmentation algorithm to obtain corresponding areas of each foam;
and S5, counting the pixel area of each foam corresponding area, and converting the pixel area into an equivalent diameter to obtain the diameter of each foam in the foam image.
Further, the segmentation algorithm in the step S4 is a marker-based watershed segmentation algorithm.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the automation degree of mineral flotation and sewage treatment processes is greatly improved by processing the adhesion foam image, and the method improves the detection accuracy of the statistical diameter of the foam image, so that subjective uncertain factors of operation of operators are avoided.
Drawings
FIG. 1 is a flow chart of a method of processing foam adhesion image region segmentation;
FIG. 2 is a schematic illustration of a valley edge detection template defined in the present invention;
FIG. 3 is a schematic diagram of a distance transform convolution template of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all, embodiments of the present invention, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
A processing method for partitioning foam adhesion image areas is shown in fig. 1, and comprises the following steps:
s1, carrying out threshold segmentation on each acquired frame of foam image, and segmenting a foam dark area and a foam highlight area to obtain a highlight foam facula image;
in this embodiment, by installing the bracket and the camera at a proper distance right above the moving foam and configuring the light source, continuous shooting of foam images is performed, shielding is given to the housing around the light source, and light scattering is avoided. Each frame of foam image captured by the camera causes a highlight spot area on the top of the foam due to the light illumination, while other foam areas exhibit significantly lower brightness. The gray level difference of the two is obvious, a segmentation threshold value can be obtained by adopting any method, and a foam image is segmented into a foam dark area and a foam highlight area; if the gray level is achieved, each frame of foam image is converted from an RGB image to a gray level image, then a proper morphological operation element is selected according to the size of a light spot, top cap operation is carried out on the gray level image, the foreground of the gray level image is extracted, and threshold segmentation is carried out on the foreground by using an OTSU method, so that a foam highlight light spot area can be obtained.
S2, defining a valley edge type pixel as a pixel point with a gray value smaller than the gray value of adjacent pixels at two sides along a certain direction, then comparing the pixel point with the gray value of the neighborhood of the pixel point by scanning the foam image, extracting the valley edge type pixel, taking the valley edge type pixel and the surrounding area thereof as an inter-foam edge area in the foam image, and generating an inter-foam edge area image;
in this embodiment, as shown in FIG. 2, a boundary detection template X is defined, and a square matrix is formed by 3*3 sub-templates XmThe arrangement is formed, and X0 is positioned in the geometric center of the sub-template. Each sub-template consists of k x k pixels. Let f (i, j) denote the gray value of the original image pixel at point (i, j), g0 (i, j) denote the eigenvalue of f (i, j) in the horizontal direction at (i, j), g45 (i, j) denote the eigenvalue of f (i, j) in the 45 ° direction at (i, j), g90 (i, j) denote the eigenvalue in the 90 ° direction, and g135 (i, j) denote the eigenvalue in the 135 ° direction. Fm represents the average gray level of k x k pixels in the mth sub-template Xm, and P is a given threshold. If the pixel average value of the sub-template X0
Satisfy->
G0 (i, j) =1, otherwise g0 (i, j) =0; if it meets->
G45 (i, j) =1, otherwise g45 (i, j) =0; if it meets
G90 (i, j) =1, otherwise g90 (i, j) =0; if it meets->
G135 (i, j) =1, otherwise g135 (i, j) =0; g (i, j) = u [ g0 (i, j), g45 (i, j), g90 (i, j), g135 (i, j)]. The resulting g (i, j) is the extracted edge region, in this example k=5, p=2.
S3, performing distance transformation on the obtained image of the edge area between the foams to generate a corresponding distance image;
in this embodiment, according to the obtained binary image representing the edge area between foams, a 5*5 array mask is used, as shown in fig. 3, each point in the array defines a distance from a point at a specific position relative to the center of the mask, and a gray image representing the distance is obtained by convolving the mask with the binary image.
S4, taking the obtained distance image as an image to be segmented, taking a foam facula image as a seed point image, and carrying out image segmentation by using a watershed segmentation algorithm based on marks to obtain corresponding areas of each foam;
in this embodiment, a foam facula image is set as a seed point to be segmented, a local minimum value is set, a distance gray level image is set as a gradient information image, a communication region of the image is searched, a water collecting basin is formed by expanding from the local minimum value to a surrounding region through simulating flood irrigation, the water potential rises along with the increase of the gray level value, the water collecting basin is gradually expanded, and a junction of the water collecting basin is a watershed and represents a segmentation boundary of each foam region.
And S5, counting the pixel area of each foam corresponding area, and converting the pixel area into an equivalent diameter to obtain the diameter of each foam in the foam image.
In this embodiment, each foam region is labeled with the same value, and different regions are labeled with different values. And counting the occurrence times of the numerical values in the image to obtain the area of each foam region. And then according to the formula:
the equivalent diameter of each foam region can be calculated. And obtaining statistical information such as distribution ratio, average diameter, standard deviation and the like of each interval of the whole foam based on the diameter of each foam.
According to the analysis processing method provided by the embodiment of the invention, aiming at the characteristic that the edge of the foam image is not clear, the edge information of the foam image is enhanced by extracting the valley edge area in the image, so that the segmentation boundary of the foam image is better attached to the real edge of the foam. Aiming at the problem that the watershed algorithm is easy to generate under-segmentation and over-segmentation in the segmentation process, the number of segmentation of the foam image and the central position of each segmentation area are better controlled by extracting the highlight foam facula area, so that the under-segmentation and over-segmentation problems are solved to a certain extent. The method improves the detection precision of the statistical diameter of the foam image, and has guiding significance for automatic detection and optimization control of production processes such as mineral flotation, sewage treatment and the like.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (2)
1. The processing method for the segmentation of the foam adhesion image area is characterized by comprising the following steps:
s1, carrying out threshold segmentation on each acquired frame of foam image, and segmenting a foam dark area and a foam highlight area to obtain a highlight foam facula image;
s2, defining a valley edge type pixel as a pixel point with a gray value smaller than the gray value of adjacent pixels at two sides along a certain direction, then comparing the pixel point with the gray value of the neighborhood of the pixel point by scanning the foam image, extracting the valley edge type pixel, taking the valley edge type pixel and the surrounding area thereof as an inter-foam edge area in the foam image, and generating an inter-foam edge area image;
s3, performing distance transformation on the obtained image of the edge area between the foams to generate a corresponding distance image;
s4, taking the obtained distance image as an image to be segmented, taking a foam facula image as a seed point image, and carrying out image segmentation by using a segmentation algorithm to obtain corresponding areas of each foam;
and S5, counting the pixel area of each foam corresponding area, and converting the pixel area into an equivalent diameter to obtain the diameter of each foam in the foam image.
2. The method for processing the segmentation of the foam adhesion image area according to claim 1, wherein the method comprises the following steps: the segmentation algorithm in the step S4 is a watershed segmentation algorithm based on a mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010227708.6A CN111524143B (en) | 2020-03-27 | 2020-03-27 | Foam adhesion image region segmentation processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010227708.6A CN111524143B (en) | 2020-03-27 | 2020-03-27 | Foam adhesion image region segmentation processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111524143A CN111524143A (en) | 2020-08-11 |
| CN111524143B true CN111524143B (en) | 2023-04-25 |
Family
ID=71901583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010227708.6A Active CN111524143B (en) | 2020-03-27 | 2020-03-27 | Foam adhesion image region segmentation processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111524143B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096180A (en) * | 2021-04-02 | 2021-07-09 | 青岛丰禾星普科技有限公司 | Method for monitoring foam in aquaculture, terminal equipment and readable storage medium |
| CN112967349A (en) * | 2021-04-02 | 2021-06-15 | 青岛丰禾星普科技有限公司 | Foam-based aquaculture monitoring and early warning method, terminal equipment and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104851105A (en) * | 2015-05-25 | 2015-08-19 | 邵阳学院 | Improved foam image segmentation method based on watershed transformation |
| CN110689020A (en) * | 2019-10-10 | 2020-01-14 | 湖南师范大学 | Segmentation method of mineral flotation froth image and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10818011B2 (en) * | 2017-12-29 | 2020-10-27 | Shenzhen Institutes Of Advanced Technology Chinese Academy Of Sciences | Carpal segmentation and recognition method and system, terminal and readable storage medium |
-
2020
- 2020-03-27 CN CN202010227708.6A patent/CN111524143B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104851105A (en) * | 2015-05-25 | 2015-08-19 | 邵阳学院 | Improved foam image segmentation method based on watershed transformation |
| CN110689020A (en) * | 2019-10-10 | 2020-01-14 | 湖南师范大学 | Segmentation method of mineral flotation froth image and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李建奇 ; 阳春华 ; 曹斌芳 ; 朱红求 ; 刘金平 ; .面向参数测量的改进分水岭浮选泡沫图像分割方法.仪器仪表学报.2013,(06),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111524143A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112766274B (en) | Water gauge image water level automatic reading method and system based on Mask RCNN algorithm | |
| CN107506798B (en) | Water level monitoring method based on image recognition | |
| CN113469177B (en) | Deep learning-based drainage pipeline defect detection method and system | |
| CN101799434B (en) | Printing image defect detection method | |
| CN111524143B (en) | Foam adhesion image region segmentation processing method | |
| CN103985108B (en) | Method for multi-focus image fusion through boundary detection and multi-scale morphology definition measurement | |
| CN106056118A (en) | Recognition and counting method for cells | |
| CN104700071B (en) | A kind of extracting method of panorama sketch road profile | |
| CN103499303A (en) | Wool fineness automatic measuring method | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| CN116703931B (en) | Surface silver vein detection method for building high polymer material | |
| CN109186706A (en) | A method of for the early warning of Urban Storm Flood flooding area | |
| CN112149543A (en) | Building raise dust identification system and method based on computer vision | |
| CN106447673A (en) | Chip pin extraction method under non-uniform illumination condition | |
| CN112287838B (en) | Cloud and fog automatic identification method and system based on static meteorological satellite image sequence | |
| CN116091505B (en) | Automatic defect detection and classification method and system for sapphire substrate | |
| CN112378591A (en) | Air tightness detection laser pose self-adaptive adjusting method based on computer vision | |
| CN111563410B (en) | Foam image movement speed detection processing method | |
| CN110211128B (en) | Loess plateau terrace extraction method based on remote sensing image and DEM | |
| CN112862898B (en) | Flow velocity measuring method based on computer vision | |
| CN112884731B (en) | Water level detection method and river channel monitoring method based on machine vision | |
| Puissant et al. | Coastline extraction in VHR imagery using mathematical morphology with spatial and spectral knowledge | |
| CN103093241A (en) | Optical remote sensing image non-homogeneous cloud layer discriminating method based on homogenization processing | |
| CN115984360A (en) | Method and system for calculating length of dry beach based on 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240319 Address after: 471000 No. 206, Jianxi, Luoyang District, Henan, Jianshe Road Patentee after: CITIC HEAVY INDUSTRIES Co.,Ltd. Country or region after: Zhong Guo Patentee after: CITIC Corporation of China Address before: 471003 No.206 Jianshe Road, Jianxi District, Luoyang City, Henan Province Patentee before: CITIC HEAVY INDUSTRIES Co.,Ltd. Country or region before: Zhong Guo |