CN106423895A - Red date grading method - Google Patents
Red date grading method Download PDFInfo
- Publication number
- CN106423895A CN106423895A CN201610763514.1A CN201610763514A CN106423895A CN 106423895 A CN106423895 A CN 106423895A CN 201610763514 A CN201610763514 A CN 201610763514A CN 106423895 A CN106423895 A CN 106423895A
- Authority
- CN
- China
- Prior art keywords
- red date
- image
- red
- defect ware
- stage division
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a red date grading method. The red data grading method comprises the following steps: S1, detecting whether defective goods exist in red dates, and removing the defective goods; S2, detecting the diameters of the red dates, and defining the red dates with the diameters being larger than a first threshold as first grade products; S3, defining the red dates as second grade products if the diameters of the red dates are larger than a second threshold and smaller than the first threshold,; and S4, defining the red dates as third grade products if the diameters of the red dates are larger than a third threshold and smaller than the second threshold, and defining the red dates as four grade edge products if the diameters of the red dates are smaller than the third threshold. According to the red date grading method, by detecting an average defective goods rate and then comparing the average defective goods rate with a defective goods rate detected in real time, grading of the red dates can be stopped when certain deviation occurs, and errors caused by the deviation are avoided.
Description
Technical field
The invention belongs to food grade technical field, particularly to a kind of red date stage division.
Background technology
The red date cultivated area of South Sinkiang only formation just alreadys exceed 1,500,000 mu, and South Sinkiang red date many reference amounts characterizing method is this
The enforcement of patent provides broad mass market.At present, the national standard of domestic only one of which relevant near infrared spectrum detection, i.e. feed
Middle moisture, crude protein, crude fibre, crude fat, lysine, methionine, quickly measure near infrared spectroscopy (standard No. be GB/
T18868-2002).A few days ago, State Grain Administration is directed to the needs of China's grain purchases, has carried out ' wheat gluten mensure-near
Infrared method ', the standard formulation such as ' wheat water content mensure-Near-Infrared Absorption Method ' work.On the whole, China feed, grain, tobacco and
Take the lead in the industries such as national defence having carried out the work of near-infrared analysis standard, to China's quality control system and near-infrared analysis section
Learn development to be of great immediate significance.
Red date cultivated area increases rapidly to rapid non-destructive detecting device demand, and this quickly sends out to contradiction restriction fruit market
Exhibition, is particularly still in South Sinkiang red date present main flow sorting mode and adds artificial sorting side based on the machinery of outward appearance and fruit weight
Formula, this mode seriously constrains the fast development of this specialty industries of red date.Because red date yield is big, pol height is commercially
It is popular, but is restricted by near-infrared corresponding fruit correction storehouse, some advanced import equipments still can not play application
Effect, constrains the development footwork of red dates industry to a certain extent, so my the present main flow of area's main flow hierarchical approaches sorts mode
It is still and artificial sorting mode is added based on the machinery of outward appearance and fruit weight, the quality grading standard of present red date is also only limitted to fruit weight
With the classification in size, because traditional sugar concentration measurement means are to choose sample to break or squeeze juice but thus can destroy red date
Completely, and testing result chosen by sample affected very big, so not slowly being given to this critically important pol of embodiment advantage
Concrete grade scale.
External red date classification is quite ripe and reaches a certain scale.The U.S., European and Australian
In developed country, red date almost 100% all through the classification of mechanization.Not only to enter by fruit color degree but also by fruit size
Row classification, is that the world today produces upper state-of-the-art fruit postharvest handling technology.
But, in the equipment using mechanization, red date is carried out being classified and remains certain error, lead to classification effect
Really not ideal enough.
Therefore, need now a kind of red date stage division badly, real-time detection can be recycled by detecting average defect ware rate
Defect ware rate in contrast, when certain deviation occurs, stop the classification to red date, it is to avoid the error thus resulting in.
Content of the invention
The present invention proposes a kind of red date stage division, and the red date solving different manifestations in prior art adulterates it is difficult to enter
Row Pricing classification and the problem sold.
The technical scheme is that and be achieved in that：Red date stage division, comprises the steps：
S1：Whether there is defect ware in detection red date, and reject defect ware,
S2：The diameter of detection red date, if red date, with diameter greater than the first threshold values, is defined as primes；
S3：If red date with diameter greater than the second threshold values and is less than the second threshold values, it is defined as seconds；
S4：If red date with diameter greater than the 3rd threshold values and is less than the second threshold values, it is defined as three-level product.
As one kind preferred embodiment, if the diameter of detection red date is less than the 3rd threshold values, it is defined as level Four edge product.
As one kind preferred embodiment, detection red date is sampled investigating, red date is determined according to n times sample investigation
Average defect ware rate X, then again the defect ware rate in real-time detection red date is contrasted with average defect ware rate X, is worked as reality
When detection red date defect ware rate contrasted with average defect ware rate X, when real-time detection red date defect ware rate is more than inferior strain
During averagely inferior device rate X of several times number, stop detection and carry out artificial screening.
As one kind preferred embodiment, determine in red date and whether there is defect ware, carried out using image capturing system,
When red date reaches precalculated position, using sensor trigger signal, using image pick-up card, red jujube image is gathered and be sent to
In controller in, defect ware is determined whether there is by red jujube image.
As one kind preferred embodiment, after completing red jujube image collection, image is processed, process content includes
Build red date mask images and remove background, it is then determined that the gray level image of red date, then brightness school is carried out to the gray level image of red date
Just, obtain the luminance picture of red date.
As one kind preferred embodiment, build red date mask images to include using threshold value, image being carried out at binaryzation
Reason, and this two-value is made mask images, the target area based on threshold definitions red date and background area, then carries out morphology and opens
Computing and filling computing, remove the cavity occurring in noise jamming and target area in target.
As one kind preferred embodiment, obtain the red date gray level image without background using formula operation：
Imark=Iorig*T, wherein Imark are target image, and Iorig is original image, and T is threshold value, wherein, T value
50-90.
As one kind preferred embodiment, gamma correction includes, using illumination-reflection model, obtaining using LPF
The brightness of R component image and using this luminance component to remove background after component image carry out gamma correction.
As one kind preferred embodiment, gamma correction includes adopting successively central transformation, discrete Fourier transform, low
Design of Bandpass Filter and Fourier inversion, definition image is f (x, y), and h (x, y) is low pass filter design, then luminance graph
PictureWhereinRepresent convolution.
As one kind preferred embodiment, the size defining f (x, y) image is M*N, and Temp is the square of size m*m
Mean filter template, by test, determines the size of mean filter template：M=round [min (M, N)/8] * 2+1, in formula：
Min (M, N) represents the smaller value taking M and N；Round () represents rounding.
After employing technique scheme, the invention has the beneficial effects as follows：Can be by the average defect ware rate of detection more sharp
With the defect ware rate of real-time detection in contrast, when certain deviation occurs, stop the classification to red date, it is to avoid thus result in
Error.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, also may be used
So that other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
As shown in figure 1, red date stage division, comprise the steps：
S1：Whether there is defect ware in detection red date, and reject defect ware,
S2：The diameter of detection red date, if red date, with diameter greater than the first threshold values, is defined as primes；
S3：If red date with diameter greater than the second threshold values and is less than the second threshold values, it is defined as seconds；
S4：If red date with diameter greater than the 3rd threshold values and is less than the second threshold values, it is defined as three-level product.
If the diameter of detection red date is less than the 3rd threshold values, it is defined as level Four edge product.
Detection red date is sampled investigating, determines average defect ware rate X of red date, Ran Houzai according to n times sample investigation
Defect ware rate in real-time detection red date is contrasted with average defect ware rate X, when real-time detection red date defect ware rate with flat
All defect ware rates X are contrasted, when real-time detection red date defect ware rate is more than averagely inferior device rate X of defect ware coefficient multiple
When, stop detection and carry out artificial screening.
Determine in red date and whether there is defect ware, carried out using image capturing system, when red date reaches precalculated position, profit
With sensor trigger signal, using image pick-up card, red jujube image is gathered and is sent in controller in, by red date figure
As determining whether there is defect ware.
After completing red jujube image collection, image is processed, process content includes building the red date mask images removal back of the body
Scape, it is then determined that the gray level image of red date, then gamma correction is carried out to the gray level image of red date, obtain the luminance picture of red date.
Build red date mask images to include carrying out binary conversion treatment using threshold value to image, and this two-value is made mask artwork
Picture, the target area based on threshold definitions red date and background area, then carry out morphology opening operation and filling computing, remove mesh
The cavity occurring in noise jamming in mark and target area.
Obtain the red date gray level image without background using formula operation：
Imark=Iorig*T, wherein Imark are target image, and Iorig is original image, and T is threshold value, wherein, T value
50-90.
Gamma correction includes, using illumination-reflection model, obtaining the brightness of R component image using LPF and using
This luminance component carries out gamma correction to the component image removing after background.
Gamma correction includes adopting successively central transformation, discrete Fourier transform, low pass filter design and Fourier
Inverse transformation, definition image is f (x, y), and h (x, y) is low pass filter design, then luminance picture
WhereinRepresent convolution.
The size defining f (x, y) image is M*N, and Temp is the square mean filter template of size m*m, by testing, really
Determine the size of mean filter template：M=round [min (M, N)/8] * 2+1, in formula：Min (M, N) represents and takes that M's and N is less
Value；Round () represents rounding.
F ' (x, y)=f (x, y)/I (x, y)；F (x, y)={ 255 if f ' (x, y) are more than or equal to 1,255f ' (x, y) if
F ' (x, y) is less than 1.
F ' (x, y) is the image after correction, can obtain high gray areas and be red date normal surface, and defect part
Image is then low gray level areas, so that it is determined that whether red date is defect ware.
Before detection red date defect ware, also by the moisture of sampling Detection red date, protein content and ash content
Content.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification, equivalent substitution and improvement made etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of red date stage division is it is characterised in that comprise the steps：
S1：Whether there is defect ware in detection red date, and reject defect ware,
S2：The diameter of detection red date, if red date, with diameter greater than the first threshold values, is defined as primes；
S3：If red date with diameter greater than the second threshold values and is less than the second threshold values, it is defined as seconds；
S4：If red date with diameter greater than the 3rd threshold values and is less than the second threshold values, it is defined as three-level product.
If 2. red date stage division according to claim 1 is it is characterised in that the diameter of detection red date is less than the 3rd valve
Value, is defined as level Four edge product.
3. red date stage division according to claim 1, its feature under, to detection red date be sampled investigate, according to N
Secondary sample investigation determines average defect ware rate X of red date, then again by the defect ware rate in real-time detection red date with averagely inferior
Product rate X is contrasted, when real-time detection red date defect ware rate and average defect ware rate X are contrasted, when real-time detection red date is residual
When defect rate is more than averagely inferior device rate X of defect ware coefficient multiple, stops detection and carry out artificial screening.
4. red date stage division according to claim 3 whether there is defect ware it is characterised in that determining in red date, adopts
Carried out with image capturing system, when red date reaches precalculated position, using sensor trigger signal, will be red using image pick-up card
Jujube IMAQ and be sent in controller in, defect ware is determined whether there is by red jujube image.
5. after red date stage division according to claim 4 is it is characterised in that complete red jujube image collection, to image
Processed, process content includes building red date mask images removal background, it is then determined that the gray level image of red date, then to red date
Gray level image carry out gamma correction, obtain the luminance picture of red date.
6. red date stage division according to claim 5 includes utilizing threshold value it is characterised in that building red date mask images
Binary conversion treatment is carried out to image, and this two-value is made mask images, the target area based on threshold definitions red date and background area
Domain, then carries out morphology opening operation and filling computing, removes the cavity occurring in noise jamming and target area in target.
7. red date stage division according to claim 6 it is characterised in that obtained red without background using formula operation
Jujube gray level image：
Imark=Iorig*T, wherein Imark are target image, and Iorig is original image, and T is threshold value, wherein, T value 50-
90.
8. red date stage division according to claim 7 is it is characterised in that gamma correction is included using illumination-reflection mould
Type, using LPF obtain R component image brightness and using this luminance component to remove background after component image enter
Row gamma correction.
9. red date stage division according to claim 8 is it is characterised in that gamma correction includes adopting center to become successively
Change, discrete Fourier transform, low pass filter design and Fourier inversion, definition image is f (x, y), and h (x, y) is low
Design of Bandpass Filter, then luminance pictureWhereinRepresent convolution.
10. red date stage division according to claim 9 it is characterised in that define f (x, y) image size be M*N,
Temp is the square mean filter template of size m*m, by test, determines the size of mean filter template：M=round [min
(M, N)/8] * 2+1, in formula：Min (M, N) represents the smaller value taking M and N；Round () represents rounding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610763514.1A CN106423895A (en) | 2016-08-29 | 2016-08-29 | Red date grading method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610763514.1A CN106423895A (en) | 2016-08-29 | 2016-08-29 | Red date grading method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106423895A true CN106423895A (en) | 2017-02-22 |
Family
ID=58091691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610763514.1A Pending CN106423895A (en) | 2016-08-29 | 2016-08-29 | Red date grading method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106423895A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109077014A (en) * | 2017-06-14 | 2018-12-25 | 北京市水产科学研究所 | The method for separating of the young tortoise figure of Cuora flavomarginate |
| CN111482381A (en) * | 2020-05-09 | 2020-08-04 | 苏州基列德智能制造有限公司 | Full-automatic sorting system and method |
| CN112791992A (en) * | 2020-12-16 | 2021-05-14 | 安徽唯嵩光电科技有限公司 | Automatic control system for red date sorting production line |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5060290A (en) * | 1989-09-05 | 1991-10-22 | Dole Dried Fruit And Nut Company | Algorithm for gray scale analysis especially of fruit or nuts |
| WO2000054034A2 (en) * | 1999-03-11 | 2000-09-14 | Metso Paper, Inc. | Method for determining the wood/bark ratio from a flow of wood material |
| US20150041372A1 (en) * | 2013-08-07 | 2015-02-12 | Kinik Company | Diamond Screening Apparatus |
| CN204523490U (en) * | 2015-01-19 | 2015-08-05 | 方家铺子（莆田）绿色食品有限公司 | A kind of multilayer red date screening system |
| CN105268659A (en) * | 2015-11-12 | 2016-01-27 | 上海电机学院 | Red jujube screening machine based on visual technique |
| CN205463252U (en) * | 2016-02-02 | 2016-08-17 | 塔里木大学 | Red date grading plant |
-
2016
- 2016-08-29 CN CN201610763514.1A patent/CN106423895A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5060290A (en) * | 1989-09-05 | 1991-10-22 | Dole Dried Fruit And Nut Company | Algorithm for gray scale analysis especially of fruit or nuts |
| WO2000054034A2 (en) * | 1999-03-11 | 2000-09-14 | Metso Paper, Inc. | Method for determining the wood/bark ratio from a flow of wood material |
| US20150041372A1 (en) * | 2013-08-07 | 2015-02-12 | Kinik Company | Diamond Screening Apparatus |
| CN204523490U (en) * | 2015-01-19 | 2015-08-05 | 方家铺子（莆田）绿色食品有限公司 | A kind of multilayer red date screening system |
| CN105268659A (en) * | 2015-11-12 | 2016-01-27 | 上海电机学院 | Red jujube screening machine based on visual technique |
| CN205463252U (en) * | 2016-02-02 | 2016-08-17 | 塔里木大学 | Red date grading plant |
Non-Patent Citations (3)
| Title |
|---|
| 松本洋: "《抽样检查法 增补修订本》", 30 June 1980, 新春印刷厂 * |
| 王志明: "<数字图像处理与分析>", 29 February 2012, 清华大学出版社 * |
| 高文焕等: "《新型大屏幕彩电电路分析及维修 上册》", 28 February 1999, 电子工业出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109077014A (en) * | 2017-06-14 | 2018-12-25 | 北京市水产科学研究所 | The method for separating of the young tortoise figure of Cuora flavomarginate |
| CN109077014B (en) * | 2017-06-14 | 2021-02-09 | 北京市水产科学研究所 | Method for sorting juvenile form of cuora flavomarginata |
| CN111482381A (en) * | 2020-05-09 | 2020-08-04 | 苏州基列德智能制造有限公司 | Full-automatic sorting system and method |
| CN111482381B (en) * | 2020-05-09 | 2021-09-28 | 苏州基列德智能制造有限公司 | Full-automatic sorting system and method |
| CN112791992A (en) * | 2020-12-16 | 2021-05-14 | 安徽唯嵩光电科技有限公司 | Automatic control system for red date sorting production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Evaluation of green tea sensory quality via process characteristics and image information | |
| CN104198324B (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
| CN107064053A (en) | Method based on polyphenol content in near-infrared hyperspectral technique Non-Destructive Testing red bayberry | |
| CN103632157B (en) | Individual plant wheat fringe portion kernal number method of counting | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| CN104990925A (en) | Defect detecting method based on gradient multiple threshold value optimization | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| CN109377487B (en) | Fruit surface defect detection method based on deep learning segmentation | |
| CN106872370A (en) | Anthocyanin content method for measuring in a kind of red bayberry based on EO-1 hyperion | |
| CN102937575B (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
| CN106423895A (en) | Red date grading method | |
| Thinh et al. | Mango classification system based on machine vision and artificial intelligence | |
| Bejo et al. | Determination of Chokanan mango sweetness ('Mangifera indica') using non-destructive image processing technique | |
| CN105044014A (en) | Method for detecting low-quality starch-doped potato starch fast | |
| CN106780446A (en) | It is a kind of to mix distorted image quality evaluating method without reference | |
| Maheshwari et al. | Non-destructive quality analysis of Indian Gujarat-17 Oryza sativa SSP Indica (Rice) using image processing | |
| CN116503402B (en) | Method and device for detecting impurity content of grain shoulder | |
| CH708057A2 (en) | Near-infrared method for determining the constituents of the lotus root. | |
| Devi et al. | Machine vision based quality analysis of rice grains | |
| CN106067173A (en) | The Complexity Measurement lossless detection method of citrusfruit pol | |
| CN106311628A (en) | Red jujube grading device | |
| CN104255118A (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| Aggarwal et al. | Aspect ratio analysis using image processing for rice grain quality | |
| CN107255624A (en) | A kind of fast and convenient method for determining protein content in fan's power mushroom entity | |
| CN103942792B (en) | Impurity detecting method in medicine detection robot based on time domain features of sequence images |
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: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |