CN106127226B - The flexible grain quality detection method of grain grain and grain grain test sample - Google Patents
The flexible grain quality detection method of grain grain and grain grain test sample Download PDFInfo
- Publication number
- CN106127226B CN106127226B CN201610424371.1A CN201610424371A CN106127226B CN 106127226 B CN106127226 B CN 106127226B CN 201610424371 A CN201610424371 A CN 201610424371A CN 106127226 B CN106127226 B CN 106127226B
- Authority
- CN
- China
- Prior art keywords
- grain
- quality
- sample
- cloud model
- concept
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention discloses the flexible grain quality detection methods of a kind of grain grain and grain grain test sample, including 1) choose m metric attribute feature；If 2) choose solid food grain training sample, metric attribute characteristic value is extracted using machine vision method；3) reverse cloud algorithm is used, the Multidimensional Cloud Model numerical characteristic of grain sample qualities is estimated, establishes grain quality Multidimensional Cloud Model；4) to tested grain grain, metric attribute characteristic value is extracted using machine vision, calculates separately degree of certainty μ for K Evolvement of quality concept, the Evolvement of quality concept of tested grain grain is determined according to degree of certainty, and foreign peoples's wheat accounting is defined, determine therefrom that the Evolvement of quality concept of grain grain test sample.The present invention indicates the ambiguity of grain quality, randomness with the representation method of qualitativing concept, carries out flexible classification to grain grain quality, and judge whether tested sample is unusual according to the regularity of distribution of grain quality attribute.
Description
Technical field
The present invention relates to artificial intelligence and its application, grain quality detection technique field, more particularly to a kind of grain grain and
The flexible grain quality detection method of grain grain test sample.
Background technique
In current grain quality detection, using deterministic quantitative criteria, it is detected seed product different in grain samples
Matter may belong to different quality ranks；Even if the same seed, since attribute value measurement result is in the presence of centainly with chance error
Difference, homogeneous result may not belong to different quality ranks.Existing method carries out grain quality according to existing quantizating index rigid
Property classification, these uncertainties can not be effectively treated, can not effectively judge whether tested sample unusual.
In recent years, the modem technologies such as utilization is embedded, computer vision, artificial intelligence, pattern-recognition, from grain
The attributes such as certain physical characteristics, geometrical characteristic, texture are started with, and are carried out automatic, the quick detection of grain quality, have been obtained increasingly
More concerns.In artificial intelligence field, there has been proposed many classification methods, as decision tree, Bayes, artificial neural network,
K- neighbour, support vector machines, rule learning, rough set, fuzzy logic, etc..For Optimum Classification device performance, also introduce
The optimization algorithms such as ant colony, population.Bayes method, fuzzy logic, D-S evidence theory are also specifically designed to uncertainty and push away
Reason.These classification methods can obtain excellent classifying quality when being applied to specific field.But, the output of these classifiers is
Rigidity.The classification results uniquely determined are obtained to identical input.This is because classifier belongs to exact method in itself.Such as
The subordinating degree function of probability density function, fuzzy reasoning in Bayesian inference, D-S evidence theory degree of belief function once true
It is fixed, it is all with the accurate result for exporting, repeating.And certain methods depend on the subjective experience of people.These obvious classification sides
Method cannot handle the boundary uncertain problem of grain quality class.
Grain is typical bulk solid.Grain seed carries information abundant.Even the grain of same kind, no
With seed no matter in the category such as geometric shape, color, weight, hardness, water content, each index of quality, various physics, chemical property
Property, all there is random difference.This determines that grain quality classification cannot impose uniformity without examining individual cases division from each attribute dimension in itself.Packet
Including including grain quality, uncertainty is only the dialectical reflection of real world.A grain quality detection inherently classification
Problem.Such as qualified, unqualified, qualified X grade classification (referred to hereinafter as grain is divided by tested by one or more attributes
Quality class or abbreviation quality class).According to specific quantitative criteria, different grain qualities may be adhered to separately in tested grain samples
In different classifications；Even if the same seed, since there are certain random errors for attribute value measurement result, homogeneous result can not
It can belong to different classes of.It can be seen that between grain quality class and clearly boundary is not present.How this handles grain quality
Uncertainty in detection?
Summary of the invention
For these problems, the present invention proposes a kind of flexible grain quality detection based on grain quality property distribution feature
Method, extract grain quality attribute the regularity of distribution, with the representation method of qualitativing concept indicates grain quality ambiguity, at random
Property, flexible classification is carried out to grain grain quality, and judge whether tested sample is unusual according to the regularity of distribution of grain quality attribute.?
When sample is normal, tested belong to is occurred more than quantity and qualities belonging to the grain grain that degree of certainty is big.
The invention is realized by the following technical scheme:
A kind of flexible grain quality detection method of grain grain, includes the following steps:
Step 1, the m metric attribute features based on image for choosing grain grain, establish m dimension cloud model, and m is whole greater than 1
Number；
Step 2, if choosing solid food grain training sample, every kind of grain grain training sample includes grain grain number amount >=N, is regarded using machine
The m that feel method extracts N grain grains in training sample ties up metric attribute characteristic value；
Step 3, the multidimensional cloud of grain sample qualities is estimated with reverse cloud algorithm to the training sample attribute value of acquisition
Model numerical characteristic establishes K grain quality Multidimensional Cloud Model；
Step 4, to tested grain grain, metric attribute characteristic value is extracted using machine vision, is distinguished for K Evolvement of quality concept
Degree of certainty μ is calculated, tested grain grain is belonged to the Evolvement of quality concept for making degree of certainty μ obtain maximum value.
Metric attribute feature includes grain grain length axial length, short axle length, axial ratio, texture and color in the step 1.
Each sample qualities Multidimensional Cloud Model parameter of reverse cloud algorithm right to use revaluation, establishes multidimensional and adds in the step 3
Weigh cloud model.
The degree of certainty method of grain grain is calculated in the step 4 are as follows:
The attribute value for remembering j-th of grain grain is xj={ xji| i=1,2 ..., m }, j=1,2 ..., n；To K quality cloud mould
Type, is utilized respectively formula (1) and formula (2) calculates K degree of certainty μ (x of grain grainj)={ μ (xjk) | k=1,2 ..., K }:
Enki'=Norm (Enki, Heki 2) (2)
Norm indicates normal distribution, Exki, EnkiAnd HekiThe phase of respectively k-th quality cloud model ith attribute feature
Prestige, entropy and super entropy.
A kind of flexible grain quality detection method of grain grain test sample, includes the following steps:
Step 1, the m metric attribute features based on image for choosing grain grain, establish m dimension cloud model, and m is whole greater than 1
Number；
Step 2, if choosing solid food grain training sample, every kind of grain grain training sample includes grain grain number amount >=N, is regarded using machine
The m that feel method extracts N grain grains in training sample ties up metric attribute characteristic value；
Step 3, the multidimensional cloud of grain sample qualities is estimated with reverse cloud algorithm to the training sample attribute value of acquisition
Model numerical characteristic establishes K grain quality Multidimensional Cloud Model；
Step 4, if the grain grain number amount of test sample is n, each grain grain of test sample is mentioned using machine vision respectively
Metric attribute characteristic value is taken, calculates separately degree of certainty μ for K Evolvement of quality concept, each grain grain, which is belonged to, makes μ obtain maximum value
Evolvement of quality concept；
Step 5, foreign peoples's grain grain accounting r is calculated according to formula (3),
R=(n-nmax)/n (3), n in formulamaxTo belong to the most grain grain number amount of same Evolvement of quality concept；
Step 6, given threshold r0, as r≤r0When, it is believed that sample is normal, and test sample is belonged to nmaxA grain grain is returned
The Evolvement of quality concept of category；Otherwise it is assumed that sample is unusual, refusal determines its quality.
Metric attribute feature includes grain grain length axial length, short axle length, axial ratio, texture and color in the step 1.
Each sample qualities Multidimensional Cloud Model parameter of reverse cloud algorithm right to use revaluation, establishes multidimensional and adds in the step 3
Weigh cloud model.
Compared with prior art, the present invention having following obvious advantage:
(1) grain quality is considered as qualitativing concept, clearly boundary is needed not necessarily exist between each quality
Since grain quality is embodied by the way that a large amount of grain grains are comprehensive, and metric attribute has random difference in the realization of each grain grain
It is different.Accordingly, with respect to the method that tradition rigidly defines grain quality according to both quantitative indices, it is regarded as that there is uncertainty
Qualitativing concept it is more particularly suitable.Grain quality is considered as qualitativing concept by the present invention, estimates grain quality concept according to grain grain sample
Uncertain feature, its ambiguity, randomness are portrayed using cloud model, use grain grain quality degree of certainty indicate grain grain quality
The degree of grain quality can be represented.Fine limit, the attribute of energy objective description grain quality are not present between grain quality concept
Distribution characteristics.
(2) the flexible output of grain grain attribute classification utensil
Grain grain quality affiliation method is designed based on grain grain quality degree of certainty.Grain grain, which is belonged in quality cloud space, takes it
Obtain the grain quality of maximum determining angle value.Since degree of certainty is the random number with steady tendency, classification results are not
It is deterministic.Even if homogeneous does not belong to algorithm with water dust to same grain grain, different classification results will be obtained.Grain grain according to
Probability belongs to several concepts in grain quality space.Therefore, the output of grain grain attribute classification device has flexibility.It is especially suitable for
Handle the quality value of borderline region.This feature has no effect on the judgement result of sample overall quality.On the contrary, if borderline region
Foreign peoples's quantity increases, and can differentiate the singularity of sample instead, plays the role of enhancing grain quality discriminant information.
Detailed description of the invention
Fig. 1 is flexible grain quality detection method schematic diagram of the invention.
Fig. 2 is wheat quality cloud exemplary diagram of the invention.
Fig. 3 is that water dust of the invention belongs to probability distribution result plane exemplary diagram.
Specific embodiment
Fig. 1 is the flexibility qualities classification method general structure schematic diagram in the grain quality detection that the present invention announces.Mainly
Detailed description is as follows.
(1) grain quality is considered as qualitativing concept.
Grain quality attribute value has otherness in the distribution of each grain grain.Different grain grains may belong to different qualities,
The not homogeneous testing result of same grain grain may also be divided into different qualities.Fine limit is not present between grain quality, at this
Belong to qualitativing concept in matter.Uncertainty includes ambiguity and randomness.Difference between each grain grain metric attribute value is smaller,
Then Evolvement of quality concept is more clear；It is on the contrary then fuzzyyer.Randomness features distribution of the grain grain metric attribute in domain.
(2) using normal cloud model as the basic research tool of qualitativing concept
Cloud model can describe the ambiguity of qualitativing concept and randomness unified quantization.Grain quality can be considered qualitative general
It reads.Grain grain quality is the Stochastic implementation of grain quality, can be considered water dust.Therefore, indicate that grain quality is most suitable not with cloud model
It crosses.The parameter of cloud model C (Ex, En, He) estimates there is objectivity from sample.
(3) using attributes such as grain grain geometrical characteristic, texture, colors as metric attribute collection
With grain grain length axial length, short axle length, axial ratio, texture, color, as grain grain quality candidate attribute collection.
(4) grain grain sample is chosen, using machine vision method, extracts attributive character value respectively
By taking wheat as an example.Choose 10 kinds or more common wheat breeds.Each sample wheat is not less than 500, as training
Sample.Each sample grain grain attribute value is obtained respectively using machine vision technique means.
(5) reverse cloud algorithm is used, the Multidimensional Cloud Model numerical characteristic of grain sample qualities is estimated, it is more to establish grain quality
Tie up normal cloud model
To the training sample attribute value of acquisition, reverse cloud algorithm is used respectively, and considers whether to estimate various kinds using weight
This quality Multidimensional Cloud Model parameter establishes their Multidimensional Cloud Model or multidimensional weighting cloud model.
(6) grain grain quality flexibility of the design based on degree of certainty μ belongs to algorithm, investigates the probability that grain grain belongs to different qualities
Feature
Water dust degree of certainty μ is the random number for having steady tendency.The flexible classification of grain grain quality can be realized using this feature.
Algorithm designs basic thought: to the grain grain of test sample, extracting metric attribute characteristic value using machine vision, respectively
Them are calculated in the joint degree of certainty μ of each attribute dimension in all Evolvement of quality concept spaces, it is belonged to the product for making μ obtain maximum value
Matter concept.Due to the randomness of μ, classification results have uncertainty.Water dust belongs to multiple concepts according to probability.
It to whole grain grains of any test sample, repeats to use algorithm, investigates the probability distribution that grain grain belongs to each quality
Feature.Fig. 3 is the distribution results exemplary diagram that water dust ownership probability is intercepted along L-S=0.7mm plane.In Fig. 3, P is estimation
The probability for belonging to some cloud model, L is the long axial length of wheat (unit: millimeter), and S is that wheat short axle is long (unit: millimeter).
C1, C2, C3 respectively correspond C { (1.8,0.05,0.02), (1.1,0.05,0.02) }, C (2.0,0.05,0.02), (1.3,
0.05,0.02)}、C{(2.2,0.05,0.02),(1.5,0.05,0.02)}。
(7) it is based on the grain grain metric attribute regularity of distribution, designs the overall quality fusion method of test sample
According to above-mentioned classification method, the grain grain of borderline region can belong to multiple Evolvement of quality concept.According to grain grain quality point
Cloth rule, further away from the expectation of Evolvement of quality concept, the degree of certainty that quality value can represent the Evolvement of quality concept is lower.Its probability occurred
It answers smaller.According to this principle, the singularity method of discrimination of grain grain attribute classification is designed.To normal sample, its quality is belonged to
Quality belonging to the grain grain more and big degree of certainty in frequency of occurrence.
For example, being detected as research object with wheat quality.
(1) quantization means of wheat quality
Wheat quality attributive character of the note based on image has m, can tie up cloud model C (X with m1, X2..., Xm) indicate small
Wheat quality.That is: C { (Exi, Eni, Hei) | i=1,2 ..., m }, wherein Exi, Eni, HeiEstimation self-training sample, respectively i-th
Expectation, entropy and the super entropy of a attributive character.The sample of different qualities is chosen, corresponding wheat quality cloud model can be established.It is assumed that
The wheat quality cloud model of foundation is K.Then K wheat quality cloud is denoted as Ck{(Exki, Enki, Heki) | i=1,2 ..., m }, k
=1,2 ..., K.For wheat quality cloud example as shown in Fig. 2, in Fig. 2, μ is degree of certainty, and L is the long axial length of wheat (unit: millimeter), S
It is long (unit: millimeter) for wheat short axle.The parameter of the long long two-dimension cloud model of axial length-short axle of three wheats be respectively C (1.8,
0.05,0.02),(1.1,0.05,0.02)}、C{(2.0,0.05,0.02),(1.3,0.05,0.02)}、C{(2.2,0.05,
0.02), (1.5,0.05,0.02) }, between different qualities and fine limit is not present as can be seen from Figure 2.
(2) the flexible ownership algorithm of wheat quality
To the n grain wheat of tested sample, the m dimension attribute characteristic value of every wheat is extracted using machine vision.Jth grain wheat
Attribute value be denoted as xj={ xji| i=1,2 ..., m }, j=1,2 ..., n.To K quality cloud model, it is utilized respectively following formula calculating
xiBelong to their degree of certainty:
Enki'=Norm (Enki, Heki 2) (2)
Norm indicates normal distribution in above formula.K degree of certainty μ (x can be obtainedj)={ μ (xjk) | k=1,2 ..., K }.If μI
=max { μ (xjk) | k=1,2 ..., K }, the maximum value in as K degree of certainty, then by water dust xjBelong to quality cloud I, I K
The subscript k value of maximum degree of certainty in a degree of certainty.
From formula (1) and (2) as can be seen that due to Enki' meet normal distribution, μ (xjk) it is also random.Therefore to water dust
xj, each calculated result may make it belong to different Evolvement of quality concept.But μ (xjk) there is steady tendency.Water dust x as a result,j
Several wheat quality cloud concepts will be belonged to according to probability, and will no longer be rigid and be divided into some quality grade.Wheat quality
Belong to the probability distribution example such as figure (3) of different quality clouds.
(3) it is detected sample singularity method of discrimination
Above-mentioned wheat can belong to the flexible sorting algorithm of different Evolvement of quality concept, it appears that the overall quality for tested sample is sentenced
Surely it causes to conflict.In fact, this method will not only cause contradiction, information enhancement can be played the role of instead.It can from Fig. 2
Out, far from desired quality value, the degree of certainty that it can represent the quality is smaller, and the number occurred is also lower.It is regular according to this,
May determine that whether sample is unusual.If the wheat quantity for belonging to different qualities is close, illustrate that the sample is unusual.And
When only belonging to the wheat quantity of a certain quality much larger than the wheat quantity for belonging to foreign peoples's quality, it could illustrate that sample is just
Normal.Principle accordingly defines foreign peoples's wheat accounting to the sample for having n wheat
R=(n-nmax)/n (3)
N in formulamaxTo belong to the most wheat quantity of same Evolvement of quality concept.Given threshold r0.As r≤r0When, it is believed that sample
This is normal.Otherwise it is assumed that sample is unusual.
(4) wheat sample qualities are detected to determine
To unusual sample, refusal determines its quality.It is n by its quality judging when sample is normalmaxA wheat institute is common
That Evolvement of quality concept of ownership.
Each attribute of grain quality shows as the synthesis of a large amount of grain grain respective attributes.It sees in turn, each seed is this
One Stochastic implementation of grain, the attribute value of each seed are a Stochastic implementations of its grain quality respective attributes.Even if
It is kind similar in integrity attribute, the attribute value distribution characteristics realized on each seed may be different.Due to grain quality
In the distributional difference of each grain grain, it has ambiguity and random nature.Ambiguity characterizes metric attribute value in domain
Intensity.Grain grain attribute value is more concentrated, and overall quality is more clear；It is on the contrary then fuzzyyer.Randomness then characterizes each grain
The difference degree of grain metric attribute value.Therefore, grain quality belongs to qualitativing concept in itself.From grain attribute in each seed
Distribution characteristics start with, according to the expression of qualitativing concept and classification method processing grain quality detection in uncertain problem,
More reasonable result can be obtained.
Grain quality determines that it belongs to qualitativing concept in the otherness that each grain grain is realized.The metric attribute of each grain grain
Value is a Stochastic implementation of grain quality respective attributes.Its degree of certainty μ, which indicates it, can represent the overall quality attribute
Degree.Due to the steady tendency and randomness of μ, classifier is related to based on it, the flexibility that can be realized grain quality classification is drawn
Point.
The technical means disclosed in the embodiments of the present invention is not limited only to technological means disclosed in above embodiment, further includes
Technical solution consisting of any combination of the above technical features.It should be pointed out that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (6)
1. a kind of flexible grain quality detection method of grain grain, characterized by the following steps:
Step 1, the m metric attribute features based on image for choosing grain grain, establish m dimension cloud model, and m is the integer greater than 1；Step
Rapid 2, if choosing solid food grain training sample, every kind of grain grain training sample includes grain grain number amount >=N, is extracted using machine vision method
The m of N grain grains ties up metric attribute characteristic value in training sample；
Step 3, the Multidimensional Cloud Model of grain sample qualities is estimated with reverse cloud algorithm to the training sample attribute value of acquisition
Numerical characteristic establishes K grain quality Multidimensional Cloud Model；
Step 4, to tested grain grain, metric attribute characteristic value is extracted using machine vision, is calculated separately for K Evolvement of quality concept
Tested grain grain is belonged to the Evolvement of quality concept for making degree of certainty μ obtain maximum value by degree of certainty μ；
The degree of certainty method of grain grain is calculated in the step 4 are as follows:
The attribute value for remembering j-th of grain grain is xj={ xji| i=1,2 ..., m }, j=1,2 ..., n；To K quality cloud model, divide
Not Li Yong formula (1) and formula (2) calculate K degree of certainty μ (x of grain grainj)={ μ (xjk) | k=1,2 ..., K }:
Enki'=Norm (Enki, Heki 2) (2)
Norm indicates normal distribution, Exki, EnkiAnd HekiThe expectation of respectively k-th quality cloud model ith attribute feature, entropy
With super entropy.
2. the flexible grain quality detection method of grain grain according to claim 1, it is characterised in that: product in the step 1
Matter attributive character includes grain grain length axial length, short axle length, axial ratio, texture and color.
3. the flexible grain quality detection method of grain grain according to claim 1, it is characterised in that: inverse in the step 3
To each sample qualities Multidimensional Cloud Model parameter of cloud algorithm right to use revaluation, multidimensional weighting cloud model is established.
4. a kind of flexible grain quality detection method of grain grain test sample, characterized by the following steps:
Step 1, the m metric attribute features based on image for choosing grain grain, establish m dimension cloud model, and m is the integer greater than 1；Step
Rapid 2, if choosing solid food grain training sample, every kind of grain grain training sample includes grain grain number amount >=N, is extracted using machine vision method
The m of N grain grains ties up metric attribute characteristic value in training sample；
Step 3, the Multidimensional Cloud Model of grain sample qualities is estimated with reverse cloud algorithm to the training sample attribute value of acquisition
Numerical characteristic establishes K grain quality Multidimensional Cloud Model；
Step 4, if the grain grain number amount of test sample is n, product are extracted using machine vision to each grain grain of test sample respectively
Matter attributive character value calculates separately degree of certainty μ for K Evolvement of quality concept, and each grain grain is belonged to the product for making μ obtain maximum value
Matter concept；
Step 5, foreign peoples's grain grain accounting r is calculated according to formula (3),
R=(n-nmax)/n (3), n in formulamaxTo belong to the most grain grain number amount of same Evolvement of quality concept；
Step 6, given threshold r0, as r≤r0When, it is believed that sample is normal, and test sample is belonged to nmaxWhat a grain grain was belonged to
Evolvement of quality concept；Otherwise it is assumed that sample is unusual, refusal determines its quality.
5. the flexible grain quality detection method of grain grain test sample according to claim 4, it is characterised in that: the step
Metric attribute feature includes grain grain length axial length, short axle length, axial ratio, texture and color in rapid 1.
6. the flexible grain quality detection method of grain grain test sample according to claim 4, it is characterised in that: the step
Each sample qualities Multidimensional Cloud Model parameter of reverse cloud algorithm right to use revaluation in rapid 3 establishes multidimensional weighting cloud model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610424371.1A CN106127226B (en) | 2016-06-14 | 2016-06-14 | The flexible grain quality detection method of grain grain and grain grain test sample |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610424371.1A CN106127226B (en) | 2016-06-14 | 2016-06-14 | The flexible grain quality detection method of grain grain and grain grain test sample |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106127226A CN106127226A (en) | 2016-11-16 |
| CN106127226B true CN106127226B (en) | 2019-09-03 |
Family
ID=57469438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610424371.1A Expired - Fee Related CN106127226B (en) | 2016-06-14 | 2016-06-14 | The flexible grain quality detection method of grain grain and grain grain test sample |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127226B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106768077A (en) * | 2017-02-18 | 2017-05-31 | 塔里木大学 | A kind of jujube quality detection system |
| CN108241290A (en) * | 2017-12-19 | 2018-07-03 | 中国农业生产资料流通协会 | A kind of warehouse recirculation fumigation control method based on fuzzy-adaptation PID control |
| CN108171432B (en) * | 2018-01-04 | 2021-08-10 | 南京大学 | Ecological risk evaluation method based on multi-dimensional cloud model-fuzzy support vector machine |
| EP3620984B1 (en) * | 2018-09-06 | 2024-04-10 | Accenture Global Solutions Limited | Digital quality control using computer visioning with deep learning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3763818B2 (en) * | 2003-01-06 | 2006-04-05 | 株式会社クボタ | Grain inspection equipment |
| CN101251526A (en) * | 2008-02-26 | 2008-08-27 | 浙江大学 | Method and apparatus for nondestructively testing food synthetic quality |
| CN102589470A (en) * | 2012-02-14 | 2012-07-18 | 大闽食品（漳州）有限公司 | Fuzzy-neural-network-based tea leaf appearance quality quantification method |
| CN103489006A (en) * | 2013-10-11 | 2014-01-01 | 河南城建学院 | Computer vision-based rice disease, pest and weed diagnostic method |
| CN104155312A (en) * | 2014-08-11 | 2014-11-19 | 华北水利水电大学 | Method for detecting pests in food grains based on near infrared machine vision, and apparatus thereof |
| CN104535646A (en) * | 2014-12-17 | 2015-04-22 | 河南工业大学 | Method for detecting imperfection of food grains |
| CN104749070A (en) * | 2015-04-15 | 2015-07-01 | 河南工业大学 | Method for rapidly evaluating wheat quality |
-
2016
- 2016-06-14 CN CN201610424371.1A patent/CN106127226B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3763818B2 (en) * | 2003-01-06 | 2006-04-05 | 株式会社クボタ | Grain inspection equipment |
| CN101251526A (en) * | 2008-02-26 | 2008-08-27 | 浙江大学 | Method and apparatus for nondestructively testing food synthetic quality |
| CN102589470A (en) * | 2012-02-14 | 2012-07-18 | 大闽食品（漳州）有限公司 | Fuzzy-neural-network-based tea leaf appearance quality quantification method |
| CN103489006A (en) * | 2013-10-11 | 2014-01-01 | 河南城建学院 | Computer vision-based rice disease, pest and weed diagnostic method |
| CN104155312A (en) * | 2014-08-11 | 2014-11-19 | 华北水利水电大学 | Method for detecting pests in food grains based on near infrared machine vision, and apparatus thereof |
| CN104535646A (en) * | 2014-12-17 | 2015-04-22 | 河南工业大学 | Method for detecting imperfection of food grains |
| CN104749070A (en) * | 2015-04-15 | 2015-07-01 | 河南工业大学 | Method for rapidly evaluating wheat quality |
Non-Patent Citations (1)
| Title |
|---|
| 基于云理论的粮食品质检测不确定性研究;范艳峰 等;《河南工业大学学报(自然科学版)》;20110430;第32卷(第4期);第2节，第4节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106127226A (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127226B (en) | The flexible grain quality detection method of grain grain and grain grain test sample | |
| Valverde-Rebaza et al. | Link prediction in complex networks based on cluster information | |
| Isa et al. | Using the self organizing map for clustering of text documents | |
| CN100557626C (en) | Image partition method based on immune spectrum clustering | |
| CN110110802A (en) | Airborne laser point cloud classification method based on high-order condition random field | |
| CN105956184B (en) | Collaborative and organized junk information issue the recognition methods of group in a kind of microblogging community network | |
| CN108304316A (en) | A kind of Software Defects Predict Methods based on collaboration migration | |
| CN101893704A (en) | Rough set-based radar radiation source signal identification method | |
| Orriols et al. | The class imbalance problem in learning classifier systems: a preliminary study | |
| CN108496185A (en) | System and method for object detection | |
| CN107766792A (en) | A kind of remote sensing images ship seakeeping method | |
| Dahiya et al. | Using clustering techniques and classification mechanisms for fault diagnosis | |
| CN112214684A (en) | Seed-expanded overlapped community discovery method and device | |
| Lobel et al. | Preliminary results on social learning with partial observations | |
| Mwebaze et al. | Causal structure learning for famine prediction | |
| CN109472712A (en) | A kind of efficient Markov random field Combo discovering method strengthened based on structure feature | |
| Li et al. | Study on the Prediction of Imbalanced Bank Customer Churn Based on Generative Adversarial Network | |
| Cesa-Bianchi et al. | Active learning on graphs via spanning trees | |
| WO2018151619A1 (en) | Network analysis tool testing | |
| Kalaibar et al. | Spam filtering by using genetic based feature selection | |
| Liu et al. | A united classification system of X-ray image based on fuzzy rule and neural networks | |
| Xu et al. | Patch SVDD (support vector data description)-based channel attention embedding and improvement of classifier | |
| Boursinos et al. | Reliable probability intervals for classification using inductive venn predictors based on distance learning | |
| Hussein et al. | A modified adaptive synthetic sampling method for learning imbalanced datasets | |
| Talavera | Dynamic feature selection in incremental hierarchical clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190903 Termination date: 20200614 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |