CN101322969A - Test and classification method - Google Patents
Test and classification method Download PDFInfo
- Publication number
- CN101322969A CN101322969A CNA2008101169153A CN200810116915A CN101322969A CN 101322969 A CN101322969 A CN 101322969A CN A2008101169153 A CNA2008101169153 A CN A2008101169153A CN 200810116915 A CN200810116915 A CN 200810116915A CN 101322969 A CN101322969 A CN 101322969A
- Authority
- CN
- China
- Prior art keywords
- vegetables
- fruits
- point
- potato
- gray value
- 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
- Sorting Of Articles (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a graduation and test method for fruits and vegetables. The graduation and test method comprises collecting images of the fruits and vegetables, extracting outlines of the fruits and vegetables in the images, determining surface germination grades of the fruits and vegetables by calculating the mean grey value of the surfaces of fruits and vegetables and grey value of a point, determining size graduations of the fruits and vegetables by calculating the maximum distance between points on the outlines, determining shape graduations of the fruits and vegetables by calculating the shape factor as well as determining the malformation of the fruits and vegetables by calculating the absolute value of the difference between normalized radiuses of adjacent sampling boundary points on the outlines. The graduation and test method is highly objective, stable and standard, has good consistence, requires no contact, causes no harm and has very good application prospect.
Description
Technical field
The present invention relates to a kind of modern agriculture informationization technology, relate in particular to and a kind ofly detect method with classification according to the fruits and vegetables appearance characteristics.
Background technology
China potato planting area and total output occupy first place in the world, and China is global the tenth-largest potato exported country.Make potato enter the domestic and international field of circulation as high-quality, high added value agricultural product, must pay much attention to potato and adopt back commercialization treatment technology, reduce and adopt back loss, raising added value, to adopt simultaneously post-processing technology automation, become more meticulous and put on the first place, this is that agricultural product are improved the grade and value-added important channel.
The external sort of potato mainly comprises defect characteristics such as size, shape, germination and deformity.Weight and size can reflect the size of potato.The regularity of profile directly influences the attractive in appearance of potato, and then influences the market value of potato.The blemish of potato also is one of key factor that influences its grade, and the surface defects detection of fruit and vegetable food is a great problem in the Quality Detection.Resting period is long, temperature is higher can make potato sprouting, and the toxin that the potato of germination is contained in young shoot and eye part can not eat, so be necessary accurately to detect budded potato all toxic effect of humans and animals again.In the stem tuber of lopsided potato, the organic nutrition of storage such as starch etc. in the former stem tuber can transform in the stem tuber that saccharogenesis is transported to new growth, and content of starch descends in the former stem tuber thereby make, and product qualitative change is bad, loses edibility and plantation value.
So it is than indispensable step in quality standardization and the commercial process that potato is carried out classification.The meaning of classification is to make product to reach consistent at aspects such as quality, color and luster, size, maturity, cleannes, helps packing, transportation and the storage of potato, helps improving the potato market competitiveness.The potato classification of China mainly is to rely on manually to finish at present, and the labour who needs is many, and labour intensity is big, and the result of classification is bigger because of labourer's individual difference difference, and the uniformity of classification is relatively poor, efficient is lower.
Summary of the invention
The purpose of this invention is to provide and a kind of sphere or elliposoidal fruits and vegetables are detected method with classification, described method can be carried out single standard grading to fruits and vegetables, perhaps simultaneously to a plurality of standards, comprising that exterior qualities such as size, shape and blemish are disposable carries out comprehensive classification.
In order to achieve the above object, the invention provides the detection stage division of a kind of sphere or elliposoidal fruits and vegetables, comprise step:
A kind of detection stage division of fruits and vegetables comprises step:
S1: gather the image of fruit and vegetable surfaces, extract the appearance profile line of fruits and vegetables in the described image; And the step of one among the S2-S5 or several step, wherein:
S2: calculate the gray value of described fruit and vegetable surfaces average gray value and fruit and vegetable surfaces point, and the difference of described certain some gray value and described average gray value, determine the germination grade of described fruit and vegetable surfaces;
S3: calculate the maximum point distance between the point on the described appearance profile line, obtain the order of magnitude of described fruits and vegetables;
S4: calculate the form factor on the described appearance profile line, obtain the shape class of described fruits and vegetables;
S5: calculate the poor of described appearance profile line neighbouring sample boundary point normalization radius, determine the lopsided grade of described fruits and vegetables.
Wherein, more than 95% of the described fruit and vegetable surfaces of surface coverage of described collection.
Wherein, among the described step S2 " calculate the gray value of described fruit and vegetable surfaces average gray value and fruit and vegetable surfaces point; and the difference of described certain some gray value and described average gray value " also comprise afterwards described difference and gray value differences threshold value are compared, if described difference, determines then that described point is the sprout point greater than the gray value differences threshold value; Otherwise, think that this point is the normal epidermis point.
Wherein, described step S2 also comprises the number of adding up described sprout point, when the number of sprout point surpasses predefined sprout point number threshold value, judges that then described fruits and vegetables have sprout, otherwise, think that described fruits and vegetables do not have sprout.
Maximum point distance between last, line is described to have 2 of maximum point distance and is major axis, calculate again with described major axis vertical direction on the length of axle, the length ratio that described form factor is on described major axis and the described major axis vertical direction spool.
Wherein, the span of described form factor be [1 ,+∞).
Wherein, if described maximum form factor is 1, then described fruits and vegetables are positive spherical; If described maximum form factor is greater than 1, then described fruits and vegetables are elliposoidal.
Wherein, the concrete grammar of the absolute value of the difference of the described appearance profile line neighbouring sample boundary point normalization radius of calculating is as follows among the described step S5:
To described fruits and vegetables border, boundary point branch such as take a sample is handled with equally spaced method;
The calculating sampling boundary point is to the distance of described appearance profile centroid point, and described distance is radius;
Described radius is carried out normalized, obtain the radius sequence after the normalization, calculate the absolute value of the difference of every adjacent two sampling boundary point normalization radiuses, and try to achieve the maximum in the described absolute value;
If described maximum, judges then that described fruits and vegetables are deformity greater than setting lopsided threshold value; If described maximum, judges then that described fruits and vegetables are non-deformity less than the lopsided threshold value of described setting.
Detection stage division provided by the present invention can carry out single standard grading to fruits and vegetables, and perhaps simultaneously to a plurality of standards, comprising that exterior qualities such as size, shape and blemish are disposable carries out comprehensive classification, practical wide.Method of the present invention have contain much information, speed height, complete function, computation complexity are low is easy to realize, can avoid the advantages such as subjective factor in the manual measurement, in addition, detection stage division objectivity of the present invention is strong, standard stable, high conformity, and contactless nothing injury, have good application prospects.
Description of drawings
Fig. 1 is the schematic flow sheet of detection stage division of the present invention.
The specific embodiment
Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention.
The invention provides the detection stage division of a kind of sphere or elliposoidal fruits and vegetables, at first gather the image of fruit and vegetable surfaces, extract the appearance profile line of fruits and vegetables in the described image; Secondly, calculate the G passage gray value of described fruit and vegetable surfaces G passage average gray value and fruit and vegetable surfaces point, and the difference of described certain some gray value and described average gray value, described difference and gray value differences threshold value are compared, the germination that detects described fruit and vegetable surfaces is whether; Then, calculate the maximum point distance between the point on the described appearance profile line, the gained maximum point apart from comparing with the size fractionation threshold value, is obtained the order of magnitude of described fruits and vegetables; Afterwards, calculate the form factor on the described appearance profile line, the maximum form factor of gained is compared with 1, obtain the shape class of described fruits and vegetables; At last, calculate the absolute value of the difference of described appearance profile line neighbouring sample boundary point normalization radius, whether with the maximum and the lopsided threshold of setting of gained absolute value, it is lopsided to detect described fruits and vegetables.
Method in utilizing the present invention is carried out in the classification to sphere or elliposoidal vegetables and fruits, image is a 2D signal, every width of cloth image of fruits and vegetables only contains the visual information on the direction, so in an embodiment of the present invention, respectively the fruits and vegetables of each classification to be detected are gathered the cubic graph picture, require the different surface of each collection, and the surface of gathering for three times can cover more than 95% of whole fruit and vegetable surfaces.In the present embodiment described fruits and vegetables are positioned potato.
The present invention adopts a kind of gray value difference method based on the G passage to detect budded potato.The stem tuber of potato is imbedded in the soil in growth course, and epidermis is dark yellow; And the young shoot sprout that potato has just grown is fresh and tender, color is vivid, differs bigger with normal potato epidermis G passage gray value.For any described potato image, adopt global threshold region segmentation method wiping out background based on G, B passage gray value differences, obtain potato monomer complete image.Extract after the zone of potato monomer, calculate the G passage average gray value G-Average of potato monomer region, scan the potato zone once more, if the gray value of certain some G passage is G-Temp, then the difference G-Difference of the gray value of this G passage and potato G passage average gray value is: G-Difference=G-Temp-G-Average.Afterwards G-Difference is compared with gray value threshold value Threshold-Difference, if G-Difference greater than described gray value threshold value the time, thinks that then this point is the sprout point, otherwise, think that then this point is a potato normal epidermis point.The number Num-Germinate of statistics sprout point for reducing the influence of normal epidermis point erroneous judgement for sprout point, thinks that greater than 10 potato image sprout is arranged with Num-Germinate.
For any width of cloth potato image, extract the R channel information, image is carried out medium filtering handle, extract potato appearance profile line, calculate the maximum point distance between the point on the outline line, the major axis of potato in promptly every width of cloth image.Described major axis is the major axis of potato maximum cross section, and three width of cloth images of each potato are calculated major axis respectively, asks three maximums in the major axis again, promptly obtains the major axis Max-Axis of this potato.With the characteristic value of Max-Axis as size, compare with predefined size fractionation threshold value, potato is divided into 1~4 grade.
To any width of cloth potato image, extract the appearance profile line of potato.The present invention adopts the method for calculating eccentricity that the shape type of potato is divided into spherical and elliposoidal two classes, the ratio of the length that described eccentricity is meant on the major axis vertical direction of the major axis of potato and this spool.Every width of cloth image for each potato that photographs, calculate the major axis Max-Axis-A of potato in the image, calculate the length M ax-Axis-B of the axle on its vertical direction again, then eccentricity Temp-Ratio is Temp-Ratio=Max-Axis-A/Max-Axis-B.Calculate form factor Max-Ratio maximum in 3 width of cloth images of each potato.Because Max-Axis-A is greater than or equal to Max-Axis-B forever, so Max-Ratio is greater than or equal to 1 all the time.Characteristics according to the appearance profile line can know that for the object of positive sphere, its Max-Ratio value is 1; For the object of elliposoidal, its Max-Ratio value is greater than 1.Depart from 1 far more when the value of Max-Ratio so, then potato is got over prolate, and this type of potato is classified as the elliposoidal potato; When the value of Max-Ratio more near 1, then the sphericity of potato is good more, when Max-Ratio is 1, this type of potato is classified as spherical potato.
To any width of cloth potato image, extract its appearance profile line.For the appearance profile line that extracts, with equally spaced method boundary point branch such as take a sample to be handled, the sampling interval is 8 pixels in the present embodiment.The boundary point of calculating sampling is to the distance of described appearance profile line centroid point, i.e. radius r ((k)).Radius is carried out normalized, obtain the radius sequence r after the normalization
n((k)).Calculate the absolute value delta r of the difference of every adjacent two sampling boundary point normalization radiuses
n((m)), i.e. Δ r
n((m))=| r
n((k+1))-r
n((k)) |, m=0 wherein, 1 ..., k-1.Because the radius of lopsided potato at the deformity place has sudden change, caused the absolute value of neighbouring sample boundary point normalization semidiameter bigger, its peak value reaches more than 0.1; Elliposoidal potato cross section is oval, and the radius sequence also has certain fluctuating, influences the size of the absolute value of neighbouring sample boundary point normalization semidiameter, and its peak value is slightly less than 0.07; Spherical potato change in radius is mild, so the absolute value of sampling boundary point normalization semidiameter is less, its peak value is less than 0.05.The maximum of getting the absolute value of neighbouring sample boundary point normalization semidiameter in above-mentioned potato three width of cloth images is lopsided detected characteristics value, if described lopsided detected characteristics value then is judged as lopsided potato greater than setting threshold.
Below introduce the order of accuarcy of technical scheme of the present invention when carrying out potato detection classification.
Outer potato is represented with A, B, C and D respectively for superfine potato, one-level potato, secondary potato and grade.Adopt following formula to draw the classification accuracy of A level potato:
In the following formula, the potato when p (A) expression detects superfine potato detects accuracy; A
iRepresent to test in the superfine potato detection at every turn and examine the potato number; A represents the superfine potato number of manual detection; N represents test number (TN); The overall classification accuracy of P representative test.
For verifying classification performance of the present invention,, adopted certain potato sample to carry out classification test according to above-mentioned introduction.The log data are listed each other sample number of level and classification accuracy in the table in, and the classification test data are as follows:
Table 1 potato size fractionation data
The total fruit m m=4+6+3=13 that scurries in the test
The total number n n=45 of potato * 6=270
The accuracy rate p that the potato size fractionation is total
Table 2 potato shape ranked data
Total 11 of fruits, the fruit rate of the scurrying q of ball-type potato of scurrying in the test
1The fruit rate of scurrying q with the spheroid shape potato
2Be respectively:
q
1=1-p
1=1-90.8%=9.2%
q
2=1-p
2=1-92.9%=8.1%
Be 13 for the spheroid shape potato or with the erroneous judgement of spheroid shape potato for the erroneous judgement number m of ball-type potato with ball-type potato erroneous judgement in the test, the total number n of potato is 276, the accuracy rate p that the classification of potato shape is total:
Table 3 potato sprouting detects test data
There is not detected budded potato number m in the test
1Be 3, the total number n of budded potato
1Be 24, then potato sprouting detects accuracy rate p
1:
Normal potato erroneous judgement is the number m of budded potato
2Be 4, the normal total number n of potato
2Be 60, the False Rate p that detects of potato sprouting then
2:
Table 4 potato deformity detects test data
There is not detected lopsided potato number m in the test
1Be 2, the total number n of lopsided potato
1Be 30, then the potato deformity detects accuracy rate p
1:
Normal potato erroneous judgement is the number m of lopsided potato
2Be 5, the normal total number n of potato
2Be 90, the False Rate p that detects of potato deformity then
2:
The comprehensive classification of table 5
Always scurry fruit number m:m=3+4+7+3+5+9+5=36
The total number n of potato: n=50 * 6=300
The accuracy rate p of the comprehensive classification of potato then:
The present invention is when the reality classification in real time that is applied to potato, and the image resolution ratio that each potato is gathered is 217 * 184 pixels, and hierarchical speed can reach 6 potatos of per second.Can get the comprehensive classification of potato rate of accuracy reached to 88.0% from result of the test.
Above embodiment only is used to illustrate the present invention; and be not limitation of the present invention; the those of ordinary skill in relevant technologies field; under the situation that does not break away from the spirit and scope of the present invention; can also make various variations; therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (8)
1, a kind of detection stage division of fruits and vegetables is characterized in that, comprises step:
S1: gather the image of fruit and vegetable surfaces, extract the appearance profile line of fruits and vegetables in the described image; And the step of one among the S2-S5 or several step, wherein:
S2: calculate the gray value of described fruit and vegetable surfaces average gray value and fruit and vegetable surfaces point, and the difference of described certain some gray value and described average gray value, determine the germination grade of described fruit and vegetable surfaces;
S3: calculate the maximum point distance between the point on the described appearance profile line, obtain the order of magnitude of described fruits and vegetables;
S4: calculate the form factor on the described appearance profile line, obtain the shape class of described fruits and vegetables;
S5: calculate the poor of described appearance profile line neighbouring sample boundary point normalization radius, determine the lopsided grade of described fruits and vegetables.
2, detection stage division as claimed in claim 1 is characterized in that, more than 95% of the described fruit and vegetable surfaces of surface coverage of described collection.
3, detection stage division as claimed in claim 1, it is characterized in that, among the described step S2 " calculate the gray value of described fruit and vegetable surfaces average gray value and fruit and vegetable surfaces point; and the difference of described certain some gray value and described average gray value " also comprise afterwards described difference and gray value differences threshold value are compared, if described difference, determines then that described point is the sprout point greater than the gray value differences threshold value; Otherwise, think that this point is the normal epidermis point.
4, detection stage division as claimed in claim 3, it is characterized in that, described step S2 also comprises the number of adding up described sprout point, when the number of sprout point surpasses predefined sprout point number threshold value, judge that then described fruits and vegetables grade is for there being sprout, otherwise, think that described fruits and vegetables grade is not for there being sprout.
5, detection stage division as claimed in claim 1, it is characterized in that, the method of calculating form factor among the described step S4 is: calculate the maximum point distance between the point on the appearance profile line, described 2 with maximum point distance of line are major axis, calculate again with described major axis vertical direction on the length of axle, the length ratio that described form factor is on described major axis and the described major axis vertical direction spool.
6, detection stage division as claimed in claim 5 is characterized in that, the span of described form factor be [1 ,+∞).
7, detection stage division as claimed in claim 6 is characterized in that, if described maximum form factor is 1, then described fruits and vegetables are positive spherical; If described maximum form factor is greater than 1, then described fruits and vegetables are elliposoidal.
8, detection stage division as claimed in claim 1 is characterized in that, the concrete grammar of the absolute value of the difference of the described appearance profile line neighbouring sample boundary point normalization radius of calculating is as follows among the described step S5:
To described fruits and vegetables border, boundary point branch such as take a sample is handled with equally spaced method;
The calculating sampling boundary point is to the distance of described appearance profile centroid point, and described distance is radius;
Described radius is carried out normalized, obtain the radius sequence after the normalization, calculate the absolute value of the difference of every adjacent two sampling boundary point normalization radiuses, and try to achieve the maximum in the described absolute value;
If described maximum, judges then that described fruits and vegetables are deformity greater than setting lopsided threshold value; If described maximum, judges then that described fruits and vegetables are non-deformity less than the lopsided threshold value of described setting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008101169153A CN101322969B (en) | 2008-07-18 | 2008-07-18 | Test and classification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008101169153A CN101322969B (en) | 2008-07-18 | 2008-07-18 | Test and classification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101322969A true CN101322969A (en) | 2008-12-17 |
CN101322969B CN101322969B (en) | 2012-11-14 |
Family
ID=40186764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2008101169153A Expired - Fee Related CN101322969B (en) | 2008-07-18 | 2008-07-18 | Test and classification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101322969B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102601063A (en) * | 2012-02-29 | 2012-07-25 | 浙江工业大学 | Automatic identifying and grading method for bamboo chips |
CN102921645A (en) * | 2012-11-19 | 2013-02-13 | 桂林电子科技大学 | Method and sorter for sorting momordica grosvenori based on image visual recognition |
CN103394472A (en) * | 2013-07-04 | 2013-11-20 | 中国农业大学 | Method for detecting and grading greening potatoes based on machine vision |
CN104056790A (en) * | 2013-03-19 | 2014-09-24 | 青岛农业大学 | Intelligent potato sorting method and apparatus |
CN104084379A (en) * | 2014-06-04 | 2014-10-08 | 中国农业大学 | Corn-seed image carefully-choosing apparatus and usage method for apparatus |
CN107564000A (en) * | 2017-09-06 | 2018-01-09 | 南京晓庄学院 | Hericium erinaceus Non-Destructive Testing stage division based on computer vision |
CN109827971A (en) * | 2019-03-19 | 2019-05-31 | 湖州灵粮生态农业有限公司 | A kind of method of non-destructive testing fruit surface defect |
CN114627056A (en) * | 2022-02-18 | 2022-06-14 | 中国人民解放军陆军军医大学第一附属医院 | Real-time high-accuracy detection method for auricle deformity of child |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2587534Y (en) * | 2002-12-27 | 2003-11-26 | 浙江大学 | Machine vision based fruit sorting machine |
DE60305437D1 (en) * | 2003-04-18 | 2006-06-29 | M M O S P A Sa | Device for visual inspection of the quality of the outer surface of domed fruit and vegetables of various shapes and sizes |
CN2923067Y (en) * | 2006-06-21 | 2007-07-18 | 中国农业大学 | Multi-path fruit vision grading picture collector |
-
2008
- 2008-07-18 CN CN2008101169153A patent/CN101322969B/en not_active Expired - Fee Related
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102601063A (en) * | 2012-02-29 | 2012-07-25 | 浙江工业大学 | Automatic identifying and grading method for bamboo chips |
CN102921645A (en) * | 2012-11-19 | 2013-02-13 | 桂林电子科技大学 | Method and sorter for sorting momordica grosvenori based on image visual recognition |
CN104056790A (en) * | 2013-03-19 | 2014-09-24 | 青岛农业大学 | Intelligent potato sorting method and apparatus |
CN103394472A (en) * | 2013-07-04 | 2013-11-20 | 中国农业大学 | Method for detecting and grading greening potatoes based on machine vision |
CN103394472B (en) * | 2013-07-04 | 2015-08-05 | 中国农业大学 | A kind of greening potato based on machine vision detects stage division |
CN104084379A (en) * | 2014-06-04 | 2014-10-08 | 中国农业大学 | Corn-seed image carefully-choosing apparatus and usage method for apparatus |
CN107564000A (en) * | 2017-09-06 | 2018-01-09 | 南京晓庄学院 | Hericium erinaceus Non-Destructive Testing stage division based on computer vision |
CN109827971A (en) * | 2019-03-19 | 2019-05-31 | 湖州灵粮生态农业有限公司 | A kind of method of non-destructive testing fruit surface defect |
CN114627056A (en) * | 2022-02-18 | 2022-06-14 | 中国人民解放军陆军军医大学第一附属医院 | Real-time high-accuracy detection method for auricle deformity of child |
CN114627056B (en) * | 2022-02-18 | 2024-04-02 | 中国人民解放军陆军军医大学第一附属医院 | Real-time high-precision children auricle deformity detection method |
Also Published As
Publication number | Publication date |
---|---|
CN101322969B (en) | 2012-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101322969B (en) | Test and classification method | |
CN107316289B (en) | Method for dividing rice ears in field based on deep learning and superpixel division | |
CN103065149B (en) | Muskmelon Fruit phenotype is extracted and quantization method | |
CN105675539B (en) | A kind of quality of agricultural product integrated evaluating method | |
CN105158186B (en) | A kind of method detected based on high spectrum image to ternip evil mind | |
CN109948596A (en) | A method of rice identification and crop coverage measurement are carried out based on vegetation index model | |
CN102788752A (en) | Non-destructive detection device and method of internal information of crops based on spectrum technology | |
Río Segade et al. | Instrumental texture analysis parameters as winegrapes varietal markers and ripeness predictors | |
Koszela et al. | Computer image analysis in the quality in procedure for selected carrot varieties | |
CN105893977B (en) | A kind of rice drafting method based on adaptive features select | |
CN103344577A (en) | Non-destructive detection method for freshness of livestock meat based on multispectral imaging technology | |
CN116188465B (en) | Crop growth state detection method based on image processing technology | |
CN112649392A (en) | Method for rapidly identifying water-saving drought resistance of wheat | |
Zhang et al. | Changes in the chlorophyll absorbance index (I AD) are related to peach fruit maturity | |
CN112465366A (en) | Comprehensive evaluation method for persimmon quality based on entropy weight TOPSIS model | |
CN102592118B (en) | Automatic detection method for time emergence of seedling of corns | |
Jena et al. | Fruit and leaf diversity of selected Indian mangoes (Mangifera indica L.) | |
CN109540814B (en) | Early detection method for gray mold of butterfly orchid based on multispectral imaging technology | |
CN110779875A (en) | Method for detecting moisture content of winter wheat ear based on hyperspectral technology | |
Mansuri et al. | Computer vision model for estimating the mass and volume of freshly harvested Thai apple ber (Ziziphus mauritiana l.) and its variation with storage days | |
CN103500458A (en) | Method for automatically detecting line number of corncobs | |
Taujuddin et al. | Detection of plant disease on leaves using blobs detection and statistical analysis | |
CN110118735A (en) | A kind of high light spectrum image-forming detection method and device detecting bergamot pear male and female | |
Khalid et al. | Image processing techniques for Harumanis disease severity and weighting estimation for automatic grading system application | |
Wani et al. | Predicting the optimum harvesting dates for different exotic apple varieties grown under North Western Himalayan regions through acoustic and machine vision techniques |
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 | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121114 Termination date: 20130718 |