CN103345634A - Automatic identification method for common vegetable insects on yellow board - Google Patents
Automatic identification method for common vegetable insects on yellow board Download PDFInfo
- Publication number
- CN103345634A CN103345634A CN2013103214949A CN201310321494A CN103345634A CN 103345634 A CN103345634 A CN 103345634A CN 2013103214949 A CN2013103214949 A CN 2013103214949A CN 201310321494 A CN201310321494 A CN 201310321494A CN 103345634 A CN103345634 A CN 103345634A
- Authority
- CN
- China
- Prior art keywords
- insect
- image
- dark position
- area
- name
- 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.)
- Granted
Links
Images
Landscapes
- Catching Or Destruction (AREA)
Abstract
The invention discloses an automatic identification method for common vegetable insects on a yellow board, which comprises the following steps: (1) image acquisition: acquiring an image of a vegetable insect on the yellow board by using an imaging device; (2) carrying out zooming, rotating, shearing and target image separation processing on the image of the vegetable insect on the yellow board; (3) calculating the area, rectangularity and elongation of the image of the vegetable insect on the yellow board; (4) separating a deep-color part of the image of the insect from the background; (5) calculating the area, rectangularity and deep-color part contour projection quantity of the deep-color part image of the image of the insect; and (6) according to the shape characteristics of different kinds of insects and the calculation results obtained in the steps (3) and (5), judging and displaying the name of the vegetable insect on the yellow board. The invention relates to a method capable of carrying out automatic identification on common vegetable insects on yellow boards. The method disclosed by the invention has the advantages that principle is simple, operation is easy, and identification can be automatically carried out on common vegetable insects on yellow boards.
Description
Technical field
The present invention is mainly concerned with the field of insect recognition methods in the insect research, refers in particular to the automatic identifying method of common vegetables insect on a kind of yellow plate.
Background technology
At present, on green house of vegetables, yellow plate is applied to monitoring and pest control more and more at large.Yellow plate can attract various insects, comprises insect and natural enemy, and the kind of therefore identifying insect on the yellow plate is the thorny problem that peasant household faces usually.Identification error will be taked wrong prophylactico-therapeutic measures, causes production cost to increase, the agricultural product underproduction, and residues of pesticides rise.
Judge the kind of insect on the yellow plate, one of existing method is: peasant household can ask the entomology person skilled that the insect on the yellow plate is identified, the entomology person skilled often stays in bureau of agriculture, plant protection unit and agricultural colleges and universities and R﹠D institution, this approach can delay the time of peasant household, spends many travel expenses and correlative charges.Two of existing method: the kind of insect on the yellow plate is judged by browsing books and online enquiries by peasant household, and this method needs peasant household to possess certain cultural competence, need possess books and reference materials or online condition, and will spend the long time.In the prior art, similarly insect image automatic identification technology has the method and system that butterfly is identified automatically, but this method does not have versatility.
Summary of the invention
The technical problem to be solved in the present invention just is: the technical matters at prior art exists the invention provides the method that a kind of principle is simple, easy and simple to handle, can identify common vegetables insect on the yellow plate automatically.
For solving the problems of the technologies described above, the present invention by the following technical solutions.
The automatic identifying method of common vegetables insect the steps include: on a kind of yellow plate
(1) image acquisition, processing and insect image extract: gather insect image on the vegetables glutinous rehmannia plate; Adjust the resolution of insect image; And the head that makes the targeted insect image all up; Then, the insect image-region is sheared; Finish the extraction of insect image;
(2) insect characteristics of image numerical evaluation: area, rectangle degree and the elongation of calculating the insect image;
(3) image at the dark position of insect health extracts and this characteristics of image numerical value is calculated: calculate dark position area (the dark position of insect health pixel quantity), rectangle degree, the concavo-convex quantity of dark position profile;
(4) insect classification identification: compare according to the data that step (2) and step (3) obtain, judge the classification of insect.
As a further improvement on the present invention, the particular content of described step (4) is:
A. working as dark position area is zero, and insect pulling degree showed insect " aleyrodid " by name less than 2 o'clock;
B. working as dark position area is zero, and insect pulling degree showed insect " leafhopper " by name greater than 2.3 o'clock;
C. when dark position profile protrusion quantity is 4 ~ 10, show insect " parasitic wasp " by name;
D. when dark position rectangle degree is between 5 ~ 20, show insect " moth class " by name;
E. subtract each other less than 6 when insect image rectangle degree and dark position rectangle degree, the logarithm of insect image area is between 7～9, and the logarithm of dark position area shows that insect is called " aphid " between 4.5～7 the time;
F. work as the logarithm of insect image area between 6.1～8.2, the logarithm of the dark position of insect area is between 3～6.7, insect image rectangle degree and dark position rectangle degree are between 25～55, and dark position rectangle degree shows insect " mosquito " by name when spending greater than insect image rectangle;
G. when the logarithm of insect image area between 8～12, the logarithm of the area at insect image and dark position subtracts each other less than 2, the ratio of insect image rectangle degree and dark position rectangle degree shows insect " wasp fly " by name between 1.7～2.3 the time;
H. subtract each other less than 7 when the logarithm of insect image area and the logarithm of dark position area, and insect image rectangle degree and dark position rectangle degree show insect " chrysomelid " by name between 61～90;
I. when numerical value did not meet above-mentioned all conditions, the demonstration insect is by name can't to be identified.
As a further improvement on the present invention, when carrying out the extraction of insect image in the described step (1), first yellow with yellow plate bleaches, blackening again, and other colors are constant, and insect image and other background areas are separated, and the insect image is extracted out like this.
As a further improvement on the present invention, when carrying out the image extraction at the dark position of insect health in the described step (3), earlier image is become ash, regulate gray threshold, insect health dark color station diagram is looked like to extract.
Compared with prior art, advantage of the present invention just is:
1, the automatic identifying method of common vegetables insect on the yellow plate of the present invention, principle is simple, easy and simple to handle rapidly; Utilize this method to identify vegetables caste on the yellow plate, can in half an hour, finish to obtaining the result from image acquisition.
2, the present invention can cost saving after application, reduce the real cost of identification operation.The equipment of this method utilization is common digital camera and computer, and power consumption is less than 1 degree electricity, and expense can be ignored.
3, method of the present invention is grasped easily, is easily promoted, and most people can read this method operation instruction alone and grasp this method within half an hour.
Description of drawings
Fig. 1 is the schematic flow sheet of the present invention in specific embodiment.
Fig. 2 is the schematic flow sheet that the present invention is rotated picture in specific embodiment.
Fig. 3 is the present invention shears the targeted insect image-region in specific embodiment schematic flow sheet.
Fig. 4 is the schematic flow sheet that the present invention extracts the insect image in specific embodiment.
Fig. 5 is the schematic flow sheet that the present invention looks like to extract to the dark station diagram of insect health in specific embodiment.
Fig. 6 is the schematic flow sheet that the present invention differentiates 8 class insects according to result of calculation in specific embodiment.
Embodiment
Below with reference to specific embodiment and Figure of description the present invention is described in further details.
As shown in Figure 1, the automatic identifying method of common vegetables insect the steps include: on the yellow plate of the present invention
(1) image acquisition: utilize imaging device to gather the image of vegetables insect on the yellow plate.As: utilize digital camera with the image acquisition of vegetables insect on the yellow plate and be transported in the computing machine.
(2) image convergent-divergent: during the digital camera photographic images, because the resolution of digital camera different model is variant, resolution is variant after also will causing target imaging from the target distance during shooting, and being the present invention, the insect size judges an important evidence of caste, therefore, need carry out convergent-divergent to the image that collects to reach the resolution that is more or less the same.
(3) image rotation: insect quantity is more on the yellow plate, and most insect is different directions and is bonded on all fours on the yellow plate, need identification the targeted insect head towards also indefinite, unified head is oriented ensuing calculation of parameter provides comparability.Therefore, need the image that collect be rotated, postrotational picture makes the targeted insect picture headers all up.
(4) image cut: the common size of yellow plate is that 200mm * 300mm is between 300mm * 400mm, when the pictures taken of field, the dark degree varies sample of whole picture, to cut apart the difficulty of insect image and background image bigger for passing threshold from the whole pictures, neither be necessary.In order to reduce the interference of other insect images, need be with the less rectangular area people at targeted insect place for cutting.
(5) the insect image extracts: common vegetables insect color is all different with yellow plate color, utilizes that this point can bleach the yellow of yellow plate, blackening again, and other colors are constant.Computing machine is red with R (red), G (green) is green, the various combination of blue three numerical value of B (blue) is represented different colors, and three numerical value of the RGB of the yellow of yellow plate are satisfied to be about respectively: 200,180 and 50.If three numerical value of the RGB of the pixel in the image file add respectively at about 55,75,205 o'clock, yellow namely becomes white, and white is blackening again, and the insect image is extracted out like this.
(6) insect characteristics of image numerical evaluation: under the equal resolution, the insect of different sizes has different image pixel number of spots, the insect of identical size is because the difference of form and the form of spreading the wings causes not of uniform size the causing in rectangular area at insect image place, the ratio of long axis to short axis of insect image is also variant, calculate area, rectangle degree and the elongation of insect image, for other judgement of insects provides foundation.
(7) the dark station diagram picture of insect health extracts: the wing of insect often is translucent, head and chest then color are often darker, also have some insects to have the decorative pattern of different depth colors, like this, earlier image is become ash, regulate gray threshold, the dark station diagram of insect health can be looked like to extract.
(8) the dark station diagram of insect health calculates as character numerical value: different types of insect, the dark position of its health is not of uniform size, profile is also variant, calculates the dark position of health pixel quantity, rectangle degree, dark position profile protrusion quantity, for other judgement of insects provides foundation.
(9) insect classification identification: common vegetables insect mainly contains fly class, mosquito, parasitic wasp, aphid, aleyrodid, leafhopper, wasp fly, chrysomelid, moth class 9 classes on the yellow plate.The similar housefly of the form of fly class, be the known insect of people, the present invention does not provide recognition methods, the invention provides the recognition methods of other 8 class insect, when step (6) and (8) result displayed meet the morphological feature of mosquito, parasitic wasp, aphid, aleyrodid, smaller green leaf hopper, wasp fly, chrysomelid, moth class respectively, the item name that shows this targeted insect, when not meeting above-mentioned 8 class insect morphological features, demonstration can't be identified.
The distinguishing characteristics of above-mentioned 8 class insects mainly contains: a. aleyrodid and smaller green leaf hopper do not have dark position; B. the body of aleyrodid is long differs less than 1 times with body is wide; C. the smaller green leaf hopper body is grown up in wide 2 times of body; D., significant depression is arranged between the parasitic wasp health cephalothorax; E. the aphid wing expanse is bigger; F. the rectangle degree of mosquito health and wing expanse is all less than normal; G. the wasp fly belly has the alternate decorative pattern of the depth; H. chrysomelid wing is opaque; I. the whole health of moth class is covered by the wing of the alternate decorative pattern of depth color.
In concrete present embodiment, the detail operations flow process is as follows:
(1) image acquisition: utilize digital camera with the image acquisition of vegetables insect on the yellow plate and be transported in the computing machine.
(2) image convergent-divergent: the actual size in kind that this picture is gathered is about 200mm * 300mm, and the total pixel of this picture is 4000 * 3000, average every mm
2Pixel be 196, approximate 200, therefore, this picture need not convergent-divergent.
(3) image rotation: through 118 degree rotations, the targeted insect head is (as Fig. 2) up with this picture.
(4) image cut: with rectangle frame with the cutting from the whole pictures of targeted insect zone get off (as Fig. 3).
(5) the insect image extracts: adjust three numerical value of RGB, make the yellow of yellow plate bleach, white is blackening again, and the insect image is extracted out (as Fig. 4) like this.
(6) insect characteristics of image numerical evaluation: deletion insect image is peripheral to be black row and column entirely, accurately locks the minimum rectangular area at insect image place, calculates and demonstration insect image area, rectangle degree and elongation.
(7) the dark station diagram picture of insect health extracts: will become ash through the insect image after the step (5), regulate gray threshold, the dark position of insect health that brightness is lower than this gray threshold is constant, brightness is higher than insect light color position and the yellow all blackening of background of this gray threshold, the dark station diagram of insect health looks like to be extracted out (Fig. 5), be not lower than the position of yellow plate brightness as fruit insect brightness, then all pixels of this shearogram bleach.
(8) the dark station diagram of insect health calculates as character numerical value: deletion step (7) back gained image periphery is black row and column entirely, the accurate minimum circumscribed rectangular region at place, the dark position of locking insect is calculated and is shown dark position image area, rectangle degree.Add up dark position profile and protrude quantity.
(9) caste identification: according to the result of calculation (as Fig. 6) of step (8) and step (6).
A. working as dark position area is zero, and insect pulling degree showed insect " aleyrodid " by name less than 2 o'clock;
B. working as dark position area is zero, and insect pulling degree showed insect " leafhopper " by name greater than 2.3 o'clock;
C. when dark position profile protrusion quantity is 4-10, show insect " parasitic wasp " by name;
D. when dark position rectangle degree is between 5～20, show insect " moth class " by name;
E. subtract each other less than 6 when insect image rectangle degree and dark position rectangle degree, the logarithm of insect image area is between 7-9, and the logarithm of dark position area shows that insect is called " aphid " between 4.5-7 the time;
F. work as the logarithm of insect image area between 6.1-8.2, the logarithm of the dark position of insect area is between 3-6.7, insect image rectangle degree and dark position rectangle degree are between 25-55, and dark position rectangle degree shows insect " mosquito " by name when spending greater than insect image rectangle;
G. when the logarithm of insect image area between 8-12, the logarithm of the area at insect image and dark position subtracts each other less than 2, the ratio of insect image rectangle degree and dark position rectangle degree shows insect " wasp fly " by name between 1.7-2.3 the time;
H. subtract each other less than 7 when the logarithm of insect image area and the logarithm of dark position area, and insect image rectangle degree and dark position rectangle degree show insect " chrysomelid " by name between 61-90;
I. when the numerical value of step (6) and (8) demonstration did not meet above-mentioned condition, the demonstration insect is by name can't to be identified.
The above only is preferred implementation of the present invention, and protection scope of the present invention also not only is confined to above-described embodiment, and all technical schemes that belongs under the thinking of the present invention all belong to protection scope of the present invention.Should be pointed out that for those skilled in the art in the some improvements and modifications that do not break away under the principle of the invention prerequisite, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (4)
1. the automatic identifying method of common vegetables insect on the yellow plate is characterized in that step is:
(1) image acquisition, processing and insect image extract: gather insect image on the vegetables glutinous rehmannia plate; Adjust the resolution of insect image; And the head that makes the targeted insect image all up; Then, the insect image-region is sheared; Finish the extraction of insect image;
(2) insect characteristics of image numerical evaluation: area, rectangle degree and the elongation of calculating the insect image;
(3) image at the dark position of insect health extracts and this characteristics of image numerical value is calculated: calculate dark position area, rectangle degree, dark position profile protrusion quantity;
(4) insect classification identification: compare according to the data that step (2) and step (3) obtain, judge the classification of insect.
2. the automatic identifying method of common vegetables insect on the yellow plate according to claim 1 is characterized in that the particular content of described step (4) is:
A. working as dark position area is zero, and insect pulling degree showed insect " aleyrodid " by name less than 2 o'clock;
B. working as dark position area is zero, and insect pulling degree showed insect " leafhopper " by name greater than 2.3 o'clock;
C. when dark position profile protrusion quantity is 4 ~ 10, show insect " parasitic wasp " by name;
D. when dark position rectangle degree is between 5 ~ 20, show insect " moth class " by name;
E. subtract each other less than 6 when insect image rectangle degree and dark position rectangle degree, the logarithm of insect image area is between 7～9, and the logarithm of dark position area shows that insect is called " aphid " between 4.5～7 the time;
F. work as the logarithm of insect image area between 6.1～8.2, the logarithm of the dark position of insect area is between 3～6.7, insect image rectangle degree and dark position rectangle degree are between 25～55, and dark position rectangle degree shows insect " mosquito " by name when spending greater than insect image rectangle;
G. when the logarithm of insect image area between 8～12, the logarithm of the area at insect image and dark position subtracts each other less than 2, the ratio of insect image rectangle degree and dark position rectangle degree shows insect " wasp fly " by name between 1.7～2.3 the time;
H. subtract each other less than 7 when the logarithm of insect image area and the logarithm of dark position area, and insect image rectangle degree and dark position rectangle degree show insect " chrysomelid " by name between 61～90;
I. when numerical value did not meet above-mentioned all conditions, the demonstration insect is by name can't to be identified.
