CN105354580B - Asiatic migrotory locust image characteristic extracting method based on machine vision - Google Patents
Asiatic migrotory locust image characteristic extracting method based on machine vision Download PDFInfo
- Publication number
- CN105354580B CN105354580B CN201510757189.3A CN201510757189A CN105354580B CN 105354580 B CN105354580 B CN 105354580B CN 201510757189 A CN201510757189 A CN 201510757189A CN 105354580 B CN105354580 B CN 105354580B
- Authority
- CN
- China
- Prior art keywords
- asiatic migrotory
- migrotory locust
- locust
- image
- asiatic
- 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
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
Abstract
The invention belongs to Computer Science and Technology fields, are related to a kind of Asiatic migrotory locust image characteristic extracting method based on machine vision.The described method includes: carrying out signature analysis to Asiatic migrotory locust, the main feature of Asiatic migrotory locust is chosen；According to the feature of Asiatic migrotory locust, image characteristic extracting method is chosen；Function is calculated with the texture in the tool box Matlab, converts numerical information for image information；According to principal component analysis and variance analysis, specific suitable component characterization is chosen as Asiatic migrotory locust characteristics of image.The Asiatic migrotory locust image characteristic extracting method that the present invention uses can distinguish Asiatic migrotory locust type well, have good accuracy.Method of the present invention can provide technical support for the Classification and Identification of Asiatic migrotory locust, and have directive significance to the image characteristics extraction and Classification and Identification of later each class pest.
Description
Technical field
The invention belongs to Computer Science and Technology fields, are related to a kind of Asiatic migrotory locust characteristics of image based on machine vision
Extracting method.
Background technique
Locust is worldwide pest, causes huge disaster in history.China migratory locusts generating region is related to 16 provinces at present
The county Jin200Ge is involved in urban district, wherein county, 100, recurrence area, and the occurring area of summer and autumn migratory locusts is up to 2500~30,000,000 mu；
Native locust generation area is related to more than 20 provinces, involves the county Jin500Ge, wherein the county of serious generating region 200, occurring area is at 200,000,000 mu
More than.Asiatic migrotory locust occurrence frequency rose in recent years, and the extent of injury aggravates, wherein in July, 2014, Chifeng Bahrain was right
There is locust disaster, 95.7 ten thousand mu of crops disaster area, careless pasture disaster area 12,000,000 in the paddy field that flag hila washes one's hair bush of falling
Mu；The serious plague of locusts, this area's locust occurring area in 2014 are broken out in Chifeng in July, 2014 Alukeerqin Banner
1200000 mu, 800,000 mu of serious occurring area, average locust density 38 every square metre, local maxima locust density reaches often flat
210, square rice or more；The Henan of in August, 2014 Yingyang 3000 mu of the Yellow River beach meets with the plague of locusts, and milpa is gnawed totally.China is annual
Because caused by locust disaster economic loss up to tens yuan.
It can be seen that scholar from domestic and international present Research to be ground based on automatic identification of the single features to insect
Study carefully, which is based on multiple features fusion there are also scholar and SIFT local feature matching process is applied to insect knowledge with morphological feature
Other research in agricultural insect Study of recognition based on computer vision, proposes research in spite of researcher with design
Scheme, but the accuracy rate identified is all to be improved.
Summary of the invention
In view of the above-mentioned problems, the invention discloses a kind of Asiatic migrotory locust image characteristic extracting method based on machine vision,
Can technical support reliably be provided for the Classification and Identification of Asiatic migrotory locust.
To achieve the goals above, the invention adopts the following technical scheme:
A kind of Asiatic migrotory locust image characteristic extracting method based on machine vision, which is characterized in that the method includes with
Lower step:
Step 1 carries out signature analysis to Asiatic migrotory locust, chooses the feature of Asiatic migrotory locust；
Feature of the step 2 according to the Asiatic migrotory locust of selection carries out image characteristics extraction；
Image information is converted numerical information by step 3；
Step 4 chooses component characterization as Asiatic migrotory locust characteristics of image.
Signature analysis is carried out to Asiatic migrotory locust in the step 1: being distinguished according to locust section feature and migratory locusts category feature
Migratory locusts, wherein locust section feature is that head is inserted into shirtfront, and two adaptive ocellis each 3, antesternum has short spike protrusion metapedes leg
Section thickeies, spinosity；Migratory locusts category feature is the long 33.5mm-41.5mm of adult hero body body, and female 39.5mm-51.2mm, face is vertical, multiple
Eye presentation is oval, dark-coloured speckle one in compound eye, the median carina presentation arc or dimple of pronotary, and the two of median carina
There is a dark-coloured vertical stripe in side, and it is glossy that fore wing is presented brown, there is dark-coloured speckle above, hind wing be it is colourless or faint yellow, surface has
Thorn；Then long and narrow further according to the pronotary for the Asiatic migrotory locust that lives scattered, median carina protuberance；The fore wing ratio of gregarious Asiatic migrotory locust is lived scattered east
The ratio that the fore wing of sub- migratory locusts grows abdomen is big；In the long ratio long with metapedes leg section of fore wing, the ratio for Asiatic migrotory locust of living in groups
Greater than 2, and the ratio for the Asiatic migrotory locust that lives scattered is less than 2；In terms of metapedes tibia color, Asiatic migrotory locust presentation of living in groups is faint yellow, lives scattered
Red characteristic is presented in the metapedes tibia of Asiatic migrotory locust, and migratory locusts are divided into gregarious and two classes of living scattered.
The feature for the Asiatic migrotory locust chosen in the step 2 be respectively from the head of Asiatic migrotory locust, pronotary, metapedes,
The top view and the extracted textural characteristics of two angles of side view, color characteristic and shape feature at four positions of wing.
Image characteristics extraction includes: that the extraction for textural characteristics uses calculating energy, entropy, unfavourable balance in the step 2
The method of square, contrast；For color characteristic using the method for calculating first moment, second moment；The extraction of shape feature is adopted
With reference area, perimeter, complexity, eccentricity, duty ratio, the method for spherical property；
It is to be calculated by the texture in the tool box Matlab that image information, which is switched to numerical information method, in the step 3
Image information is converted numerical information by function；Digital textural characteristics have: the auto-correlation function of image local area, gray scale are total
The various statistics of raw matrix, the gray scale distance of swimming and intensity profile.
The method that component characterization is chosen in the step 4 is Principal Component Analysis and discriminant analysis, according to principal component point
Analysis adjustment variable number takes 2 times of principle then according to variance analysis, and excluding outlier is extracted top n and made according to analysis
For principal component, N is setting value.
It includes the second moment on head, the color first moment B component of head side, metapedes side that component characterization is chosen in the step 4
Spot ratio, the smoothness of pronotary and the color first moment B component of pronotary.
Beneficial effect
The feature identification that a kind of Asiatic migrotory locust image characteristic extracting method based on machine vision of the present invention extracts
Rate is high, can lay a solid foundation for the Classification and Identification of Asiatic migrotory locust.Method proposed by the present invention can be applied to other insects
Feature extraction.
Detailed description of the invention
Fig. 1 is the method for the invention flow chart；
Fig. 2 is characteristics of image content graph of the invention；
Fig. 3 is principal component analysis block diagram of the invention；
Fig. 4 is principal component analysis rubble figure of the invention；
Fig. 5 is principal component analysis result figure of the invention；
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.
Fig. 1 is the flow chart of the Asiatic migrotory locust image characteristic extracting method of the present invention based on machine vision, the party
Method follows the steps below:
S1, signature analysis is carried out to Asiatic migrotory locust, chooses the main feature of Asiatic migrotory locust；
S1-1: biological characteristic analysis is carried out to Asiatic migrotory locust, table 1 is the biological characteristic analysis of Asiatic migrotory locust.
1 Asiatic migrotory locust signature analysis of table
S1-2: the main feature of Asiatic migrotory locust is chosen.By the biological analysis to Asiatic migrotory locust characteristic, primarily determine from
Wing, pronotary, metapedes, four, head aspect distinguish different types of Asiatic migrotory locust.
S2, the feature according to Asiatic migrotory locust, choose image characteristic extracting method, as shown in Figure 2；
Textural characteristics
Gray level co-occurrence matrixes are the matrix functions of pixel distance and angle, it is by certain distance in calculating image and centainly
Correlation between the two o'clock gray scale in direction, integrated information of the Lai Fanying image on direction, interval, amplitude of variation and speed.
If f (x, y) is a width two-dimensional digital image, size is M × N, grey level Ng, then meets certain space pass
The gray level co-occurrence matrixes of system are G (i, j)=# { (x1, y1), (x2, y2) ∈ M × N | f (x1, y1)=i, f (x2, y2)=j },
Middle # (x) indicates the element number in set x.
1, energy
Image grayscale is evenly distributed a measurement of degree and texture thickness, if all values of co-occurrence matrix are equal,
Then ASM value is small；On the contrary, ASM value is big if the big and other value of some of values is small.When element integrated distribution in co-occurrence matrix
When, ASM value is big at this time.ASM value shows greatly a kind of texture pattern of uniform and regular variation.
2, entropy
The measurement for the information content that image has shows the complicated process of image, is the measurement of a randomness, when symbiosis square
When all elements have maximum randomness in battle array, all values are almost equal in the co-occurrence matrix of space, element dispersion in co-occurrence matrix
When distribution, entropy is larger.It illustrates the non-uniform degree or complexity of texture in image.
3, inverse difference moment
The readability and regular degree of texture are reflected, clean mark, regularity is relatively strong, is easy to description, is worth larger；
It is rambling, it is difficult to description, it is worth smaller.
4, contrast
Reflect the clarity of image and the degree of the texture rill depth.Texture rill is deeper, and contrast is bigger, vision
Effect is more clear；Conversely, contrast is small, then rill is shallow, and effect is fuzzy.The big pixel of gray scale difference, that is, contrast to more, this
It is worth bigger.Bigger far from cornerwise element value in the raw matrix of gray scale public affairs, CON is bigger.
Color characteristic
Color moment be mainly used to filter image and reduce range of search, have first moment (mean value, mean), second moment (variance,
Viarance) and third moment (gradient, skewness) etc., because colouring information is distributed mainly in low-order moment, with first moment, two
Rank square can express the distribution of color of image.Color moment can effectively indicate colouring information.
1, first moment
2, second moment
Wherein, pi,jIndicate that the probability that the pixel that gray scale is j in i-th of Color Channel component of color image occurs, N indicate
The number of pixel in image.
Advantage: not needing color space quantization, and feature vector dimension is low
Disadvantage: recall precision is relatively low
Shape feature
1, area
Wherein f (x, y) is a width two-dimensional digital image, and size is M × N.
2, perimeter:
P=A-SUM (in)
Wherein A indicates area, the sum of the pixel inside SUM (in) expression.
3, complexity:
C=P2/4πA
Wherein P indicates that perimeter, A indicate area.
The compactedness of object is described, the complexity of circular object is 1
4, eccentricity: EC=p/q
Wherein p indicates the length of region main shaft (long axis), and q indicates the length of the auxiliary axis in region (short axle).
The compactedness in region is described, target long axis and the definition mode of short axle ratio are influenced by body form and noise
It is very big, and it is stronger based on the eccentricity anti-interference ability that inertia defines.
5, spherical property: SP=ri/rc
Wherein, ri、rcThe respectively radius of inscribed circle and circumscribed circle, the center of circle is all in center of gravity.
S3, function is calculated with the texture in the tool box Matlab, converts numerical information for image information；
By the research of S1 and S2, four positions such as the head from Asiatic migrotory locust, pronotary, metapedes, wing are drafted, point
Not from two angle extraction correlated characteristics of top view and side view: textural characteristics, color characteristic, shape feature.
Textural characteristics are the extraction and analysis to image grayscale Spatial Distribution Pattern.Texture can reflect the structure of object.
Common number textural characteristics have: auto-correlation function, gray level co-occurrence matrixes, the gray scale distance of swimming and the gray scale of image local area point
The various statistics of cloth.Textural characteristics can be used to measure the texture features on Asiatic migrotory locust surface, using in the tool box Matlab
Texture calculate function, convert numerical information for image information.
Asiatic migrotory locust head feature extraction result is as follows, other genius locis extract as head.
Locust texture feature extraction value analysis (part) is tested on 2 Asiatic migrotory locust head of table
Locust texture feature extraction value analysis (part) is tested on 3 Asiatic migrotory locust head of table
Locust texture feature extraction value analysis (part) is tested on 4 Asiatic migrotory locust head of table
S4, according to principal component analysis and variance analysis, choose specific suitable component characterization as Asiatic migrotory locust image spy
Sign.
S4-1: when carrying out feature extraction, more Asiatic migrotory locust feature can be generally selected, therefore principal component point need to be passed through
Analysis adjusts variable number.Principal component analysis step is as shown in Figure 3.
Data analysis result is as follows:
5 descriptive analysis amount of table
It is exceptional value more than ± 2 α of μ, excluding outlier, table 5 is the population variance explained according to above-mentioned analysis.
The population variance that table 6 is explained
As shown in figure 4, extracting first 15 according to analysis and being used as principal component.
S4-2: utilizing principal component analysis and variance analysis, and result is as shown in figure 5, take the second moment on head, the face of head side
Color first moment B component, the spot ratio of metapedes side, the smoothness of pronotary, the color first moment B component conduct of pronotary
The feature of component.
Claims (4)
1. a kind of Asiatic migrotory locust image characteristic extracting method based on machine vision, which is characterized in that the method includes following
Step:
Step 1 carries out signature analysis to Asiatic migrotory locust, chooses the feature of Asiatic migrotory locust；
Feature of the step 2 according to the Asiatic migrotory locust of selection carries out image characteristics extraction；
Image information is converted numerical information by step 3；It is by Matlab tool that image information, which is switched to numerical information method,
Texture in case calculates function, converts numerical information for image information；Digital textural characteristics have: image local area from phase
Close the various statistics of function, gray level co-occurrence matrixes, the gray scale distance of swimming and intensity profile；
The numerical information that step 4 is obtained according to step 3 chooses component characterization conduct using Principal Component Analysis and discriminant analysis
Asiatic migrotory locust characteristics of image；Wherein, color first moment B component, the metapedes that component characterization includes the second moment on head, head side are chosen
The color first moment B component of the spot ratio of side, the smoothness of pronotary and pronotary；
It is described that component characterization is chosen using Principal Component Analysis and discriminant analysis, i.e., variable is adjusted according to principal component analysis
Number takes 2 times of principle then according to variance analysis, and excluding outlier extracts top n as principal component, N is according to analysis
Setting value.
2. the Asiatic migrotory locust image characteristic extracting method according to claim 1 based on machine vision, which is characterized in that institute
It states in step 1 and signature analysis is carried out to Asiatic migrotory locust: migratory locusts being distinguished according to locust section feature and migratory locusts category feature, wherein locust
Section's feature is that head is inserted into shirtfront, and two adaptive ocellis each 3, antesternum has short spike protrusion metapedes leg section to thicken, spinosity；
Migratory locusts category feature is the long 33.5mm-41.5mm of adult hero body body, and female 39.5mm-51.2mm, face is vertical, and compound eye presentation is oval,
Arc or dimple is presented in dark-coloured speckle one in compound eye, the median carina of pronotary, and the two sides of median carina have dark-coloured vertical
Striped, fore wing presentation brown is glossy, there is dark-coloured speckle above, and hind wing is colourless or faint yellow, surface spinosity；Then root again
Pronotary according to the Asiatic migrotory locust that lives scattered is long and narrow, median carina protuberance；Before the fore wing of gregarious Asiatic migrotory locust is than the Asiatic migrotory locust that lives scattered
The ratio that wing grows abdomen is big；In the long ratio long with metapedes leg section of fore wing, the ratio for Asiatic migrotory locust of living in groups is greater than 2, and dissipates
The ratio of Asiatic migrotory locust is occupied less than 2；In terms of metapedes tibia color, living in groups, Asiatic migrotory locust presentation is faint yellow, and live scattered Asiatic migrotory locust
Red characteristic is presented in metapedes tibia, and migratory locusts are divided into gregarious and two classes of living scattered.
3. the Asiatic migrotory locust image characteristic extracting method according to claim 1 based on machine vision, which is characterized in that institute
The feature for stating the Asiatic migrotory locust chosen in step 2 is respectively from four head of Asiatic migrotory locust, pronotary, metapedes, wing portions
The top view and the extracted textural characteristics of two angles of side view, color characteristic and shape feature of position.
4. the Asiatic migrotory locust image characteristic extracting method according to claim 1 based on machine vision, which is characterized in that institute
Image characteristics extraction includes: that the extraction for textural characteristics uses calculating energy, entropy, inverse difference moment, contrast in the step 2 stated
Method；For color characteristic using the method for calculating first moment, second moment；For shape feature extraction using reference area,
Perimeter, complexity, eccentricity, duty ratio, the method for spherical property.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510757189.3A CN105354580B (en) | 2015-11-09 | 2015-11-09 | Asiatic migrotory locust image characteristic extracting method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510757189.3A CN105354580B (en) | 2015-11-09 | 2015-11-09 | Asiatic migrotory locust image characteristic extracting method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105354580A CN105354580A (en) | 2016-02-24 |
| CN105354580B true CN105354580B (en) | 2019-03-08 |
Family
ID=55330547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510757189.3A Expired - Fee Related CN105354580B (en) | 2015-11-09 | 2015-11-09 | Asiatic migrotory locust image characteristic extracting method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354580B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096612A (en) * | 2016-06-01 | 2016-11-09 | 中国科学院动物研究所 | Trypetid image identification system and method |
| CN110276280B (en) * | 2019-06-06 | 2021-06-04 | 刘嘉津 | Optical processing method for automatically identifying crop pest images |
| CN111291702A (en) * | 2020-02-20 | 2020-06-16 | 北京嘉景生物科技有限责任公司 | Identification method for distinguishing locust species by image recognition technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646192A (en) * | 2011-02-22 | 2012-08-22 | 彭炘烽 | Coordinate information conversion and display system |
| CN102663752A (en) * | 2012-04-11 | 2012-09-12 | 南京理工大学 | SAM weighted KEST hyperspectral anomaly detection algorithm |
| CN103135008A (en) * | 2011-12-05 | 2013-06-05 | 财团法人资讯工业策进会 | Power abnormal detection device and power abnormal detection method |
| CN103440488A (en) * | 2013-09-03 | 2013-12-11 | 江苏物联网研究发展中心 | Method for identifying pest |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100166303A1 (en) * | 2008-12-31 | 2010-07-01 | Ali Rahimi | Object recognition using global similarity-based classifier |
-
2015
- 2015-11-09 CN CN201510757189.3A patent/CN105354580B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646192A (en) * | 2011-02-22 | 2012-08-22 | 彭炘烽 | Coordinate information conversion and display system |
| CN103135008A (en) * | 2011-12-05 | 2013-06-05 | 财团法人资讯工业策进会 | Power abnormal detection device and power abnormal detection method |
| CN102663752A (en) * | 2012-04-11 | 2012-09-12 | 南京理工大学 | SAM weighted KEST hyperspectral anomaly detection algorithm |
| CN103440488A (en) * | 2013-09-03 | 2013-12-11 | 江苏物联网研究发展中心 | Method for identifying pest |
Non-Patent Citations (3)
| Title |
|---|
| "东亚飞蝗生境的遥感分类研究";李开丽;《中国优秀硕士学位论文全文数据库 农业科技辑》;20060315;论文正文第2章 |
| "基于色度和形态特征的蝗虫信息提取技术";毛文华 等;《农业机械学报》;20080930;第1-3章 |
| "机器视觉技术在果园自动化中的应用研究";王辉;《中国博士学位论文全文数据库 农业科技辑》;20120515;论文正文第2.3节、4.2节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105354580A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107229917B (en) | A kind of several remote sensing image general character well-marked target detection methods based on iteration cluster | |
| CN105354580B (en) | Asiatic migrotory locust image characteristic extracting method based on machine vision | |
| CN109063724A (en) | A kind of enhanced production confrontation network and target sample recognition methods | |
| CN108319957A (en) | A kind of large-scale point cloud semantic segmentation method based on overtrick figure | |
| CN105608692B (en) | Polarization SAR image segmentation method based on deconvolution network and sparse classification | |
| CN102496023A (en) | Region of interest extraction method of pixel level | |
| CN110458750A (en) | A kind of unsupervised image Style Transfer method based on paired-associate learning | |
| CN105678261B (en) | Based on the direct-push Method of Data with Adding Windows for having supervision figure | |
| Tao et al. | Mesh saliency via ranking unsalient patches in a descriptor space | |
| CN110048827A (en) | A kind of class template attack method based on deep learning convolutional neural networks | |
| CN105160623B (en) | Unsupervised high-spectral data dimension reduction method based on chunking low-rank tensor model | |
| Liu et al. | Image recognition of citrus diseases based on deep learning | |
| CN109034269A (en) | A kind of bollworm female male imago method of discrimination based on computer vision technique | |
| CN108596126A (en) | A kind of finger venous image recognition methods based on improved LGS weighted codings | |
| CN106650744A (en) | Image object co-segmentation method guided by local shape migration | |
| CN109034231A (en) | The deficiency of data fuzzy clustering method of information feedback RBF network valuation | |
| CN109784192A (en) | Hyperspectral Image Classification method based on super-pixel feature extraction neural network algorithm | |
| CN106446500B (en) | It is a kind of based on it is improved have supervision Orthogonal Neighborhood keep Embedded dimensions reduction fault identification method | |
| CN102592150A (en) | Gait identification method of bidirectional two-dimensional principal component analysis based on fuzzy decision theory | |
| Yang et al. | A comparative evaluation of convolutional neural networks, training image sizes, and deep learning optimizers for weed detection in alfalfa | |
| Dai et al. | ITF-WPI: Image and text based cross-modal feature fusion model for wolfberry pest recognition | |
| Pan et al. | A hybrid clustering algorithm combining cloud model iwo and k-means | |
| Wang et al. | Accurate detection and precision spraying of corn and weeds using the improved YOLOv5 model | |
| CN104077610B (en) | The method of the SAR image target recognition of two-dimension non linearity projection properties | |
| CN106373129A (en) | FCM remote sensing image segmentation method based on dual degree of membership |
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: 20190308 Termination date: 20191109 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |