CN105335705A - Corn abnormal cluster screening method based on computer vision, device and system - Google Patents
Corn abnormal cluster screening method based on computer vision, device and system Download PDFInfo
- Publication number
- CN105335705A CN105335705A CN201510674358.7A CN201510674358A CN105335705A CN 105335705 A CN105335705 A CN 105335705A CN 201510674358 A CN201510674358 A CN 201510674358A CN 105335705 A CN105335705 A CN 105335705A
- Authority
- CN
- China
- Prior art keywords
- image
- corn
- abnormal
- ear
- sieved
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention provides a corn abnormal cluster screening method based on the computer vision, a device and a system. The method comprises steps of intercepting images of to-be-screened corn clusters based on preset image intercepting rules so as to obtain intercepted images, wherein the images of to-be-screened corn clusters are images acquired by an image acquiring device; extracting characteristic parameters in the intercepted images based on the preset characteristic parameter extracting rules; and determining the abnormity categories of the corn clusters based on the preset abnormal cluster screening models according to the characteristic parameters. Thus, lossless identification of common abnormal clusters can be achieved and screening speed is greatly increased; and via the application of the computer vision technology, manpower can be well replaced, and the technical problem of low manual screening efficiency of abnormal corn clusters in the prior art is solved.
Description
Technical field
The present invention relates to computer vision field, particularly relate to the abnormal fruit ear method for sieving of a kind of corn based on computer vision, Apparatus and system.
Background technology
The domestic screening to the abnormal fruit ear of corn at present mainly relies on artificial cognition, and it is all very large often to criticize the corn quantity needing to sieve, traditional screening process often needs lasting more than one month, there is human cost consumes excessive and waste is serious, inefficiency and the not high many drawbacks of precision.Utilize computer vision to carry out screening to the abnormal fruit ear of corn and can replace manual labor well, effectively improve screening efficiency.
Prior art discloses a kind of corn ear test mthods, systems and devices based on computer vision technique, multiple apparent parameters such as the spike length of corn ear, tassel row number, row grain number, bald sharp length can be measured.In similar apparatus and method, the spike length isophenous mainly for corn ear is studied, and does not propose the method for sieving about the abnormal fruit ear of corn.
Therefore, do not have in prior art to realize the abnormal fruit ear method for sieving of corn based on computer vision.
Summary of the invention
The invention provides the abnormal fruit ear method for sieving of a kind of corn based on computer vision, system and device, to solve in prior art the technical matters relying on the abnormal fruit ear inefficiencies such as artificial screening corn goes mouldy.
First aspect, the invention provides the abnormal fruit ear method for sieving of a kind of corn based on computer vision, comprising:
Based on the image interception rule preset, intercept the image of described corn ear to be sieved, obtain cut-away view picture; The image of described corn ear to be sieved is the image of image acquisition device;
Based on the characteristic parameter extraction rule preset, extract the characteristic parameter in described cut-away view picture;
According to described characteristic parameter, based on the abnormal fruit ear screening model preset, determine the abnormal class of corn ear.
Alternatively, in the described image interception rule based on presetting, intercept the image of described corn ear to be sieved, before obtaining cut-away view picture, described method also comprises:
Adopt the image of corn ear to be sieved described in medium filtering process, obtain the first image;
Adopt the first image described in Statistical Techniques dividing processing, obtain the second image;
Adopt the second image described in morphological image disposal route smoothing processing, obtain the 3rd image;
Correspondingly, the described image interception rule based on presetting, intercepts the image of described corn ear to be sieved, obtains cut-away view picture, comprising:
Based on the image interception rule preset, intercept described 3rd image, obtain cut-away view picture.
Alternatively, the described image interception rule based on presetting, intercepts the image of described corn ear to be sieved, obtains cut-away view picture, comprising:
According to the image of corn ear to be sieved, determine the minimum enclosed rectangle of described corn ear to be sieved;
According to described minimum enclosed rectangle, intercept the image of described corn ear to be sieved, obtain cut-away view picture.
Alternatively, described according to described cut-away view picture, based on the characteristic parameter extraction rule preset, before extracting the characteristic parameter in described cut-away view picture, described method also comprises:
Utilize the image window preset to scan described cut-away view picture, determine at least one piece of region of interest ROI.
Alternatively, the described characteristic parameter extraction rule based on presetting, extract the characteristic parameter in described cut-away view picture, comprising:
According to described at least one piece of ROI, based on RGB color model, extract the Color characteristics parameters of each ROI;
Each ROI is converted into gray level image, extracts the textural characteristics parameter of each gray level image.
Alternatively, described according to described at least one piece of ROI, based on RGB color model, extract the Color characteristics parameters of each ROI, comprising:
According to described at least one piece of ROI, determine the pixel number of each ROI;
According to the pixel number of described each ROI, based on RGB color model, extract the Color characteristics parameters of each ROI;
Described each ROI image is converted into gray level image, extracts the textural characteristics parameter of each gray level image, comprising:
Each ROI is converted into gray level image, gray compression is carried out to each gray level image, obtain the 4th image that described each gray level image is corresponding;
Based on the gray level co-occurrence matrixes computation model preset, calculate the gray level co-occurrence matrixes of each 4th image;
According to the gray level co-occurrence matrixes of described each 4th image, based on the textural characteristics parameter extraction rule preset, extract the textural characteristics parameter of described each 4th image.
Alternatively, described default abnormal fruit ear screening model is obtained by following steps:
From the abnormal area of the image of each Exception Type of corn ear preset, intercept at least one width subimage, form sample image storehouse;
Based on the characteristic parameter extraction rule preset, extract the characteristic parameter of each image in described sample image storehouse, form sample characteristics parameter library;
Utilize the characteristic parameter in sample characteristics parameter library, support vector machines is trained, obtain described default abnormal fruit ear screening model.
Alternatively, described according to described characteristic parameter, based on the abnormal fruit ear screening model preset, determine the abnormal class of corn ear, comprising:
According to described characteristic parameter, based on the abnormal fruit ear screening model preset, determine the abnormal area that each Exception Type default in described corn ear to be sieved is corresponding;
Determine the number percent of the abnormal area area occupied that described each Exception Type is corresponding;
Determine that the Exception Type of described corn ear to be sieved is the Exception Type that the maximum abnormal area of area percentage is corresponding.
Second aspect, the invention provides the abnormal fruit ear screening plant of a kind of corn based on computer vision, comprising:
Image interception unit, for based on the image interception rule preset, intercepts the image of described corn ear to be sieved, obtains cut-away view picture; The image of described corn ear to be sieved is the image of image acquisition device;
Parameter extraction unit, for based on the characteristic parameter extraction rule preset, extracts the characteristic parameter in described cut-away view picture;
Classification determination unit, for according to described characteristic parameter, based on the abnormal fruit ear screening model preset, determines the abnormal class of corn ear.
The third aspect, the invention provides the abnormal fruit ear screening system of a kind of corn based on computer vision, comprising:
The abnormal fruit ear screening plant of corn as described in second aspect, image collecting device, support and background board;
Described background board is placed in horizontal table top, and described support is connected with described background board, and described image collecting device is fixed on described support, and the abnormal fruit ear screening plant of described corn is connected with described image collecting device;
Described support, for fixing described image collecting device, to make described image collector setting in directly over background board;
Described background board, for carrying described corn ear to be sieved, and provides background for the image gathering corn ear to be sieved.
As shown from the above technical solution, the abnormal fruit ear method for sieving of the corn based on computer vision of the present invention, Apparatus and system, can realize several abnormal fruit ear that non-damage drive is common, screening speed improves greatly.The application of computer vision technique, can replace manual labor well, greatly improve screening efficiency, can be widely used in agriculture corn variety seed selection production and scientific research field.
Accompanying drawing explanation
The abnormal fruit ear method for sieving of the corn based on the computer vision schematic flow sheet that Fig. 1 provides for one embodiment of the invention;
The abnormal fruit ear screening plant of the corn based on the computer vision structural representation that Fig. 2 provides for one embodiment of the invention;
The abnormal fruit ear screening plant of the corn based on the computer vision structural representation that Fig. 3 provides for one embodiment of the invention;
The image of three kinds of Common Abnormity corn ears that Fig. 4 provides for one embodiment of the invention;
The image of the abnormal corn ear of the intercepting process that Fig. 5 provides for one embodiment of the invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
As shown in Figure 1, the present embodiment discloses the abnormal fruit ear method for sieving of a kind of corn based on computer vision, and its step can comprise step 101 to 103:
101, based on the image interception rule preset, intercept the image of described corn ear to be sieved, obtain cut-away view picture; The image of described corn ear to be sieved is the image of image acquisition device.
102, based on the characteristic parameter extraction rule preset, the characteristic parameter in described cut-away view picture is extracted.
103, according to described characteristic parameter, based on the abnormal fruit ear screening model preset, the abnormal class of corn ear is determined.
In a concrete example, before step 101, the abnormal fruit ear method for sieving of above-mentioned corn also to comprise in Fig. 1 unshowned step 1001 to step 1003.
1001, adopt the image of medium filtering process corn ear to be sieved, obtain the first image.
In the present embodiment, adopt the image of the medium filtering process corn ear to be sieved of 3*3 neighborhood, fully can retain the minutia of image, effectively remove the salt-pepper noise in image, retain the edge feature of corn ear to be sieved to greatest extent.
1002, adopt the first image described in Statistical Techniques dividing processing, obtain the second image.
In the present embodiment, adopt based on B component statistical dividing method the first Image Segmentation Using process.
1003, adopt the second image described in morphological image disposal route smoothing processing, obtain the 3rd image.
In the present embodiment, utilize morphological image disposal methods second image, effectively can remove the said minuscule hole of image inside, smoothed image edge.
Correspondingly, step 101 to can be in Fig. 1 unshowned 101 ':
101 ', based on the image interception rule preset, intercept described 3rd image, obtain cut-away view picture.
In a concrete example, step 101 specifically comprises unshowned sub-step 1011 and 1012 in Fig. 1.
1011, according to the image of corn ear to be sieved, the minimum enclosed rectangle of corn ear to be sieved is determined.
1012, according to minimum enclosed rectangle, intercept the image of corn ear to be sieved, obtain cut-away view picture.
Wherein, the fruit ear part of corn ear to be sieved is only comprised in cut-away view picture.
In a concrete example, before step 102, the abnormal fruit ear method for sieving of above-mentioned corn also comprises unshowned step 102 in Fig. 1 ':
102 ', utilize the image window preset to scan described cut-away view picture, determine at least one piece of region of interest ROI.
In the present embodiment, the image window size preset is 50*50 pixel, and the direction of scanning of window is from left to right, from top to bottom, and an image window often mobile position will determine one piece of ROI.
In a concrete example, step 102 specifically comprises unshowned sub-step 1021 and 1022 in Fig. 1.
1021, according at least one piece of ROI, based on RGB color model, the Color characteristics parameters of each ROI is extracted.
1022, each ROI is converted into gray level image, extracts the textural characteristics parameter of each gray level image.
In a concrete example, step 1021 specifically comprises unshowned sub-step 10211 and 10212 in Fig. 1.
10211, according at least one piece of ROI, the pixel number of each ROI is determined.
10212, according to the pixel number of each ROI, based on RGB color model, the Color characteristics parameters of each ROI is extracted.
In the present embodiment, Color characteristics parameters comprises R component average, G component average, B component average, color average and tone average, totally 5.
In a concrete example, step 1022 specifically comprises unshowned sub-step 10221 to 10223 in Fig. 1.
10221, each ROI is converted into gray level image, gray compression is carried out to each gray level image, obtain the 4th image that described each gray level image is corresponding.
In the present embodiment, gray compression is carried out for its gray scale 256 grades is quantized into 8 grades to each gray level image.
10222, based on the gray level co-occurrence matrixes computation model preset, the gray level co-occurrence matrixes of each 4th image is calculated.
In the present embodiment, be 1 to the image after quantizing in distance, angle be respectively level, 45 degree, vertically, 135 degree of directions calculate gray level co-occurrence matrixes.
10223, according to the gray level co-occurrence matrixes of described each 4th image, based on the textural characteristics parameter extraction rule preset, the textural characteristics parameter of described each 4th image is extracted.
In the present embodiment, according to the gray level co-occurrence matrixes of the four direction calculated, add up the contrast of four direction, energy, entropy, unfavourable balance square and the degree of correlation respectively.Four contrasts, energy, entropy, unfavourable balance square and the degree of correlation that obtain are averaged respectively, obtain contrast average, average energy value, entropy average, unfavourable balance square average and degree of correlation average, as 5 textural characteristics parameters.
In a concrete example, the abnormal fruit ear screening model preset obtains by step a to c unshowned in Fig. 1.
A, from preset each Exception Type of corn ear image abnormal area intercept at least one width subimage, form sample image storehouse.
In the present embodiment, the corn ear quantity setting each Exception Type is no less than 30, and the number of sub-images of the corn ear intercepting of often kind of Exception Type is for being no less than 50 width.
B, based on the characteristic parameter extraction rule preset, extract the characteristic parameter of each image in described sample image storehouse, form sample characteristics parameter library.
Based on above-mentioned characteristic parameter extraction rule, 5 Color characteristics parameters and 5 textural characteristics parameters are extracted to the every width subimage intercepted, form sample characteristics parameter library.
C, the characteristic parameter utilized in sample characteristics parameter library, train support vector machines, obtains described default abnormal fruit ear screening model.
In the present embodiment, the kernel function of support vector machines adopts Radial basis kernel function.
In a concrete example, step 103 specifically comprises unshowned sub-step 1031 to 1033 in Fig. 1.
1031, according to described characteristic parameter, based on the abnormal fruit ear screening model preset, the abnormal area that each Exception Type default in described corn ear to be sieved is corresponding is determined.
1032, the number percent of the abnormal area area occupied that described each Exception Type is corresponding is determined.
1033, determine that the Exception Type of described corn ear to be sieved is the Exception Type that the maximum abnormal area of area percentage is corresponding.
Effectively can improve the screening speed of corn ear, be applicable to the statistics to the corn ear of Exception Type and research.
As shown in Figure 2, present embodiment discloses the abnormal fruit ear screening plant of a kind of corn based on computer vision, comprise image interception unit 21, parameter extraction unit 22 and classification determination unit 23.
Image interception unit 21, for based on the image interception rule preset, intercepts the image of described corn ear to be sieved, obtains cut-away view picture.
Wherein, the image of corn ear to be sieved is the image of image acquisition device.
Parameter extraction unit 22, for based on the characteristic parameter extraction rule preset, extracts the characteristic parameter in described cut-away view picture.
Classification determination unit 23, for according to described characteristic parameter, based on the abnormal fruit ear screening model preset, determines the abnormal class of corn ear.
The abnormal fruit ear screening plant of the corn that the present embodiment provides, can realize the abnormal corn ear of non-damage drive, improve screening speed.
As shown in Figure 3, present embodiments provide the abnormal fruit ear screening system of a kind of corn based on computer vision, comprise the abnormal fruit ear screening plant 31 of corn, image collecting device 32, support 33 and background board 34 in above-described embodiment.
Background board 34 is placed in horizontal table top, and support 33 is connected with background board 34, and image collecting device 32 is fixed on support 33, and the abnormal fruit ear screening plant 31 of corn is connected with image collecting device 32.
Support 33, for still image harvester 32, is positioned at directly over background board 34 to make image collecting device 32.
Background board 34, for carrying corn ear to be sieved, and provides background for the image gathering corn ear to be sieved.
In the present embodiment, the abnormal fruit ear screening plant 31 of corn is computing machine; Image collecting device 32 is 5,000,000 pixel CCD camera; The height of setting support 33 is 55cm; Background board 34 size is 32cm × 50cm, can place single ear corn fruit ear, and the angles of corn ear is random; The color of setting background board 34 is pure blue, because corn ear is golden yellow mostly, at the image of pure blue background board photographs corn ear, the contrast of image can be made to increase, and improves computing machine to the processing speed of image.
It is low, easy to operate that the abnormal fruit ear of corn disclosed in the present embodiment screening plant has cost, less demanding to operating personnel, has the advantages that universality is high; Meanwhile, the data of screening and image are easily preserved and are expanded, and are more suitable for scientific research and statistics.
Fig. 4 shows the image of three kinds of Common Abnormity corn ears, and as shown in Figure 4,1 is mechanical damage fruit ear, and 2 is fruit ear of damaging by worms, and 3 is the fruit ear that goes mouldy.The Crack cause of three kinds of abnormal corn ears is as follows:
Mechanical damage fruit ear: what mechanical harvesting corn ear adopted is physical impacts principle, fresh corn fruit ear is comparatively large due to water cut, easily causes fruit ear epidermis injury, thus expose white endosperm in collision process.This fruit ear exposing white endosperm due to mechanical damage fruit ear epidermis is exactly mechanical damage fruit ear;
To damage by worms fruit ear: corn ear, when field, due to planting environment impact, disease and pest occurs, or in storing process, insect bites to corn ear fringe portion, make corn ear lose the production of hybrid seeds and be worth.This corn insect pest impact and lose fruit ear that the production of hybrid seeds is worth and to damage by worms exactly corn ear;
Go mouldy fruit ear: corn ear is in field or storing process, and cross more high factors due to ambient moisture content and cause corn ear fringe portion to go mouldy, fringe portion seed presents various mildew color, loses the production of hybrid seeds, edibility.This corn ear is referred to as the fruit ear that goes mouldy.
As shown in Figure 5, the present embodiment, using the image of fruit ear of damaging by worms as handling object, represents the intercepting process of the present embodiment to corn ear image in detail with the change of image.
(1) be the original image of corn ear of damaging by worms, (1) is carried out to the medium filtering process of 3*3 neighborhood, remain the detail characteristic of (1), eliminate salt-pepper noise wherein, remain the edge feature of fruit ear of damaging by worms to greatest extent, obtain (2).
(2) be the image of the corn ear of damaging by worms after denoising, adopt, based on B component statistical dividing method, dividing processing is carried out to (2), obtain (3).
(3) be the image of the corn ear of damaging by worms after segmentation, adopt morphological image disposal route to remove (3) inner said minuscule hole, smoothed image edge, obtains (4).
(4) be the image of the corn ear of damaging by worms after morphological image process, determine the minimum enclosed rectangle of (4), obtain (5).
(5) for determining the image of the corn ear of damaging by worms of minimum enclosed rectangle, with the size of minimum enclosed rectangle, at (1) upper cut-away view picture, obtain (6).
(6) be the image of the corn ear of damaging by worms of intercepting.
The image interception process of abnormal corn ear to be sieved disclosed in the present embodiment, ensure that whole features of the abnormal corn ear of shooting, effectively reduces the sweep time to image in image processing process simultaneously, and then improves the screening speed of image.
One of ordinary skill in the art will appreciate that: above each embodiment, only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of the claims in the present invention.
Claims (10)
1., based on the abnormal fruit ear method for sieving of corn of computer vision, it is characterized in that, comprising:
Based on the image interception rule preset, intercept the image of described corn ear to be sieved, obtain cut-away view picture; The image of described corn ear to be sieved is the image of image acquisition device;
Based on the characteristic parameter extraction rule preset, extract the characteristic parameter in described cut-away view picture;
According to described characteristic parameter, based on the abnormal fruit ear screening model preset, determine the abnormal class of corn ear.
2. method according to claim 1, is characterized in that, in the described image interception rule based on presetting, intercept the image of described corn ear to be sieved, before obtaining cut-away view picture, described method also comprises:
Adopt the image of corn ear to be sieved described in medium filtering process, obtain the first image;
Adopt the first image described in Statistical Techniques dividing processing, obtain the second image;
Adopt the second image described in morphological image disposal route smoothing processing, obtain the 3rd image;
Correspondingly, the described image interception rule based on presetting, intercepts the image of described corn ear to be sieved, obtains cut-away view picture, comprising:
Based on the image interception rule preset, intercept described 3rd image, obtain cut-away view picture.
3. method according to claim 1, is characterized in that, the described image interception rule based on presetting, intercepts the image of described corn ear to be sieved, obtain cut-away view picture, comprising:
According to the image of corn ear to be sieved, determine the minimum enclosed rectangle of described corn ear to be sieved;
According to described minimum enclosed rectangle, intercept the image of described corn ear to be sieved, obtain cut-away view picture.
4. method according to claim 1, is characterized in that, described according to described cut-away view picture, based on the characteristic parameter extraction rule preset, before extracting the characteristic parameter in described cut-away view picture, described method also comprises:
Utilize the image window preset to scan described cut-away view picture, determine at least one piece of region of interest ROI.
5. method according to claim 4, is characterized in that, the described characteristic parameter extraction rule based on presetting, and extracts the characteristic parameter in described cut-away view picture, comprising:
According to described at least one piece of ROI, based on RGB color model, extract the Color characteristics parameters of each ROI;
Each ROI is converted into gray level image, extracts the textural characteristics parameter of each gray level image.
6. method according to claim 5, is characterized in that,
Described according to described at least one piece of ROI, based on RGB color model, extract the Color characteristics parameters of each ROI, comprising:
According to described at least one piece of ROI, determine the pixel number of each ROI;
According to the pixel number of described each ROI, based on RGB color model, extract the Color characteristics parameters of each ROI;
Described each ROI image is converted into gray level image, extracts the textural characteristics parameter of each gray level image, comprising:
Each ROI is converted into gray level image, gray compression is carried out to each gray level image, obtain the 4th image that described each gray level image is corresponding;
Based on the gray level co-occurrence matrixes computation model preset, calculate the gray level co-occurrence matrixes of each 4th image;
According to the gray level co-occurrence matrixes of described each 4th image, based on the textural characteristics parameter extraction rule preset, extract the textural characteristics parameter of described each 4th image.
7. method according to claim 1, is characterized in that, described default abnormal fruit ear screening model is obtained by following steps:
From the abnormal area of the image of each Exception Type of corn ear preset, intercept at least one width subimage, form sample image storehouse;
Based on the characteristic parameter extraction rule preset, extract the characteristic parameter of each image in described sample image storehouse, form sample characteristics parameter library;
Utilize the characteristic parameter in sample characteristics parameter library, support vector machines is trained, obtain described default abnormal fruit ear screening model.
8. method according to claim 7, is characterized in that, described according to described characteristic parameter, based on the abnormal fruit ear screening model preset, determines the abnormal class of corn ear, comprising:
According to described characteristic parameter, based on the abnormal fruit ear screening model preset, determine the abnormal area that each Exception Type default in described corn ear to be sieved is corresponding;
Determine the number percent of the abnormal area area occupied that described each Exception Type is corresponding;
Determine that the Exception Type of described corn ear to be sieved is the Exception Type that the maximum abnormal area of area percentage is corresponding.
9., based on the abnormal fruit ear screening plant of corn of computer vision, it is characterized in that, comprising:
Image interception unit, for based on the image interception rule preset, intercepts the image of described corn ear to be sieved, obtains cut-away view picture; The image of described corn ear to be sieved is the image of image acquisition device;
Parameter extraction unit, for based on the characteristic parameter extraction rule preset, extracts the characteristic parameter in described cut-away view picture;
Classification determination unit, for according to described characteristic parameter, based on the abnormal fruit ear screening model preset, determines the abnormal class of corn ear.
10., based on the abnormal fruit ear screening system of corn of computer vision, it is characterized in that, comprising:
The abnormal fruit ear screening plant of corn as claimed in claim 9, image collecting device, support and background board;
Described background board is placed in horizontal table top, and described support is connected with described background board, and described image collecting device is fixed on described support, and the abnormal fruit ear screening plant of described corn is connected with described image collecting device;
Described support, for fixing described image collecting device, to make described image collector setting in directly over background board;
Described background board, for carrying described corn ear to be sieved, and provides background for the image gathering corn ear to be sieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510674358.7A CN105335705A (en) | 2015-10-16 | 2015-10-16 | Corn abnormal cluster screening method based on computer vision, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510674358.7A CN105335705A (en) | 2015-10-16 | 2015-10-16 | Corn abnormal cluster screening method based on computer vision, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105335705A true CN105335705A (en) | 2016-02-17 |
Family
ID=55286221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510674358.7A Pending CN105335705A (en) | 2015-10-16 | 2015-10-16 | Corn abnormal cluster screening method based on computer vision, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105335705A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876903A (en) * | 2018-05-24 | 2018-11-23 | 北京农业信息技术研究中心 | A kind of corn variety differentiating method and system based on maize male ears three-dimensional phenotype |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7123750B2 (en) * | 2002-01-29 | 2006-10-17 | Pioneer Hi-Bred International, Inc. | Automated plant analysis method, apparatus, and system using imaging technologies |
| CN101957313A (en) * | 2010-09-21 | 2011-01-26 | 吉林大学 | Method and device for computer visual inspection classification of quality of fresh corn ears |
| CN103020970A (en) * | 2012-12-25 | 2013-04-03 | 北京农业信息技术研究中心 | Corn ear image grain segmentation method |
| CN103190224A (en) * | 2013-03-26 | 2013-07-10 | 中国农业大学 | Computer vision technique-based corn ear species test method, system and device |
-
2015
- 2015-10-16 CN CN201510674358.7A patent/CN105335705A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7123750B2 (en) * | 2002-01-29 | 2006-10-17 | Pioneer Hi-Bred International, Inc. | Automated plant analysis method, apparatus, and system using imaging technologies |
| CN101957313A (en) * | 2010-09-21 | 2011-01-26 | 吉林大学 | Method and device for computer visual inspection classification of quality of fresh corn ears |
| CN103020970A (en) * | 2012-12-25 | 2013-04-03 | 北京农业信息技术研究中心 | Corn ear image grain segmentation method |
| CN103190224A (en) * | 2013-03-26 | 2013-07-10 | 中国农业大学 | Computer vision technique-based corn ear species test method, system and device |
Non-Patent Citations (2)
| Title |
|---|
| 周金辉 等: ""基于机器视觉的玉米果穗产量组分性状测量方法"", 《农业工程学报》 * |
| 王慧慧: ""鲜玉米果穗自动分级方法研究"", 《中国博士学位论文全文数据库 工程科技I辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876903A (en) * | 2018-05-24 | 2018-11-23 | 北京农业信息技术研究中心 | A kind of corn variety differentiating method and system based on maize male ears three-dimensional phenotype |
| CN108876903B (en) * | 2018-05-24 | 2022-04-08 | 北京农业信息技术研究中心 | Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| US11282181B2 (en) | Methods of yield assessment with crop photometry | |
| Nielsen et al. | Vision-based 3D peach tree reconstruction for automated blossom thinning | |
| CN107316289A (en) | Crop field spike of rice dividing method based on deep learning and super-pixel segmentation | |
| CN109522899B (en) | Detection method and device for ripe coffee fruits and electronic equipment | |
| Samanta et al. | Scab diseases detection of potato using image processing | |
| Pereira et al. | Recent advances in image processing techniques for automated harvesting purposes: A review | |
| CN112990103A (en) | String mining secondary positioning method based on machine vision | |
| CN102612892A (en) | Identification method for sprouting conditions of wheat ears | |
| CN110428374B (en) | Small-size pest automatic detection method and system | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN114067207A (en) | Vegetable seedling field weed detection method based on deep learning and image processing | |
| CN112734083A (en) | Rice harvester path planning control system based on machine vision | |
| CN113222959A (en) | Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network | |
| Khunkhett et al. | Non-destructive identification of pure breeding rice seed using digital image analysis | |
| CN104484653A (en) | Bad corn kernel detecting method based on image recognition technology | |
| CN114387343A (en) | Method for detecting picking position of mushroom stem of clustered oyster mushroom | |
| CN105335705A (en) | Corn abnormal cluster screening method based on computer vision, device and system | |
| CN105427279A (en) | Grassland drought status monitoring system based on and machine vision and Internet of things, grassland drought status monitoring method | |
| CN108734054B (en) | Non-shielding citrus fruit image identification method | |
| KR20180096966A (en) | Automatic Counting Method of Rice Plant by Centroid of Closed Rice Plant Contour Image | |
| Singh et al. | A novel algorithm for segmentation of diseased apple leaf images | |
| CN113791078A (en) | Method and device for batch detection of internal cracks of corn seeds | |
| CN114332626A (en) | Rice yield prediction method based on visual analysis | |
| CN113887940A (en) | Pasture dominance degree identification method based on convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160217 |
|
| RJ01 | Rejection of invention patent application after publication |