3. the automatic identifying method of common vegetables insect on the yellow plate according to claim 1 and 2, it is characterized in that, when carrying out the extraction of insect image in the described step (1), first yellow with yellow plate bleaches, blackening again, and other colors are constant, insect image and other background areas are separated, and the insect image is extracted out like this.
4. the automatic identifying method of common vegetables insect on the yellow plate according to claim 1 and 2, it is characterized in that, when carrying out the image extraction at the dark position of insect health in the described step (3), earlier image is become ash, regulate gray threshold, the dark station diagram of insect health is looked like to extract.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310321494.9A CN103345634B (en) | 2013-07-29 | 2013-07-29 | The automatic identifying method of Vegetables insecticide on a kind of yellow plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310321494.9A CN103345634B (en) | 2013-07-29 | 2013-07-29 | The automatic identifying method of Vegetables insecticide on a kind of yellow plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103345634A true CN103345634A (en) | 2013-10-09 |
| CN103345634B CN103345634B (en) | 2016-12-28 |
Family
ID=49280429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310321494.9A Expired - Fee Related CN103345634B (en) | 2013-07-29 | 2013-07-29 | The automatic identifying method of Vegetables insecticide on a kind of yellow plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103345634B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894131A (en) * | 2016-04-28 | 2016-08-24 | 广东石油化工学院 | Fruit-piercing moth rapid early-warning method |
| CN107066938A (en) * | 2017-02-08 | 2017-08-18 | 清华大学 | Video analysis equipment, method and computer program product |
| CN108040997A (en) * | 2017-12-25 | 2018-05-18 | 仲恺农业工程学院 | A kind of insect pest monitoring method based on machine vision |
| CN110276278A (en) * | 2019-06-04 | 2019-09-24 | 刘嘉津 | Insect image identification entirety and the recognition methods of multiple clips comprehensive automation |
| CN112949625A (en) * | 2021-01-29 | 2021-06-11 | 西安电子科技大学 | Target identification method and system based on centroid contour distance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030026484A1 (en) * | 2001-04-27 | 2003-02-06 | O'neill Mark | Automated image identification system |
| CN102239793A (en) * | 2011-04-18 | 2011-11-16 | 浙江大学 | Real-time classification method and system of rice pests |
| CN102819748A (en) * | 2012-07-19 | 2012-12-12 | 河南工业大学 | Classification and identification method and classification and identification device of sparse representations of destructive insects |
| CN102930249A (en) * | 2012-10-23 | 2013-02-13 | 四川农业大学 | Method for identifying and counting farmland pests based on colors and models |
-
2013
- 2013-07-29 CN CN201310321494.9A patent/CN103345634B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030026484A1 (en) * | 2001-04-27 | 2003-02-06 | O'neill Mark | Automated image identification system |
| CN102239793A (en) * | 2011-04-18 | 2011-11-16 | 浙江大学 | Real-time classification method and system of rice pests |
| CN102819748A (en) * | 2012-07-19 | 2012-12-12 | 河南工业大学 | Classification and identification method and classification and identification device of sparse representations of destructive insects |
| CN102930249A (en) * | 2012-10-23 | 2013-02-13 | 四川农业大学 | Method for identifying and counting farmland pests based on colors and models |
Non-Patent Citations (4)
| Title |
|---|
| NATALIA LARIOS等: "Automated insect identification through concatenated histograms of local appearance features: feature vector generation and region detection for deformable objects", 《MACHINE VISION AND APPLICATIONS》, 7 July 2007 (2007-07-07) * |
| 姚青等: "基于图像的昆虫自动识别与计数研究进展", 《中国农业科学》, no. 14, 16 July 2011 (2011-07-16) * |
| 张学庆等: "数学形态学在储量昆虫图像识别中的应用", 《武汉工业学院学报》, vol. 23, no. 1, 30 March 2004 (2004-03-30) * |
| 黄世国等: "快速几何可变形彩色昆虫图像分割算法", 《计算机应用》, vol. 28, no. 12, 1 December 2008 (2008-12-01) * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894131A (en) * | 2016-04-28 | 2016-08-24 | 广东石油化工学院 | Fruit-piercing moth rapid early-warning method |
| CN107066938A (en) * | 2017-02-08 | 2017-08-18 | 清华大学 | Video analysis equipment, method and computer program product |
| CN107066938B (en) * | 2017-02-08 | 2020-02-07 | 清华大学 | Video analysis apparatus, method and computer program product |
| CN108040997A (en) * | 2017-12-25 | 2018-05-18 | 仲恺农业工程学院 | A kind of insect pest monitoring method based on machine vision |
| CN108040997B (en) * | 2017-12-25 | 2020-09-11 | 仲恺农业工程学院 | Insect pest monitoring method based on machine vision |
| CN110276278A (en) * | 2019-06-04 | 2019-09-24 | 刘嘉津 | Insect image identification entirety and the recognition methods of multiple clips comprehensive automation |
| CN112949625A (en) * | 2021-01-29 | 2021-06-11 | 西安电子科技大学 | Target identification method and system based on centroid contour distance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103345634B (en) | 2016-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dorj et al. | An yield estimation in citrus orchards via fruit detection and counting using image processing | |
| Anand et al. | An application of image processing techniques for detection of diseases on brinjal leaves using k-means clustering method | |
| CN105184824B (en) | Reading intelligent agriculture bird-repeller system based on image sensing net | |
| CN106203265B (en) | A kind of Construction Fugitive Dust Pollution source monitors automatically and coverage forecasting system and method | |
| Kulkarni et al. | Applying image processing technique to detect plant diseases | |
| CN103345634A (en) | Automatic identification method for common vegetable insects on yellow board | |
| CN102915446A (en) | Plant disease and pest detection method based on SVM (support vector machine) learning | |
| CN110070526A (en) | Defect inspection method based on the prediction of deep neural network temperature figure | |
| CN103323455A (en) | Tobacco leaf grading method based on reflection, perspective and microscopic images | |
| CN110263609A (en) | A kind of automatic identifying method of safety cap wear condition | |
| CN110100149A (en) | Survey label, image processing apparatus, image processing method and program | |
| CN102096808A (en) | Method for automatically monitoring and reporting insect condition of rice planthopper | |
| CN109886129B (en) | Prompt message generation method and device, storage medium and electronic device | |
| CN109034268A (en) | A kind of red turpentine beetle detector optimization method of Information element trapper | |
| CN110659546B (en) | Illegal booth detection method and device | |
| CN102208099A (en) | Illumination-change-resistant crop color image segmentation method | |
| CN102768757A (en) | Remote sensing image color correcting method based on image type analysis | |
| CN106650822A (en) | Identification method and device for diseases and insect pests | |
| CN108734277A (en) | A kind of targeted drug spray method based on convolutional neural networks | |
| Rahim et al. | Deep learning-based accurate grapevine inflorescence and flower quantification in unstructured vineyard images acquired using a mobile sensing platform | |
| CN115512134A (en) | Express item stacking abnormity early warning method, device, equipment and storage medium | |
| CN108898098A (en) | Early stage video smoke detection method based on monitor supervision platform | |
| CN106650824B (en) | Moving object classification method based on support vector machines | |
| CN108491759A (en) | A kind of process detection device and its process detection method based on deep learning | |
| CN103699907B (en) | Pesticide spraying detection method based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161228 Termination date: 20170729 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |