CN104568639A - Method and device for determination of fruit sugar degree - Google Patents
Method and device for determination of fruit sugar degree Download PDFInfo
- Publication number
- CN104568639A CN104568639A CN201310472798.5A CN201310472798A CN104568639A CN 104568639 A CN104568639 A CN 104568639A CN 201310472798 A CN201310472798 A CN 201310472798A CN 104568639 A CN104568639 A CN 104568639A
- Authority
- CN
- China
- Prior art keywords
- pol
- fruit
- parameter
- sugar degree
- weight
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- RFSUNEUAIZKAJO-ARQDHWQXSA-N Fructose Chemical compound OC[C@H]1O[C@](O)(CO)[C@@H](O)[C@@H]1O RFSUNEUAIZKAJO-ARQDHWQXSA-N 0.000 title abstract 7
- 229930091371 Fructose Natural products 0.000 title abstract 7
- 229960002737 fructose Drugs 0.000 title abstract 7
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 43
- 238000004040 coloring Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 2
- 101710114792 Repair DNA polymerase X Proteins 0.000 claims 1
- 238000009434 installation Methods 0.000 claims 1
- 241000675108 Citrus tangerina Species 0.000 description 77
- 238000012360 testing method Methods 0.000 description 5
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000008103 glucose Substances 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 235000009508 confectionery Nutrition 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 235000005976 Citrus sinensis Nutrition 0.000 description 1
- 240000002319 Citrus sinensis Species 0.000 description 1
- 241000032242 Festuca myuros Species 0.000 description 1
- 229930006000 Sucrose Natural products 0.000 description 1
- CZMRCDWAGMRECN-UGDNZRGBSA-N Sucrose Chemical compound O[C@H]1[C@H](O)[C@@H](CO)O[C@@]1(CO)O[C@@H]1[C@H](O)[C@@H](O)[C@H](O)[C@@H](CO)O1 CZMRCDWAGMRECN-UGDNZRGBSA-N 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000007864 aqueous solution Substances 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 235000015203 fruit juice Nutrition 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000002420 orchard Substances 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000005720 sucrose Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and device for determination of a fruit sugar degree. The method and device realize lossless estimation of a fruit sugar degree. The method comprises the following steps of acquiring a colorized image and weight of a fruit, acquiring a sugar degree parameter from the colorized image of the fruit and determining a fruit sugar degree by a sugar degree model according to the sugar degree parameter and the weight. The device comprises an information acquisition device for acquiring a colorized image and weight of a fruit, a calculating unit for acquiring a sugar degree parameter from the colorized image of the fruit, and a determination unit for determining a fruit sugar degree by the sugar degree model according to the sugar degree parameter and the weight. Through a common camera and a computer, fruit sugar degree determination is realized and thus the method can realize estimation of a fruit sugar degree without an additional device and is very suitable for fruit grading of a small enterprise.
Description
Technical field
The present invention relates to a kind of fruit quality determination technology, particularly relate to a kind of determination method and apparatus of sugar degree.
Background technology
Its price of fruit of different quality differs greatly, and fruit quality classification is subject to the attention of orchard worker and businessman always.Different from the sampling check of a lot of article quality, fruit grading requires to accomplish to carry out classification to each fruit.Due to fruit quality quality often with external morphologic appearance out, by fruit external morphology, this infers that its internal information provides possibility for people.Along with simplification, the cheap of digital image acquisition work, the fruit quality objectively promoted based on image is studied, and wishes the robotization realizing fruit quality detection.In this type of research of fruit quality, because oranges and tangerines distribution range is comparatively wide, output great achievement is the focus of attention of people, for oranges and tangerines, fruit quality is studied below.
Two aspects are mainly concentrated on to the research of oranges and tangerines image: be the research to external sort features such as fruit shape, degree of staining, pericarp fold, physiological defect, disease and pests on the one hand; The research to inside quality features such as pol, acidity, hardness, pulp quality, fruit juice amounts on the other hand.External sort feature is owing to being external, visual, and this makes the researchist be engaged in this respect identify external sort by machine, facts have proved, discrimination is usual also higher.Automatically detect as Fernando etc. uses multivariate image analysis method to carry out pericarp defect to the orange from 4 different cultivars, defects detection success ratio is 91.5%, and failure modes rate reaches 94.2%.And inside quality feature is owing to being wrapped in pericarp inside, the inside quality based on external image judges, is to have under certain is related to this prerequisite in hypothesis oranges and tangerines external morphology architectural feature and inside quality parameter to judge to there is certain difficulty.But, due to its lossless characteristic, can internal information be found out when not destroying fruit, therefore, being subject to the most attention of people.
In many inside quality parameters of oranges and tangerines, pol is very important index parameter, is also one of important symbol of degree of ripeness.Pol refers to the sucrose grams of dissolving in every 100 grams of aqueous solution in 20 DEG C of situations, pol higher give people feel sweeter.Although sugariness varies with each individual, the oranges and tangerines that pol is too small under normal circumstances, its mouthfeel generally can not allow most people satisfied.Because higher pol can win public praise and the desire to buy of consumer more; therefore; create in oranges and tangerines operation is cultivated under guaranteeing sunshine time, tree and cultivate rattail fescue sward, some specific aim measures that protection tree root etc. of not turning over is intended to improve oranges and tangerines pol, also as can be seen here people to the degree deeply concerned of oranges and tangerines pol.
Summary of the invention
The embodiment provides a kind of determination method and apparatus of sugar degree, oranges and tangerines pol content can be obtained by quick nondestructive.
The invention provides a kind of defining method of sugar degree, comprising:
Obtain coloured image and the weight of fruit;
Pol parameter is obtained from the coloured image of fruit;
Pol model determination sugar degree is utilized according to pol parameter and weight.
Described pol parameter comprises: green component average x
1, tone average x
2, red green two colouring components average x
3.
Described pol model is any one in following three formulas:
Wherein,
Y: pol
X
1: green component average brightness
X
2: tone mean value
X
3: the average brightness of redness and green component
X
4: weight
K
1, k
2: dummy variable
A
0, a
1, a
2, a
3, b
0, b
1, b
2: treat scaling parameter;
Described undetermined parameter obtains by experiment.
Before the coloured image step of described acquisition fruit, the background of fruit is set to uniform background.
Before utilize pol model determination sugar degree step according to pol parameter and weight, described method also comprises the calibration process treating scaling parameter, to determine pol estimation models parameter.
Present invention also offers a kind of determining device of sugar degree, described device comprises:
Information acquisition device, for obtaining coloured image and the weight of fruit;
Computing unit, for obtaining pol parameter from the coloured image of fruit;
Determining unit, for utilizing pol model determination sugar degree according to pol parameter and weight.
According to the present invention, the pol that just can realize fruit by ordinary camera and computing machine measures, and therefore, the present invention does not need to increase extras just can estimate sugar degree, and the technology of the present invention is extremely suitable for the fruit grading work of small business.
Accompanying drawing explanation
Fig. 1 shows the flow process of the determination sugar degree of the embodiment of the present invention;
Fig. 2 shows the flow process of the calculating pol parameter of the embodiment of the present invention;
Fig. 3 shows the flow process of the fruit grading of the embodiment of the present invention.
Embodiment
Understand for the ease of persons skilled in the art and realize the present invention, now describing embodiments of the invention by reference to the accompanying drawings.
Embodiment one
The oranges and tangerines of different pol content, in growth course, there are differences, thus make its outward appearance painted also different the electromagnetic absorption of different-waveband, reflection, thus form different colors in fruit appearance.Therefore, find out oranges and tangerines pol content by coloured image and carry out harmless classification.
As shown in Figure 1, present embodiments provide a kind of defining method of sugar degree, comprise the steps:
Step 11, the coloured image obtaining fruit and weight.
Coloured image is obtained by camera, and weight obtains by weight sensor or electronic scale.
Step 12, from the coloured image of fruit, obtain pol parameter;
Step 13, utilize pol model determination sugar degree according to pol parameter and weight
In step 12, in order to obtain pol parameter from the coloured image of fruit, first from the background of coloured image, being partitioned into prospect oranges and tangerines image, then obtaining pol parameter.According to a large amount of test findings, described pol parameter comprises: green component average x
1, tone average x
2, red green two colouring components average x
3and oranges and tangerines weight x
4.
In order to be partitioned into foreground image (that is, oranges and tangerines image) more easily from the background of coloured image, according to the embodiment of the present invention, preferentially, adopt uniform background when photographing, the single and reflective less black background of such as color, can show prospect so to greatest extent.
Because prospect and background image there are differences, the relationship of the two can be judged by the correlativity of analysis prospect and background two parts image, and then realize being partitioned into foreground image from the background of coloured image.
If x=is (x
1x
2x
n) ', y=(y
1y
2y
n) ' be stochastic variable, their variance is respectively Var(x), Var(y), covariance is Cov(x, y), then
Illustrate the degree of correlation of vector x, y, statistically, generally claim R
2for determining index.This concept is incorporated in oranges and tangerines Iamge Segmentation, and then realizes being separated of oranges and tangerines prospect and background.After obtaining oranges and tangerines foreground image, just can according to foreground image determination pol parameter: yellow color component, tone, the oranges and tangerines weight of green component, red and green syt.As shown in Figure 2, here is the arthmetic statement solving pol parameter.
Step 21, oranges and tangerines picture centre is clicked oranges and tangerines image-region as impact point or left mouse button provide impact point.Aiming spot requires not strict, as long as photograph near oranges and tangerines centre position when pickup image, in other words, image center is oranges and tangerines internal image;
Step 22, centered by impact point, get all pixels in 3 × 3 masks, in this, as the target area that will compare;
Step 23, pointer movement to the reference position (0,0) of image, using reference position as current point, according to 3 × 3 mask sizes, traversing graph picture;
Step 24, according to (1) formula, calculate the determination index of 3 × 3 regions centered by current point and target area, and this value and certain are determined that index threshold compares, if this value is greater than threshold value, then current pixel is judged as prospect and oranges and tangerines image, otherwise, this pixel is set to background.Owing to determining that index threshold and image and impact point chosen position have relation, therefore it is not a fixing numerical value, but is easily determined by hit-and-miss method according to concrete image.From our test result to a large amount of oranges and tangerines image, determine index R
2generally good result can be obtained between 0.25 ~ 0.50.In addition, due to photography time oranges and tangerines are put in middle position, institute take the photograph image periphery have very large background, therefore, do reality Iamge Segmentation time, the boundary pixel of image outermost is all processed into background pixel.
Step 25, according to order pointer movement from top to bottom, from left to right to next pixel, judge whether it is last pixel, if not transferring to step 24, otherwise perform step 26;
Step 26, extract prospect part calculate 3 pol parameters by foreground image: the yellow color component of green component, tone, red and green syt, above-mentioned component can represent by average, that is: green component average (x
1), tone average (x
2), the average (x of red green two colouring components
3).
After trying to achieve the pol parameter of all oranges and tangerines, namely the parameter then solved in pol model completes the calibration work of pol model, finally according to pol model determination pol.Pol model can select (2) following-any one (4) in three formulas:
Wherein,
Y: pol
X
1: green component average brightness
X
2: tone mean value
X
3: the average brightness of redness and green component
X
4: oranges and tangerines weight
K
1, k
2: dummy variable
A
0, a
1, a
2, a
3, b
0, b
1, b
2: treat scaling parameter;
According to document, pol and oranges and tangerines size also exist certain relation, and therefore the present invention introduces dummy variable when estimating pol, and oranges and tangerines size is divided into several grade, for estimating oranges and tangerines pol more accurately.Concrete described dummy variable is determined according to the different pol situation of varying in size, and describes after referring to.
Outward appearance according to oranges and tangerines finds following features: (i) in transformable interval, the larger oranges and tangerines of green component values are more sweetless, can be rough be interpreted as " more green more sweetless "; (ii) yellow color component and green component show identical trend, i.e. x
3larger pol is lower, the parameter a therefore in forecast model (2)
3<0; (iii) the constant interval of tone H is many between 0.36 ~ 0.71, and be that blood orange arrives between yellow zone of transition, H increases to yellow convergence, and H reduces to orange red convergence, and in other words, it is higher that oranges and tangerines are more tending towards orange red pol; (iv) the oranges and tangerines image larger then pol of area percentage of occupying is lower, and namely oranges and tangerines are more large more sweetless.Can see, these conclusions are more identical with our experience.
Oranges and tangerines pol is relevant to the factor such as kind, the place of production, if directly use model in following embodiment one or embodiment two to carry out the estimation of oranges and tangerines pol can produce comparatively big error, therefore, before using the present invention to carry out pol mensuration, need to extract representational oranges and tangerines and determine to treat scaling parameter a
0, a
1, a
2, a
3, b
0, b
1, b
2, and according to determining that the pol estimation models after scaling parameter carries out glucose prediction.
the picture weight forecast model calibration of oranges and tangerines pol
Scaling parameter a is treated in order to what determine pol prediction model
0, a
1, a
2, a
3, b
0, b
1, b
2first need to obtain the image of some oranges and tangerines and weight and survey pol, after utilizing method of the present invention to extract pol parameter and weight, adopt statistical method just can estimate model parameter, and then the practical application of implementation model, the process of this Confirming model parameter is calibrated exactly, extracts quantitative requirement>=60 of oranges and tangerines during calibration.As an example, we get oranges and tangerines 60, are placed on photographs under fixed tripod respectively, then weigh, measure pol.The camera type that photography uses is Canon EOS Kiss Digital X, and image resolution ratio 3888 × 2592, ISO speed are 800, shutter speed 1/50s, lens opening F/8.Saccharometer is Atago Portable digital saccharometer, sugar concentration measurement scope (Brix%) 0 ~ 53, sugar concentration measurement precision (Brix%) 0.2, minimum scale 0.1.The pol distribution range that this sample records is between 9-18%.
60 oranges and tangerines are divided into 2 groups at random, and one group of 45 another group 15, according to the algorithm of step 21-26, asks the pol parameter calculating each oranges and tangerines respectively, then uses one group of calibration model parameter of 45, and the group of 15 is used for the quality of testing model.
Pol is divided into y < 11,11≤y≤14, y > 14 3 grades, and specifies corresponding k
1and k
2be respectively
k 1 =1, k 2 =0,
k 1 =0, k 2 =1,
k 1 =1, k 2 =1.Possesses the total data yx ' that oranges and tangerines glucose prediction model parameter solves
i=(y
ix
1ix
2ix
3ix
4ik
1ik
1i) after, just can calculate (2) ~ (4) middle model parameter, the solving model parameters such as existing statistical software such as SAS, SPSS can certainly be utilized.And detect by other data, the present embodiment models fitting data 45 groups (i=1,2 ... 45), model testing data 15 groups, comprehensive 2 groups of data test results, the precision obtaining model (2) is the highest, determines that index is 0.949, may be used for the prediction classification of oranges and tangerines pol.Forecast model is as follows:
Corresponding dummy variable estimation model:
Now, pol classification process is:
First y is calculated according to formula (6)
0, then based on y
0pol rank according to setting determines k
1, k
2, finally estimate pol by (5) and carry out classification.
The present embodiment also discloses a kind of method of fruit quality classification.It comprises aforementioned pol defining method, and carries out classification according to the determined pol of pol defining method to fruit quality.As shown in Figure 3, stage division is as follows:
Step 31, determine dummy variable k
1, k
2.Forecast model based on dummy variable comprises a pair model usually, and one of them is the model not having dummy variable, for determining dummy variable.For determining dummy variable, first according to not having the model of dummy variable to calculate pol y
0,
If y
0< T
1, then k
1=1, k
2=0
If T
1≤ y
0≤ T
2, then k
1=0, k
2=1
If y
0> T
2, then k
1=1, k
2=1
Wherein, T
1, T
2be the pol rank boundary set according to concrete oranges and tangerines, if oranges and tangerines pol value is defined as " sweet " between certain two numerical value, then the lower limit of these two numerical value and the upper limit are exactly T
1, T
2.
Step 32, calculate oranges and tangerines pol y to be estimated.The image parameter x obtained
1~ x
4and the dummy variable k just calculated
1, k
2substitute into glucose prediction model, calculate y.
Step 33, pol classification.Pol grade scale according to setting is divided into a few class oranges and tangerines.Because each one impression of identical pol can be variant, therefore this standard does not have strict regulation, such as following grade III Standard:
If y < 11, " sweetless "
If 11≤y≤14, " sweet "
If y > 14, " very sweet "
After above-mentioned pol classification, pol can be carried out quality grading as the key factor of quality to oranges and tangerines, and according to quality grading result packing oranges and tangerines.That is, the oranges and tangerines of different pol rank are cased respectively, mark different price.
Embodiment two
Present embodiments provide a kind of determining device of sugar degree, this device comprises:
Information acquisition device, for obtaining coloured image and the weight of fruit; But image acquiring device camera and any equipment with taking pictures, weight weight sensor or electronic scales obtain; Computing unit, for obtaining pol parameter from the coloured image of fruit; Determining unit, for utilizing pol model determination sugar degree according to pol parameter and weight.
The principle of work of the unit of the present embodiment can see the description of embodiment one.
According to the present invention, the pol that just can realize fruit by ordinary camera and computing machine measures, and therefore, the present invention does not need to increase extras just can estimate sugar degree, and the technology of the present invention is extremely suitable for the fruit grading work of small business.
We are in the oranges and tangerines pol based on pure graphical method is estimated, employ this pol parameter of pixel percentage that oranges and tangerines image accounts for whole image, because this is an amount relevant with camera positions, for the purpose of convenient application, we are placed in camera on photographic car, this ensure that the property freely of movement.
Why oranges and tangerines image affects pol if accounting for whole image percentage, may be that oranges and tangerines vary in weight and cause, and indirectly embodies because oranges and tangerines image percentage is of oranges and tangerines volume, and oranges and tangerines volume and weight is height correlation, therefore, can infer, there is contact in oranges and tangerines weight and pol.Actual result shows, replaces the estimate accuracy that oranges and tangerines images accounts for after whole image percentage higher by oranges and tangerines weight, this show oranges and tangerines image account for whole image percentage be oranges and tangerines weight to substitute this supposition be correct.Why there are differences both when estimating pol, may because: be (i) only under oranges and tangerines are placed on camera lens instead of under camera lens on certain point of fixity during photography, cause oranges and tangerines to distance of camera lens difference in addition the reason such as lens distortion oranges and tangerines image size is changed; (ii) the difference of oranges and tangerines composition; (iii) the reasons such as error are extracted in segmentation.
If we measure weight, just need not calculate the number percent that oranges and tangerines image accounts for whole image again, the advantage of this way is the operation obtaining oranges and tangerines image will be more flexible.The present embodiment is that this pol parameter of pixel percentage that the oranges and tangerines image in the estimation of the oranges and tangerines pol of pure graphical method accounts for whole image is replaced to oranges and tangerines weight, glucose prediction model form and other step are all identical with pure graphical method, difference is, all needs to measure oranges and tangerines weight when calibration and prediction.
Due to directly using oranges and tangerines weight as an independent variable, decrease photo distance, impact that error etc. is extracted in segmentation, precision of prediction should be higher.
Although depict the present invention by embodiment, those of ordinary skill in the art know, without departing from the spirit and substance in the present invention, the present invention just can be made to have many distortion and change, and scope of the present invention is limited to the appended claims.
Claims (6)
1. a defining method for sugar degree, is characterized in that, comprising:
Obtain coloured image and the weight of fruit;
Pol parameter is obtained from the coloured image of fruit;
Pol model determination sugar degree is utilized according to pol parameter and weight.
2. method according to claim 1, is characterized in that, described pol parameter comprises: green component average x
1, tone average x
2, red green two colouring components average x
3.
3. method according to claim 1 and 2, is characterized in that, described pol model is any one in following three formulas:
Wherein,
Y: pol
X
1: green component average brightness
X
2: tone mean value
X
3: the average brightness of redness and green component
X
4: weight
K
1, k
2: dummy variable
A
0, a
1, a
2, a
3, b
0, b
1, b
2: treat scaling parameter;
Described undetermined parameter obtains by experiment.
4. method according to claim 1, is characterized in that, before the coloured image step of described acquisition fruit, the background of fruit is set to uniform background.
5. method according to claim 1, is characterized in that, before utilize pol model determination sugar degree step according to pol parameter and weight, described method also comprises the calibration process treating scaling parameter, to determine pol estimation models parameter.
6. a determination installation method for sugar degree, is characterized in that, described device comprises:
Information acquisition device, for obtaining coloured image and the weight of fruit;
Computing unit, for obtaining pol parameter from the coloured image of fruit;
Determining unit, for utilizing pol model determination sugar degree according to pol parameter and weight.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310472798.5A CN104568639B (en) | 2013-10-11 | 2013-10-11 | A kind of determination method and apparatus of sugar degree |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310472798.5A CN104568639B (en) | 2013-10-11 | 2013-10-11 | A kind of determination method and apparatus of sugar degree |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104568639A true CN104568639A (en) | 2015-04-29 |
CN104568639B CN104568639B (en) | 2017-08-25 |
Family
ID=53085218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310472798.5A Expired - Fee Related CN104568639B (en) | 2013-10-11 | 2013-10-11 | A kind of determination method and apparatus of sugar degree |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104568639B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826552A (en) * | 2019-11-05 | 2020-02-21 | 华中农业大学 | Grape nondestructive automatic detection device and method based on deep learning |
CN111551499A (en) * | 2020-04-28 | 2020-08-18 | 中国农业科学院农业信息研究所 | Method and device for measuring sugar content of fruits, computer equipment and storage medium |
CN113426693A (en) * | 2021-07-26 | 2021-09-24 | 四川农业大学 | Fruit multistage screening device and screening method |
CN113655038A (en) * | 2021-08-24 | 2021-11-16 | 南昌航空大学 | Method for nondestructive testing of sugar content of fruits by using smart phone |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4650323A (en) * | 1984-12-30 | 1987-03-17 | Susumu Nakagawa | Sugar concentration gauge |
CN1837788A (en) * | 2006-03-24 | 2006-09-27 | 浙江大学 | Method and apparatus for non-destructive testing of fruit internal quality based on optical properties |
CN101008611A (en) * | 2007-01-12 | 2007-08-01 | 浙江大学 | Portable fruit sugar content non-destructive detection device capable of weighing |
US20100233327A1 (en) * | 2009-03-11 | 2010-09-16 | Hersh Seth J | System and method for formulating compositions of concentrated liquid sweeteners for individual servings in recyclable and compostable packaging |
CN102890057A (en) * | 2012-10-24 | 2013-01-23 | 华东交通大学 | Portable quality detection device for simultaneously detecting sugar degree and hardness of fruit |
CN102937575A (en) * | 2012-11-21 | 2013-02-20 | 浙江大学 | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination |
US20130194572A1 (en) * | 2012-01-30 | 2013-08-01 | Seiko Epson Corporation | Optical measurement device and optical measurement method |
-
2013
- 2013-10-11 CN CN201310472798.5A patent/CN104568639B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4650323A (en) * | 1984-12-30 | 1987-03-17 | Susumu Nakagawa | Sugar concentration gauge |
CN1837788A (en) * | 2006-03-24 | 2006-09-27 | 浙江大学 | Method and apparatus for non-destructive testing of fruit internal quality based on optical properties |
CN101008611A (en) * | 2007-01-12 | 2007-08-01 | 浙江大学 | Portable fruit sugar content non-destructive detection device capable of weighing |
US20100233327A1 (en) * | 2009-03-11 | 2010-09-16 | Hersh Seth J | System and method for formulating compositions of concentrated liquid sweeteners for individual servings in recyclable and compostable packaging |
US20130194572A1 (en) * | 2012-01-30 | 2013-08-01 | Seiko Epson Corporation | Optical measurement device and optical measurement method |
CN102890057A (en) * | 2012-10-24 | 2013-01-23 | 华东交通大学 | Portable quality detection device for simultaneously detecting sugar degree and hardness of fruit |
CN102937575A (en) * | 2012-11-21 | 2013-02-20 | 浙江大学 | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination |
Non-Patent Citations (2)
Title |
---|
曹乐平等: "基于统计纹理的柑橘糖度与有效酸度检测", 《测试技术学报》 * |
王建黑等: "自然场景下不同成熟度柑橘的自适应识别", 《光学与光电技术》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826552A (en) * | 2019-11-05 | 2020-02-21 | 华中农业大学 | Grape nondestructive automatic detection device and method based on deep learning |
CN111551499A (en) * | 2020-04-28 | 2020-08-18 | 中国农业科学院农业信息研究所 | Method and device for measuring sugar content of fruits, computer equipment and storage medium |
CN113426693A (en) * | 2021-07-26 | 2021-09-24 | 四川农业大学 | Fruit multistage screening device and screening method |
CN113655038A (en) * | 2021-08-24 | 2021-11-16 | 南昌航空大学 | Method for nondestructive testing of sugar content of fruits by using smart phone |
CN113655038B (en) * | 2021-08-24 | 2023-09-22 | 南昌航空大学 | Method for nondestructive detection of fruit sugar degree by using smart phone |
Also Published As
Publication number | Publication date |
---|---|
CN104568639B (en) | 2017-08-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107145908B (en) | A kind of small target detecting method based on R-FCN | |
CN104598908B (en) | A kind of crops leaf diseases recognition methods | |
Liu et al. | Assessment of in situ crop LAI measurement using unidirectional view digital photography | |
CN103702015B (en) | Exposure control method for human face image acquisition system under near-infrared condition | |
CN100443856C (en) | A flat leaf area nondestructive measuring system and method thereof | |
CN111968080A (en) | Hyperspectrum and deep learning-based method for detecting internal and external quality of Feicheng peaches | |
US10388099B2 (en) | Paper currency fold recognition apparatus and method | |
CN109214470A (en) | Image visibility detection method based on coding network fine adjustment | |
CN102404602A (en) | Vidicon definition detection method based on definition test card | |
CN110378232A (en) | The examination hall examinee position rapid detection method of improved SSD dual network | |
CN101692037A (en) | Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component | |
CN107423537A (en) | A kind of method of the surface temperature NO emissions reduction based on adaptive threshold | |
CN104568639B (en) | A kind of determination method and apparatus of sugar degree | |
CN104121850A (en) | Canopy density measurement method and device | |
CN106483130B (en) | A kind of detection method and its automatic detection device of rice disease | |
CN103076334A (en) | Method for quantitatively evaluating perceived quality of digital printed lines and texts | |
CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
CN109741285A (en) | A kind of construction method and system of underwater picture data set | |
CN106017328A (en) | Method and device for measuring various types of line widths | |
CN106096527A (en) | A kind of recognition methods of real-time high-precision online bank note face amount | |
CN106680478A (en) | Gold labeled detection system and method based on cloud platform | |
CN104574341A (en) | Method and device for determining sugar degree of fruit | |
CN104573647A (en) | Recognition method and device for illegal identity document | |
CN103200349A (en) | Scanned image color cast automatic detection method | |
CN107862683A (en) | A kind of more exposure high-dynamics images of synthesis rebuild effect evaluation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170825 |