CN113160098A - Processing method of dense particle image under condition of uneven illumination - Google Patents
Processing method of dense particle image under condition of uneven illumination Download PDFInfo
- Publication number
- CN113160098A CN113160098A CN202110414176.1A CN202110414176A CN113160098A CN 113160098 A CN113160098 A CN 113160098A CN 202110414176 A CN202110414176 A CN 202110414176A CN 113160098 A CN113160098 A CN 113160098A
- Authority
- CN
- China
- Prior art keywords
- image
- column
- processing
- line
- histogram equalization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002245 particle Substances 0.000 title claims abstract description 84
- 238000005286 illumination Methods 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000005315 distribution function Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 239000011859 microparticle Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002209 hydrophobic effect Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
Images
Classifications
-
- 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
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T7/155—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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a processing method of a dense particle image under the condition of uneven illumination, belonging to the technical field of image processing. The method comprises the following steps: 1) extracting an uneven background generated by uneven illumination in the image; 2) removing uneven background in the image; 3) judging whether a nozzle exists in the image or not; if not, executing the step 4); if yes, executing step 5); 4) carrying out histogram equalization processing on the image column by column; 5) firstly, carrying out sectional histogram equalization processing on the row where the nozzle is positioned, and then carrying out histogram equalization on other rows; 6) and carrying out binarization processing on the image line by line. Column-by-column histogram equalization and line-by-line binarization are carried out on the image, and the spout part is processed independently, so that the influence of uneven illumination on particles and background brightness is eliminated, and the particles with different light and shade are completely identified. Dense particles are further distinguished one by one, and good visual effect and authenticity are achieved. The method is very effective in identifying dense particles under the condition of uneven lighting.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a processing method of a dense particle image under the condition of uneven illumination.
Background
Dense particles are widely present in human production and living environments. On the one hand, particles such as dust in the atmosphere, smoke discharged from a chimney, suspended particles in water and the like have adverse effects on us, and it is desirable to monitor the concentration, the particle size, the distribution and the like of the particles so as to judge the environmental quality. On the other hand, some particles play an important role, such as the need to characterize the water flow rate by measuring the trace particle speed, the need to make the metal material into a certain shape, size powder for easy filling, etc.
In order to achieve the purposes, particle images are collected and then image processing, particle identification and parameter measurement are carried out, so that the method is the most intuitive and accurate method.
With the development of science and technology, digital image processing technology has played an increasingly important role in various industries, and has also become an important means for detecting particles. However, because the absorption and reflection performance of the object to be shot on light rays are different, the phenomenon of uneven illumination often occurs during image acquisition, so that the brightness of an image is reduced along with the increase of the distance from a light source; in addition, the illumination can generate shadow, bright spots and the like, and the quality of the picture is seriously influenced. Especially for densely distributed particle images, the general background segmentation algorithm cannot directly and thoroughly separate the gray scales of the particles of the whole image from the background, and when binarization is performed later, the particles with weak illumination cannot be extracted together with the particles with strong illumination, so that the detection accuracy is reduced.
Most of the existing image enhancement algorithms with uneven illumination aim at large-scale images [1], [2], [3] or images [4] with small scale but clear original boundaries, and the details of the images can be seen by naked eyes before processing, so most of information of the images can be restored only by eliminating uneven backgrounds. However, for dense particles, the size of the image represented by the particles is small, and some particles even occupy only one pixel point, so that a clear outline cannot be found. Secondly, the dense representation of the particles is large in number, and the uneven brightness is more likely to occur, and it is difficult to identify bright particles together with dim particles. The dense density also means that particles in some areas are connected into one piece, and the particles need to be separated one by one when being identified. In some particle identification algorithms [5], the particle brightness is uniform and regular, the particles can be identified by a simple algorithm, and the dense particle identification with uneven illumination has no great reference significance. The existing correction algorithm [6] for uneven illumination particle images has poor effect, and cannot ensure that dense particles under the condition of uneven illumination are completely identified.
[1] A human face image acquisition method under the condition of non-uniform illumination;
[2] a processing method for eliminating uneven illumination of face images;
[3] a filtering algorithm for hydrophobic image uneven illumination;
[4] a correction method for uneven brightness of microcosmic oil displacement experiment images;
[5]《Image analysis algorithm for detection and measurement of Martian sand grains》；
[6] a method for correcting an image of a particle with uneven illumination.
Disclosure of Invention
The invention aims to provide a processing method of a dense particle image under the condition of uneven illumination, which on one hand eliminates the influence of uneven illumination on the image background, on the other hand, enables dense particles at different positions to be effectively identified, and has important significance for the detection and research of particles.
In order to achieve the above object, the method for processing dense particle images under uneven illumination conditions provided by the present invention comprises the following steps:
1) extracting an uneven background generated by uneven illumination in the image;
2) removing uneven background in the image;
3) judging whether a spout exists in the image, wherein the spout is a white area of the original extracted image; if not, executing the step 4); if yes, executing step 5);
4) carrying out histogram equalization processing on the image column by column;
5) firstly, carrying out sectional histogram equalization processing on the row where the nozzle is positioned, and then carrying out histogram equalization on other rows;
6) carrying out binarization processing on the image line by line;
7) and obtaining a final image.
In the technical scheme, column-by-column histogram equalization and line-by-line binarization are performed on the image, and the spout part is processed independently, so that the influence of uneven illumination on particles and background brightness is eliminated, and the particles with different light and shade are completely identified. In addition, dense particles are distinguished one by one, and good visual effect and authenticity are achieved. The method is very effective in identifying dense particles under the condition of uneven lighting.
Specifically, in step 1), an opening operation in the morphological processing is adopted, firstly, a flat disc structure element with a certain radius is created according to the property of the image, and then the element is used for expanding and then corroding the original image to obtain a smooth and uneven image background.
Specifically, in step 2), the gray-scale matrix I of the image after the background is removed3＝I1-I2Wherein, I1Is a gray-scale matrix of the original image, I2Is a gray scale matrix of the non-uniform background image.
Specifically, in step 4), histogram equalization processing is performed on the image of a × m pixels column by columnWhile, for each column Sk(k ═ 0, 1.. times, a), the probability that each gray level occupies m pixels of the column can be found:
pi＝ni/m(i＝0,1,...,255)
wherein n isiIs the number of pixels in the column for gray level i;
thereby obtaining a gray level distribution vector P for the columnk1＝(p0,p1,...,p255) (ii) a Then to Pk1Transforming to obtain new gray level distribution vector Pk2＝(p0’,p1’,...,p255’)，Pk2Namely, the gray level distribution vector after histogram equalization:
Pk2＝Pk1·T
where T is a 256x256 transformation matrix, resulting in a new gray level distribution vector Pk2The difference between each adjacent element is reduced;
converting the probability distribution into the number of each gray level:
ni’＝pi’*m(i＝0,1,...,255)
then based on the new gray level distribution vector Pk2Redistributing pixel value to each element on the column to obtain column vector S after histogram equalizationk', noted:
Sk’＝f(Sk)。
specifically, in step 5), performing segmented histogram equalization processing on the column where the nozzles are located includes:
firstly, finding a column vector where the nozzle is located: judging pixels in each column vector, finding out pixel points where the nozzles are located, and dividing the whole column vector into 2 parts, namely a non-nozzle area and a nozzle area;
and then, the spout area is assigned to be 255, and histogram equalization is carried out on the non-spout area to obtain a new column vector.
Specifically, in step 5), the method used in step 4) is adopted when histogram equalization processing is performed on the other columns.
Specifically, in step 6), the graph is alignedWhen the image is binarized line by line, for a pixel points of each line in the lines not containing the nozzle, the probability p of each gray level in the line can be obtainedi：
pi＝ni/a(i＝0,1,...,255)
Wherein n isiIs the number of pixels in the row for gray level i;
further, a probability distribution function f (x) for each gray level is obtained:
the probability of the pixel points occupied by the particles in each row is e, and then the probability of the pixel points occupied by the background is 1-e; f (x) is calculated starting from x ═ 0 until x ═ x0When, F (x) is satisfied0)>1-e, then x0Is the threshold value of the binarization; for all gray levels x, let
I.e. the binarization result of each line, x of different lines0Different.
Specifically, in the step 5), when the row where the nozzle is located is subjected to binarization processing, a row vector where the nozzle is located is found, and the gray value at the nozzle is 255, so that the row vector belongs to the gray level range where the particles are located, and for the row vector, the probability that each row of particles and the nozzle occupy pixel points together is e ', so that the probability that the background occupies the pixel points is 1-e'; threshold value x0The judgment conditions of (1) become: f (x0)>1-e'; for all gray levels x, let
Namely the binarization result of each line.
Compared with the prior art, the invention has the advantages that:
1. different from the traditional uneven illumination image enhancement algorithm, the method provided by the invention firstly performs column-by-column histogram equalization on the image after removing the uneven background according to the characteristic that the light source is positioned at one side, and eliminates the light and shade difference of particles generated by uneven illumination among columns, thereby generating a good equalization effect.
2. And calculating different threshold values for each row according to the characteristic of uniform particle density to ensure that the particles and the background of each row are completely divided.
3. Under the condition of spout interference, the image is flexibly processed, the row and the column where the spout is located are independently operated according to the property of the spout, and the row and the column which do not contain the spout are uniformly operated, so that the precision of the particle identification result is ensured, and the time is saved.
Drawings
FIG. 1 is a flow chart illustrating a method for processing a dense particle image under non-uniform illumination conditions according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an initial image in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an extracted uneven background in an embodiment of the present invention;
FIG. 4 is a schematic diagram of an image with background removed according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an image after column-by-column histogram equalization according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an image binarized line by line in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the following embodiments and accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments without any inventive step, are within the scope of protection of the invention.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of the word "comprise" or "comprises", and the like, in the context of this application, is intended to mean that the elements or items listed before that word, in addition to those listed after that word, do not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
Examples
Referring to fig. 1, the method for processing a dense particle image under uneven lighting conditions of the present embodiment includes the following steps:
s10: uneven background generated due to illumination unevenness in the image is extracted.
The opening operation in the morphological processing is adopted. Firstly, according to the properties of the image (1280x800 pixel points) in the example, a flat disc structural element with the radius of 20 is created, and then the element is used for expanding and then corroding the original image (open operation) to obtain a smooth and uneven image background I2See fig. 3.
S20: removing non-uniform background in images
I3＝I1-I2
I3Is a gray matrix of the image after background removal, I1Is a gray-scale matrix of the original image, I2Is a gray scale matrix of the non-uniform background image. As shown in fig. 4, the background of the resulting image is uniform, but the brightness of the particles is darker in the areas where the illumination is weaker.
S30: if no spout exists in the image, directly equalizing the column-by-column histogram of the image in the following mode
As can be seen from fig. 4, the brightness of the particles is high-low from left to right, and low-high-low from top to bottom, so that if the histogram of the entire image is equalized, the darker particles and the background at the lighter position are located in the same gray scale interval, and cannot be extracted. However, even if the right particle has a lower brightness, it is still higher than the background brightness of the column in which the particle is located, so that the histogram equalization is performed column by column, which ensures that the left particle and the right particle have a larger gray value together.
For each column Sk(k 0, 1.., 1280), the probability that each gray level occupies 800 pixels of the column can be found:
pi＝ni/800(i＝0,1,...,255)
wherein n isiIs the number of pixels in the column for gray level i.
Thereby obtaining a gray level distribution vector P for the columnk1＝(p0,p1,...,p255). Then to Pk1Transforming to obtain new gray level distribution vector Pk2＝(p0’,p1’,...,p255’)，Pk2Namely, the gray level distribution vector after histogram equalization:
Pk2＝Pk1·T
where T is a 256x256 transform matrix. The resulting new gray scale distribution vector Pk2The difference between adjacent elements decreases.
Converting the probability distribution into the number of each gray level:
ni’＝pi’*800(i＝0,1,...,255)
then based on the new gray level distribution vector Pk2Redistributing pixel value to each element on the column to obtain column vector S after histogram equalizationk', noted:
Sk’＝f(Sk)
if there is a spout in the image, steps S31 and S32 are performed
S31: finding the column where the nozzle is located and equalizing the sectional histogram of the column
The white area under the image is a small spout,if the column where the nozzle is located is directly subjected to histogram equalization, the error of the result is large, so that the column vector S where the nozzle is located needs to be found firsti,Si+1,...Sj(ii) a Judging the pixels in each column vector, and dividing the whole column vector into 2 parts by finding out the pixel point where the spout is located:
then the area(s) where the nozzle is locatedk+1,...,s800) Assigned value of 255, region of non-ejection(s)1,s2,...,sk) Histogram equalization to obtain a new column vector(s)1’,s2’,...,sk’,sk+1’,...,s800') namely:
s32: histogram equalization for other columns
For a column vector S1,S2,...,Si-1,Sj+1,...,S1280Directly adopting the histogram equalization method in step S30 to obtain a new column vector Sk’。
After histogram equalization is performed column by column, the brightness difference of the particles due to uneven illumination between columns is substantially eliminated, and the gray scale values of the image from left to right become equalized as shown in fig. 5.
In the case of the binarization processing for the image line by line, the step S40 is executed when the row does not contain the spout, and the step S50 is executed when the row contains the spout.
S40: binarizing the image line by line (not including the line where the nozzle is located)
For each line, there is a dark-light-dark law in the image from top to bottom, so the brightness difference of the particles between lines is eliminated. Unlike the column-to-column difference before histogram equalization, the problem between rows is not the unevenness in the overall brightness of the microparticles, but the microparticles with high brightness are distributed in each row, except that the proportion of the microparticles expressed as high brightness in each row to the total number of the microparticles in the entire row is different. It is therefore desirable to eliminate this difference.
According to the uniformity of particle distribution, the particle density of any region should be basically equal (except for a nozzle), so that for each line, the probability of pixel points occupied by the particles should be equal, the image is binarized line by utilizing the characteristic, the critical gray level between the background of each line and the particle particles is found and used as a binarization threshold, and the particles can be completely extracted.
For 1280 pixel points in each row, the probability p of each gray level in the row can be obtainedi：
pi＝ni/1280(i＝0,1,...,255)
Wherein n isiIs the number of pixels in the row for gray level i.
Further, a probability distribution function F (x) of each gray level is obtained
In the image of this embodiment, the probability of the pixel point occupied by the particles in each row is 0.03, and then the probability of the pixel point occupied by the background:
1-0.03＝0.97
f (x) is calculated starting from x ═ 0 until x ═ x0When it is satisfied
F(x0)>0.97
Then x0Is the threshold value for binarization. For all gray levels x, let
I.e. the binarization result of each line, x of different lines0Different.
S50: performing binarization operation on rows containing nozzles
Finding out the line vector S of the nozzlei,Si+1,...SjSince the gray value at the nozzle is 255, the gray value belongs to the gray level range of the particles, and for the row vector Si,Si+1,...SjAnd the probability that each row of particles and the nozzle occupy the pixel point together is 0.07, so that the probability that the background occupies the pixel point is as follows:
1-0.07＝0.93
threshold value x0The judgment conditions of (1) become:
F(x0)>0.93
the other steps are equal to S40, and the particle extraction result of the row where the nozzle is located can be obtained.
S60: obtaining a final image
Finish to image I1And extracting a background, removing the background, equalizing a column-by-column histogram and binarizing line-by-line to obtain a final image which is the image after the particle recognition.
Claims (8)
1. A processing method of dense particle images under the condition of uneven illumination is characterized by comprising the following steps:
1) extracting an uneven background generated by uneven illumination in the image;
2) removing uneven background in the image;
3) judging whether a spout exists in the image, wherein the spout is a white area of the original extracted image; if not, executing the step 4); if yes, executing step 5);
4) carrying out histogram equalization processing on the image column by column;
5) firstly, carrying out sectional histogram equalization processing on the row where the nozzle is positioned, and then carrying out histogram equalization on other rows;
6) carrying out binarization processing on the image line by line;
7) and obtaining a final image.
2. The method for processing the dense particle image under the uneven illumination condition as claimed in claim 1, wherein in the step 1), an open operation in the morphological processing is adopted, firstly, a flat disk structure element with a certain radius is created according to the property of the image, and then the element is used for expanding and then corroding the original image to obtain a smooth and uneven image background.
3. The method for processing the image of dense particles under the uneven illumination condition as claimed in claim 1, wherein in the step 2), the gray-scale matrix I of the image after the background is removed3＝I1-I2Wherein, I1Is a gray-scale matrix of the original image, I2Is a gray scale matrix of the non-uniform background image.
4. The method according to claim 1, wherein in step 4), when performing histogram equalization on a x m pixel images column by column, S is applied to each columnk(k ═ 0, 1.. times, a), the probability that each gray level occupies m pixels of the column can be found:
pi＝ni/m(i＝0,1,...,255)
wherein n isiIs the number of pixels in the column for gray level i;
thereby obtaining a gray level distribution vector P for the columnk1＝(p0,p1,...,p255) (ii) a Then to Pk1Transforming to obtain new gray level distribution vector Pk2＝(p0’,p1’,...,p255’)，Pk2Namely, the gray level distribution vector after histogram equalization:
Pk2＝Pk1·T
where T is a 256x256 transformation matrix, resulting in a new gray level distribution vector Pk2The difference between each adjacent element is reduced;
converting the probability distribution into the number of each gray level:
ni’＝pi’*m(i＝0,1,...,255)
then based on the new gray level distribution vector Pk2Redistributing pixel value to each element on the column to obtain column vector S after histogram equalizationk', noted:
Sk’＝f(Sk)。
5. the method for processing the dense particle image under the uneven illumination condition as recited in claim 1, wherein the step 5) of performing the segmented histogram equalization process on the column where the nozzles are located comprises:
firstly, finding a column vector where the nozzle is located: judging pixels in each column vector, finding out pixel points where the nozzles are located, and dividing the whole column vector into 2 parts, namely a non-nozzle area and a nozzle area;
and then, the spout area is assigned to be 255, and histogram equalization is carried out on the non-spout area to obtain a new column vector.
6. The method for processing the dense particle image under the uneven illumination condition as claimed in claim 1, wherein the method used in step 4) is adopted when histogram equalization processing is performed on other columns in step 5).
7. The method for processing the dense particle image under the uneven illumination condition as claimed in claim 4, wherein in the step 6), when the image is binarized line by line, for a pixel points of each line in the lines not including the nozzle, the probability p of each gray level in the line can be obtainedi：
pi＝ni/a(i＝0,1,...,255)
Wherein n isiIs the number of pixels in the row for gray level i;
further, a probability distribution function f (x) for each gray level is obtained:
the probability of the pixel points occupied by the particles in each line ise, the probability of the pixel points occupied by the background is 1-e; f (x) is calculated starting from x ═ 0 until x ═ x0When, F (x) is satisfied0)>1-e, then x0Is the threshold value of the binarization; for all gray levels x, let
I.e. the binarization result of each line, x of different lines0Different.
8. The method for processing the dense particle image under the uneven illumination condition as claimed in claim 7, wherein in the step 5), when the row containing the nozzle is subjected to binarization processing, a row vector where the nozzle is located is found, and as the gray value at the nozzle is 255, the row vector belongs to the gray level range where the particles are located, and for the row vector, the probability that each row of particles and the nozzle occupy the pixel point together is e ', and the probability that the background occupies the pixel point is 1-e'; threshold value x0The judgment conditions of (1) become: f (x0)>1-e'; for all gray levels x, let
Namely the binarization result of each line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110414176.1A CN113160098B (en) | 2021-04-16 | 2021-04-16 | Processing method of dense particle image under condition of uneven illumination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110414176.1A CN113160098B (en) | 2021-04-16 | 2021-04-16 | Processing method of dense particle image under condition of uneven illumination |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113160098A true CN113160098A (en) | 2021-07-23 |
| CN113160098B CN113160098B (en) | 2022-11-11 |
Family
ID=76868634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110414176.1A Expired - Fee Related CN113160098B (en) | 2021-04-16 | 2021-04-16 | Processing method of dense particle image under condition of uneven illumination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160098B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070058862A1 (en) * | 2005-09-09 | 2007-03-15 | Meier Michael R | Histogram equalization method for a vision-based occupant sensing system |
| CN101739672A (en) * | 2009-12-02 | 2010-06-16 | 北京中星微电子有限公司 | Method and device for equalizing histogram based on sub-regional interpolation |
| CN104269012A (en) * | 2014-09-28 | 2015-01-07 | 浙江大学 | Method for monitoring mountain fire nearby electric transmission line based on MODIS data |
| CN105844656A (en) * | 2016-04-22 | 2016-08-10 | 中国电子科技集团公司第三研究所 | Image binaryzation target segmentation device and method |
| WO2016165064A1 (en) * | 2015-04-14 | 2016-10-20 | 中国科学院自动化研究所 | Robust foreground detection method based on multi-view learning |
| CN110443807A (en) * | 2019-06-27 | 2019-11-12 | 中国地质大学（武汉） | A kind of even carrying out image threshold segmentation method of uneven illumination based on luminance proportion |
-
2021
- 2021-04-16 CN CN202110414176.1A patent/CN113160098B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070058862A1 (en) * | 2005-09-09 | 2007-03-15 | Meier Michael R | Histogram equalization method for a vision-based occupant sensing system |
| CN101739672A (en) * | 2009-12-02 | 2010-06-16 | 北京中星微电子有限公司 | Method and device for equalizing histogram based on sub-regional interpolation |
| CN104269012A (en) * | 2014-09-28 | 2015-01-07 | 浙江大学 | Method for monitoring mountain fire nearby electric transmission line based on MODIS data |
| WO2016165064A1 (en) * | 2015-04-14 | 2016-10-20 | 中国科学院自动化研究所 | Robust foreground detection method based on multi-view learning |
| CN105844656A (en) * | 2016-04-22 | 2016-08-10 | 中国电子科技集团公司第三研究所 | Image binaryzation target segmentation device and method |
| CN110443807A (en) * | 2019-06-27 | 2019-11-12 | 中国地质大学（武汉） | A kind of even carrying out image threshold segmentation method of uneven illumination based on luminance proportion |
Non-Patent Citations (5)
| Title |
|---|
| 李华美等: "基于精确直方图规格化的医学超声图像增强", 《中国医学影像技术》 * |
| 焦日华: "基于机器视觉的车道标志线检测与车道定位技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 王茜: "车辆识别系统中的背景去除算法研究", 《装备制造技术》 * |
| 谭东杰等: "基于局部直方图规定化的红外图像非均匀性校正", 《红外技术》 * |
| 赵玉峰等: "沙粒图像中沙粒粒径的检测与识别", 《兰州大学学报(自然科学版)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113160098B (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115375676A (en) | Stainless steel product quality detection method based on image recognition | |
| CN107845087A (en) | The detection method and system of the uneven defect of liquid crystal panel lightness | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN109242853A (en) | A kind of PCB defect intelligent detecting method based on image procossing | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN114998198A (en) | Injection molding surface defect identification method | |
| CN115222743B (en) | Furniture surface paint spraying defect detection method based on vision | |
| CN115063430B (en) | Electric pipeline crack detection method based on image processing | |
| CN115830033A (en) | Automobile hub surface defect detection method based on machine vision | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN112085651B (en) | Automatic shock wave detection and tracking algorithm based on image self-adaptive threshold and feature extraction | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| WO2020037573A1 (en) | Method and device for detecting bright spots on image, and computer program product | |
| CN113743473A (en) | Intelligent identification and detection method for automatic spraying process of complex parts | |
| CN112308854A (en) | Automatic detection method and system for chip surface flaws and electronic equipment | |
| CN110910367A (en) | Bioreactor cell culture quality evaluation method | |
| CN112669286A (en) | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall | |
| CN110687122A (en) | Method and system for detecting surface cracks of ceramic tile | |
| CN113034464A (en) | Method for detecting defects of liquid crystal display in real time under multiple backgrounds | |
| CN108230334B (en) | High-concentration wind-blown sand image segmentation method based on gray threshold | |
| CN116630312B (en) | Visual detection method for polishing quality of constant-force floating polishing head | |
| CN113160098B (en) | Processing method of dense particle image under condition of uneven illumination | |
| CN110530894B (en) | Light guide plate bright spot defect detection method | |
| CN112465047B (en) | Industrial image visual identification method based on prior model | |
| CN110827272B (en) | Tire X-ray image defect detection method 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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20221111 |