CN110969153A - Bubble identification method based on space optical characteristics - Google Patents
Bubble identification method based on space optical characteristics Download PDFInfo
- Publication number
- CN110969153A CN110969153A CN201911148457.6A CN201911148457A CN110969153A CN 110969153 A CN110969153 A CN 110969153A CN 201911148457 A CN201911148457 A CN 201911148457A CN 110969153 A CN110969153 A CN 110969153A
- Authority
- CN
- China
- Prior art keywords
- bubble
- light source
- bubbles
- camera
- image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000003287 optical effect Effects 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 238000003384 imaging method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000001678 irradiating effect Effects 0.000 claims abstract description 4
- 238000009826 distribution Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000008034 disappearance Effects 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 230000008961 swelling Effects 0.000 claims 2
- 230000010339 dilation Effects 0.000 description 8
- 230000000877 morphologic effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000003628 erosive effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000016776 visual perception Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000001802 infusion Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a bubble identification method based on space optical characteristics, which can realize identification and detection of bubbles in a transparent medium. The bubble identification method based on the space optical characteristics adopts a bubble identification system; and comprises the steps of: s1, collecting shape recognition bubbles imaged by reflected light rays of light sources with different shapes by a camera; s2, lighting a light source switch, irradiating on the bubbles of the recognized body, and imaging the recognized body by a camera; s3, automatically recognizing the image of the recognized body through a software algorithm by a PC controller connected with the camera; and S4, carrying out binarization processing on the image shot by the camera, and calculating various parameters of the bubbles. The bubble identification method based on the space optical characteristics is diversified, simple and feasible in judgment, accurate and reliable in judgment result and applicable to the white spirit industry.
Description
Technical Field
The invention relates to the field of optical characteristic identification steam drums, in particular to a bubble identification method based on space optical characteristics.
Background
It is well known that: with the continuous development of advanced optical imaging recognition technology, strict requirements are made on the amount of bubbles in products in the application fields of food industry, industrial glue industry, microelectronic equipment, laser communication, pharmaceutical industry and the like, so that the product quality is improved. Therefore, higher technical requirements are put on the detection requirements of bubbles in partial products. However, due to various uncertainties, it is difficult to avoid the generation of bubbles even with advanced pairs of production processes and techniques. Therefore, the bubble detection technology has important significance as a product with strict requirements on bubbles, and how to realize accurate detection is key.
At present, the mainstream bubble detection standard mainly adopts an ultrasonic direct detection method and a mechanical vibration method to indirectly detect bubbles. The ultrasonic direct detection is that the liquid guide pipe passes through the ultrasonic generating head and the receiving head to detect whether bubbles exist in the liquid in the guide pipe; the mechanical vibration indirect bubble detection is that the bubbles in the liquid are vibrated to be separated from the inner wall of the container through mechanical vibration, the bubbles float upwards and pass through a photoelectric sensor, and the photoelectric sensor detects whether the bubbles exist or not. These methods are only to detect the presence or absence of bubbles, and cannot accurately detect the diameter and the amount of bubbles. The specific position of the bubble can not be accurately obtained, the detection precision is not high, the detection efficiency is low, and quantitative analysis can not be carried out.
With the continuous development of the space optical detection technology, the method has obvious advantages and advancement in the aspects of image recognition and target detection, so that a better solution is provided for the problem of bubble recognition detection based on the space optical characteristics. The shape and the number of the specific light source can be reflected into a high-precision camera for imaging by utilizing the reflection principle of bubbles on light rays in space optics, the imaging numerical value of the specific light source is subjected to plane expansion through an image algorithm, the shape and the number of the light source can be calculated by judging the size and the distribution of the numerical value in a gray scale image, and then whether the specific light source is a bubble or not is judged; the bubbles can be irradiated and imaged by parallel light or a small-angle light source, and the space optical brightness is judged: the edge is in a continuous circle shape, and whether the measured object is a bubble can be judged by the characteristic that the central brightness value is low; the quantity and the dissipation time of the bubbles are counted by an identification bubble technology, and the related characteristics of the substances are judged by detecting the dissipation time of the bubbles, for example, the alcohol degree is judged by judging the size and the dissipation time of the bubbles in the white spirit industry. Therefore, on the basis of microscopic imaging detection method, rapid identification, detection and accurate measurement analysis of bubbles in the transparent medium can be performed by virtue of spatial optical characteristics.
Disclosure of Invention
The invention aims to solve the technical problem of providing a bubble identification method based on space optical characteristics, which identifies and detects bubbles based on the space optical characteristics in a transparent medium, thereby realizing the identification and detection of the bubbles in the transparent medium.
The technical scheme adopted by the invention for solving the technical problems is as follows: a bubble identification method based on space optical characteristics adopts a bubble identification system; the bubble identification system comprises a camera, a light source and a back plate with variable brightness;
the back plate is provided with an identified body; the camera is connected with a PC controller; the light source is connected with an industrial personal computer; the light source is used for emitting a light source with a specific optical frequency, a specific light-emitting duration, a specific position and a specific shape; the light emitted by the light source is emitted to the identified body; the camera is used for shooting an identified object; the PC controller is used for collecting images and identifying the bubble space optical characteristics of the identified body;
and comprises the steps of:
s1, collecting shape recognition bubbles imaged by reflected light rays of light sources with different shapes by a camera;
statically placing a detected bubble detection object in an area of a back plate, placing a camera and a light source on the same side of the detected bubble, placing the camera right in front of an identified body, and placing the light source in front of the identified body and forming a certain included angle with the camera;
s2, lighting a light source switch, irradiating on the bubbles of the recognized body, and imaging the recognized body by a camera;
s3, automatically recognizing the image of the recognized body through a software algorithm by a PC controller connected with the camera; the software algorithm can adopt binary morphology of an OSTU segmentation method and mathematical morphology;
s4, carrying out binarization processing on the image shot by the camera, calculating the shape of a light source, matching the shape with the light source, and if the imaging shape is consistent with the shape of the light source, judging that the object to be measured has bubbles; for example, point light source irradiation, bubble reflected light imaging is also a point, strip light source irradiation, and bubble reflected light imaging is also strip;
s5, calculating the size of the bubbles by calculating the size of a light and dark area in the binary image;
calculating the number of bubbles by calculating and counting the number of bright areas in the binary image;
and calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
Further, a predetermined number N of light sources are placed in front of the recognized body in step S1; n is a natural number of 2 or more.
Further, a predetermined number N of light sources are placed in front of the recognized body in step S1; n is a natural number more than or equal to 2; and the light sources are arranged in a distributed manner.
Further, the distribution mode can adopt uniform distribution along an arc.
Further, the light sources emitted by the respective light sources have different shapes.
Specifically, in step S3, an OSTU segmentation method is used to identify the special spectral feature image; the method specifically comprises the following steps: firstly, converting an image into a gray scale image; the number of pixels in the image, of which the gray value A is smaller than the threshold T, is H0, and the number of pixels of which the gray value A is larger than the threshold T is H1; recording the average gray value of H0 as H0 and the average gray value of H1 as H1 in the image with the image size of X X Y and the threshold value of T;
the probability that the pixel gray value is less than T is:
r0＝h0/(X*Y)；
the probability that the pixel gray value is greater than T is:
r1＝h1/(X*Y)；
h0+h1＝X*Y；
r0+r1＝1；
the average gray is multiplied by the probability and then added:
e＝r0*h0+r1*h1；
the between-class variance is:
d＝r0(h0-e)^2+r1(h1-e)^2；
d＝r0*r1(h0-h1)^2。
specifically, the binary morphology of the mathematical morphology includes a special spectral feature image recognition by a corrosion algorithm, a dilation algorithm or a dilation algorithm of gray scale morphology.
The invention has the beneficial effects that: compared with the prior art, the bubble identification method based on the space optical characteristics has the following advantages and beneficial effects:
1. according to the bubble identification method based on the space optical characteristics, the bubbles in the transparent medium are identified and detected by means of the space optical characteristics on the basis of optical lens imaging, so that the problems of subjective interference, difficulty in accurate quantification and the like in the traditional manual visual detection process are solved;
2. according to the bubble identification method based on the space optical characteristics, a space optical characteristic bubble identification environment is established by adopting a special light source and an irradiation mode, characteristics are collected to establish an identification model, so that identification and quantitative detection of bubbles in a transparent medium are realized, and continuous strengthening training of the bubble identification detection model is performed by using a large number of bubble space optical characteristic samples, so that the identification detection capability of the bubble model is effectively improved, and the problems that other modes of identification detection methods are low in accuracy, incapable of quantification and the like in the bubble identification detection process are solved.
3. The bubble identification method based on the space optical characteristics can calculate and count the dissipation time of bubbles, and can be used for judging the relevant characteristics such as the alcohol degree of white spirit and the like by judging the size and the dissipation time of the bubbles in the white spirit industry.
4. According to the bubble identification detection method based on the space optical characteristics, the determination method is diversified, the determination is simple and feasible, and the determination result is accurate and reliable through the mutual combination of the light source shapes, the light source quantity and the light source distributed positions.
Drawings
FIG. 1 is a schematic diagram of a bubble identification system according to an embodiment of the present invention;
FIG. 2 is a schematic view of an embodiment of the invention for indoor irradiation of air bubbles in rainy or cloudy days;
FIG. 3 is an optical characteristic of an illumination bubble in a rainy day in an embodiment of the present invention;
FIG. 4 is a schematic view of a point source illuminating a bubble in an embodiment of the present invention;
FIG. 5 is an optical feature of a point source illuminating a bubble in an embodiment of the present invention;
FIG. 6 is a schematic diagram of two point light sources illuminating a bubble in an embodiment of the present invention;
FIG. 7 shows the optical characteristics of two point light sources illuminating a bubble in an embodiment of the present invention;
FIG. 8 is a schematic view of three point light sources illuminating a bubble in an embodiment of the present invention;
FIG. 9 shows the optical characteristics of a bubble illuminated by three point sources in an embodiment of the present invention;
FIG. 10 is a schematic diagram of two bar light sources illuminating a bubble in an embodiment of the present invention;
FIG. 11 is an optical signature of two bar light sources illuminating a bubble in an embodiment of the present invention;
FIG. 12 is a flow chart of a binary morphological erosion algorithm in accordance with an embodiment of the present invention;
FIG. 13 is a flow chart of a binary morphological dilation algorithm in accordance with an embodiment of the present invention;
FIG. 14 is a flowchart of a gray scale morphological erosion algorithm in an embodiment of the invention;
FIG. 15 is a flow chart of a gray scale morphological dilation algorithm in an embodiment of the present invention;
the following are marked in the figure: the system comprises a first industrial computer, a second industrial computer, a third industrial computer, a first light source, a second industrial computer, a third light source, a third industrial computer and a backboard 10, wherein the first industrial computer is 1-an identified body, the camera 2, the PC 3, the first light source 4, the first industrial computer 5, the second industrial computer 6, the second industrial computer 7, the third industrial computer 8, the third industrial computer 9 and the backboard 10.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
As shown in fig. 1, the bubble identification method based on the spatial optical characteristics according to the present invention employs a bubble identification system; the bubble identification system comprises a camera 2, a light source and a back plate 10 with variable brightness;
the back plate 10 is provided with an identified body 1; the camera 2 is connected with a PC controller 3; the light source is connected with an industrial personal computer; the light source is used for emitting a light source with a specific optical frequency, a specific light-emitting duration, a specific position and a specific shape; the light emitted by the light source is emitted to the identified body 1; the camera 2 is used for shooting the identified object 1; the PC controller 3 is used for collecting images and identifying the bubble space optical characteristics of the identified body 1;
and comprises the steps of:
s1, collecting shape recognition bubbles imaged by reflected light rays of light sources with different shapes by a camera;
the method comprises the following steps of statically placing a detected bubble object in an area of a back plate 10, placing a camera 2 and a light source 4 on the same side of a detected bubble, placing the camera 2 right in front of an identified body 1, and placing the light source in front of the identified body 1 and forming a certain included angle with the camera 2;
s2, illuminating the bubble of the object 1 with a light source switch, and imaging the object 1 with the camera 2;
s3, automatically recognizing the image of the recognized body 11 through the PC controller 3 connected with the camera 2 through a software algorithm; the software algorithm can adopt binary morphology of an OSTU segmentation method and mathematical morphology;
s4, carrying out binarization processing on the image shot by the camera 2, calculating the shape of a light source, matching the shape with the light source, and if the imaging shape is consistent with the shape of the light source, judging that the object to be measured has bubbles; for example, point light source irradiation, bubble reflected light imaging is also a point, strip light source irradiation, and bubble reflected light imaging is also strip;
s5, calculating the size of the bubbles by calculating the size of a light and dark area in the binary image;
calculating the number of bubbles by calculating and counting the number of bright areas in the binary image;
and calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
Further, a predetermined number N of light sources are placed in front of the recognized body 1 in step S1; n is a natural number of 2 or more.
Further, a predetermined number N of light sources are placed in front of the recognized body 1 in step S1; n is a natural number more than or equal to 2; and the light sources are arranged in a distributed manner.
Further, the distribution mode can adopt uniform distribution along an arc.
Further, the light sources emitted by the respective light sources have different shapes.
In the application process:
1. the camera collects the shape recognition bubbles imaged by the reflected light rays of the light sources with different shapes, as shown in fig. 2 and 3:
the method comprises the steps of statically placing a detected body 1 of a detected bubble in a specific area, placing a video camera and a light source with a specific shape on the same side of the detected bubble, placing the video camera right in front of the detected body 1, and placing the light source with the specific shape in front of the detected body 1 and forming a certain included angle with the video camera.
The specific-shape light source switch is turned on, and the bubble of the object 1 is irradiated with the light, and the object 1 is imaged by the camera.
Carrying out binarization processing on the image through an algorithm, calculating the shape of a light source, matching the light source with a specific light source, and judging that the object to be measured has bubbles if the imaging shape is consistent with the shape of the specific light source; for example, point light source irradiation, bubble reflected light imaging are also a point, strip light source irradiation, and bubble reflected light imaging are also strip.
And calculating the size of the bubbles by calculating the size of a bright and dark area in the binary image.
And calculating the number of the bubbles by counting the number of the bright areas in the binary image.
And calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
2. The cameras collect the quantity of identification bubbles imaged by different quantities of reflected light of the uniformly placed light sources, as shown in fig. 3 and 4:
the detected bubble detection object is statically placed in a specific area, the video camera and the light sources with specific quantity are placed on the same side of the detected bubble, the video camera is arranged right in front of the identified body 1, and the light sources with specific quantity are placed in front of the identified body 1 and form a certain included angle with the video camera.
When a specific number of light source switches are turned on, the bubbles of the object 1 are irradiated, and the camera images the object 1.
And carrying out binarization processing on the image through an algorithm, calculating the number of light sources, matching the number of the light sources with the number of specific light sources, and judging that the detected object has bubbles if the imaging number is consistent with the number of the specific light sources.
And calculating the size of the bubbles by calculating the size of a bright and dark area in the binary image.
The number of bubbles is calculated by dividing the number of bright areas in the statistical binarized image by the number of specific light sources.
And calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
3. The camera collects the quantity of the identification bubbles imaged by the reflected light rays of different distributed placement light sources, as shown in fig. 5 and 6;
the detected bubble detection object is statically placed in a specific area, the video camera and a specific number of light sources are placed on the same side of the detected bubble, the video camera is positioned in front of the identified body 1, and the distributed light sources are placed in front of the identified body 1 and form a certain included angle with the video camera.
And turning on a certain number of distributed light source switches, irradiating bubbles on the identified body 1, and imaging the identified body 1 by the camera.
And (3) carrying out binarization processing on the image by an algorithm, calculating the number of light sources and the plane spread bright spot distribution, matching with the number of specific light sources and the distribution mode, and judging that the detected object has bubbles if the imaging number is consistent with the bright spot distribution mode and the number of specific light sources is consistent with the distribution mode.
And calculating the size of the bubbles by calculating the size of a bright and dark area in the binary image.
The number of bubbles is calculated by dividing the number of bright areas in the statistical binarized image by the number of specific light sources.
And calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
4. The camera collects the corresponding quantity, shape and distribution condition of images formed by the reflected light rays of the distributed light sources with different quantities and different shapes to identify bubbles; as shown in fig. 7 and 8:
the detected bubble detection object is statically placed in a specific area, the video camera and the light sources with specific quantity and shape are placed on the same side of the detected bubble, the video camera is positioned right in front of the identified body 1, and the distributed light source is placed in front of the identified body 1 and forms a certain included angle with the video camera.
The specific number, shape and distributed light source switches are turned on, the bubbles of the object 1 are irradiated, and the camera images the object 1.
The imaging of the object 1 to be measured is automatically identified through a software algorithm by a PC controller 3 connected with the camera 2; the software algorithm can adopt binary morphology of an OSTU segmentation method and mathematical morphology;
carrying out binarization processing on the image shot by the camera 2, calculating the shape of a light source, matching the shape of the light source with the shape of the light source, and judging that the object to be measured has bubbles if the imaging shape is consistent with the shape of the light source; for example, point light source irradiation, bubble reflected light imaging is also a point, strip light source irradiation, and bubble reflected light imaging is also strip;
calculating the size of bubbles by calculating the size of a bright and dark area in a binary image;
calculating the number of bubbles by calculating and counting the number of bright areas in the binary image;
and calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
Specifically, identifying the special spectral feature image by adopting an OSTU segmentation method; the method specifically comprises the following steps: firstly, converting an image into a gray scale image; the number of pixels in the image, of which the gray value A is smaller than the threshold T, is H0, and the number of pixels of which the gray value A is larger than the threshold T is H1; recording the average gray value of H0 as H0 and the average gray value of H1 as H1 in the image with the image size of X X Y and the threshold value of T;
the probability that the pixel gray value is less than T is:
r0＝h0/(X*Y)；
the probability that the pixel gray value is greater than T is:
r1＝h1/(X*Y)；
h0+h1＝X*Y；
r0+r1＝1；
the average gray is multiplied by the probability and then added:
e＝r0*h0+r1*h1；
the between-class variance is:
d＝r0(h0-e)^2+r1(h1-e)^2；
d＝r0*r1(h0-h1)^2。
specifically, the binary morphology of the mathematical morphology includes a special spectral feature image recognition by a corrosion algorithm, a dilation algorithm or a dilation algorithm of gray scale morphology.
Examples
1. A spatial optical characteristic body for trapping bubbles by an optical technique;
adopting a bubble identification system; the bubble identification system comprises a camera 2, a light source and a back plate 10 with variable brightness; the back plate 10 is provided with an identified body 1; the camera 2 is connected with a PC controller 3; the light source is connected with an industrial personal computer; the light source is used for emitting a light source with a specific optical frequency, a specific light-emitting duration, a specific position and a specific shape; the light emitted by the light source is emitted to the identified body 1; the camera 2 is used for shooting the identified object 1; the PC controller 3 is used for collecting images and identifying the bubble space optical characteristics of the identified body 1;
and is carried out according to the following steps:
s1, collecting shape recognition bubbles imaged by reflected light rays of light sources with different shapes by a camera;
the method comprises the following steps of statically placing a detected bubble object in an area of a back plate 10, placing a camera 2 and a light source 4 on the same side of a detected bubble, placing the camera 2 right in front of an identified body 1, and placing the light source in front of the identified body 1 and forming a certain included angle with the camera 2;
s2, the lighting source is turned on and off, and the bubble of the object 1 is irradiated with light, and the object to be measured is imaged by the camera 2.
2. Identifying the special spectral feature image by a software algorithm:
based on an OSTU segmentation method, binary morphology and gray-scale morphology in mathematical morphology and other special algorithms, the identification function of numbers, letters, Chinese characters, images and foreign matters on the infusion bag image with multispectral characteristics is realized.
OSTU segmentation method:
the image is first converted to a grayscale image. The number of pixels in the image, of which the gray value A is smaller than the threshold T, is H0, and the number of pixels of which the gray value A is larger than the threshold T is H1; recording the average gray value of H0 as H0 and the average gray value of H1 as H1 in the image with the image size of X X Y and the threshold value of T;
the probability that the pixel gray value is less than T is:
r0＝h0/(X*Y)；
the probability that the pixel gray value is greater than T is:
r1＝h1/(X*Y)；
h0+h1＝X*Y；
r0+r1＝1；
the average gray is multiplied by the probability and then added:
e＝r0*h0+r1*h1；
the between-class variance is:
d＝r0(h0-e)^2+r1(h1-e)^2；
d＝r0*r1(h0-h1)^2
binary morphology of mathematical morphology
And (3) corrosion algorithm:
the method is simply understood as reducing the range of a target area, and the image boundary is contracted from the visual perception of the image; in practice, it is often used to eliminate noise or unwanted objects. The expression is as follows:
the expression is expressed as corroding the set A by the set B, namely, enabling B to move in A by a starting point and convolving with an overlapping area of A, and if the values at the position B and the position A are the same, outputting a result of 1, otherwise, outputting a result of 0. The flow chart of the binary morphological erosion algorithm is shown in fig. 12.
And (3) expansion algorithm:
simply comprehending that the range of a target area is enlarged, and the image boundary is expanded from the visual perception of the image; in practical application, the method is mainly used for filling the holes in the target area and eliminating small particle noise. The expression is as follows:
the above expression is expressed as using the set B to expand the set A, i.e. let B move in A with a starting point, and make convolution with the overlapping area of A, if the intersection of the values at the position B and the position A is not null, the output result is 1, otherwise, the output result is 0. The flow chart of the binary morphology inflation algorithm is shown in fig. 13.
Grayscale morphology of mathematical morphology
The image element is marked as A, the structural element is marked as B, and the area of the structural element covering the image is marked as C.
Etching of gray scale morphology:
simply understood as the operation of convolution, a small rectangle C formed by subtracting the structural element B from A is used, the minimum value in C is taken, and the minimum value is assigned to the origin corresponding to B. As shown in fig. 14, a gray scale morphological erosion algorithm flow chart.
Dilation algorithm for gray morphology:
simply understood as the operation of convolution, a small rectangle C formed by adding A and the structural element B is used, the maximum value in C is taken, and the original point corresponding to B is assigned. The gray scale morphological dilation algorithm flow chart shown in fig. 15.
And performing binarization processing on the image based on the algorithm, calculating the number of light sources and the distribution of the plane unfolded bright spots, matching the number of the light sources with the shape of a specific light source, and matching the number of the specific light sources with the distribution mode, wherein if the number, the shape and the distribution mode of the bright spots are consistent with those of the specific light sources, the detected object is judged to have bubbles.
And calculating the size of the bubbles by calculating the size of a bright and dark area in the binary image.
The number of bubbles is calculated by dividing the number of bright areas in the statistical binarized image by the number of specific light sources.
And calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
Claims (7)
1. A bubble identification method based on space optical characteristics is characterized in that a bubble identification system is adopted; the bubble identification system comprises a camera (2), a light source and a back plate (10) with variable brightness;
the back plate (10) is provided with an identified body (1); the camera (2) is connected with a PC controller (3); the light source is connected with an industrial personal computer; the light source is used for emitting a light source with a specific optical frequency, a specific light-emitting duration, a specific position and a specific shape; the light emitted by the light source is emitted to the identified object (1); the camera (2) is used for shooting an identified body (1); the PC controller (3) is used for collecting images and identifying the bubble space optical characteristics of the identified body (1);
and comprises the steps of:
s1, collecting shape recognition bubbles imaged by reflected light rays of light sources with different shapes by a camera;
the method comprises the following steps of statically placing a detected bubble detection object in an area of a back plate (10), placing a camera (2) and a light source (4) on the same side of a detected bubble, placing the camera (2) right in front of an identified body (1), and placing the light source in front of the identified body (1) and forming a certain included angle with the camera (2);
s2, lighting a light source switch, irradiating on the bubbles of the identified object (1), and imaging the detected object by the camera (2);
s3, automatically identifying the imaging of the measured object (1) through a software algorithm by a PC controller (3) connected with the camera (2); the software algorithm can adopt binary morphology of an OSTU segmentation method and mathematical morphology;
s4, carrying out binarization processing on the image shot by the camera (2), calculating the shape of a light source, matching the shape with the light source, and if the imaging shape is consistent with the shape of the light source, judging that the object to be measured has bubbles; for example, point light source irradiation, bubble reflected light imaging is also a point, strip light source irradiation, and bubble reflected light imaging is also strip;
s5, calculating the size of the bubbles by calculating the size of a light and dark area in the binary image;
calculating the number of bubbles by calculating and counting the number of bright areas in the binary image;
and calculating the disappearance time of the bright area in the binary image by continuous sampling and photographing, calculating the bubble dissipation time, and judging the material characteristics through the bubble dissipation time.
2. A method for identifying bubbles based on spatial optical characteristics according to claim 1, wherein: placing a predetermined number N of light sources in front of the identified object (1) in step S1; n is a natural number of 2 or more.
3. A method for identifying bubbles based on spatial optical characteristics according to claim 2, wherein: placing a predetermined number N of light sources in front of the identified object (1) in step S1; n is a natural number more than or equal to 2; and the light sources are arranged in a distributed manner.
4. A method as claimed in claim 3 for identifying bubbles based on spatial optical properties, wherein: the distribution mode can adopt uniform distribution along the circular arc.
5. A method for identifying bubbles based on spatial optical characteristics according to claim 4, characterized in that: the light sources emitted by the respective light sources have different shapes.
6. A method for identifying bubbles based on spatial optical characteristics according to claim 1, wherein: in step S3, identifying the special spectral feature image by using an OSTU segmentation method; the method specifically comprises the following steps: firstly, converting an image into a gray scale image; the number of pixels in the image, of which the gray value A is smaller than the threshold T, is H0, and the number of pixels of which the gray value A is larger than the threshold T is H1; recording the average gray value of H0 as H0 and the average gray value of H1 as H1 in the image with the image size of X X Y and the threshold value of T;
the probability that the pixel gray value is less than T is:
r0＝h0/(X*Y)；
the probability that the pixel gray value is greater than T is:
r1＝h1/(X*Y)；
h0+h1＝X*Y；
r0+r1＝1；
the average gray is multiplied by the probability and then added:
e＝r0*h0+r1*h1；
the between-class variance is:
d＝r0(h0-e)^2+r1(h1-e)^2；
d＝r0*r1(h0-h1)^2。
7. a method for identifying bubbles based on spatial optical characteristics according to claim 1, wherein: the binary morphology of the mathematical morphology comprises a corrosion algorithm, a swelling algorithm or a swelling algorithm of gray scale morphology for identifying the special spectral feature image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911148457.6A CN110969153A (en) | 2019-11-21 | 2019-11-21 | Bubble identification method based on space optical characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911148457.6A CN110969153A (en) | 2019-11-21 | 2019-11-21 | Bubble identification method based on space optical characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969153A true CN110969153A (en) | 2020-04-07 |
Family
ID=70031090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911148457.6A Pending CN110969153A (en) | 2019-11-21 | 2019-11-21 | Bubble identification method based on space optical characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969153A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114235809A (en) * | 2021-12-15 | 2022-03-25 | 上海交通大学 | Optical non-contact method for measuring large particles in pipeline |
| WO2023164809A1 (en) * | 2022-03-01 | 2023-09-07 | 京东方科技集团股份有限公司 | Bubble detection method and detection system for curved substrate |
| CN117333488A (en) * | 2023-12-01 | 2024-01-02 | 深圳市英迈通信技术有限公司 | Visual detection method and system for defects of mobile phone motherboard |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060119847A1 (en) * | 2002-09-10 | 2006-06-08 | Sapporo Breweries Limited | Method and instrument for measuring size of bubbles of malt alcohol beverage |
| CN108120392A (en) * | 2017-11-30 | 2018-06-05 | 东南大学 | Bubble three-dimension measuring system and method in biphase gas and liquid flow |
-
2019
- 2019-11-21 CN CN201911148457.6A patent/CN110969153A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060119847A1 (en) * | 2002-09-10 | 2006-06-08 | Sapporo Breweries Limited | Method and instrument for measuring size of bubbles of malt alcohol beverage |
| CN108120392A (en) * | 2017-11-30 | 2018-06-05 | 东南大学 | Bubble three-dimension measuring system and method in biphase gas and liquid flow |
Non-Patent Citations (3)
| Title |
|---|
| 周博文等: "基于机器视觉的酒液智能检测系统研究与开发", 《中国机械工程》 * |
| 康乐等: "液体泡沫中单气泡的图像识别算法", 《渤海大学学报(自然科学版)》 * |
| 朱秀昌等: "《数字图像处理与图像信息》", 30 August 2016, 北京邮电大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114235809A (en) * | 2021-12-15 | 2022-03-25 | 上海交通大学 | Optical non-contact method for measuring large particles in pipeline |
| WO2023164809A1 (en) * | 2022-03-01 | 2023-09-07 | 京东方科技集团股份有限公司 | Bubble detection method and detection system for curved substrate |
| CN117333488A (en) * | 2023-12-01 | 2024-01-02 | 深圳市英迈通信技术有限公司 | Visual detection method and system for defects of mobile phone motherboard |
| CN117333488B (en) * | 2023-12-01 | 2024-03-08 | 深圳市英迈通信技术有限公司 | Visual detection method and system for defects of mobile phone motherboard |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969153A (en) | Bubble identification method based on space optical characteristics | |
| CN110389127B (en) | System and method for identifying metal ceramic parts and detecting surface defects | |
| Zhou et al. | Automated visual inspection of glass bottle bottom with saliency detection and template matching | |
| CN108229561B (en) | Particle product defect detection method based on deep learning | |
| Liu et al. | Automatic detection technology of surface defects on plastic products based on machine vision | |
| CN101566582B (en) | Medicine bottle label information online detection system in powder injection production based on mechanical vision | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN114119526A (en) | Steel plate surface defect detection and identification system and method based on machine vision | |
| US11747284B2 (en) | Apparatus for optimizing inspection of exterior of target object and method thereof | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN111239142A (en) | Paste appearance defect detection device and method | |
| CN111879735B (en) | Rice appearance quality detection method based on image | |
| CN110763600A (en) | Real-time online detection device for suspended particles | |
| Ebrahimi et al. | Detection of greening in potatoes using image processing techniques | |
| CN116091505B (en) | Automatic defect detection and classification method and system for sapphire substrate | |
| US11047807B2 (en) | Defect detection | |
| CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
| US6382510B1 (en) | Automatic inspection system using barcode localization and method thereof | |
| CN114450711A (en) | Workpiece surface defect detection device and detection method, workpiece surface inspection system, and program | |
| CN107545565B (en) | Solar screen plate detection method | |
| CN109785290A (en) | Normalized steel plate defect detection method is shone based on local light | |
| JP7282894B2 (en) | particle quantifier | |
| Ghosh et al. | A low cost data acquisition system from digital display instruments employing image processing technique | |
| Park et al. | REAL‐TIME DUAL‐WAVELENGTH IMAGE PROCESSING FOR POULTRY SAFETY INSPECTION 1 | |
| CN116237266A (en) | Flange size measuring method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200407 |