CN109785315A - Measurement method, storage medium, terminal and the device of offal weight - Google Patents
Measurement method, storage medium, terminal and the device of offal weight Download PDFInfo
- Publication number
- CN109785315A CN109785315A CN201910059963.1A CN201910059963A CN109785315A CN 109785315 A CN109785315 A CN 109785315A CN 201910059963 A CN201910059963 A CN 201910059963A CN 109785315 A CN109785315 A CN 109785315A
- Authority
- CN
- China
- Prior art keywords
- offal
- image
- sample
- measured
- weight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Processing (AREA)
Abstract
The present invention provides measurement method, storage medium, terminal and the device of offal weight, and described method includes following steps: obtaining the sample of offal to be tested at random, weighs the weight of each offal sample, and shoots the appearance photo of each offal sample using industrial camera;The appearance photo of each offal sample is subjected to gray proces and obtains gray level image;Binary conversion treatment is carried out to image and removes background;Edge extracting is carried out to removal background image using Hough transformation;The number of pixels of each offal sample and the elemental area of each offal sample are calculated according to the offal image of edge extracting;Linear relation model is established by the elemental area of each offal sample is corresponding with the weight of corresponding offal.Use in the application method can offal weight is detected with quick nondestructive, improve detection efficiency, and accuracy is high, be very suitable to the use of tobacco redrying enterprise.
Description
Technical field
The invention belongs to weight measurement fields, more particularly to measurement method, storage medium, the terminal of a kind of offal weight
And device.
Background technique
Offal is the by-product of tobacco industry, is the thick and stiff vein of tobacco leaf, accounts for about the 25% to 30% or so of leaf weight, no
Also different with the offal physical characteristic of position tobacco leaf, under regular situation, upper smoke offal is most thick, and lower part cigarette offal is most thin, contains
There is more active chemical, active chemical is substantially consistent with active chemical in tobacco leaf, is valuable natural money
Source.Currently as tobacco big country, China has nearly 100,000 tons of offals directly to be discarded every year, wastes a large amount of precious resources, together
When also result in biggish environmental pollution.
Most redrying enterprise reprocesses offal using following several methods at this stage: offal stem ginseng is matched and cigarette
In silk, increase the fillibility of pipe tobacco, reinforce the gas permeability of tobacco product burning, to have great work to cigarette flammability is improved
With;Accumulation does organic fertilizer use after crushing, and since there are many active chemical content in offal, reinforces to tobacco stem waste
It recycles, extracts the effective component in offal, the utility value of waste tobacco stem can not only be increased, and can be by reasonable
Measure expand the profit point of enterprise to a certain extent, reduce cost;Accumulation nature is concentrated to rot to become not using rubbish
And then destroy, this method is not only time-consuming and laborious in the processes such as the transfer of offal, stacking, corruption, loading, transport, occupied area
It is larger, and renewable resource is wasted, while causing environmental pollution.Therefore now mostly redrying enterprise all using or by
First two method is gradually begun to use to reprocess offal.
Redrying enterprise is primarily present in blade construction detection to the detection of offal, contains stalk and slightly stalk rate to leaf using weight method
It is calculated, and is difficult to realize and the weight of single offal is quickly calculated, if artificial single weighing, it will greatly
Detection efficiency is influenced, and there are one for the wind dispensing effect quality in present lot for the weight of single offal and length and width information
Fixed role of evaluation, therefore the offal weight detection system for establishing a set of quick nondestructive is very urgent.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide the measurement method of offal weight, deposit
Storage media, terminal and device, being used to solve the problems, such as in the prior art can not rapid survey offal weight.
In order to achieve the above objects and other related objects, the present invention is by including that the following technical solution is realized.
The present invention provides a kind of measurement method of offal weight, includes the following steps:
The appearance photo of each offal sample of known weight is subjected to gray proces and obtains gray level image;
Binary conversion treatment is carried out to image and removes background:
Edge extracting is carried out to removal background image using Hough transformation;
The number of pixels of each offal sample and the elemental area of each offal sample are calculated according to the offal image of edge extracting;
Linear relation model is established by the elemental area of each offal sample is corresponding with the weight of corresponding offal;
The weight of offal to be measured is obtained according to the elemental area of the linear relation model and offal to be measured.
In technical scheme, the offal sample is multiple;Preferably, it is at least 3, for example 4 or 5
It is a or 10,20 or 30 etc..More offal samples facilitates the accuracy of linear relation model, and specific determining
Degree is difficult to when taking into account the accuracy and implementation of linear relation model when number.
In a preferred embodiment, it before carrying out binary conversion treatment removal background, is gone first with median filtering algorithm
Except gray scale picture noise.
In a preferred embodiment, the appearance photo of the offal sample carries out shooting acquisition using industrial camera
When, shooting environmental needs to meet following two condition: 1) industrial camera is shot under closed environment, avoid detection environment by
The interference of the factors such as external light source;2) ensure the uniformity of the light of shooting environmental.
In a preferred embodiment, gray proces refer to the appearance photo of offal sample by the true coloured picture of rgb space
Be converted to gray level image.
In a more specific embodiment, the calculation formula of gray proces are as follows:
Wherein, g (x, y) is that offal appearance photo carries out the image exported after gray proces;
F (x, y) is offal appearance photo, is the true coloured picture of rgb space;
A, b, c and d are numerical value, and the tonal range of offal appearance photo f (x, y) is [a, b], is exported after gray proces
The tonal range of image g (x, y) is [c, d].
In a preferred embodiment, the window for determining an odd pixel is referred to median filtering algorithm removal noise
Mouthful, according to the big minispread of gray scale, window center gray value g (x, y) is used in window in each grey scale pixel value each pixel in window
It is worth gray value g*(x, y) substitution.
In a specific embodiment,
g*(x, y)=Med { g (x-k, y-1) }, wherein (k, 1) ∈ W;
In formula: g*(x, y) is that the gray value of image after noise remove is the image exported
W is selected window size;K is the central value k=(W-1)/2 of window;
G (x-k, y-1) is the grey scale pixel value of window W.
In a preferred embodiment, carrying out binary conversion treatment removal background to image is to make image g*(x's, y)
Grey level histogram, and using gray value corresponding to the point of the lowest point as threshold value t, target image is split according to threshold value.
In a preferred embodiment, total pixel N of the image after background is removedSampleAre as follows:
I is the grey level range of gray level image,
I=0,1 ..., L-1;L is number of greyscale levels;niPixel when for gray level being i.
In a preferred embodiment, the formula of edge extracting is as follows:
ρ=xcos θ+ysin θ;
In formula: ρ indicates normal distance of the origin away from straight line;
θ is the angle of the normal and x-axis;
X is the abscissa of the gray value of offal sample;Y is the ordinate of the gray value of offal sample.
In a preferred embodiment, then total pixel T of the profile of offal sampleSampleAre as follows:
T is the grey level range of offal sample contour images, t=0,1 ..., m-1;M is number of greyscale levels;ntFor gray level
Pixel when for t.
In a preferred embodiment, the elemental area M of offal sampleSampleAre as follows:
Wherein,
MSampleFor the elemental area of offal sample
TSampleFor total pixel of the profile of offal sample
NSampleTotal pixel of image after background is removed for offal sample.
In a preferred embodiment, the elemental area M of offal sampleSampleWith offal weight WSampleBetween linear relationship
Are as follows:
WSample=α MSample+β
In formula: α indicates that slope, β are expressed as intercept;
WSampleFor the weight of offal sample, obtained by the way that offal sample is weighed;
MSampleFor the elemental area of offal sample.
In a preferred embodiment, the elemental area of the offal to be measured is obtained using following method: by cigarette to be measured
Obstruct appearance photo and obtain gray level image by gray proces, then carries out binary conversion treatment and obtain the image after removal background;Using
Hough transformation carries out edge extracting to the image after removal background;Offal to be measured is calculated according to the offal image to be measured of edge extracting
The elemental area of the number of pixels of sample and offal to be measured.In a preferred embodiment, right before carrying out binary conversion treatment
Gray level image removes noise using median filtering algorithm.
In a preferred embodiment, it is obtained according to the elemental area of the linear relation model of foundation and offal to be measured
The weight of offal to be measured:
WIt is to be measured=α MIt is to be measured+β
Wherein, WIt is to be measuredFor the weight for calculating the offal to be measured obtained according to the elemental area of linear relation model and offal to be measured
Amount;
MIt is to be measuredFor the elemental area of offal to be measured;
TIt is to be measuredTotal pixel of the profile of offal to be measured;
tIt is to be measuredFor the grey level range of offal contour images to be measured, tIt is to be measured=0,1 ..., m-1;mIt is to be measuredFor number of greyscale levels;nT is to be measured
It is t for gray levelIt is to be measuredWhen pixel;
NIt is to be measuredTotal pixel of image after removing background for offal to be measured;
iIt is to be measuredFor the grey level range of the gray level image of offal to be measured,
iIt is to be measured=0,1 ..., LIt is to be measured-1;LIt is to be measuredFor number of greyscale levels;nI is to be measuredIt is i for gray levelIt is to be measuredWhen pixel.
The invention also discloses a kind of computer readable storage mediums, are stored thereon with computer program, which is located
The step of reason device realizes method as described above when executing.
The invention also discloses a kind of terminal, including processor and above-mentioned computer readable storage medium, the processors
The step of executing the computer program on the computer readable storage medium, realizing the above method.
It is as described above the invention also discloses a kind of device for measuring offal weight, including at least one industrial camera
Terminal, the terminal are connect with the industrial camera signal.
As described above, measurement method, storage medium, terminal and the device of offal weight of the present invention, have following
The utility model has the advantages that
Use in the application method can offal weight is detected with quick nondestructive, improve detection efficiency, and
Accuracy is high, is very suitable to the use of tobacco redrying enterprise.
Detailed description of the invention
Fig. 1 is shown as the structural schematic diagram of industrial camera of the invention
Fig. 2 is shown as image grayscale figure in the embodiment of the present invention
Fig. 3 is shown as image median filter algorithm in the embodiment of the present invention to scheme after removing dryness
Fig. 4 is shown as grey level histogram in the embodiment of the present invention
Fig. 5 is shown as binarization segmentation figure in the embodiment of the present invention
Fig. 6 is shown as Edge extraction figure in the embodiment of the present invention
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of computer program is crossed to complete.Computer program above-mentioned can store in a computer readable storage medium
In.When being executed, execution includes the steps that above-mentioned each method embodiment to the program;And storage medium above-mentioned include: ROM,
The various media that can store program code such as RAM, magnetic or disk.
Industrial camera described herein is product known in the state of the art, in the following specific embodiment of the application,
It is Daheng's camera.When being shot using industrial camera, shooting environmental needs to meet following two condition: 1) industrial camera
It is shot under closed environment, avoids interference of the detection environment by factors such as external light sources;2) ensure the light of shooting environmental
Uniformity, as shown in Figure 1, in order to ensure the uniformity of shooting environmental light, in the work in the application specific embodiment
Light source (light source A and light source B) is respectively provided at the two sides sustained height of industry camera.Camera parameter is adjusted in specific shooting: setting
Camera light-source brightness, camera exposure time, white balance coefficients, areas imaging;Reflective and color will not be generated to image by, which ensuring, loses
Really influence imaging effect.
(1) former cigarette sample is obtained in A Redrying Factory, former cigarette sample is subjected to stalk leaf separation, so that offal sample is obtained, it will
Each offal sample is weighed, and the appearance photo for obtaining offal sample is shot by industrial camera;It is specifically real in the application
Apply the weight for claiming measurement offal sample in mode using digital display electronic.
(2) by offal appearance photo by the true color-map representation of rgb space be gray matrix, this step be to offal picture into
Row gray proces, situation that treated is as shown in Figure 2.Wherein, the calculation formula of gray proces are as follows:
Wherein, g (x, y) is that offal appearance photo carries out the image exported after gray proces
F (x, y) is offal appearance photo, is the true coloured picture of rgb space;
A, b, c and d are numerical value, and the tonal range of offal appearance photo f (x, y) is [a, b], is exported after gray proces
The tonal range of image g (x, y) is [c, d];
1. if the tonal range of offal appearance photo be less than its gray proces after export image tonal range, i.e., (d-c)/
(b-a) > 1 it, then can make image grayscale treated that gray scale dynamic range broadens, under-exposed defect can be improved in this way, or
Make full use of the dynamic range of image display;2. if the tonal range of offal appearance photo exports after being equal to its gray proces
The tonal range of image, i.e. (d-c)/(b-a)=1, then can make image grayscale treated that gray scale dynamic range is constant, but gray scale
Value interval can be translated with the size of a and c;3. if the tonal range of offal appearance photo exports image after being greater than its gray proces
Tonal range, i.e., 0 < (d-c)/(b-a) < 1 can then make image grayscale treated that gray scale dynamic range narrows;4. if (d-
C)/(b-a)<0 has d<c for b>a, then the gray value of image can invert after converting, i.e., original bright dimmed, originally dark change
It is bright;5. if (d-c)/(b-a)=- 1, g (x, y) is negating for f (x, y).
(3) noise is removed using median filtering algorithm to gray level image
The window W for determining an odd pixel first, obtains g (x-k) ..., g (x) ..., g (x+k);Each picture in window W
After element is lined up according to gray scale size, take that number among its serial number as filtering output, i.e., the picture hit exactly original window
The intermediate value gray value g of each grey scale pixel value in plain gray value g (x, y) window*(x, y) substitution.
g*(x, y)=Med { g (x-k, y-1) }, wherein (k, 1) ∈ W;
In formula: g*(x, y) is that the gray value of image after noise remove is the image exported
W is selected window size;K is the central value k=(W-1)/2 of window;
G (x-k, y-1) is the grey scale pixel value of window W.
Grayscale image after noise remove is as shown in Figure 3.
(4) binary conversion treatment is carried out to image and removes background
Since the gray scale difference of target and background is larger, histogram has the case where obvious the lowest point, makes image g*The ash of (x, y)
Histogram is spent, as shown in Figure 4;Using gray value corresponding to the point of the lowest point as threshold value t, target is divided from image according to threshold value
Out, target image is as shown in Figure 5.
The grey level range of gray level image is i=0,1 ..., L-1;L is number of greyscale levels.
Total pixel N of image after then removing background are as follows:
niPixel when for gray level being i.
(5) edge extracting is carried out with Hough (Hough) transformation obtain offal profile
Using Hough transformation to Edge extraction, straight line is searched, sees Fig. 6.
The formula of edge extracting is as follows:
ρ=xcos θ+ysin θ;
In formula: ρ indicates normal distance of the origin away from straight line;
θ is the angle of the normal and x-axis;
X is the abscissa of the gray value of offal sample;Y is the ordinate of the gray value of offal sample.
The grey level range of offal sample contour images is t=0,1 ..., m-1;M is number of greyscale levels.
Then total pixel T of the profile of offal sampleSampleAre as follows:
ntPixel when for gray level being t.
(6) the elemental area M for obtaining offal sample is calculatedSample
Wherein,
MSampleFor the elemental area of offal sample
TSampleFor total pixel of the profile of offal sample
NSampleTotal pixel of image after background is removed for offal sample.
(7) the elemental area M of offal sample is establishedSampleWith offal weight WSampleBetween linear relationship.
WSample=α MSample+β
In formula: α indicates that slope, β are expressed as intercept;
WSampleFor the weight of offal sample, obtained by the way that offal sample is weighed;
MSampleFor the elemental area of offal sample.
Actual verification has been carried out to the linear relationship established according to the above method in the present embodiment.
The offal sampled pixel area M actually establishedSampleWith offal sample weight WSampleBetween linear relationship in α be-
0.6739;β is 34.305.
The weight of offal to be measured is then obtained according to the elemental area of above-mentioned linear relation model and offal to be measured.
WIt is to be measured=α MIt is to be measured+ β, at this time WPrediction=-0.6739MIt is to be measured+34.305
Wherein,
WIt is to be measuredFor the weight for calculating the offal to be measured obtained according to the elemental area of linear relation model and offal to be measured;
MIt is to be measuredFor the elemental area of offal to be measured.
The results are shown in Table 1 for specific weight.
Table 1
20 offals to be measured are obtained in A Redrying Factory random sampling in table 1, claim to measure each cigarette cigarette to be measured by digital display electronic
The weight of stalk is shown in Table the actual weight in 1, through this embodiment in above-mentioned linear model WIt is to be measured=-0.6739MIt is to be measured+ 34.305 obtain
The weight of the offal to be measured obtained is shown in Table the pre- measured weight in 1.
In table 1, the mean absolute error between pre- measured weight and actual weight is 0.00535;
Average relative error between pre- measured weight and actual weight is 3.405181145%.
It is illustrated by the above specific embodiment in the reasonable scope, and work is based on claimed in the application
The method of industry camera measurement offal weight has feasibility and reliability, not only quick and convenient but also belong to for offal sample
Non-destructive testing.
In conclusion the present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (10)
1. a kind of measurement method of offal weight, which comprises the steps of:
The appearance photo of each offal sample of known weight is subjected to gray proces and obtains gray level image;
Binary conversion treatment is carried out to image and removes background;
Edge extracting is carried out to removal background image using Hough transformation;
The number of pixels of each offal sample and the elemental area of each offal sample are calculated according to the offal image of edge extracting;
Linear relation model is established by the elemental area of each offal sample is corresponding with the weight of corresponding offal;
The weight of offal to be measured is obtained according to the elemental area of the linear relation model and offal to be measured.
2. the method according to claim 1, wherein carry out binary conversion treatment removal background before, in
Value filtering algorithm removes gray level image noise.
3. the method according to claim 1, wherein gray proces refer to by the appearance photo of offal sample by
The true color-map representation of rgb space is gray level image.
4. according to the method described in claim 2, determining a surprise it is characterized in that, being referred to median filtering algorithm removal noise
The window of pixel is counted, each pixel is according to the big minispread of gray scale in window, with the intermediate value gray value generation of grey scale pixel value each in window
For window center gray value.
5. the method according to claim 1, wherein carrying out binary conversion treatment removal background to image is away
Except the grey level histogram of image after noise, and using gray value corresponding to the point of the lowest point as threshold value, according to threshold value by target image
It splits.
6. the method according to claim 1, wherein the elemental area of the offal to be measured is obtained using following method
: by offal appearance photo to be measured by gray proces obtain gray level image, then carry out binary conversion treatment obtain removal background after
Image;Edge extracting is carried out to the image after removal background using Hough transformation;According to the offal image to be measured of edge extracting
Calculate the number of pixels of offal to be measured and the elemental area of offal to be measured.
7. according to the method described in claim 6, it is characterized in that, utilizing intermediate value to gray level image before carrying out binary conversion treatment
Filtering algorithm removes noise.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1~7 the method is realized when row.
9. a kind of terminal, including processor and computer readable storage medium according to any one of claims 8, which is characterized in that described
Processor executes the computer program on the computer readable storage medium, realizes any the method for claim 1~7
Step.
10. a kind of device for measuring offal weight, which is characterized in that as claimed in claim 9 including at least one industrial camera
Terminal, the terminal are connect with the industrial camera signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910059963.1A CN109785315A (en) | 2019-01-22 | 2019-01-22 | Measurement method, storage medium, terminal and the device of offal weight |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910059963.1A CN109785315A (en) | 2019-01-22 | 2019-01-22 | Measurement method, storage medium, terminal and the device of offal weight |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109785315A true CN109785315A (en) | 2019-05-21 |
Family
ID=66501153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910059963.1A Pending CN109785315A (en) | 2019-01-22 | 2019-01-22 | Measurement method, storage medium, terminal and the device of offal weight |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785315A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113340904A (en) * | 2021-06-01 | 2021-09-03 | 贵州中烟工业有限责任公司 | Method for detecting shrinkages of tobacco flakes |
CN114612549A (en) * | 2022-01-14 | 2022-06-10 | 北京市农林科学院信息技术研究中心 | Method and device for predicting optimal fruiting picking time |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103175835A (en) * | 2013-02-26 | 2013-06-26 | 上海烟草集团有限责任公司 | Method for determining area quality of tobacco leaves based on intelligent image processing and model estimation |
CN106289070A (en) * | 2016-08-03 | 2017-01-04 | 上海创和亿电子科技发展有限公司 | The method measuring irregularly shaped object length and width |
-
2019
- 2019-01-22 CN CN201910059963.1A patent/CN109785315A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103175835A (en) * | 2013-02-26 | 2013-06-26 | 上海烟草集团有限责任公司 | Method for determining area quality of tobacco leaves based on intelligent image processing and model estimation |
CN106289070A (en) * | 2016-08-03 | 2017-01-04 | 上海创和亿电子科技发展有限公司 | The method measuring irregularly shaped object length and width |
Non-Patent Citations (3)
Title |
---|
ZHANGHAO 等: ""基于计算机图像处理技术整精米重量自动测定研究"", 《2011 INERNATIONAL SYMPOSIUM ON BIOMEDICINE AND ENGINEERING》 * |
刘启全: ""基于线阵相机的哈密瓜分级机改进设计与试验研究"", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
刘馨阳: ""基于机器视觉的动态马铃薯外部品质无损检测研究"", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113340904A (en) * | 2021-06-01 | 2021-09-03 | 贵州中烟工业有限责任公司 | Method for detecting shrinkages of tobacco flakes |
CN114612549A (en) * | 2022-01-14 | 2022-06-10 | 北京市农林科学院信息技术研究中心 | Method and device for predicting optimal fruiting picking time |
CN114612549B (en) * | 2022-01-14 | 2024-06-07 | 北京市农林科学院信息技术研究中心 | Fruiting picking optimal time prediction method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023077404A1 (en) | Defect detection method, apparatus and system | |
CN109509187B (en) | Efficient inspection algorithm for small defects in large-resolution cloth images | |
CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
CN111105405B (en) | New energy lithium battery surface defect detection method based on adaptive deep learning | |
CN104880389B (en) | A kind of automatic measurement, sophisticated category method and its system of steel crystal grain mixed crystal degree | |
CN108444934B (en) | Automatic segmentation and quantification method for debonding defect of composite material | |
CN111881851A (en) | Garden seedling intelligent detection and counting method based on UAV and convolutional neural network | |
Tao et al. | Rolling surface defect inspection for drum-shaped rollers based on deep learning | |
CN109785315A (en) | Measurement method, storage medium, terminal and the device of offal weight | |
CN109613023A (en) | A kind of fruit surface defect rapid detection method of regional luminance adaptively correcting | |
CN110554052A (en) | artificial board surface defect detection method and system | |
CN106289070A (en) | The method measuring irregularly shaped object length and width | |
CN114973032A (en) | Photovoltaic panel hot spot detection method and device based on deep convolutional neural network | |
CN113052804A (en) | Concrete member appearance quality quantitative evaluation processing method and device | |
CN109241948A (en) | A kind of NC cutting tool visual identity method and device | |
CN116434206A (en) | Cotton quality character detection method based on machine vision technology | |
CN116703909A (en) | Intelligent detection method for production quality of power adapter | |
CN116310548A (en) | Method for detecting invasive plant seeds in imported seed products | |
CN115170520A (en) | Metal mesh defect detection method based on structure contrast information lamination | |
CN116645351A (en) | Online defect detection method and system for complex scene | |
CN113012244A (en) | Egg freshness detection method based on inclusion module and Attention mechanism | |
CN101718674A (en) | Method for measuring shape parameters of particles of particulate materials | |
CN116718609A (en) | Water eutrophication detection method and device | |
CN112213244B (en) | Device and method for measuring ringeman blackness of motor vehicle tail gas based on machine learning | |
CN104165696A (en) | Material surface color feature on-line automatic detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |
|
RJ01 | Rejection of invention patent application after publication |