CN108427971A - The method and system of tobacco leaf grading based on mobile terminal - Google Patents
The method and system of tobacco leaf grading based on mobile terminal Download PDFInfo
- Publication number
- CN108427971A CN108427971A CN201810354436.9A CN201810354436A CN108427971A CN 108427971 A CN108427971 A CN 108427971A CN 201810354436 A CN201810354436 A CN 201810354436A CN 108427971 A CN108427971 A CN 108427971A
- Authority
- CN
- China
- Prior art keywords
- tobacco leaf
- image
- mobile terminal
- grading
- image data
- 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
- 241000208125 Nicotiana Species 0.000 title claims abstract description 118
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 118
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 abstract description 10
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 238000012706 support-vector machine Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 235000019504 cigarettes Nutrition 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000000697 sensory organ Anatomy 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000015541 sensory perception of touch Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the method and system of the tobacco leaf grading based on mobile terminal, this method includes obtaining green tobacco leaf and dry tobacco leaf image data；Image data is pre-processed；Obtain the characteristics of image of pretreated image data；It grades to the characteristics of image of extraction；Obtain rating result.The present invention is by obtaining tobacco leaf image, classify after image is pre-processed and grades, the high in the clouds for conveying image under the conditions of network condition is good, carry out extremely efficient classification and grading, accurate tobacco classification is efficiently realized under noisy current conditions, full automatic data chain system gets through production line mobile terminal and high in the clouds machine learning system, it is high with classification effectiveness accuracy rate, hardware calculated level is required flexible, it is easy to operate, realize the classification tobacco leaf of very high degree of precision, with high universality, classification effectiveness accuracy rate is high, hardware system performance is required low, it is easy to operate, save a large amount of human resources.
Description
Technical field
The present invention relates to tobacco leaf rating technique field, more specifically refer to based on mobile terminal dry tobacco leaf grading and
The method and system of green tobacco leaf maturity grading.
Background technology
Tobacco leaf crop occupies an important position in China's agricultural production.In the purchase of tobacco leaf crop, rating system is to peasant
It is of great significance with the interests of businessman.For a long time, whether domestic or external, the detection and classification of quality of tobacco are all
With reference to the tobacco leaf sample of tobacco leaf grading standard and standard that each department are promulgated, judge by the vision and tactile sense organ of people
Classification.Therefore, before every purchase tobacco leaf, each cigarette district in the whole nation will set up study class, collect a large amount of, standard tobacco leaf sample
This is as training material, and for training the tobacco leaf grading personnel of purchasing station, such hierarchical approaches need to consume and take damage largely
Human and material resources and financial resources, and mesh efficiency is also very low.Prior aspect is that the sense organ of the mankind judges to carry strong master
The property seen and ambiguity, affect the careful property of tobacco leaf grading and variational judgement are made the result of inspection and classification there is
Larger difference.
China's tobacco leaf rating system and implementation rely primarily on the field monitoring in expert at present, have efficiency low, of high cost,
The obvious shortcomings such as subjectivity is strong, also, expert's classification is very high to manual request.The culture of expert needs stringent training mechanism,
The qualification of professional ability needs prolonged practical experience.
In recent years, the rise with artificial intelligence in agricultural is applied has a small number of based on automatic intelligent equipment and algorithm
Technology and system have found value in agricultural is applied.However, existing automatic tobacco leaf grading system has many limitations
Property, cause its effect in practical application that expected standard is not achieved, therefore checked there is still a need for a large amount of manpower, it is existing
The categorizing system that automatic classification system is mainly based upon traditional supervised learning and magnanimity calculates, such system have apparent limitation
Property：Require high, traditional machine learning algorithm that a large amount of calculate is needed to reach satisfied precision hardware device, therefore tradition point
Class system is present under the controllable monitoring of environmental in laboratory more, and the grading of tobacco leaf needs to carry out quickly in industry spot in reality
Classification, precision is low, traditional machine learning and image processing algorithm, needs the monitoring of environmental condition strictly controlled, it is difficult in reality
The performance being optimal in the noisy workshop on border needs a large amount of manpower and materials completions to reach to strictly monitoring condition, such as
Manually tobacco leaf is transported from workshop to laboratory, greatly reduces production efficiency.
Therefore, it is necessary to design a kind of new tobacco leaf ranking method, the classification tobacco leaf of very high degree of precision is realized, have high pervasive
Property, classification effectiveness accuracy rate is high, low to hardware system performance requirement, easy to operate, saves a large amount of human resources.
Invention content
It is an object of the invention to overcome the deficiencies of existing technologies, provide based on mobile terminal tobacco leaf grading method and
System.
To achieve the above object, the present invention uses following technical scheme：The method of tobacco leaf grading based on mobile terminal, institute
The method of stating includes：
Obtain green tobacco leaf and dry tobacco leaf image data；
Image data is pre-processed；
Obtain the characteristics of image of pretreated image data；
It grades to the characteristics of image of extraction；
Obtain rating result.
Its further technical solution is：Pretreated step, including step in detail below are carried out to image data：
The relevant parameter for adjusting image, generates normalized image pattern；
Tobacco leaf in image pattern is positioned and divided.
Its further technical solution is：The relevant parameter of image is adjusted, it is the step of generating normalized image pattern, described
Relevant parameter include illumination condition, shooting angle, ratio and tobacco leaf position in it is at least one.
Its further technical solution is：The step of obtaining the characteristics of image of pretreated image data, including following tool
Body step：
Obtain tobacco leaf validity feature；
Classify to validity feature, forms the characteristics of image of each tobacco leaf.
Its further technical solution is：In the step of obtaining tobacco leaf validity feature, the validity feature includes obtaining tobacco leaf
Textural characteristics, length, at least one in color and residual degree of wound.
The present invention also provides the systems of the tobacco leaf grading based on mobile terminal, including image acquisition unit, pretreatment list
Member, feature acquiring unit, grading unit and result acquiring unit；
Described image acquiring unit, for obtaining green tobacco leaf and dry tobacco leaf image data；
The pretreatment unit, for being pre-processed to image data；
The feature acquiring unit, the characteristics of image for obtaining pretreated image data；
The grading unit, grades for the characteristics of image to extraction；
The result acquiring unit, for obtaining rating result.
Its further technical solution is：The pretreatment unit includes normalization module and locating segmentation module；
The normalization module, the relevant parameter for adjusting image generate normalized image pattern；
The locating segmentation module, for being positioned and being divided the tobacco leaf in image pattern.
Its further technical solution is：The feature acquiring unit includes validity feature acquisition module and sort module；
The validity feature acquisition module, for obtaining tobacco leaf validity feature；
The sort module forms the characteristics of image of each tobacco leaf for classifying to validity feature.
Compared with the prior art, the invention has the advantages that：The side of the tobacco leaf grading based on mobile terminal of the present invention
Method, by obtaining tobacco leaf image, grading of classifying after image is pre-processed is defeated by image under the conditions of network condition is good
The high in the clouds sent carries out extremely efficient classification and grading, accurate tobacco classification is efficiently realized under noisy current conditions, entirely
Automatic data chain system gets through production line mobile terminal and high in the clouds machine learning system, has classification effectiveness accuracy rate height,
Hardware calculated level is required flexibly, it is easy to operate, it realizes the classification tobacco leaf of very high degree of precision, there is high universality, classification effectiveness
Accuracy rate is high, low to hardware system performance requirement, easy to operate, saves a large amount of human resources.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Description of the drawings
Fig. 1 is the flow chart one of the method for the tobacco leaf grading based on mobile terminal that the specific embodiment of the invention provides；
Fig. 2 is the flowchart 2 of the method for the tobacco leaf grading based on mobile terminal that the specific embodiment of the invention provides；
Fig. 3 carries out pretreated flow chart for what the specific embodiment of the invention provided to image data；
Fig. 4 is the flow chart of the characteristics of image for the pretreated image data of acquisition that the specific embodiment of the invention provides
One；
Fig. 5 is the flow chart of the characteristics of image for the pretreated image data of acquisition that the specific embodiment of the invention provides
Two；
Fig. 6 is the structure diagram of the system for the tobacco leaf grading based on mobile terminal that the specific embodiment of the invention provides；
Fig. 7 is the structure diagram for the pretreatment unit that the specific embodiment of the invention provides；
Fig. 8 is the structure diagram for the feature acquiring unit that the specific embodiment of the invention provides.
Specific implementation mode
In order to more fully understand the present invention technology contents, with reference to specific embodiment to technical scheme of the present invention into
One step introduction and explanation, but not limited to this.
The specific embodiment as shown in Fig. 1~8, the method for the tobacco leaf grading provided in this embodiment based on mobile terminal,
It can be used in in dry tobacco leaf grading and green tobacco leaf maturity ranking process, realizing the classification tobacco leaf of very high degree of precision, having
High universality, classification effectiveness accuracy rate is high, low to hardware system performance requirement, easy to operate, saves a large amount of human resources.
As shown in Figure 1, the method for present embodiments providing the tobacco leaf grading based on mobile terminal, this method include：
S1, green tobacco leaf and dry tobacco leaf image data are obtained；
S2, image data is pre-processed；
S3, the characteristics of image for obtaining pretreated image data；
S4, it grades to the characteristics of image of extraction；
S5, rating result is obtained.
For above-mentioned S1 steps, specifically, green tobacco leaf and dry tobacco leaf are obtained from tobacco leaf grading scene using video camera
Image data, as the input data based on machine learning rating system.
Further, in certain embodiments, above-mentioned S2 steps carry out pretreated step, packet to image data
Include step in detail below：
S21, the relevant parameter for adjusting image, generate normalized image pattern；
S22, the tobacco leaf in image pattern is positioned and is divided.
It is described the step of adjusting the relevant parameter of image, generate normalized image pattern for above-mentioned S21 steps
Relevant parameter include illumination condition, shooting angle, ratio and tobacco leaf position in it is at least one.
For above-mentioned S22 steps, specifically, by the image segmentation algorithm based on super-pixel and supervised learning by cigarette
Leaf is split, and to effectively reduce the noise that may be brought under the conditions of actual photographed, is greatly increased in practical stage
Accuracy rate.
In addition, in certain embodiments, above-mentioned S3 steps obtain the step of the characteristics of image of pretreated image data
Suddenly, including in detail below step：
S31, tobacco leaf validity feature is obtained；
S32, classify to validity feature, form the characteristics of image of each tobacco leaf.
Wherein, for above-mentioned S31 steps, in the step of obtaining tobacco leaf validity feature, the validity feature includes obtaining
It is at least one in the textural characteristics of tobacco leaf, length, color and residual degree of wound.
Based on mobile terminal carry out validity feature extraction and classification, due to mobile terminal computing capability limit, image it is pre-
Processing and characteristics of image of the characteristic extracting module based on lightweight and the grader based on support vector machines, using few
High-precision classification is provided under conditions of computing resource, and high in the clouds Distributed Calculation is serviced especially by the network based on deep learning
Very high degree of precision categorizing system, can in the case that network state it is good by network transmission obtain image data carry out it is high
The classification of precision.High-precision tobacco classification, full automatic data chain are efficiently realized in the case where network condition limits
System gets through mobile terminal and high in the clouds machine learning system, and the classification of very high degree of precision is carried out under the conditions of network condition is good,
With high universality, classification effectiveness accuracy rate is high, low to hardware system performance requirement, easy to operate, saves a large amount of human resources
The characteristics of.
For above-mentioned S32 steps, the lower validity feature extraction of operand requirement is carried out on the tobacco leaf being partitioned into, with
And the Fast Classification carried out in feature vector includes specifically the textural characteristics of tobacco leaf by the extraction of mobile terminal processor, it is long
Degree, color, residual degree of wound etc.；Again by having moduli type based on supervised learning and support vector machines, model size is effectively carried out
Control and forecasting accuracy；The high in the clouds for conveying image under the conditions of network condition is good, carries out extremely efficient classification and comments
Grade；By the assessment to network state and hardware computing capability, the categorised decision in mobile terminal or high in the clouds is carried out.
