CN106446968A - FPGA (field programmable gate array)-based automatic tobacco leaf grading system - Google Patents
FPGA (field programmable gate array)-based automatic tobacco leaf grading system Download PDFInfo
- Publication number
- CN106446968A CN106446968A CN201611026465.XA CN201611026465A CN106446968A CN 106446968 A CN106446968 A CN 106446968A CN 201611026465 A CN201611026465 A CN 201611026465A CN 106446968 A CN106446968 A CN 106446968A
- Authority
- CN
- China
- Prior art keywords
- nicotiana tabacum
- fpga
- grade
- grading
- tobacco leaf
- 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
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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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 invention discloses an FPGA (field programmable gate array)-based automatic tobacco leaf grading system. A method includes: performing tobacco leaf region segmentation according to an acquired image, and extracting concerned tobacco leaf content; extracting color components of tobacco leaves according to segmented tobacco leaf regions, making statistics on the color components of grade samples, recording a value of each RGB channel of tobacco leaves at each grade, and converting the obtained color components into Lab values to make parameters suitable for tobacco leaves grading; judging according to the obtained Lab values through a decision algorithm including three steps of known sample learning, new sample analysis and new sample judgement. Through the color feature based tobacco leaves grading algorithm, the system has the advantages of fast processing, short development period, low development cost and the like; the purpose of improving accuracy in tobacco leaves grading, stability in tobacco leaves grading and grading efficiency and the like is achieved; the system has high practical value in tobacco leaves quality inspection and grading.
Description
Technical field
The invention belongs to tobacco planting technical field, more particularly to a kind of Nicotiana tabacum L. automatic classification method, system based on FPGA.
Background technology
China is the big country of tobacco planting and consumption, and Nicotiana tabacum L. is Enshi State of Hubei Province " green bank ", all the time,
Leaf tobacco production is grabbed by Enshi as pillar industry, is devoted to making Hubei Province's high-quality characteristic tobacco.Nicotiana tabacum L. is used as a kind of weight
The industrial crops that wants, it is important agricultural exports of bestowing favour, and the growth to Enshi economy serves larger effect.With
Tobacco industry flourish, people propose requirements at the higher level, tobacco industry sustainable and stable development to the quality grading of Nicotiana tabacum L..Mesh
Before, Nicotiana tabacum L. arable land in Enshi has reached more than 3,000,000 mu, 1,500,000 mu of Basic tobacco field protected area.The long-term tobacco leaf planting area in Quanzhou
Stablize and carry on a shoulder pole in more than 60 ten thousand mu, purchase volume more than 150 ten thousand.Yield of tobacco accounts for the 70% of the whole province's Nicotiana tabacum L. total amount, and outlet stock amount accounts for the whole nation
More than 80%, rank the 6th in national 31 emphasis Nicotiana tabacum L. producing regions." Qing Jiangyuan " characteristic sound tobacco has become as the country
The main formula of the well-known key brand of numerous emphasis Cigarette Industrial Enterprises.The detection of overseas utilization computer vision technique research Nicotiana tabacum L.
Start from 1984 with classification, early many for domestic research is carried out.1988, the Thomas C.E. in the U.S.
An entitled ((Techniques of image analysis applied to the measurement of is delivered
Tobacco and relatedproducts)) opinion of (application of the image analysis technology in terms of Nicotiana tabacum L. and Related product measurement)
Text, proposes for image procossing to be applied to Nicotiana tabacum L. and Related product.This shows that research worker is had started to the theory of computer vision
With the Quality Detection that technology is applied to Nicotiana tabacum L. and classification.Hereafter, the research of this one side is progressively had made some progress again.1993
Year, the MacCormac of University of Zimbabwe devises a graphics processing unit original shape that can be used for Nicotiana tabacum L. real-time graded.1997
Year, CHO and PAEK have studied how to extract the features such as shape, the color of burley tobaccos to be classified to which using machine vision.
Tattersfield and Forbes extracts the features such as the shape of cured tobacco leaf, color, and the growth site to flue-cured tobacco and color are carried out
Packet identification.But for China, the research starting for carrying out Nicotiana tabacum L. automatic identification and classification technique is relatively later, mainly should
Colourity theory is used, and by the difference of the gray value in image between Nicotiana tabacum L. and background, Nicotiana tabacum L. is extracted using RGB color model
Colouring information.
But the information in terms of can not effectively providing color due to RGB model, while exist between RGB component very high
Dependency, so easily missing some useful information or being mingled with garbage, is unfavorable for being directly used as identification feature parameter.
Content of the invention
It is an object of the invention to provide a kind of Nicotiana tabacum L. automatic grading system based on FPGA, it is intended to solve due to RGB mould
Type color effectively can not be provided in terms of information, while there is very high dependency between RGB component, easily missing some has
Information or it is mingled with garbage, is unfavorable for being directly used as the problem of identification feature parameter.
The present invention is achieved in that a kind of Nicotiana tabacum L. automatic grading method based on FPGA, the Nicotiana tabacum L. based on FPGA
Automatic grading method is comprised the following steps：
Step one, carries out Nicotiana tabacum L. region segmentation according to acquired image, filters white background and black shaded area.
Step 2, according to the color component of the Nicotiana tabacum L. region contents extraction Nicotiana tabacum L. being partitioned into, to each of each grade sample
Color component is counted, and records the value of each grade Nicotiana tabacum L. RGB channel, and the value of each for RGB component is converted into Lab mould by formula
The value of type, is suitable for tobacco leaf grading so as to parameter；
Step 3, makes judgement according to obtained Lab value, mainly by the Nicotiana tabacum L. sample to certain amount known grades
This study obtains the spatial distribution domain of these level Nicotiana tabacum L., represents this scale color distributed areas with border circular areas.Again
By the Lab value of unknown grade Nicotiana tabacum L. sample is calculated, determine that its circular distribution region for falling into which grade is just defined as
Which grade.
Further, the Nicotiana tabacum L. automatic grading method based on FPGA is with FPGA Digital Image Processing, first using linear CCD
Photographic head is acquired to the image of Nicotiana tabacum L., transplants FPGA2HPS high speed bridge, the DDR3 of the direct high speed incoming data of FPGA to ARM
In, executable file is sent to by Linux by network, using effective differentiation and the analysis of C language algorithm, is extracted corresponding
Rgb value, uses dual pathways partitioning algorithm, the Nicotiana tabacum L. pixel for meeting above-mentioned condition is retained, reject other and do not meet bar in image
The pixel of part.Then the value of RGB is converted to the value of Lab model by formula.Under Lab system, only a, b is related to color,
So referred in the middle of algorithm design is a, b component, thus three-dimensional color space is compressed on two dimensional surface.One-level
Distribution of color of the Nicotiana tabacum L. in ab plane corresponds to border circular areas 1, is designated as Class1；The distribution of color of two grades of Nicotiana tabacum Lves in ab plane
Corresponding border circular areas 2, are designated as Class2；Distribution of color of the three-level Nicotiana tabacum L. in ab plane corresponds to border circular areas 3, is designated as
Class3；Distribution of color of the level Four Nicotiana tabacum L. in ab plane corresponds to border circular areas 4, is designated as Class4.New sample to unknown grade
This image segmentation obtains Nicotiana tabacum L. effective coverage, calculates new samples Nicotiana tabacum L. region institute a, b component a little under Lab color space and corresponds to
Average A, B.Which hierarchical region Nicotiana tabacum L. to be measured falls into or center of circle place border circular areas close together are classified；Other
Situation is judged to problem Nicotiana tabacum L..
Further, the Nicotiana tabacum L. automatic grading method based on FPGA is by the Nicotiana tabacum L. sample to certain amount known grades
Study obtains the spatial distribution region of these level tobacco leaf color, represents this scale color areal area with border circular areas
Domain；The Lab value of unknown grade Nicotiana tabacum L. sample is calculated again, and its circular distribution region for falling into which grade is just defined as that
Grade；If there is distribution of color region overlap between two tobacco leaf degree, and the sample of new unknown grade be lucky
When falling into overlapping region, then by new samples drop point position from the two round heart of distribution distance determining its grade ownership.
Another object of the present invention is to provide a kind of Nicotiana tabacum L. automatic grading method based on FPGA based on FPGA
Nicotiana tabacum L. automatic grading system, the Nicotiana tabacum L. automatic grading system based on FPGA includes：
Segmented extraction module, for carrying out Nicotiana tabacum L. region segmentation according to acquired image, extracts in Nicotiana tabacum L. of interest
Hold；
Color component transition module is for the color component according to the Nicotiana tabacum L. region contents extraction Nicotiana tabacum L. being partitioned into, right
Each color component of each grade sample is counted, and records the value of each grade Nicotiana tabacum L. RGB channel, gained color component is changed into
Lab value is suitable for tobacco leaf grading so as to parameter；
Judging module, for making judgement according to obtained Lab value, decision algorithm is divided into known sample study, new sample
This analysis, new samples are adjudicated 3 steps and are carried out.
Another object of the present invention is to provide a kind of being classified using the Nicotiana tabacum L. automatic grading method based on FPGA
Nicotiana tabacum L..
The Nicotiana tabacum L. automatic grading system based on FPGA that the present invention is provided, using linear CCD photographic head, by DE1-SoC
On Video Decoder ADV7180 image acquisition is got off, wherein embed one piece of ARM stone, make use of FPGA's well
Internal resource, the color characteristic identification to Nicotiana tabacum L. has good analysis and recognizes.The present invention is based on friendly crystalline substance DE1-SoC product,
High-speed parallel disposal ability and the flexible computing of ARM Linux of FPGA is made full use of, the collection of design tobacco leaf image and form turn
Change, and by the exclusive FPGA2HPS high speed bridge of SoC, data are stored in the DDR3 of HPS in real time；Linux system is run at HPS end
System, carries out tobacco leaf grading using Lab color mode, Nicotiana tabacum L. grade and accumulative frequency is transferred to LCD industry control screen；Meanwhile, HPS leads to
H2F_LW bridge control step motor drive is crossed, realizes the function of leaf dish automatic switchover.Present invention achieves the image acquisition of Nicotiana tabacum L.,
Light supply, the function such as automatically deliver, be classified judgement and show in real time；In order to reduce the construction cycle of current Nicotiana tabacum L. hierarchy system
And cost, it is proposed that in the method for FPGA Digital Image Processing.Its principle is image first using linear CCD photographic head to Nicotiana tabacum L.
It is acquired, FPGA2HPS high speed bridge is transplanted, the direct high speed incoming data of FPGA can be held by network in the DDR3 of ARM
Style of writing part is sent to Linux, using effective differentiation and the analysis of C language algorithm, extracts corresponding rgb value, is split with the dual pathways
Algorithm, the Nicotiana tabacum L. pixel for meeting above-mentioned condition is retained, reject other ineligible pixels in image；By one kind
Tobacco leaf grading algorithm based on color characteristic is realized.The tobacco leaf grading of China is worked mainly by being accomplished manually at present, by observing
Handss the mode such as are touched and are rule of thumb judged.And the present invention such as Fig. 1, tested by 14 groups of Nicotiana tabacum Lves, (a, the b) for reading from system
Value, is transformed by the rgb value of collection picture, and display level is the interdependent result of determination for reading from LCD liquid crystal, contrast
Conclusion is actual tobacco leaf degree, and the accuracy of its test is more than 90%, can realize the function of tobacco leaf grading.Grading accuracy rate
Height, efficiency high, low cost, with higher practical value in terms of quality of tobacco detection with classification.
Description of the drawings
Fig. 1 is measured data analysis chart provided in an embodiment of the present invention.
Fig. 2 is the Nicotiana tabacum L. automatic grading method flow chart based on FPGA provided in an embodiment of the present invention.
Fig. 3 is the flow chart of embodiment provided in an embodiment of the present invention 1.
Fig. 4 is LAB color model provided in an embodiment of the present invention classification schematic diagram.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that specific embodiment described herein is not used to only in order to explain the present invention
Limit the present invention.
Below in conjunction with the accompanying drawings the application principle of the present invention is explained in detail.
As shown in figure 1, the measured data for the present invention.
As shown in Fig. 2 the Nicotiana tabacum L. automatic grading method based on FPGA provided in an embodiment of the present invention is comprised the following steps：
S101：Nicotiana tabacum L. region segmentation is carried out according to acquired image, extracts Nicotiana tabacum L. content of interest；
S102：According to the color component of the Nicotiana tabacum L. region contents extraction Nicotiana tabacum L. being partitioned into, each face to each grade sample
Colouring component is counted, and records the value of each grade Nicotiana tabacum L. RGB channel, is changed into Lab value to gained color component and is fitted so as to parameter
Share in tobacco leaf grading；
S103：Judgement is made according to obtained Lab value, decision algorithm is divided into known sample study, new samples analysis, new
Sample is adjudicated 3 steps and is carried out.
In order to reduce construction cycle and the cost of current Nicotiana tabacum L. hierarchy system, it is proposed that with the side of FPGA Digital Image Processing
Method.Its principle is first using linear CCD photographic head, the image of Nicotiana tabacum L. to be acquired, and transplants FPGA2HPS high speed bridge, and FPGA is straight
High speed incoming data is connect in the DDR3 of ARM, executable file is sent to by Linux by network, using having for C language algorithm
Effect differentiates and analyzes, and extracts corresponding rgb value, uses dual pathways partitioning algorithm, will meet the Nicotiana tabacum L. pixel of above-mentioned condition in image
Point retains, and rejects other ineligible pixels.By a kind of tobacco leaf grading algorithm based on color characteristic；Have and process
Speed is fast, the construction cycle is short, the low advantage of development cost；To raising tobacco leaf grading accuracy, tobacco leaf grading stability, improve and divide
The purposes such as stage efficiency.With higher practical value in terms of quality of tobacco detection with classification.
With reference to specific embodiment, the application principle of the present invention is further described.
Embodiment 1：
As shown in figure 3, decision algorithm main thought provided in an embodiment of the present invention is by certain amount known grades
Nicotiana tabacum L. sample learning obtain the spatial distribution region of these level tobacco leaf color, representing this grade face with border circular areas
Color distributed areas.The Lab value of unknown grade Nicotiana tabacum L. sample is calculated again, and the circular distribution region which grade which falls into is just true by which
It is set to that grade.Because between tobacco leaf degree, the difference of color is all transitional type rather than significant notch cuttype, adjacent
Distribution of color region between grade Nicotiana tabacum L. there may be a little overlap.If there is color between two tobacco leaf degree
Distributed areas overlap, and when the sample of new unknown grade falls into overlapping region just, then by the position of new samples drop point
Distance from the two round heart of distribution is determining its grade ownership.Fig. 4 is LAB color model provided in an embodiment of the present invention classification
Figure.
Presently preferred embodiments of the present invention is the foregoing is only, not in order to limit the present invention, all essences in the present invention
Any modification, equivalent and improvement that is made within god and principle etc., should be included within the scope of the present invention.
Claims (5)
1. a kind of Nicotiana tabacum L. automatic grading method based on FPGA, it is characterised in that the Nicotiana tabacum L. automatic classification side based on FPGA
Method is comprised the following steps：
Step one, carries out Nicotiana tabacum L. region segmentation according to acquired image, extracts Nicotiana tabacum L. content of interest；
Step 2, according to the color component of the Nicotiana tabacum L. region contents extraction Nicotiana tabacum L. being partitioned into, each color to each grade sample
Component is counted, and records the value of each grade Nicotiana tabacum L. RGB channel, is changed into Lab value to gained color component and is suitable for so as to parameter
For tobacco leaf grading；
Step 3, makes judgement according to obtained Lab value, and decision algorithm is divided into oneself and knows sample learning, new samples analysis, new sample
3 steps of this judgement are carried out.
2. the Nicotiana tabacum L. automatic grading method based on FPGA as claimed in claim 1, it is characterised in that the cigarette based on FPGA
Leaf automatic grading method is first acquired to the image of Nicotiana tabacum L. using linear CCD photographic head with FPGA Digital Image Processing, transplanting
FPGA2HPS high speed bridge, executable file is sent to in the DDR3 of ARM by the direct high speed incoming data of FPGA by network
Linux, using effective differentiation and the analysis of C language algorithm, extracts corresponding rgb value, uses dual pathways partitioning algorithm, by image
The Nicotiana tabacum L. pixel for meeting above-mentioned condition retains, and rejects other ineligible pixels.
3. the Nicotiana tabacum L. automatic grading method based on FPGA as claimed in claim 1, it is characterised in that the cigarette based on FPGA
Leaf automatic grading method is by certain amount, oneself knows that the Nicotiana tabacum L. sample learning of grade obtains the space of these level tobacco leaf color and divides
Cloth region, represents this scale color distributed areas with border circular areas；The Lab of unknown grade Nicotiana tabacum L. sample is calculated again
Value, its circular distribution region for falling into which grade is just defined as that grade；If deposited between two tobacco leaf degree
Overlap in distribution of color region, and when the sample of new unknown grade falls into overlapping region just, then fallen by new samples
The position of point from the two round heart of distribution distance determining its grade ownership.
4. a kind of Nicotiana tabacum L. automatic classification system based on FPGA as claimed in claim 1 based on the Nicotiana tabacum L. automatic grading method of FPGA
System, it is characterised in that the Nicotiana tabacum L. automatic grading system based on FPGA includes：
Segmented extraction module, for carrying out Nicotiana tabacum L. region segmentation according to acquired image, extracts Nicotiana tabacum L. content of interest；
Color component transition module, for the color component according to the Nicotiana tabacum L. region contents extraction Nicotiana tabacum L. being partitioned into, to each etc.
Each color component of level sample is counted, and is recorded the value of each grade Nicotiana tabacum L. RGB channel, is changed into Lab to gained color component
Value is suitable for tobacco leaf grading so as to parameter；
Judging module, for making judgement according to obtained Lab value, decision algorithm is divided into oneself and knows that sample learning, new samples divide
Analysis, new samples are adjudicated 3 steps and are carried out.
5. the Nicotiana tabacum L. that the Nicotiana tabacum L. automatic grading method described in a kind of utilization claim 1～3 any one based on FPGA is classified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611026465.XA CN106446968A (en) | 2016-11-22 | 2016-11-22 | FPGA (field programmable gate array)-based automatic tobacco leaf grading system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611026465.XA CN106446968A (en) | 2016-11-22 | 2016-11-22 | FPGA (field programmable gate array)-based automatic tobacco leaf grading system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106446968A true CN106446968A (en) | 2017-02-22 |
Family
ID=58220514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611026465.XA Pending CN106446968A (en) | 2016-11-22 | 2016-11-22 | FPGA (field programmable gate array)-based automatic tobacco leaf grading system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446968A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767449A (en) * | 2016-12-28 | 2017-05-31 | 云南昆船设计研究院 | The uniformity of tobacco leaf distinguishes choosing method and device |
| CN107423755A (en) * | 2017-07-03 | 2017-12-01 | 云南中烟工业有限责任公司 | A kind of method that piece cigarette is described and classified based on piece cigarette morphological feature |
| CN108335307A (en) * | 2018-04-19 | 2018-07-27 | 云南佳叶现代农业发展有限公司 | Adaptive tobacco leaf picture segmentation method and system based on dark primary |
| CN108416782A (en) * | 2018-04-19 | 2018-08-17 | 云南佳叶现代农业发展有限公司 | View-based access control model identifies and the tobacco leaf ranking method and system of illumination correction |
| CN109829943A (en) * | 2018-11-13 | 2019-05-31 | 上海烟草集团有限责任公司 | Blade construction detection method, system, medium and equipment based on machine vision |
| CN110415181A (en) * | 2019-06-12 | 2019-11-05 | 勤耕仁现代农业科技发展(淮安)有限责任公司 | Flue-cured tobacco RGB image intelligent recognition and grade determination method under a kind of open environment |
| WO2023226103A1 (en) * | 2022-05-23 | 2023-11-30 | 云南中烟工业有限责任公司 | Leaf structure measurement method during threshing, redrying and air separation process and leaf outlet amount measurement method of air separator |
-
2016
- 2016-11-22 CN CN201611026465.XA patent/CN106446968A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 陈亮亮等 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767449A (en) * | 2016-12-28 | 2017-05-31 | 云南昆船设计研究院 | The uniformity of tobacco leaf distinguishes choosing method and device |
| CN107423755A (en) * | 2017-07-03 | 2017-12-01 | 云南中烟工业有限责任公司 | A kind of method that piece cigarette is described and classified based on piece cigarette morphological feature |
| CN107423755B (en) * | 2017-07-03 | 2020-06-16 | 云南中烟工业有限责任公司 | Method for describing and classifying tobacco flakes based on morphological characteristics of tobacco flakes |
| CN108335307A (en) * | 2018-04-19 | 2018-07-27 | 云南佳叶现代农业发展有限公司 | Adaptive tobacco leaf picture segmentation method and system based on dark primary |
| CN108416782A (en) * | 2018-04-19 | 2018-08-17 | 云南佳叶现代农业发展有限公司 | View-based access control model identifies and the tobacco leaf ranking method and system of illumination correction |
| CN108416782B (en) * | 2018-04-19 | 2023-09-26 | 云南佳叶现代农业发展有限公司 | Tobacco leaf grading method and system based on visual identification and illumination correction |
| CN109829943A (en) * | 2018-11-13 | 2019-05-31 | 上海烟草集团有限责任公司 | Blade construction detection method, system, medium and equipment based on machine vision |
| CN109829943B (en) * | 2018-11-13 | 2023-02-10 | 上海烟草集团有限责任公司 | Blade structure detection method, system, medium and equipment based on machine vision |
| CN110415181A (en) * | 2019-06-12 | 2019-11-05 | 勤耕仁现代农业科技发展(淮安)有限责任公司 | Flue-cured tobacco RGB image intelligent recognition and grade determination method under a kind of open environment |
| CN110415181B (en) * | 2019-06-12 | 2023-07-14 | 勤耕仁现代农业科技发展(淮安)有限责任公司 | Intelligent identification and grade judgment method for RGB (red, green and blue) images of flue-cured tobacco in open environment |
| WO2023226103A1 (en) * | 2022-05-23 | 2023-11-30 | 云南中烟工业有限责任公司 | Leaf structure measurement method during threshing, redrying and air separation process and leaf outlet amount measurement method of air separator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446968A (en) | FPGA (field programmable gate array)-based automatic tobacco leaf grading system | |
| WO2020063461A1 (en) | Urban extent extraction method and apparatus based on random forest classification algorithm, and electronic device | |
| WO2016054908A1 (en) | Internet of things big data platform-based intelligent user profiling method and apparatus | |
| CN104050481B (en) | Multi-template infrared image real-time pedestrian detection method combining contour feature and gray level | |
| CN102261892A (en) | Rapid width measurement system for tobacco shreds | |
| CN103976468A (en) | Tobacco leaf grading method | |
| CN104484410A (en) | Data fusion method and system applied to big data system | |
| CN110080549A (en) | A kind of protection decision-making technique of gallows timber ancient building in Architectural Heritage | |
| CN104077806A (en) | Automatic separate extraction method based on city building three-dimensional model | |
| CN106503695A (en) | A kind of tobacco plant identification and method of counting based on Aerial Images | |
| CN101706926A (en) | Method for investigating and processing cigarette consumption information | |
| CN106650795A (en) | Sorting method of hotel room type images | |
| WO2024021359A1 (en) | Built environment dominant color measurement method and system based on image eeg sensitivity data | |
| CN112819066A (en) | Res-UNet single tree species classification technology | |
| CN111428298A (en) | Indoor decoration design method and system based on AR virtual reality technology | |
| CN110378736A (en) | The method that tourist experiences satisfaction to natural resources is evaluated by facial expression recognition | |
| O’Neil-Dunne et al. | An object-based approach to statewide land cover mapping | |
| CN106845366A (en) | Sugarcane coverage automatic testing method based on image | |
| CN105023272A (en) | Crop leaf insect pest detection method and system | |
| CN114299059A (en) | Method for judging scratch defects of unsorted casting blanks on surfaces of hot-rolled strip steel | |
| CN109933583A (en) | A kind of passenger flow statistics and objective group's portrait analysis method and system | |
| CN110111263B (en) | Flue-cured tobacco planting guidance system based on image processing | |
| Masdiyasa et al. | A new method to improve movement tracking of human sperms | |
| Gu | Estimating capital input for measuring business sector multifactor productivity growth in Canada: Response | |
| CN106845554A (en) | A kind of image of santal plant strain growth soil iron content determines method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |