CN116952931A - System and method for measuring water content of sludge particles based on image method - Google Patents
System and method for measuring water content of sludge particles based on image method Download PDFInfo
- Publication number
- CN116952931A CN116952931A CN202310637236.5A CN202310637236A CN116952931A CN 116952931 A CN116952931 A CN 116952931A CN 202310637236 A CN202310637236 A CN 202310637236A CN 116952931 A CN116952931 A CN 116952931A
- Authority
- CN
- China
- Prior art keywords
- image
- sludge
- particle
- unit
- water content
- 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 263
- 239000010802 sludge Substances 0.000 title claims abstract description 197
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000008187 granular material Substances 0.000 claims abstract description 27
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 238000009826 distribution Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 17
- 230000001502 supplementing effect Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000003921 particle size analysis Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000001035 drying Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 241001584785 Anavitrinella pampinaria Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- 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
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Dispersion Chemistry (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention provides a system and a method for measuring the water content of sludge particles based on an image method, which relate to the technical field of sludge particle water content measurement and comprise the following steps: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image; based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image; obtaining the average particle size of the sludge particle image based on the image characteristics; constructing a sludge granule water content prediction model based on the grain size distribution and the gray value; and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content. The collected sludge particle images are processed to obtain average particle sizes and gray values of sludge particles, the average particle sizes and gray values are input into a sludge particle water content prediction model, online measurement of the water content of the sludge particles is realized, rapid, nondestructive, accurate and continuous online measurement is realized, and the measurement efficiency of the water content of the sludge particles is improved.
Description
Technical Field
The invention relates to the technical field of sludge granule water content measurement, in particular to a system and a method for measuring the water content of sludge granules based on an image method.
Background
At present, a sludge treatment process of drying and separate incineration is often adopted for sludge treatment. For the disposal mode, the moisture content of the dried sludge particles is an important factor for measuring whether the sludge drying reaches the standard. The water content of the sludge after the drying treatment is reduced to meet the standard condition, and the next incineration treatment can be performed. Under the existing condition, the analysis of the water content of the dried sludge particles in the actual production process mainly depends on a manual experience method, and workers judge whether the water content of the sludge particles accords with the standard according to experience. If the operation condition of the sludge drier does not meet the standard, the operation condition of the sludge drier is adjusted according to experience, so that the operation efficiency of the sludge drier is lower.
Therefore, the invention provides a system and a method for measuring the water content of sludge particles based on an image method.
Disclosure of Invention
The invention provides a system and a method for measuring the water content of sludge particles based on an image method, which are used for processing an acquired sludge particle image to obtain the average particle size and gray value of the sludge particles, combining a constructed sludge particle water content prediction model based on the average particle size and gray value of the sludge particles to realize the online measurement of the water content of the sludge particles, expanding the image method to the online measurement field of the water content of the sludge, solving the defects of long time consumption, complicated steps and incapability of online measurement in the traditional sludge particle water content measurement process, and being suitable for on-site application and improving the efficiency of the sludge particle water content measurement.
The invention provides a sludge granule water content measuring system based on an image method, which comprises the following steps:
an image processing module: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
gray value analysis module: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
particle size analysis module: obtaining the average particle size of the sludge particle image based on the image characteristics;
model construction module: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
the water content prediction module: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, an image processing module comprises:
an image acquisition unit: acquiring shooting parameters of an industrial camera to obtain continuous sludge particle images within preset time;
background removal unit: obtaining a corresponding first image with the background removed based on a preset background and all the sludge particle images;
contour transformation unit: based on each first image, a corresponding first contour is obtained;
profile screening unit: screening the second contour with the largest area from the contour areas of all the first contours;
profile supplementing unit: supplementing the second contour according to the coordinates of each remaining first contour to obtain a third contour after supplementing;
an image restoration unit: based on the third contour, a corresponding second image is obtained.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, an image acquisition unit comprises:
shooting parameter acquisition block: based on the speed of the mobile platform of the imaging system, shooting parameters of the corresponding industrial camera are obtained.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, and an image processing module, which further comprises:
edge expansion unit: performing edge expansion on the second image based on a preset search half value and a preset neighborhood half value to obtain a third image;
center point selection unit: selecting a pixel point in the third image as a first point;
search rectangle construction unit: based on the first point as a center, carrying out rectangular construction on the first point according to a preset searching half value to obtain a first searching rectangle;
a control point selection unit: selecting a pixel point except the first point as a second point in the first search rectangle range;
neighborhood block construction unit: carrying out neighborhood construction on the first point and each second point based on a preset neighborhood radius to obtain a corresponding first neighborhood block and a corresponding second neighborhood block;
similarity calculation unit: calculating the mean square error of the first neighborhood block and the second neighborhood block to obtain corresponding neighborhood similarity;
gaussian analysis unit: inputting the neighborhood similarity to a Gaussian weight analysis model to obtain corresponding Gaussian weights and Gaussian coefficients;
a filter value calculation unit: calculating a weighted average value of pixel values of all pixel points in the first search rectangle to obtain a filter value of the first point;
a primary filtering unit: filtering the third image once based on the filtering value and a preset filtering difference value to obtain a fourth image;
and (3) a normalization processing unit: based on all Gaussian coefficients, carrying out normalization processing on each Gaussian weight to obtain a first weight;
and a secondary filtering unit: performing secondary filtering on the fourth image based on the first weight and the preset weight to obtain a fifth image;
enhancement unit: enhancing the fifth image based on a Retinex image enhancement algorithm to obtain a sixth image;
binarization unit: performing image binarization on the sixth image to obtain a sludge binarization image;
threshold analysis unit: obtaining an optimal threshold value of each pixel point based on a two-dimensional maximum entropy method and the processed sludge binarization image;
an image dividing unit: dividing the sludge binarization image based on all the optimal threshold values to obtain a plurality of area binarization images;
and a communication analysis unit: acquiring eight connected areas of each point in each area binarized image, and judging whether the eight connected areas have connectivity or not;
feature marking unit: if the eight connected areas have connectivity, marking the eight connected areas as a particle area and marking corresponding generalized gray values;
an effective calculation unit: based on all the particle areas, calculating to obtain a sample effective index of a corresponding area binarization image;
an effective judging unit: if the effective index of the sample is larger than the preset effective index, constructing and obtaining the image characteristics of the corresponding area binarized image based on all the particle areas and the corresponding gray values.
Preferably, the present invention provides a system for measuring the water content of sludge particles based on an image method, an effective calculation unit, comprising:
wherein S represents a sample effective index of the region binarized image; t represents the number of all particle areas in the area binarized image;an average value of gaussian coefficients corresponding to all the particle areas in the area binarized image is represented; k (k) j A Gaussian weight representing a jth particle region in the region binarized image; k (k) j-1 Gaussian weights of the j-1 th particle region in the region binarized image are represented; g j Representing the generalized gray value of the j-th grain region in the region binarized image.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, and a gray value analyzing module, comprising:
a first gradation value calculation unit: based on the image characteristics of each area binarized image, obtaining the average gray value of each area binarized image as a first gray value;
a second gray value calculation unit: and obtaining an average gray value of the sludge particle image as a second gray value based on the number of all the area binarized images and the first gray value.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, a granule size analyzing module, comprising:
equivalent particle diameter calculation unit: calculating the corresponding equivalent particle size based on the total particle area;
wherein L represents the pixel length of the industrial camera sensor; m represents the magnification of the lens; a represents the number of pixels contained in the particle region in the binary image;
a first average particle diameter calculation unit: calculating a corresponding first average particle diameter based on the equivalent particle diameter;
wherein ,representing a first average particle size of sludge particles in the regional binarized image; n is the number of particle areas in the image; d (D) i Is the equivalent particle diameter of the ith sludge particle.
A second average particle diameter calculation unit: and obtaining the second average particle size of the sludge particle image based on the total first average particle size and the number of the total area binarized images.
Preferably, the invention provides a sludge granule water content measuring system based on an image method, a model building module comprises:
number range determining unit: based on a preset sampling range, obtaining a particle quantity range in the acquired sludge particle image;
an input/output determination unit: taking the maximum particle number in the particle number range as an input layer and the water content of the sludge particles as an output layer;
a hidden layer determination unit: obtaining a corresponding hidden layer transfer function based on a preset particle size function and a preset gray value function;
frame construction unit: constructing a neural network structure frame based on the input layer, the output layer and the hidden layer transfer function;
model training unit: training the neural network structure frame according to a preset sludge particle water content data set to obtain a first model;
an error acquisition unit: calculating the output first water content and a corresponding first error value of the water content based on the first model;
error judgment unit: if the first error value is larger than the preset error value, adjusting the hidden layer;
model output unit: and continuing training the adjusted first model, and if the continuously output water content in the preset quantity is smaller than the preset water content, obtaining a sludge particle water content prediction model.
The invention provides a method for measuring the water content of sludge particles based on an image method, which comprises the following steps:
step 1: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
step 2: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
step 3: obtaining the average particle size of the sludge particle image based on the image characteristics;
step 4: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
step 5: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of a system for measuring the water content of sludge particles based on an image method in an embodiment of the invention;
FIG. 2 is a flow chart of a method for measuring the water content of sludge particles based on an image method in an embodiment of the invention;
FIG. 3 is a schematic block diagram of a measurement system in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
the embodiment of the invention provides a sludge granule water content measuring system based on an image method, which is shown in fig. 1 and comprises an image processing module: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
gray value analysis module: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
particle size analysis module: obtaining the average particle size of the sludge particle image based on the image characteristics;
model construction module: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
the water content prediction module: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
In this embodiment, the industrial camera refers to a black-and-white industrial camera.
In this embodiment, the sludge particle image refers to a black and white image of sludge particles on a moving platform acquired by an industrial camera.
In this embodiment, the pretreatment refers to filtering, noise reduction, binarization and segmentation of the obtained sludge particle image.
In this embodiment, the region binarized image refers to a region binarized image obtained by performing two-dimensional maximum entropy analysis on each pixel of the binarized image after noise reduction processing to obtain an optimal threshold value of each pixel, connecting adjacent pixels according to the same optimal threshold value, and dividing the image according to the connected pixels, wherein the optimal threshold value refers to a threshold value of a gray value of a pixel at an edge of the optimal division of the image.
In this embodiment, the image feature refers to a general gray value of eight connected regions having connectivity in the region binarized image, where the eight connected regions refer to regions made up of pixels of up, down, left, right, up left, down left, up right, down right, and the general gray value refers to the same gray value of pixels and pixels of up, down, left, right, up left, down left, up right, and down right of the pixels.
In this embodiment, the average gradation value refers to an average gradation value of a sludge particle image processed by filtering noise reduction.
In this embodiment, the average particle diameter refers to an average particle radius of the sludge particle image processed by filtering noise reduction.
In this embodiment, the sludge granule water content prediction model refers to a model trained from an average gray value, an average particle diameter, and a corresponding water content of sludge granules.
In this example, the sludge granule water content refers to the water content of the sludge granule sample.
The working principle and the beneficial effects of the technical scheme are as follows: the method has the advantages that the acquired sludge particle images are processed to obtain the average particle size and the gray value of the sludge particles, the constructed sludge particle water content prediction model based on the average particle size and the gray value of the sludge particles is combined, the online measurement of the water content of the sludge particles is realized, an image method is expanded to the online measurement field of the water content of the sludge, the defects that the traditional sludge particle water content measurement process is long in time consumption, complicated in steps and incapable of online measurement are overcome, and the method is suitable for on-site application and improves the efficiency of the sludge particle water content measurement.
Example 2:
according to the system provided in embodiment 1 of the present invention, an image processing module includes:
an image acquisition unit: acquiring shooting parameters of an industrial camera to obtain continuous sludge particle images within preset time;
background removal unit: obtaining a corresponding first image with the background removed based on a preset background and all the sludge particle images;
contour transformation unit: based on each first image, a corresponding first contour is obtained;
profile screening unit: screening the second contour with the largest area from the contour areas of all the first contours;
profile supplementing unit: supplementing the second contour according to the coordinates of each remaining first contour to obtain a third contour after supplementing;
an image restoration unit: based on the third contour, a corresponding second image is obtained.
In this embodiment, the photographing parameters refer to photographing time, exposure time, and frame rate of the industrial camera.
In this embodiment, the preset time refers to a time when a sludge particle sample is completely collected by analyzing the speed of the mobile platform and the shooting time, exposure time and frame rate of the industrial camera.
In this embodiment, the preset background refers to an image of the mobile platform where the light source is on and no sludge particles are placed.
In this embodiment, the first image refers to an image obtained by removing the same image as the preset background in the image of the sludge particles, and only the image of the sludge particles is obtained.
In this embodiment, the first contour refers to a contour corresponding to each of the first images.
In this embodiment, the second contour refers to a contour having the largest contour area of the first contour.
In this embodiment, the third profile refers to the profile of the most complete sludge particle sample obtained by supplementing the second profile with the profile of each first profile that exceeds the second profile.
In this embodiment, the second image refers to an image obtained by stitching the first contour and the image corresponding to the second contour of each stitching corresponding to the third contour.
The working principle and the beneficial effects of the technical scheme are as follows: the outline of the continuous sludge particle image in the preset time is supplemented to obtain the most complete sludge particle image, so that the analysis of sludge particles is facilitated.
Example 3:
the system provided in embodiment 2 of the invention includes: an image acquisition unit comprising:
shooting parameter acquisition block: based on the speed of the mobile platform of the imaging system, shooting parameters of the corresponding industrial camera are obtained.
In this embodiment, the imaging system refers to an imaging system where an industrial camera is located, and as shown in fig. 3, the imaging system where the industrial camera is located is composed of a controller, an industrial camera, an optical lens, an LED light source, a mobile platform, a computer, data acquisition processing software, and the like.
The working principle and the beneficial effects of the technical scheme are as follows: the imaging system speed of the industrial camera is analyzed to obtain the shooting time, the exposure time and the frame rate of the industrial camera, so that the sludge particle image can be accurately acquired.
Example 4:
according to the system provided in embodiment 1 of the present invention, the image processing module further includes:
edge expansion unit: performing edge expansion on the second image based on a preset search half value and a preset neighborhood half value to obtain a third image;
center point selection unit: selecting a pixel point in the third image as a first point;
search rectangle construction unit: based on the first point as a center, carrying out rectangular construction on the first point according to a preset searching half value to obtain a first searching rectangle;
a control point selection unit: selecting a pixel point except the first point as a second point in the first search rectangle range;
neighborhood block construction unit: carrying out neighborhood construction on the first point and each second point based on a preset neighborhood radius to obtain a corresponding first neighborhood block and a corresponding second neighborhood block;
similarity calculation unit: calculating the mean square error of the first neighborhood block and the second neighborhood block to obtain corresponding neighborhood similarity;
gaussian analysis unit: inputting the neighborhood similarity to a Gaussian weight analysis model to obtain corresponding Gaussian weights and Gaussian coefficients;
a filter value calculation unit: calculating a weighted average value of pixel values of all pixel points in the first search rectangle to obtain a filter value of the first point;
a primary filtering unit: filtering the third image once based on the filtering value and a preset filtering difference value to obtain a fourth image;
and (3) a normalization processing unit: based on all Gaussian coefficients, carrying out normalization processing on each Gaussian weight to obtain a first weight;
and a secondary filtering unit: performing secondary filtering on the fourth image based on the first weight and the preset weight to obtain a fifth image;
enhancement unit: enhancing the fifth image based on a Retinex image enhancement algorithm to obtain a sixth image;
binarization unit: performing image binarization on the sixth image to obtain a sludge binarization image;
threshold analysis unit: obtaining an optimal threshold value of each pixel point based on a two-dimensional maximum entropy method and the processed sludge binarization image;
an image dividing unit: dividing the sludge binarization image based on all the optimal threshold values to obtain a plurality of area binarization images;
and a communication analysis unit: acquiring eight connected areas of each point in each area binarized image, and judging whether the eight connected areas have connectivity or not;
feature marking unit: if the eight connected areas have connectivity, marking the eight connected areas as a particle area and marking corresponding generalized gray values;
an effective calculation unit: based on all the particle areas, calculating to obtain a sample effective index of a corresponding area binarization image;
an effective judging unit: if the effective index of the sample is larger than the preset effective index, constructing and obtaining the image characteristics of the corresponding area binarized image based on all the particle areas and the corresponding gray values.
In this embodiment, the preset search half value refers to a value of half of the side length of the preset search rectangle.
In this embodiment, the preset neighborhood half value refers to a value of half of the side length of the preset neighborhood block.
In this embodiment, edge expansion refers to adding a preset search half value and a preset neighborhood half value to each pixel point of the edge of the second image to obtain expansion points, and filling a blank except the second image with an image with a minimum gray value based on a line segment connected with each expansion point.
In this embodiment, the third image refers to an image expanded from the second image.
In this embodiment, the rectangular construction means constructing a search rectangle by 2 times the preset search half value centering on the first point.
In this embodiment, the first search rectangle refers to a search rectangle in which the first point is constructed 2 times as large as the preset search half value.
In this embodiment, the neighborhood construction refers to a rectangle constructed by 2 times the half value of the preset neighborhood with the pixel point as the center.
In this embodiment, the first neighborhood block refers to a rectangle built by 2 times the half value of the preset neighborhood centered on the first point.
In this embodiment, the second neighborhood block refers to a rectangle constructed by 2 times the half value of the preset neighborhood centered on the second point.
In this embodiment, the mean square error refers to the expected value of the square of the difference between the parameter estimation value and the parameter true value in the mathematical statistics, and represents the similarity between the first neighborhood block and the second neighborhood block.
In this embodiment, the neighborhood similarity refers to the similarity of the first neighborhood block and the second neighborhood block.
In this embodiment, the gaussian weight analysis model refers to a model trained by the mean square error of two neighboring blocks and corresponding gaussian weights and gaussian coefficients.
In this embodiment, the gaussian weight refers to the similarity of the first neighborhood block to the second neighborhood block.
In this embodiment, the gaussian coefficient refers to a digital factor of the degree to which the similarity of the first neighborhood block and the second neighborhood block affects the first neighborhood block.
In this embodiment, the filtered value refers to the minimum threshold value at which the image is filtered.
In this embodiment, the fourth image refers to an image constituted by the remaining pixels obtained by removing pixels smaller than the filter value in the third image.
In this embodiment, the normalization process refers to the gaussian weight of the first point divided by the sum of the gaussian coefficients of all pixel points within the first search rectangle.
In this embodiment, the first weight refers to a weight value of a gaussian weight of the first point divided by a sum of gaussian coefficients of all pixel points within the first search rectangle.
In this embodiment, the preset weight refers to a preset value of the first weight of the pixel point having the analysis value.
In this embodiment, the fifth image refers to an image formed by removing the pixels with the first weight smaller than the preset weight in the fourth image, and the obtained remaining pixels.
In this embodiment, the Retinex image enhancement algorithm refers to an image enhancement method based on scientific experiments and scientific analysis, and the basic theory is that the color of an object is determined by the reflection capability of the object to long-wave (red), medium-wave (green) and short-wave (blue) light rays, rather than by the absolute value of the intensity of reflected light, and the color of the object is not affected by the non-uniformity of illumination.
In this embodiment, the sixth image refers to an image in which the fifth image is enhanced by the Retinex image enhancement algorithm.
In this embodiment, image binarization refers to a process of setting the gray value of a pixel point on an image to 0 or 255, that is, rendering the entire image to a clear black-and-white effect.
In this embodiment, the sludge binarized image refers to an image obtained by image binarizing the sixth image.
In this embodiment, the two-dimensional maximum entropy method refers to converting an image into a two-dimensional histogram, which illustrates the distribution of sludge particles in the image, and analyzing the obtained threshold value of the gray value of the pixel point of the edge where the image is best segmented.
In this embodiment, the optimal threshold refers to a threshold of a gray value of a pixel point of an edge of optimal division of an image.
In this embodiment, the eight-connected region refers to a region constituted by pixel points of up, down, left, right, up left, down left, up right, down right of the pixel point.
In this embodiment, the particle region refers to a region where eight connected regions have connectivity, meaning that eight connected regions are one sludge particle.
In this embodiment, the common gray value pixel and the pixels above, below, left, right, upper left, lower left, upper right, lower right of the pixel have the same gray value.
In this embodiment, the sample effectiveness index refers to a numerical value of the effectiveness of the sludge granule sample.
In this embodiment, the preset validity index refers to a preset minimum value indicating the validity of the sludge granule sample.
The working principle and the beneficial effects of the technical scheme are as follows: carrying out edge expansion on a complete sludge particle image, carrying out neighborhood block analysis in a search rectangle to obtain neighborhood similarity between neighborhood blocks, inputting the neighborhood similarity into a Gaussian weight analysis model to obtain Gaussian weights and Gaussian coefficients, carrying out primary filtering according to filtering values, carrying out secondary filtering according to the Gaussian weights and the Gaussian coefficients to obtain a fifth image, carrying out enhancement on the fifth image according to a Retinex image enhancement algorithm to obtain a sixth image, carrying out binarization, judging whether adjacent pixels belong to the same particle according to connectivity judgment standard of 8 connectivity, obtaining a particle region and a corresponding generalized gray value, calculating to obtain a sample effective index of the corresponding region binarization image, and if the sample effective index is larger than a preset effective index, constructing to obtain image characteristics of the corresponding region binarization image based on all the particle regions and the corresponding gray values to improve the accuracy of sludge particle water content measurement.
Example 5:
according to the system provided in embodiment 4 of the present invention, the effective calculating unit includes:
wherein S represents a sample effective index of the region binarized image; t represents the number of all particle areas in the area binarized image;an average value of gaussian coefficients corresponding to all the particle areas in the area binarized image is represented; k (k) j A Gaussian weight representing an ith particle region in the region binarized image; k (k) j-1 Gaussian weights of the j-1 th particle region in the region binarized image are represented; g j Representing the generalized gray value of the j-th grain region in the region binarized image.
The working principle and the beneficial effects of the technical scheme are as follows: and the effective index of the sample of the corresponding area binarization image is obtained through calculation, so that the accuracy of measuring the water content of the sludge particles is improved, and the efficiency of measuring the water content of the sludge particles is improved.
Example 6:
according to the system provided in embodiment 1 of the present invention, the gray value analysis module includes:
a first gradation value calculation unit: based on the image characteristics of each area binarized image, obtaining the average gray value of each area binarized image as a first gray value;
a second gray value calculation unit: and obtaining an average gray value of the sludge particle image as a second gray value based on the number of all the area binarized images and the first gray value.
In this embodiment, the first gray value refers to the average gray value of all the grain areas of the area binarized image.
In this embodiment, the second gray value refers to the average gray value of all the grain regions of the all-region binarized image.
The working principle and the beneficial effects of the technical scheme are as follows: and the average gray value of the corresponding sludge particle image is obtained by analyzing the image characteristics, so that the accuracy of measuring the water content of the sludge particles is improved.
Example 7:
according to the system provided in embodiment 1 of the present invention, the particle size analysis module includes:
equivalent particle diameter calculation unit: calculating the corresponding equivalent particle size based on the total particle area;
wherein L represents the pixel length of the industrial camera sensor; m represents the magnification of the lens; a represents the number of pixels contained in the particle region in the binary image;
a first average particle diameter calculation unit: calculating a corresponding first average particle diameter based on the equivalent particle diameter;
wherein ,representing a first average particle size of sludge particles in the regional binarized image; n is the number of particle areas in the image; d (D) i Is the equivalent particle diameter of the ith sludge particle.
A second average particle diameter calculation unit: and obtaining the second average particle size of the sludge particle image based on the total first average particle size and the number of the total area binarized images.
In this example, the equivalent particle diameter refers to the particle diameter introduced by the characterization method of the projected area equivalent circle diameter.
The working principle and the beneficial effects of the technical scheme are as follows: and by analyzing the image characteristics, the average particle size of the sludge particle image is obtained, the accuracy of measuring the water content of the sludge particles is improved, and the efficiency of measuring the water content of the sludge particles is improved.
Example 8:
according to the system provided in embodiment 1 of the present invention, a model building module includes:
number range determining unit: based on a preset sampling range, obtaining a particle quantity range in the acquired sludge particle image;
an input/output determination unit: taking the maximum particle number in the particle number range as an input layer and the water content of the sludge particles as an output layer;
a hidden layer determination unit: obtaining a corresponding hidden layer transfer function based on a preset particle size function and a preset gray value function;
frame construction unit: constructing a neural network structure frame based on the input layer, the output layer and the hidden layer transfer function;
model training unit: training the neural network structure frame according to a preset sludge particle water content data set to obtain a first model;
an error acquisition unit: calculating the output first water content and a corresponding first error value of the water content based on the first model;
error judgment unit: if the first error value is larger than the preset error value, adjusting the hidden layer;
model output unit: and continuing training the adjusted first model, and if the continuously output water content in the preset quantity is smaller than the preset water content, obtaining a sludge particle water content prediction model.
In this embodiment, the preset sampling range refers to a mass range of sludge particles obtained by tiling sludge particles as much as possible according to an area of a mobile platform and an acquisition range of an industrial camera.
In this embodiment, the particle number range refers to a range of the obtained sludge particles by calculating a preset sampling range and a mass of each sludge particle.
In this embodiment, the maximum particle number refers to the maximum value in the range of particle numbers.
In this embodiment, the preset particle diameter function refers to a function of the average particle diameter of the sludge particles and the water content of the sludge particles, which are preset.
In this embodiment, the preset gray value function refers to a function of a preset average gray value of sludge particles and a water content of the sludge particles.
In this embodiment, the hidden layer transfer function refers to a function set in two hidden layers by integrating a preset particle size function and a preset gray value function.
In this embodiment, the preset sludge particle water content data set refers to a preset data set including an average particle diameter of one thousand sludge particles, an average gray value, and a corresponding sludge particle water content.
In this embodiment, the first model refers to a model obtained by training a neural network structure frame constructed by presetting a transfer function of the sludge granule moisture content data set on an input layer, an output layer and a hidden layer.
In this embodiment, the first water content refers to the sludge granule water content output by the first model.
In this example, the water content to be obtained refers to the water content of the sludge particles to be obtained by weighing the average particle diameter and the average gradation value of the input corresponding to the first water content by a weighing method.
In this embodiment, the first error value refers to a difference between the first water content and the corresponding water content.
In this embodiment, the preset error value refers to a preset, reasonable difference value between the first water content and the corresponding water content.
The working principle and the beneficial effects of the technical scheme are as follows: and a neural network is constructed to construct a water content prediction model, so that the analysis precision of the water content of the sludge particles is improved.
Example 9:
the embodiment of the invention provides a method for measuring the water content of sludge particles based on an image method, which is shown in fig. 2 and comprises the following steps:
step 1: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
step 2: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
step 3: obtaining the average particle size of the sludge particle image based on the image characteristics;
step 4: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
step 5: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
The working principle and the beneficial effects of the technical scheme are as follows: the method has the advantages that the acquired sludge particle images are processed to obtain the average particle size and the gray value of the sludge particles, the constructed sludge particle water content prediction model based on the average particle size and the gray value of the sludge particles is combined, the online measurement of the water content of the sludge particles is realized, an image method is expanded to the online measurement field of the water content of the sludge, the defects that the traditional sludge particle water content measurement process is long in time consumption, complicated in steps and incapable of online measurement are overcome, and the method is suitable for on-site application and improves the efficiency of the sludge particle water content measurement.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. An image method-based sludge granule water content measurement system, which is characterized by comprising:
an image processing module: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
gray value analysis module: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
particle size analysis module: obtaining the average particle size of the sludge particle image based on the image characteristics;
model construction module: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
the water content prediction module: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
2. The system of claim 1, wherein the image processing module comprises:
an image acquisition unit: acquiring shooting parameters of an industrial camera to obtain continuous sludge particle images within preset time;
background removal unit: obtaining a corresponding first image with the background removed based on a preset background and all the sludge particle images;
contour transformation unit: based on each first image, a corresponding first contour is obtained;
profile screening unit: screening the second contour with the largest area from the contour areas of all the first contours;
profile supplementing unit: supplementing the second contour according to the coordinates of each remaining first contour to obtain a third contour after supplementing;
an image restoration unit: based on the third contour, a corresponding second image is obtained.
3. The system of claim 2, wherein the image acquisition unit comprises:
shooting parameter acquisition block: based on the speed of the mobile platform of the imaging system, shooting parameters of the corresponding industrial camera are obtained.
4. The system of claim 2, wherein the image processing module further comprises:
edge expansion unit: performing edge expansion on the second image based on a preset search half value and a preset neighborhood half value to obtain a third image;
center point selection unit: selecting a pixel point in the third image as a first point;
search rectangle construction unit: based on the first point as a center, carrying out rectangular construction on the first point according to a preset searching half value to obtain a first searching rectangle;
a control point selection unit: selecting a pixel point except the first point as a second point in the first search rectangle range;
neighborhood block construction unit: carrying out neighborhood construction on the first point and each second point based on a preset neighborhood radius to obtain a corresponding first neighborhood block and a corresponding second neighborhood block;
similarity calculation unit: calculating the mean square error of the first neighborhood block and the second neighborhood block to obtain corresponding neighborhood similarity;
gaussian analysis unit: inputting the neighborhood similarity to a Gaussian weight analysis model to obtain corresponding Gaussian weights and Gaussian coefficients;
a filter value calculation unit: calculating a weighted average value of pixel values of all pixel points in the first search rectangle to obtain a filter value of the first point;
a primary filtering unit: filtering the third image once based on the filtering value and a preset filtering difference value to obtain a fourth image;
and (3) a normalization processing unit: based on all Gaussian coefficients, carrying out normalization processing on each Gaussian weight to obtain a first weight;
and a secondary filtering unit: performing secondary filtering on the fourth image based on the first weight and the preset weight to obtain a fifth image;
enhancement unit: enhancing the fifth image based on a Retinex image enhancement algorithm to obtain a sixth image;
binarization unit: performing image binarization on the sixth image to obtain a sludge binarization image;
threshold analysis unit: obtaining an optimal threshold value of each pixel point based on a two-dimensional maximum entropy method and the processed sludge binarization image;
an image dividing unit: dividing the sludge binarization image based on all the optimal threshold values to obtain a plurality of area binarization images;
and a communication analysis unit: acquiring eight connected areas of each point in each area binarized image, and judging whether the eight connected areas have connectivity or not;
feature marking unit: if the eight connected areas have connectivity, marking the eight connected areas as a particle area and marking corresponding generalized gray values;
an effective calculation unit: based on all the particle areas, calculating to obtain a sample effective index of a corresponding area binarization image;
an effective judging unit: if the effective index of the sample is larger than the preset effective index, constructing and obtaining the image characteristics of the corresponding area binarized image based on all the particle areas and the corresponding gray values.
5. The system of claim 4, wherein the active computing unit comprises:
wherein S represents a sample effective index of the region binarized image; t represents the number of all particle areas in the area binarized image;an average value of gaussian coefficients corresponding to all the particle areas in the area binarized image is represented; k (k) j A Gaussian weight representing a jth particle region in the region binarized image; k (k) j-1 Gaussian weights of the j-1 th particle region in the region binarized image are represented; g j Representing the generalized gray value of the j-th grain region in the region binarized image.
6. The system of claim 1, wherein the gray value analysis module comprises:
a first gradation value calculation unit: based on the image characteristics of each area binarized image, obtaining the average gray value of each area binarized image as a first gray value;
a second gray value calculation unit: and obtaining an average gray value of the sludge particle image as a second gray value based on the number of all the area binarized images and the first gray value.
7. The system of claim 4, wherein the particle size analysis module comprises:
equivalent particle diameter calculation unit: calculating the corresponding equivalent particle size based on the total particle area;
wherein L represents the pixel length of the industrial camera sensor; m represents the magnification of the lens; a represents the number of pixels contained in the particle region in the binary image;
a first average particle diameter calculation unit: calculating a corresponding first average particle diameter based on the equivalent particle diameter;
wherein ,representing a first average particle size of sludge particles in the regional binarized image; n is the number of particle areas in the image; d (D) i Is the equivalent particle diameter of the ith sludge particle.
A second average particle diameter calculation unit: and obtaining the second average particle size of the sludge particle image based on the total first average particle size and the number of the total area binarized images.
8. The system of claim 1, wherein the model building module comprises:
number range determining unit: based on a preset sampling range, obtaining a particle quantity range in the acquired sludge particle image;
an input/output determination unit: taking the maximum particle number in the particle number range as an input layer and the water content of the sludge particles as an output layer;
a hidden layer determination unit: obtaining a corresponding hidden layer transfer function based on a preset particle size function and a preset gray value function;
frame construction unit: constructing a neural network structure frame based on the input layer, the output layer and the hidden layer transfer function;
model training unit: training the neural network structure frame according to a preset sludge particle water content data set to obtain a first model;
an error acquisition unit: calculating the output first water content and a corresponding first error value of the water content based on the first model;
error judgment unit: if the first error value is larger than the preset error value, adjusting the hidden layer;
model output unit: and continuing training the adjusted first model, and if the continuously output water content in the preset quantity is smaller than the preset water content, obtaining a sludge particle water content prediction model.
9. The method for measuring the water content of the sludge particles based on the image method is characterized by comprising the following steps of:
step 1: acquiring a sludge particle image acquired by an industrial camera, preprocessing and dividing the sludge particle image to obtain image characteristics of a region binarization image;
step 2: based on the image characteristics, obtaining the average gray value of the corresponding sludge particle image;
step 3: obtaining the average particle size of the sludge particle image based on the image characteristics;
step 4: constructing a sludge granule water content prediction model based on the grain size distribution and the gray value;
step 5: and inputting the average gray value and the average particle diameter into a sludge particle water content prediction model to obtain the predicted sludge particle water content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310637236.5A CN116952931B (en) | 2023-05-31 | System and method for measuring water content of sludge particles based on image method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310637236.5A CN116952931B (en) | 2023-05-31 | System and method for measuring water content of sludge particles based on image method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116952931A true CN116952931A (en) | 2023-10-27 |
| CN116952931B CN116952931B (en) | 2024-07-26 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117819796A (en) * | 2024-01-15 | 2024-04-05 | 北京艺高人和工程设备有限公司 | Sludge micro-negative pressure drying treatment system and process |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11108821A (en) * | 1997-10-03 | 1999-04-23 | Kurita Water Ind Ltd | Sludge image processing device |
| JP2007201549A (en) * | 2006-01-23 | 2007-08-09 | Optrex Corp | Image display apparatus and image processing method |
| JP2011103586A (en) * | 2009-11-11 | 2011-05-26 | Examastica:Kk | Photographing apparatus and image processing method for image photographed by the same |
| JP2014025720A (en) * | 2012-07-24 | 2014-02-06 | Nippon Steel & Sumikin Engineering Co Ltd | System for measuring moisture contents and grain sizes |
| JP2014025719A (en) * | 2012-07-24 | 2014-02-06 | Nippon Steel & Sumikin Engineering Co Ltd | Moisture content measuring system |
| JP2016038654A (en) * | 2014-08-06 | 2016-03-22 | セイコーエプソン株式会社 | Image processing apparatus, contour extraction method, and program |
| CN207202051U (en) * | 2017-09-22 | 2018-04-10 | 陈铁山 | One kind heats the cryotronics flue-cured tobacco component that do not burn |
| CN112529858A (en) * | 2020-12-02 | 2021-03-19 | 南京理工大学北方研究院 | Welding seam image processing method based on machine vision |
| CN113607758A (en) * | 2021-09-06 | 2021-11-05 | 中国计量大学 | Device and method for detecting water content of sludge |
| WO2021261173A1 (en) * | 2020-06-26 | 2021-12-30 | 巴工業株式会社 | Machine learning device, device for measuring water content of solid, deduction device, and machine learning method |
| CN115523855A (en) * | 2022-10-10 | 2022-12-27 | 中建安装集团有限公司 | On-line monitoring system and monitoring method for flocculated aggregates in dredging mud |
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11108821A (en) * | 1997-10-03 | 1999-04-23 | Kurita Water Ind Ltd | Sludge image processing device |
| JP2007201549A (en) * | 2006-01-23 | 2007-08-09 | Optrex Corp | Image display apparatus and image processing method |
| JP2011103586A (en) * | 2009-11-11 | 2011-05-26 | Examastica:Kk | Photographing apparatus and image processing method for image photographed by the same |
| JP2014025720A (en) * | 2012-07-24 | 2014-02-06 | Nippon Steel & Sumikin Engineering Co Ltd | System for measuring moisture contents and grain sizes |
| JP2014025719A (en) * | 2012-07-24 | 2014-02-06 | Nippon Steel & Sumikin Engineering Co Ltd | Moisture content measuring system |
| JP2016038654A (en) * | 2014-08-06 | 2016-03-22 | セイコーエプソン株式会社 | Image processing apparatus, contour extraction method, and program |
| CN207202051U (en) * | 2017-09-22 | 2018-04-10 | 陈铁山 | One kind heats the cryotronics flue-cured tobacco component that do not burn |
| WO2021261173A1 (en) * | 2020-06-26 | 2021-12-30 | 巴工業株式会社 | Machine learning device, device for measuring water content of solid, deduction device, and machine learning method |
| CN112529858A (en) * | 2020-12-02 | 2021-03-19 | 南京理工大学北方研究院 | Welding seam image processing method based on machine vision |
| CN113607758A (en) * | 2021-09-06 | 2021-11-05 | 中国计量大学 | Device and method for detecting water content of sludge |
| CN115523855A (en) * | 2022-10-10 | 2022-12-27 | 中建安装集团有限公司 | On-line monitoring system and monitoring method for flocculated aggregates in dredging mud |
Non-Patent Citations (3)
| Title |
|---|
| HUAZHEN MAO, ET AL.: "Measurement of water content and moisture distribution in sludge by 1H nuclear magnetic resonance spectroscopy", DRYING TECHNOLOGY, 1 February 2016 (2016-02-01), pages 267 - 274, XP055493948, DOI: 10.1080/07373937.2015.1047952 * |
| 中国能源学会: "第三届能源科学家论坛 论文集 下", 29 February 2012, 中国环境科学出版社, pages: 1648 - 1650 * |
| 宋宇宁;郭天太;赵军;孔明;: "基于图像处理的内衬套表面缺陷检测", 中国计量大学学报, no. 03, 15 September 2017 (2017-09-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117819796A (en) * | 2024-01-15 | 2024-04-05 | 北京艺高人和工程设备有限公司 | Sludge micro-negative pressure drying treatment system and process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112419250B (en) | Pavement crack digital image extraction, crack repair and crack parameter calculation method | |
| CN110389127B (en) | System and method for identifying metal ceramic parts and detecting surface defects | |
| CN113240626B (en) | Glass cover plate concave-convex type flaw detection and classification method based on neural network | |
| CN108764345B (en) | Underwater dam crack detection method based on local and global clustering | |
| CN115131354B (en) | Laboratory plastic film defect detection method based on optical means | |
| CN116205919A (en) | Hardware part production quality detection method and system based on artificial intelligence | |
| CN111523540A (en) | Metal surface defect detection method based on deep learning | |
| CN114549981A (en) | Intelligent inspection pointer type instrument recognition and reading method based on deep learning | |
| CN113781510B (en) | Edge detection method and device and electronic equipment | |
| CN111369526B (en) | Multi-type old bridge crack identification method based on semi-supervised deep learning | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN114882040B (en) | Sewage treatment detection method based on template matching | |
| CN113052804A (en) | Concrete member appearance quality quantitative evaluation processing method and device | |
| CN115457044B (en) | Pavement crack segmentation method based on class activation mapping | |
| CN116703911A (en) | LED lamp production quality detecting system | |
| CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
| CN116805416A (en) | Drainage pipeline defect identification model training method and drainage pipeline defect identification method | |
| CN109115775A (en) | A kind of betel nut level detection method based on machine vision | |
| Yu et al. | Optimized self-adapting contrast enhancement algorithm for wafer contour extraction | |
| CN116952931B (en) | System and method for measuring water content of sludge particles based on image method | |
| CN113076959A (en) | Concrete structure surface microcrack feature extraction method based on convolutional neural network | |
| CN116797602A (en) | Surface defect identification method and device for industrial product detection | |
| CN116952931A (en) | System and method for measuring water content of sludge particles based on image method | |
| CN116645351A (en) | Online defect detection method and system for complex scene | |
| CN115761613B (en) | Automatic tunnel crack detection method based on convolutional network |
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 |