CN111899146A - MATLAB engine spray image automatic screening method - Google Patents
MATLAB engine spray image automatic screening method Download PDFInfo
- Publication number
- CN111899146A CN111899146A CN202010773227.5A CN202010773227A CN111899146A CN 111899146 A CN111899146 A CN 111899146A CN 202010773227 A CN202010773227 A CN 202010773227A CN 111899146 A CN111899146 A CN 111899146A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- component
- value
- screening
- 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
- 238000012216 screening Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000007921 spray Substances 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 20
- 239000002245 particle Substances 0.000 claims description 60
- 238000009826 distribution Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000011161 development Methods 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 3
- 239000000295 fuel oil Substances 0.000 description 3
- 238000000889 atomisation Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of data processing, and discloses an automatic screening method of engine spray images based on MATLAB, which comprises the steps of image digitization, preliminary screening, final screening, graphical user interface GUI (graphical user interface) creation and the like. The MATLAB engine spray image-based automatic screening method provided by the invention realizes automatic screening of images, improves screening efficiency and accuracy, and is convenient to operate. The invention is suitable for automatic screening of engine spray images.
Description
Technical Field
The invention belongs to the technical field of data processing, and relates to an image screening method, in particular to an automatic screening method based on MATLAB engine spray images.
Background
Facing the increasingly pressing energy and environmental crisis, internal combustion engines face significant challenges in terms of economy and emissions. The spraying is a key ring of the combustion process for the engine, and the atomization effect of the fuel oil has a decisive role in the economy, the dynamic property, the emission property and the like of the engine.
A large number of fuel oil spray images can be obtained through an engine spray test, few and few images capable of truly reflecting the fuel oil atomization condition exist, a large amount of time is spent on workers through manual screening of the images, and due to the fact that judgment standards among people are different, the judgment of the images is deviated, and image screening is inaccurate. Therefore, how to realize automatic screening of engine spray images is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide an automatic screening method based on MATLAB engine spray images, so as to improve the efficiency and accuracy of image screening.
In order to achieve the purpose, the technical method comprises the following steps:
an automatic screening method based on MATLAB engine spray images is carried out according to the following steps:
(I) image digitization
Sampling the image, and then quantizing to obtain a digital image;
(II) preliminary screening
a1) Carrying out gray processing on the digital image to obtain a gray image;
a2) drawing a gray level histogram of the gray level image, counting a gray level peak value of each gray level interval and a peak value digit corresponding to the gray level peak value, and screening out an overexposed image and an underexposed image according to an interval where the peak value of the image gray level histogram is located;
a3) calculating the absolute value of the difference between the integral average gray value and the local average gray value of the gray map, and screening out images with uneven brightness according to an artificially set absolute value threshold;
a4) calculating the average gray gradient of the gray image, and screening out trailing blurred images according to an artificially set average gray gradient threshold;
(III) Final screening
b1) Carrying out binarization processing on the gray-scale image after denoising processing to obtain a binary image;
b2) counting the number of particles in the binary image, and screening out the images without particles or with few particles according to a manually set particle number threshold;
b3) carrying out region division on the binary image, counting the number of particles in each region after the division, calculating the standard deviation of the number of particles in each region in the binary image, and screening out the image with non-uniform particle distribution according to a manually set standard deviation threshold;
(IV) creating a Graphical User Interface (GUI).
As a limitation: the sampling method in the step (one) comprises the following steps: scanning along the vertical direction to obtain a pixel value one-dimensional scanning line of each line of the image, and then scanning the pixel value one-dimensional scanning line of each line along the horizontal direction to obtain pixel points;
the quantization method comprises the following steps: the pixel point value range of the image is divided into intervals, and the pixel value distribution is in [ f [ ]i-1,fi]The quantized value of the pixel points in the interval is fsiThe distribution of pixel values falls on [ f ]j-1,fj]The quantized value of the pixel points in the interval is fsjAnd (i, j) is the coordinate of the pixel point in the matrix after the image is digitized, and f (i, j) is the pixel value on the corresponding pixel point.
As a further limitation: calling an rgb2gray function in the graying processing of the digital image in the step (two) a 1); drawing and calling an imhist function by using a gray histogram of the gray map in the step (II) a2), and calling a findpeaks function by using statistics of a gray peak value of each gray interval and a peak value digit corresponding to the gray peak value; in the step (two), calculating the absolute value of the difference between the integral average gray value and the local average gray value of the gray map in the step (a 3) and calling a mean function; the calculation formula of the average gradient of the image gray scale in the step (two) a4) is
Where GMG represents the average gradient value of the gray scale map, f is the pixel value of the gray scale map, and (i, j) is the imageThe coordinates of the pixel points in the matrix, M and N, are the number of pixels in the rows and columns of the gray scale image.
As yet a further limitation: b1) in the step (III), the grayscale image denoising processing adopts a median filtering method, a medfilt2 function is called, the grayscale image binarization processing calls a graythresh function to obtain a global threshold value of the grayscale image, and an im2bw function is called to convert the grayscale image into a binary image; b2) in the step (three), calling a bwlabel function by counting the number of particles in the binary image; calling a bwleabel function in the step (three) b3) to count the number of particles in each region after the partition, and calling an std function to calculate the standard deviation of the number of particles in each region of the binary image.
As a final definition: creating a graphical user interface GUI by adopting an M file or a graphical user interface development tool GUIDE, wherein the specific method comprises the following steps:
c1) drawing an interface sketch according to the step (I), the step (II) and the step (III);
c2) adding an original image component, an overexposure component, an underexposure component, a brightness unevenness component and a deblurring component in the primary screening according to the interface sketch, and adding a component with a higher particle number and a component with uniform particle distribution in the final screening;
c3) writing the program code of each component and running the viewing effect;
c4) debugging the program, detecting and modifying the program, and finishing the creation of the GUI.
Due to the adoption of the scheme, compared with the prior art, the invention has the beneficial effects that:
(1) according to the MATLAB-based engine spray image automatic screening method, the images are automatically screened based on the MATLAB, manual screening is not needed, and screening efficiency and accuracy are improved;
(2) the MATLAB engine spray-based image automatic screening method provided by the invention has the advantages that firstly, the image is subjected to digital processing, and the image is converted into a digital image, so that the subsequent processing and screening are facilitated; according to the MATLAB engine spray image-based automatic screening method, the images are subjected to primary screening and final screening, so that the finally obtained images are more accurate; according to the MATLAB engine spray image-based automatic screening method, a Graphical User Interface (GUI) is created, and the operation is convenient;
(3) according to the MATLAB engine spray image-based automatic screening method, the digital image is subjected to gray level processing in primary screening, so that the calculation time is shortened, and the workload of a computer is reduced; a findpeaks function is called to directly calculate the peak value and the peak value digit, manual judgment is not needed, and convenience and rapidness are achieved; the tailing blurred image is screened by adopting an average gradient algorithm, so that the operation time is short; and the graythresh function is called to calculate the threshold, so that the processing speed is high and the processing effect is good.
In conclusion, the MATLAB engine spray image-based automatic screening method provided by the invention realizes automatic screening of images, improves screening efficiency and accuracy, and is convenient to operate.
The invention is suitable for automatic screening of engine spray images.
Drawings
The invention is described in further detail below with reference to the figures and the embodiments.
FIG. 1 is a flow chart of a primary screening process according to an embodiment of the present invention;
FIG. 2 is a flow chart of a final screening process according to an embodiment of the present invention;
FIG. 3 is a spray image before screening according to an embodiment of the present invention;
FIG. 4 is a spray image after screening according to an embodiment of the present invention;
FIG. 5 is a graphical user interface of an embodiment of the present invention.
Detailed Description
The present invention is further described with reference to the following examples, but it should be understood by those skilled in the art that the present invention is not limited to the following examples, and any modifications and equivalent changes based on the specific examples of the present invention are within the scope of the claims of the present invention.
Embodiment is based on MATLAB engine spray image automatic screening method
An automatic screening method based on MATLAB engine spray images is carried out according to the following steps:
(I) image digitization
Firstly, sampling an image, wherein the sampling method comprises the steps of firstly scanning the image from top to bottom along the vertical direction to obtain a pixel value one-dimensional scanning line of each line of the image, and then scanning the pixel value one-dimensional scanning line of each line from left to right along the horizontal direction to obtain pixel points; and then carrying out quantization, wherein the quantization method is to divide the value range of the pixel points of the image into intervals, all values in each interval are replaced by a numerical value, and the distribution of the pixel values is in [ fi-1,fi]The quantized value of the pixel points in the interval is fsi(ii) a Sampling and quantizing each image to obtain a digital matrix, wherein the digital matrix is data of a two-dimensional structure, the row coordinate is i, the column coordinate is j, (i, j) is the coordinate of a pixel point in the digitized image matrix, and f (i, j) is the pixel value of the corresponding pixel point;
(II) preliminary screening
a1) Image graying treatment: the image is an RGB mode color image with the bit depth of 24, is converted into a gray scale image with the bit depth of 8, calls the RGB2gray function in MATLAB, and calls the format of
I＝rgb2gray(RGB)
Wherein, I is a gray scale image after conversion;
a2) calling an imhist function in MATLAB to draw a gray level histogram of a gray level map, wherein the calling format is
h＝imhist(I,b)
Wherein b is the number of grey levels of the histogram, and h is the grey histogram of the grey map;
calling a findpeaks function in MATLAB to count the gray peak value of each gray interval and the corresponding peak value digit, wherein the calling format of the findpeaks function is
[pks,locs]＝findpeaks(h)
In the formula, pks is the peak value, locs is the peak value digit;
the gray histogram is a function of image gray level distribution, reflects the frequency of the occurrence of the gray value of an image, is the most basic statistical characteristic, the overall brightness of the spray image with overexposure is bright, the overall gray value is large, and the peak value of the gray histogram is distributed between the intervals [130,255 ]; the luminance of the spray image which is not exposed enough is dark, the integral gray value is small, and the peak value of the gray histogram is distributed between the intervals [0,60 ]; the spray image with reasonable exposure has moderate brightness, the integral gray value is centered, and the peak value of the gray histogram is distributed between the intervals [60,130 ];
screening out overexposed and underexposed images according to the interval of the peak value of the image gray level histogram, and carrying out next screening;
a3) calling a mean function in MATLAB to calculate the absolute value of the difference between the overall average gray value and the local average gray value of the gray map, wherein the calculation formula is
Tag＝|mean(I)-mean(I')|
Where mean (I) is the global mean gray value, mean (I') is the local mean gray value, M and N are the number of pixels in the rows and columns of the gray scale map, aijThe gray value of the pixel point (i, j) is shown, and Tag represents the absolute value of the difference between the overall average gray value and the local average gray value of the gray map;
the AGV is the integral average gray value of the gray map and reflects the integral brightness, and the LAGV is the local average gray value of the gray map and reflects the local brightness;
after the absolute value of the difference between the integral average gray value and the local average gray value of the gray image is calculated, screening out the image with uneven brightness according to an artificially set absolute value threshold value 19, when the obtained Tag is more than 19, screening out the image, and carrying out the next screening;
a4) the gradient calculation formula of the gray scale image is
G(x,y)＝dx(i)+dy(j)
Wherein dx (i, j) ═ f (i +1, j) -f (i, j), dy (i, j) ═ f (i, j +1) -f (i, j), where G (x, y) is the image gradient;
the calculation formula of the gray level average gradient of the gray level map is
Wherein GMG represents an average gradient value of the gray scale map;
the average gradient is the gray scale change rate, which represents the gray scale change difference of the gray scale image at a certain pixel point and reflects the difference of the tiny detail contrast change of the gray scale image, the change rate can reflect the image definition, and the higher the quality of the image is, the larger the average degree of the gray scale change is;
screening out trailing blurred images according to an artificially set gray average gradient threshold 1.6777, and when the gray average gradient value of the gray image is smaller than a gray average gradient threshold 1.6777, screening out the images and carrying out next screening, wherein the gray change rate of the gray image is small, and the image blur does not meet the requirement;
(III) Final screening
b1) The method for denoising the gray-scale image by adopting a median filtering method can eliminate the influence of bubbles in the gray-scale image and keep the definition of particle edges, lays a foundation for subsequent screening, calls a medfilt2 function to carry out median filtering, and has a calling format of
K＝medfilt2(I,[m,n])
In the formula, K is a denoised gray scale image, and [ m n ] represents that the size of the adopted template is mxn;
in order to facilitate the statistics of the number of particles and the judgment of the distribution uniformity of the particles, the image needs to be converted into a binary image, a graythresh function is called to obtain a global threshold of the image, and the calling format is
[E,M]＝graythresh(K)
Where E is a global threshold for K, and M represents a measure of validity;
calling an im2bw function to convert the denoised gray scale image into a binary image in a calling format
W＝im2bw(K,E)
In the formula, W is a binary image;
b2) the highlight of the binary image is the particle to be counted, the number of the particles in the binary image is counted by calling a bwlabel function, and the calling format is
[L,NUM]＝bwlabel(W,n)
Where L is a matrix indicating the same size as W, NUM is the number of particles, and the value of n may be 4 or 8, where n is 4, a four-way seek is indicated, the adjacent positions are upper, lower, left, and right of the corresponding pixel point position, and n is 8, an eight-way seek is indicated, the adjacent positions are upper, lower, left, right, upper left, upper right, lower left, and lower right of the corresponding pixel point position, and the value of n in this embodiment is 8;
screening out images without particles or with few particles according to a manually set particle number threshold value 4000, screening out the images with few particles or without particles when the particles in the binary image are smaller than the particle number threshold value 4000, and carrying out the next screening;
b3) performing region division on the binary image by adopting a3 x 3 division method, wherein particles in each region are sample data, and all the particles in the binary image become a sample set;
counting the number of particles in each divided region, wherein the change of the number of particles in each region reflects the particle distribution condition of different regions of the binary image, and calling a bwleael function to count the number of particles in each divided region;
establishing standard deviation, also called mean square error, of binary image particles, wherein the standard deviation is a common tool for reflecting data discrete degree, calling std function to calculate the standard deviation of the number of particles in each region of the binary image, and the calling format is
s＝std(X)
The function command can not directly calculate the integral standard deviation of the matrix, only the standard deviation of each row or each column of elements can be returned, the standard deviation of each column of elements is returned under the default condition, and the standard deviation distribution is obtained through a large amount of statistical analysis, wherein X is a sample set of all particles, and s is the standard deviation of the number of particles in each area of the binary image;
screening out two groups of data with the same average number and non-uniform particle distribution according to a manually set standard deviation threshold 220, wherein the standard deviation is not necessarily the same, the smaller the standard deviation or variance is, the more uniform the distribution of the characteristic points is, and when the standard deviation of the particle number of the binary image is greater than the standard deviation threshold 220, the non-uniform particle distribution of the image is screened out, and the next operation is carried out;
(IV) creating a Graphical User Interface (GUI).
The method for creating the GUI by adopting the M file or the GUIDE comprises the following specific steps:
c1) drawing an interface sketch according to the step (I), the step (II) and the step (III);
c2) adding an original image component, an overexposure component, an underexposure component, a brightness unevenness component and a deblurring component in the primary screening according to the interface sketch, and adding a component with a higher particle number and a component with uniform particle distribution in the final screening;
c3) writing the program code of each component and running the viewing effect;
c4) debugging the program, detecting and modifying the program, and completing the creation of the graphical user interface GUI, wherein the created graphical user interface GUI is shown in FIG. 5.
In this embodiment, a spray image before screening is selected, as shown in fig. 3; selecting a screened spray image, as shown in fig. 4, wherein the screened spray image has moderate exposure, uniform and clear brightness, large particle number and uniform distribution compared with the spray image before screening.
Claims (8)
1. An automatic screening method of engine spray images based on MATLAB is characterized by comprising the following steps:
(I) image digitization
Sampling the image, and then quantizing to obtain a digital image;
(II) preliminary screening
a1) Carrying out gray processing on the digital image to obtain a gray image;
a2) drawing a gray level histogram of the gray level image, counting a gray level peak value of each gray level interval and a peak value digit corresponding to the gray level peak value, and screening out an overexposed image and an underexposed image according to an interval where the peak value of the image gray level histogram is located;
a3) calculating the absolute value of the difference between the integral average gray value and the local average gray value of the gray map, and screening out images with uneven brightness according to an artificially set absolute value threshold;
a4) calculating the average gray gradient of the gray image, and screening out trailing blurred images according to an artificially set average gray gradient threshold;
(III) Final screening
b1) Carrying out binarization processing on the gray-scale image after denoising processing to obtain a binary image;
b2) counting the number of particles in the binary image, and screening out the images without particles or with few particles according to a manually set particle number threshold;
b3) carrying out region division on the binary image, counting the number of particles in each region after the division, calculating the standard deviation of the number of particles in each region in the binary image, and screening out the image with non-uniform particle distribution according to a manually set standard deviation threshold;
(IV) creating a Graphical User Interface (GUI).
2. The MATLAB-based engine spray image autofilter method of claim 1, wherein the sampling method in step (one): scanning along the vertical direction to obtain a pixel value one-dimensional scanning line of each line of the image, and then scanning the pixel value one-dimensional scanning line of each line along the horizontal direction to obtain pixel points;
the quantization method comprises the following steps: the pixel point value range of the image is divided into intervals, and the pixel value distribution is in [ f [ ]i-1,fi]The quantized value of the pixel points in the interval is fsiThe distribution of pixel values falls on [ f ]j-1,fj]The quantized value of the pixel points in the interval is fsjAnd (i, j) is the coordinate of the pixel point in the matrix after the image is digitized, and f (i, j) is the pixel value on the corresponding pixel point.
3. The MATLAB-based engine spray image autofilter method according to claim 1 or 2, characterized in that the graying process of the digitized image in a1) of step (two) calls the rgb2gray function; the gray scale histogram of the gray scale map in step (ii) a2)Drawing and calling an imhist function, and calling a findpeaks function by statistics of the gray peak value of each gray interval and the corresponding peak value digit; in the step (two), calculating the absolute value of the difference between the integral average gray value and the local average gray value of the gray map in the step (a 3) and calling a mean function; the calculation formula of the average gradient of the image gray scale in the step (two) a4) is
Where GMG represents the average gradient value of the gray scale image, f is the pixel value of the gray scale image, (i, j) is the coordinate of the pixel in the matrix, and M and N are the number of pixels in the rows and columns of the gray scale image.
4. The MATLAB engine spray image automatic screening method based on claim 1 or 2, characterized in that, in step (three), the grayscale map denoising processing in step (b 1) adopts a median filtering method, a medfilt2 function is called, the grayscale map binarization processing calls a gradythresh function to obtain a global threshold value of the grayscale map, and an im2bw function is called to convert the grayscale map into a binary map; b2) in the step (three), calling a bwlabel function by counting the number of particles in the binary image; calling a bwleabel function in the step (three) b3) to count the number of particles in each region after the partition, and calling an std function to calculate the standard deviation of the number of particles in each region of the binary image.
5. The MATLAB engine spray image automatic screening method as claimed in claim 3, characterized in that, in step (three), the grayscale map denoising processing in b1) adopts a median filtering method, a medfilt2 function is called, the grayscale map binarization processing calls a graythresh function to obtain the global threshold value of the grayscale map, and im2bw function is called to convert the grayscale map into a binary map; b2) in the step (three), calling a bwlabel function by counting the number of particles in the binary image; calling a bwleabel function in the step (three) b3) to count the number of particles in each region after the partition, and calling an std function to calculate the standard deviation of the number of particles in each region of the binary image.
6. The MATLAB engine spray image-based automatic screening method according to any one of claims 1, 2 and 5, characterized in that the graphical user interface GUI created in step (IV) is implemented by using M file or using GUI development tool GUIDE, and the specific method is as follows:
c1) drawing an interface sketch according to the step (I), the step (II) and the step (III);
c2) adding an original image component, an overexposure component, an underexposure component, a brightness unevenness component and a deblurring component in the primary screening according to the interface sketch, and adding a component with a higher particle number and a component with uniform particle distribution in the final screening;
c3) writing the program code of each component and running the viewing effect;
c4) debugging the program, detecting and modifying the program, and finishing the creation of the GUI.
7. The MATLAB engine spray image-based automatic screening method according to claim 3, characterized in that the graphical user interface GUI created in step (four) is implemented using M files or using a graphical user interface development tool GUIDE, and the specific method is as follows:
c1) drawing an interface sketch according to the step (I), the step (II) and the step (III);
c2) adding an original image component, an overexposure component, an underexposure component, a brightness unevenness component and a deblurring component in the primary screening according to the interface sketch, and adding a component with a higher particle number and a component with uniform particle distribution in the final screening;
c3) writing the program code of each component and running the viewing effect;
c4) debugging the program, detecting and modifying the program, and finishing the creation of the GUI.
8. The MATLAB engine spray image-based automatic screening method according to claim 4, characterized in that the graphical user interface GUI created in step (four) is implemented using M files or using a graphical user interface development tool GUIDE, and the specific method is as follows:
c1) drawing an interface sketch according to the step (I), the step (II) and the step (III);
c2) adding an original image component, an overexposure component, an underexposure component, a brightness unevenness component and a deblurring component in the primary screening according to the interface sketch, and adding a component with a higher particle number and a component with uniform particle distribution in the final screening;
c3) writing the program code of each component and running the viewing effect;
c4) debugging the program, detecting and modifying the program, and finishing the creation of the GUI.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010773227.5A CN111899146A (en) | 2020-08-04 | 2020-08-04 | MATLAB engine spray image automatic screening method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010773227.5A CN111899146A (en) | 2020-08-04 | 2020-08-04 | MATLAB engine spray image automatic screening method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111899146A true CN111899146A (en) | 2020-11-06 |
Family
ID=73184034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010773227.5A Pending CN111899146A (en) | 2020-08-04 | 2020-08-04 | MATLAB engine spray image automatic screening method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111899146A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019014810A1 (en) * | 2017-07-17 | 2019-01-24 | 深圳市大疆创新科技有限公司 | Image processing method and device, and intelligent terminal |
| WO2019041842A1 (en) * | 2017-08-28 | 2019-03-07 | 京东方科技集团股份有限公司 | Image processing method and device, storage medium and computer device |
| CN109816678A (en) * | 2019-02-27 | 2019-05-28 | 青岛伴星智能科技有限公司 | A kind of the nozzle atomization angle automatic checkout system and method for view-based access control model |
| CN110245626A (en) * | 2019-06-19 | 2019-09-17 | 北京万里红科技股份有限公司 | A method of accurately detecting eyelash image in iris image |
-
2020
- 2020-08-04 CN CN202010773227.5A patent/CN111899146A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019014810A1 (en) * | 2017-07-17 | 2019-01-24 | 深圳市大疆创新科技有限公司 | Image processing method and device, and intelligent terminal |
| WO2019041842A1 (en) * | 2017-08-28 | 2019-03-07 | 京东方科技集团股份有限公司 | Image processing method and device, storage medium and computer device |
| CN109816678A (en) * | 2019-02-27 | 2019-05-28 | 青岛伴星智能科技有限公司 | A kind of the nozzle atomization angle automatic checkout system and method for view-based access control model |
| CN110245626A (en) * | 2019-06-19 | 2019-09-17 | 北京万里红科技股份有限公司 | A method of accurately detecting eyelash image in iris image |
Non-Patent Citations (1)
| Title |
|---|
| 曹福来;刘怡杉;张亚赠;楚慧闯;娄金辉;: "基于matlab的发动机喷雾图像筛选程序设计", 科技创新与应用, no. 15, pages 2 - 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109978839B (en) | Method for detecting wafer low-texture defects | |
| CN110264466A (en) | A kind of reinforcing bar detection method based on depth convolutional neural networks | |
| CN101710425B (en) | Self-adaptive pre-segmentation method based on gray scale and gradient of image and gray scale statistic histogram | |
| CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
| CN111354047B (en) | Computer vision-based camera module positioning method and system | |
| CN115760826B (en) | Bearing wear condition diagnosis method based on image processing | |
| CN114882040B (en) | Sewage treatment detection method based on template matching | |
| Srinivas et al. | Remote sensing image segmentation using OTSU algorithm | |
| CN114913138A (en) | Method and system for detecting defects of pad printing machine product based on artificial intelligence | |
| CN109389569A (en) | Based on the real-time defogging method of monitor video for improving DehazeNet | |
| CN114985150B (en) | Visual perception-based control method for accurate spraying of spraying machine | |
| CN115170570A (en) | Fabric fuzzing and pilling detection method based on gray level run-length matrix | |
| CN114677340B (en) | Concrete surface roughness detection method based on image edge | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| CN114219773A (en) | Pre-screening and calibration method for bridge crack detection data set | |
| CN110909772B (en) | High-precision real-time multi-scale dial pointer detection method and system | |
| CN109543686A (en) | Character recognition based on adaptive multi-thresholding pre-processes binarization method | |
| CN101799920A (en) | Tongue picture analysis method based on colour feature and application thereof | |
| CN111899146A (en) | MATLAB engine spray image automatic screening method | |
| TWI498830B (en) | A method and system for license plate recognition under non-uniform illumination | |
| CN112345548A (en) | Method and device for detecting surface forming smoothness of graphite plate of fuel cell | |
| CN111738984A (en) | Skin image spot evaluation method and system based on watershed and seed filling | |
| CN116740375A (en) | Image feature extraction method, system and medium | |
| CN115760825A (en) | Rammed earth wall apparent crack intelligent detection system | |
| CN115187788A (en) | Crop seed automatic counting method based on machine vision |
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 |