In addition, for above-mentioned S32 steps, using the grader based on support vector machines, few computing resource is being used
Under conditions of high-precision classification is provided, specifically, use
(xi,yi) it is one group of training data, wherein xiIt is that tobacco leaf image is indicated in the vectorial of feature space, yiFor the correct grading of tobacco leaf
Mark, n are disaggregated model training data total amount, and b is the intercept parameter of disaggregated model.By the optimization to this object function, obtain
To supporting vector machine model w, it to be used for the prediction of test data.
Preferably, in some instances, system is decided whether by the computing capability of current network conditions and mobile terminal
The classification based on mobile terminal is carried out, or image transmitting is carried out to the complicated categorizing system based on high in the clouds.
Specifically, when textural characteristics, length, color and residual degree of wound are more eligible, then higher grade, such as same line
Feature, length, color are managed, the more low then more high grade of residual degree of wound.
The method of the above-mentioned tobacco leaf grading based on mobile terminal is pre-processed image by obtaining tobacco leaf image
Classification grading afterwards, the high in the clouds for conveying image under the conditions of network condition is good, carries out extremely efficient classification and grading, efficiently
Realize accurate tobacco classification under noisy current conditions, full automatic data chain system get through production line mobile terminal with
And high in the clouds machine learning system, there is classification effectiveness accuracy rate height, require hardware calculated level flexible, easy to operate, realization
The classification tobacco leaf of very high degree of precision has high universality, and classification effectiveness accuracy rate is high, requires hardware system performance low, operation letter
It is single, save a large amount of human resources.
As shown in fig. 6, the system that the present embodiment additionally provides the grading of the tobacco leaf based on mobile terminal, which is characterized in that packet
Include image acquisition unit 1, pretreatment unit 2, feature acquiring unit 3, grading unit 4 and result acquiring unit 5.
Image acquisition unit 1, for obtaining green tobacco leaf and dry tobacco leaf image data.
Pretreatment unit 2, for being pre-processed to image data.
Feature acquiring unit 3, the characteristics of image for obtaining pretreated image data.
Grading unit 4, grades for the characteristics of image to extraction.
As a result acquiring unit 5, for obtaining rating result.
For image acquisition unit 1, specifically, green tobacco leaf and dry cigarette are obtained from tobacco leaf grading scene using video camera
Leaf image data, as the input data based on machine learning rating system.
Further, in certain embodiments, pretreatment unit 2 includes normalization module 21 and locating segmentation module
22。
Module 21 is normalized, the relevant parameter for adjusting image generates normalized image pattern.The relevant parameter
It is at least one in position including illumination condition, shooting angle, ratio and tobacco leaf.
Locating segmentation module 22, for being positioned and being divided the tobacco leaf in image pattern.Specifically, by being based on surpassing
Tobacco leaf is split by the image segmentation algorithm of pixel and supervised learning, thus can energy band under the conditions of effectively reducing actual photographed
The noise come greatly increases the accuracy rate in practical stage.
In addition, in certain embodiments, above-mentioned feature acquiring unit 3 includes validity feature acquisition module 31 and classification
Module 32.
Validity feature acquisition module 31, for obtaining tobacco leaf validity feature.The validity feature includes the line for obtaining tobacco leaf
It manages at least one in feature, length, color and residual degree of wound.
Sort module 32 forms the characteristics of image of each tobacco leaf for classifying to validity feature.
Based on mobile terminal carry out validity feature extraction and classification, due to mobile terminal computing capability limit, image it is pre-
Processing and characteristics of image of the characteristic extracting module based on lightweight and the grader based on support vector machines, using few
High-precision classification is provided under conditions of computing resource, and high in the clouds Distributed Calculation is serviced especially by the network based on deep learning
Very high degree of precision categorizing system, can in the case that network state it is good by network transmission obtain image data carry out it is high
The classification of precision.High-precision tobacco classification, full automatic data chain are efficiently realized in the case where network condition limits
System gets through mobile terminal and high in the clouds machine learning system, and the classification of very high degree of precision is carried out under the conditions of network condition is good,
With high universality, classification effectiveness accuracy rate is high, low to hardware system performance requirement, easy to operate, saves a large amount of human resources
The characteristics of.
For above-mentioned sort module 32, the progress lower validity feature of operand requirement carries on the tobacco leaf being partitioned into
It takes, and the Fast Classification carried out in feature vector, includes the texture spy of tobacco leaf by the extraction of mobile terminal processor specifically
Sign, length, color, residual degree of wound etc.；Again by having moduli type based on supervised learning and support vector machines, model is effectively carried out
Size controls and forecasting accuracy；The high in the clouds for conveying image under the conditions of network condition is good, carries out extremely efficient classification
With grading；By the assessment to network state and hardware computing capability, the categorised decision in mobile terminal or high in the clouds is carried out.
In addition, for above-mentioned sort module 32, using the grader based on support vector machines, provided using few calculate
High-precision classification is provided under conditions of source, specifically, is used
(xi,yi) it is one group of training data, wherein xiIt is that tobacco leaf image is indicated in the vectorial of feature space, yiFor the correct grading of tobacco leaf
Mark, n are disaggregated model training data total amount, and b is the intercept parameter of disaggregated model.By the optimization to this object function, obtain
To supporting vector machine model w, it to be used for the prediction of test data.
Preferably, in some instances, system is decided whether by the computing capability of current network conditions and mobile terminal
The classification based on mobile terminal is carried out, or image transmitting is carried out to the complicated categorizing system based on high in the clouds.
Specifically, when textural characteristics, length, color and residual degree of wound are more eligible, then higher grade, such as same line
Feature, length, color are managed, the more low then more high grade of residual degree of wound.
In addition, the system that the present embodiment additionally provides the grading of the tobacco leaf based on mobile terminal comprising：At one or more
Reason device, memory, and, one or more programs, the one or more program is stored in memory, and being configured as can quilt
The processor, which is read, to be executed, and one or more of programs include the instruction that can be used for executing following steps：
Obtain green tobacco leaf and dry tobacco leaf image data；
Image data is pre-processed；
Obtain the characteristics of image of pretreated image data；
It grades to the characteristics of image of extraction；
Obtain rating result.
The processor further includes any application described in above method embodiment when executing based on account view angle switch
Some or all of information-pushing method step.
It should be noted that for each method embodiment above-mentioned, for simple description, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the described action sequence because
According to the present invention, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, for example, the unit division, it is only a kind of
Division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored or not executed.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, also may be used
It, can also be during two or more units be integrated in one unit to be that each unit physically exists alone.It is above-mentioned integrated
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a processor, i.e., in computer read/write memory medium.Based on this understanding, skill of the invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be with soft in other words for art scheme
The form of part product embodies, which is stored in a storage medium, including some instructions are making
A computer equipment (can be personal computer, server or network equipment etc.) is obtained to execute described in each embodiment of the present invention
The all or part of step of method.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various
The medium of program code can be stored.
The system of the above-mentioned tobacco leaf grading based on mobile terminal is pre-processed image by obtaining tobacco leaf image
Classification grading afterwards, the high in the clouds for conveying image under the conditions of network condition is good, carries out extremely efficient classification and grading, efficiently
Realize accurate tobacco classification under noisy current conditions, full automatic data chain system get through production line mobile terminal with
And high in the clouds machine learning system, there is classification effectiveness accuracy rate height, require hardware calculated level flexible, easy to operate, realization
The classification tobacco leaf of very high degree of precision has high universality, and classification effectiveness accuracy rate is high, requires hardware system performance low, operation letter
It is single, save a large amount of human resources.
It is above-mentioned only with embodiment come the technology contents that further illustrate the present invention, in order to which reader is easier to understand, but not
It represents embodiments of the present invention and is only limitted to this, any technology done according to the present invention extends or recreation, by the present invention's
Protection.Protection scope of the present invention is subject to claims.
Claims (8)
1. the method for the tobacco leaf grading based on mobile terminal, which is characterized in that the method includes：
Obtain green tobacco leaf and dry tobacco leaf image data；
Image data is pre-processed；
Obtain the characteristics of image of pretreated image data；
It grades to the characteristics of image of extraction；
Obtain rating result.
2. it is according to claim 1 based on mobile terminal tobacco leaf grading method, which is characterized in that image data into
The pretreated step of row, including step in detail below：
The relevant parameter for adjusting image, generates normalized image pattern；
Tobacco leaf in image pattern is positioned and divided.
3. the method for the tobacco leaf grading according to claim 2 based on mobile terminal, which is characterized in that adjust the phase of image
Related parameter, the step of generating normalized image pattern, the relevant parameter include illumination condition, shooting angle, ratio and
It is at least one in the position of tobacco leaf.
4. the method for the tobacco leaf grading according to any one of claims 1 to 3 based on mobile terminal, which is characterized in that obtain
The step of taking the characteristics of image of pretreated image data, including step in detail below：
Obtain tobacco leaf validity feature；
Classify to validity feature, forms the characteristics of image of each tobacco leaf.
5. the method for the tobacco leaf grading according to claim 4 based on mobile terminal, which is characterized in that it is effective to obtain tobacco leaf
In feature, the validity feature includes at least one in the textural characteristics for obtaining tobacco leaf, length, color and residual degree of wound.
6. the system of the tobacco leaf grading based on mobile terminal, which is characterized in that including image acquisition unit, pretreatment unit, spy
Levy acquiring unit, grading unit and result acquiring unit；
Described image acquiring unit, for obtaining green tobacco leaf and dry tobacco leaf image data；
The pretreatment unit, for being pre-processed to image data；
The feature acquiring unit, the characteristics of image for obtaining pretreated image data；
The grading unit, grades for the characteristics of image to extraction；
The result acquiring unit, for obtaining rating result.
7. the system of the tobacco leaf grading according to claim 6 based on mobile terminal, which is characterized in that the pretreatment is single
Member includes normalization module and locating segmentation module；
The normalization module, the relevant parameter for adjusting image generate normalized image pattern；
The locating segmentation module, for being positioned and being divided the tobacco leaf in image pattern.
8. the system of the tobacco leaf grading according to claim 7 based on mobile terminal, which is characterized in that the feature obtains
Unit includes validity feature acquisition module and sort module；
The validity feature acquisition module, for obtaining tobacco leaf validity feature；
The sort module forms the characteristics of image of each tobacco leaf for classifying to validity feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810354436.9A CN108427971A (en) | 2018-04-19 | 2018-04-19 | The method and system of tobacco leaf grading based on mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810354436.9A CN108427971A (en) | 2018-04-19 | 2018-04-19 | The method and system of tobacco leaf grading based on mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108427971A true CN108427971A (en) | 2018-08-21 |
Family
ID=63161404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810354436.9A Pending CN108427971A (en) | 2018-04-19 | 2018-04-19 | The method and system of tobacco leaf grading based on mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108427971A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109887055A (en) * | 2019-02-27 | 2019-06-14 | 云南省烟草公司昆明市公司 | A kind of generation method and device emulating tobacco leaf image |
| CN110111263A (en) * | 2019-03-29 | 2019-08-09 | 中国地质大学（武汉） | A kind of tobacco planting based on image procossing instructs system |
| CN110414422A (en) * | 2019-07-25 | 2019-11-05 | 秒针信息技术有限公司 | The detection method and device of food quality |
| CN110633684A (en) * | 2019-09-20 | 2019-12-31 | 南京邮电大学 | Tobacco purchasing grading system and grading method based on deep learning |
| CN110895804A (en) * | 2018-09-10 | 2020-03-20 | 上海市农业科学院 | Fuzzy edge lesion extraction method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4018674A (en) * | 1972-02-24 | 1977-04-19 | Morris Bennie A | Apparatus for automatically grading leaf tobacco |
| CN103323455A (en) * | 2013-04-24 | 2013-09-25 | 南京文采科技有限责任公司 | Tobacco leaf grading method based on reflection, perspective and microscopic images |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN107016413A (en) * | 2017-03-31 | 2017-08-04 | 征图新视（江苏）科技有限公司 | A kind of online stage division of tobacco leaf based on deep learning algorithm |
-
2018
- 2018-04-19 CN CN201810354436.9A patent/CN108427971A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4018674A (en) * | 1972-02-24 | 1977-04-19 | Morris Bennie A | Apparatus for automatically grading leaf tobacco |
| CN103323455A (en) * | 2013-04-24 | 2013-09-25 | 南京文采科技有限责任公司 | Tobacco leaf grading method based on reflection, perspective and microscopic images |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN107016413A (en) * | 2017-03-31 | 2017-08-04 | 征图新视（江苏）科技有限公司 | A kind of online stage division of tobacco leaf based on deep learning algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 李雪君等: "融合时空多特征表示的无监督视频分割算法", 计算机应用, no. 11, 30 November 2017 (2017-11-30), pages 3137 - 3138 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110895804A (en) * | 2018-09-10 | 2020-03-20 | 上海市农业科学院 | Fuzzy edge lesion extraction method and device |
| CN109887055A (en) * | 2019-02-27 | 2019-06-14 | 云南省烟草公司昆明市公司 | A kind of generation method and device emulating tobacco leaf image |
| CN110111263A (en) * | 2019-03-29 | 2019-08-09 | 中国地质大学（武汉） | A kind of tobacco planting based on image procossing instructs system |
| CN110111263B (en) * | 2019-03-29 | 2021-08-27 | 中国地质大学（武汉） | Flue-cured tobacco planting guidance system based on image processing |
| CN110414422A (en) * | 2019-07-25 | 2019-11-05 | 秒针信息技术有限公司 | The detection method and device of food quality |
| CN110633684A (en) * | 2019-09-20 | 2019-12-31 | 南京邮电大学 | Tobacco purchasing grading system and grading method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108427971A (en) | The method and system of tobacco leaf grading based on mobile terminal | |
| Xu et al. | Light-YOLOv3: fast method for detecting green mangoes in complex scenes using picking robots | |
| CN111079639B (en) | Method, device, equipment and storage medium for constructing garbage image classification model | |
| Hossain et al. | Improving consumer satisfaction in smart cities using edge computing and caching: A case study of date fruits classification | |
| CN109509187B (en) | Efficient inspection algorithm for small defects in large-resolution cloth images | |
| CN110378235A (en) | A kind of fuzzy facial image recognition method, device and terminal device | |
| Abbasgholipour et al. | Color image segmentation with genetic algorithm in a raisin sorting system based on machine vision in variable conditions | |
| CN110222686B (en) | Object detection method, object detection device, computer equipment and storage medium | |
| CN107330451A (en) | Clothes attribute retrieval method based on depth convolutional neural networks | |
| Bianco et al. | Predicting image aesthetics with deep learning | |
| CN110245697B (en) | Surface contamination detection method, terminal device and storage medium | |
| Reddy et al. | Optimized convolutional neural network model for plant species identification from leaf images using computer vision | |
| CN113283404B (en) | Pedestrian attribute identification method and device, electronic equipment and storage medium | |
| CN110827312A (en) | Learning method based on cooperative visual attention neural network | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN110458027A (en) | One kind being based on marblized fresh meat stage division, system and device | |
| CN107918767A (en) | Object detection method, device, electronic equipment and computer-readable medium | |
| Zhao et al. | Automatic blur region segmentation approach using image matting | |
| CN111222545A (en) | Image classification method based on linear programming incremental learning | |
| AU2017208235A1 (en) | Relative position encoding based networks for action recognition | |
| Feng et al. | A novel saliency detection method for wild animal monitoring images with WMSN | |
| Ubbens et al. | Autocount: Unsupervised segmentation and counting of organs in field images | |
| CN109359677A (en) | A kind of resistance to online kernel-based learning method of classifying of making an uproar more | |
| CN109740692A (en) | A kind of target classifying method of the logistic regression based on principal component analysis | |
| CN101504723A (en) | Projection space establishing method and apparatus |
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 |