CN101275824A - Method for detecting rice granule type - Google Patents
Method for detecting rice granule type Download PDFInfo
- Publication number
- CN101275824A CN101275824A CNA2008101117055A CN200810111705A CN101275824A CN 101275824 A CN101275824 A CN 101275824A CN A2008101117055 A CNA2008101117055 A CN A2008101117055A CN 200810111705 A CN200810111705 A CN 200810111705A CN 101275824 A CN101275824 A CN 101275824A
- Authority
- CN
- China
- Prior art keywords
- rice
- grain
- granule type
- detects
- background
- 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
Images
Abstract
The invention discloses a detection method of large grain of rice, comprising placing a rice sample in the image acquisition system for collecting original image information; reading the original image information and detaching the background from the rice sample; identifying whole grain rice and crushed rice; randomly selecting for a required amount in the whole grain rice according to rice varieties of set parameters and the whole grain rice amount required for detection, and searching point by point. The invention is used for the large grain of rice detection process of on-the-spot rice purchasing and market deal, achieving a rapid detection.
Description
Technical field
The invention belongs to the computer image processing technology field, the method that particularly a kind of rice granule type detects.
Background technology
Rice granule type is one of key character of rice variety, uses information such as length and width, length breadth ratio to describe usually.Rice granule type has significant effects to other main quality index (as glue denseness, whole grain rice rate, amylose content etc.), is one of main foundation of commodity rice classification and price.
At present, mainly rely on survey instruments such as manually utilizing ruler or particulate meter to measure to the detection method of rice granule type at home.According to standard GB/T 17891-1999 " high quality paddy ", rice granule type detects and adopts ruler to measure, be that random number is got 10 in the undamaged grain of rice, lie against and measure on the plate, according to head to head, tail is to tail, not overlapping, the mode of clearance not, put into delegation near ruler, read length, ask its mean value to be grain of rice length, grain of rice method for measuring width is similar, and the personal error that causes thus is bigger; And employing particulate instrumentation amount, need to use tweezers to clamp grain of rice measurement because the grain of rice is less, and an end of the particulate instrumentation amount grain of rice is unfixing, can vacillate now to the left, now to the right, when measuring rice grain type, require two ends parallel, difficult operation, the particulate meter can only be surveyed a rice at every turn, efficient is low, and sample is not representative.
Along with the development of machine vision, utilize computer image processing technology can obtain the information of rice granule type quickly and accurately, the testing staff is freed from the heavy duplication of labour.Utilize machine vision to detect, algorithm commonly used has following two kinds: minimum boundary rectangle method, bianry image is carried out Contour tracing, and obtain a series of closed regions, obtain the circumscribed rectangle of this profile, write down the length and width of this rectangle; Make image be rotated counterclockwise 3 ° and repeat the step; After rotating 30 times, the rectangular area in the each rotation of statistics rear enclosed zone is asked for the minimum boundary rectangle of closed region, writes down the length and the width of minimum boundary rectangle; Calculate the length breadth ratio of minimum boundary rectangle, be the grain type of rice, utilize this method to carry out the calculating of rice granule type, need bigger calculated amount.Another method is for fitting elliptic method, the rice profile is assumed ellipse, by grain of rice profile is carried out ellipse fitting, oval major and minor axis after the calculating match, with length and the width of major and minor axis as rice, thereby calculate the grain type of the grain of rice,, and when the profile match, also need bigger calculated amount because the rice profile is not real ellipse.
The present invention proposes rice granule type detection method based on the point by point search method at the problems referred to above, this method calculated amount is little, and speed is fast, and is more more accurate than GB prescriptive procedure.
Summary of the invention
The purpose of this invention is to provide the method that a kind of rice granule type detects, it is characterized in that may further comprise the steps:
Obtain grain of rice image information;
Identify the whole grain of rice and broken rice;
Calculate rice granule type.
The described grain of rice image information of obtaining specifically comprises the following steps:
The rice sample is placed image acquisition device, gather original image information;
Read original image information, and background colour is set to and other color of grain of rice color phase region, cuts apart the background and the grain of rice.
Described rice sample quantity is the 10-1000 grain.
The described method of cutting apart the background and the grain of rice is a process of iteration.
Described process of iteration specifically comprises the following steps:
Obtain the minimum and maximum gray-scale value Z in the image
1And Z
k, make threshold value initial value T
k=(Z
1+ Z
k)/2;
According to threshold value T
kImage segmentation is become target and background two parts, obtain two-part average gray value Z
0, Z
B
Obtain new threshold value T
K+1=(Z
0+ Z
B)/2;
If T
k=T
K+1, then gained is threshold value, otherwise according to the T that calculates
kValue continues calculated threshold, iterative computation.
Described when cutting apart the background and the grain of rice, it is RGB (0,0,0) that background color is selected ater.
Described rice granule type calculates and specifically comprises the following steps:
Calculate per distance on the whole grain of rice profile at 2, find out two maximum pixels of distance, 2 distances are as the long L of the big grain of rice;
L is divided into two parts with profile, finds out respectively on the profile of both sides and L vertical range point farthest, and its distance is designated as R respectively
1, R
2, R
1+ R
2Be the wide W of the big grain of rice;
Calculate the length and the width of every whole grain of rice successively, obtain total length and overall width, the two ratio is the rice length breadth ratio, i.e. the grain type.
Beneficial effect of the present invention is: utilize computer vision to replace the manual inspection method of GB/T 17891-1999 " high quality paddy " regulation, can calculate quick, objective, exactly rice the grain type, overcome that detection time is long in the prior art scheme, subjectivity is strong, accuracy is low, the defective of operability and poor repeatability.Satisfied in on-the-spot purchase of paddy and marketing requirement to Quality Detection is quick, objective, accuracy is high.And, computer picture recognition system according to the method for the invention establishment, the function that also has the detection that to finish chalkiness degree, the white grain of chalk rate, whole grain of rice rate and many indexs such as yellow rice kernel, fluent meterial detection simultaneously, make the detection of carrying out the many index that is mutually independent in the national standard, can finish together by a cover system, can can detect 1000 rice at most at every turn, have the automaticity height, operate quick, easy characteristics.
Description of drawings
Fig. 1 is Image Acquisition of the present invention and treating apparatus connection diagram;
Fig. 2 is the external form synoptic diagram of the single big grain of rice of the present invention.
Number in the figure:
The 1-scanner; The 2-computing machine; The 3-printer.
Embodiment
The invention will be further described below in conjunction with accompanying drawing:
Fig. 1 is Image Acquisition of the present invention and treating apparatus connection layout,
1, utilizes the tally sampling plate of holding concurrently from rice lot sample to be measured, to get 10-1000 grain rice sample, put sampler on scanner 1, gather and obtain original image, be stored as 24 bmp formatted files.Wherein the brightness of scanner 1, contrast are made as between-15~25;
2, read original image information, store the chrominance information of each pixel in every grain of rice, its original chrominance information is the RGB colouring information;
3, on computing machine 2, utilize process of iteration to cut apart the background and the grain of rice, background be made as all black RGB (0,0,0),
The concrete steps of process of iteration are:
(1) obtains minimum and maximum gray-scale value Z in the image
1And Z
k, make threshold value initial value T
k=(Z
1+ Z
k)/2;
(2) according to threshold value T
kImage segmentation is become target and background two parts, obtain two-part average gray value Z
0, Z
B
(3) obtain new threshold value T
K+1=(Z
0+ Z
B)/2;
(4) if T
k=T
K+1, then gained is threshold value, otherwise changes (2), iterative computation;
4, on computing machine 2, utilize rice quality evaluation system RQS1.0 will put in order the identification of the grain of rice and broken rice and open, and will put in order the grain of rice respectively with blue and green lines and indicate with cracking rice;
5, on computing machine 2, utilize human-computer interaction interface that the kind of detection grain needed whole grain of rice quantity of type and rice sample to be measured is set;
6, on computing machine 2, utilize the grain type to detect software,, in the whole grain of rice, select the required whole grain of rice and carry out the calculating of rice granule type at random, will mark with the whole grain of rice that yellow line will be used to a type that calculates simultaneously according to rice variety according to the parameter that is provided with;
The concrete calculation procedure of rice granule type is as follows:
(1) calculate per distance on the whole grain of rice profile at 2, find out two maximum pixels of distance, 2 distances are as the length of the big grain of rice, i.e. L among Fig. 2;
(2) as shown in Figure 2, L is divided into two parts with profile, finds out respectively on the profile of both sides and L vertical range point farthest, and its distance is designated as R respectively
1, R
2, R
1+ R
2Be the wide W of the big grain of rice;
(3) calculate the length and the width of every whole grain of rice successively, obtain total length and overall width, the two ratio is rice grain length breadth ratio, i.e. the grain type;
7, on computing machine 2, the gained result is outputed to printer 3, print.
Above-described embodiment is a more preferably embodiment of the present invention, and those skilled in the art can make various modifications within the scope of the appended claims.
Claims (7)
1. the method that rice granule type detects is characterized in that comprising the following steps:
Obtain grain of rice image information;
Identify the whole big grain of rice and broken rice;
Calculate rice granule type.
2. the method that a kind of rice granule type according to claim 1 detects is characterized in that the described grain of rice image information of obtaining specifically comprises the following steps:
The rice sample is placed image acquisition device, gather original image information;
Read original image information, and background colour is set to and other color of grain of rice color phase region, cuts apart the background and the grain of rice.
3. the method that a kind of rice granule type according to claim 2 detects is characterized in that, described rice sample quantity is the 10-1000 grain.
4. the method that a kind of rice granule type according to claim 2 detects is characterized in that the described method of cutting apart the background and the grain of rice is a process of iteration.
5. the method that a kind of rice granule type according to claim 4 detects is characterized in that described process of iteration specifically comprises the following steps:
Obtain the minimum and maximum gray-scale value Z in the image
1And Z
k, make threshold value initial value T
k=(Z
1+ Z
k)/2;
According to threshold value T
kImage segmentation is become target and background two parts, obtain two-part average gray value Z
0, Z
B
Obtain new threshold value T
K+1=(Z
0+ Z
B)/2;
If T
k=T
K+1, then gained is threshold value, otherwise according to the T that calculates
kValue continues calculated threshold, iterative computation.
6. the method that a kind of rice granule type according to claim 2 detects is characterized in that, described when cutting apart background and the grain of rice, background color selection ater is RGB (0,0,0).
7. the method that a kind of rice granule type according to claim 1 detects is characterized in that described rice granule type calculates and specifically comprises the following steps:
Calculate per distance on the whole grain of rice profile at 2, find out two maximum pixels of distance, 2 distances are as the long L of the big grain of rice;
L is divided into two parts with profile, finds out respectively on the profile of both sides and L vertical range point farthest, and its distance is designated as R respectively
1, R
2, R
1+ R
2Be the wide W of the big grain of rice;
Calculate the length and the width of every whole big grain of rice successively, obtain total length and overall width, the two ratio is the rice length breadth ratio, i.e. the grain type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008101117055A CN101275824A (en) | 2008-05-16 | 2008-05-16 | Method for detecting rice granule type |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008101117055A CN101275824A (en) | 2008-05-16 | 2008-05-16 | Method for detecting rice granule type |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101275824A true CN101275824A (en) | 2008-10-01 |
Family
ID=39995494
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2008101117055A Pending CN101275824A (en) | 2008-05-16 | 2008-05-16 | Method for detecting rice granule type |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101275824A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102494977A (en) * | 2011-11-29 | 2012-06-13 | 浙江工商大学 | Method and system for detecting broken rice rate on line |
CN103884274A (en) * | 2013-11-25 | 2014-06-25 | 天津思博科科技发展有限公司 | Rice grain type detection system |
CN105139405A (en) * | 2015-09-07 | 2015-12-09 | 中国人民解放军理工大学 | Visual separating and detection method of overlapping broken grain and whole grain |
CN105258643A (en) * | 2015-10-30 | 2016-01-20 | 山东省农作物种质资源中心 | Measuring device and measuring method for length, width, and thickness of grain |
CN105300291A (en) * | 2015-10-30 | 2016-02-03 | 山东省农作物种质资源中心 | Seed form size observer and observation method |
CN105300292A (en) * | 2015-10-30 | 2016-02-03 | 山东省农作物种质资源中心 | Wheat seed size measuring device and measuring method |
CN105547919A (en) * | 2015-12-09 | 2016-05-04 | 中国水稻研究所 | Image measuring method of gel consistency of rice |
CN105067784B (en) * | 2015-07-22 | 2016-08-24 | 中国水稻研究所 | Utilize the physicochemical character index of rice quality to the method judging rice eating-quality |
CN107240088A (en) * | 2016-12-07 | 2017-10-10 | 浙江工商大学 | Detection dividing method, system and the device of the adhesion grain of rice |
CN109211740A (en) * | 2018-10-31 | 2019-01-15 | 江南大学 | It is a kind of based on image recognition to the rapid detection method of broken rice rate |
CN110838128A (en) * | 2019-11-07 | 2020-02-25 | 华侨大学 | Image method aggregate stacking void ratio prediction method and system |
CN111435427A (en) * | 2019-01-14 | 2020-07-21 | 珠海格力电器股份有限公司 | Method and device for identifying rice and cooking appliance |
CN111435444A (en) * | 2019-01-14 | 2020-07-21 | 珠海格力电器股份有限公司 | Method and device for identifying grains |
CN112683922A (en) * | 2020-12-07 | 2021-04-20 | 泰州可以信息科技有限公司 | System and method for analyzing incomplete degree of rice grains on site |
CN112730273A (en) * | 2021-01-06 | 2021-04-30 | 淮阴工学院 | Portable rice quality detection device and detection method thereof |
CN113776993A (en) * | 2021-07-28 | 2021-12-10 | 深圳市麦稻智联科技有限公司 | Rice online detection system, detection method and detection equipment |
-
2008
- 2008-05-16 CN CNA2008101117055A patent/CN101275824A/en active Pending
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102494977A (en) * | 2011-11-29 | 2012-06-13 | 浙江工商大学 | Method and system for detecting broken rice rate on line |
CN103884274A (en) * | 2013-11-25 | 2014-06-25 | 天津思博科科技发展有限公司 | Rice grain type detection system |
CN105067784B (en) * | 2015-07-22 | 2016-08-24 | 中国水稻研究所 | Utilize the physicochemical character index of rice quality to the method judging rice eating-quality |
CN105139405A (en) * | 2015-09-07 | 2015-12-09 | 中国人民解放军理工大学 | Visual separating and detection method of overlapping broken grain and whole grain |
CN105139405B (en) * | 2015-09-07 | 2018-06-05 | 中国人民解放军理工大学 | It is a kind of to be overlapped the vision method for separating and detecting cracked rice with whole rice |
CN105300291B (en) * | 2015-10-30 | 2017-10-31 | 山东省农作物种质资源中心 | Seed morphology size visualizer and observation procedure |
CN105300292A (en) * | 2015-10-30 | 2016-02-03 | 山东省农作物种质资源中心 | Wheat seed size measuring device and measuring method |
CN105258643B (en) * | 2015-10-30 | 2017-09-12 | 山东省农作物种质资源中心 | Grain length grain width thickness measuring device and measuring method |
CN105300291A (en) * | 2015-10-30 | 2016-02-03 | 山东省农作物种质资源中心 | Seed form size observer and observation method |
CN105300292B (en) * | 2015-10-30 | 2017-12-29 | 山东省农作物种质资源中心 | Wheat class seed size measurement apparatus and measuring method |
CN105258643A (en) * | 2015-10-30 | 2016-01-20 | 山东省农作物种质资源中心 | Measuring device and measuring method for length, width, and thickness of grain |
CN105547919A (en) * | 2015-12-09 | 2016-05-04 | 中国水稻研究所 | Image measuring method of gel consistency of rice |
CN105547919B (en) * | 2015-12-09 | 2018-05-25 | 中国水稻研究所 | The image measuring method of Rice gel consistency |
CN107240088A (en) * | 2016-12-07 | 2017-10-10 | 浙江工商大学 | Detection dividing method, system and the device of the adhesion grain of rice |
CN109211740A (en) * | 2018-10-31 | 2019-01-15 | 江南大学 | It is a kind of based on image recognition to the rapid detection method of broken rice rate |
CN111435427A (en) * | 2019-01-14 | 2020-07-21 | 珠海格力电器股份有限公司 | Method and device for identifying rice and cooking appliance |
CN111435444A (en) * | 2019-01-14 | 2020-07-21 | 珠海格力电器股份有限公司 | Method and device for identifying grains |
CN110838128A (en) * | 2019-11-07 | 2020-02-25 | 华侨大学 | Image method aggregate stacking void ratio prediction method and system |
CN110838128B (en) * | 2019-11-07 | 2023-04-07 | 华侨大学 | Image method aggregate stacking void ratio prediction method and system |
CN112683922A (en) * | 2020-12-07 | 2021-04-20 | 泰州可以信息科技有限公司 | System and method for analyzing incomplete degree of rice grains on site |
CN112730273A (en) * | 2021-01-06 | 2021-04-30 | 淮阴工学院 | Portable rice quality detection device and detection method thereof |
CN113776993A (en) * | 2021-07-28 | 2021-12-10 | 深圳市麦稻智联科技有限公司 | Rice online detection system, detection method and detection equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101275824A (en) | Method for detecting rice granule type | |
US7430485B2 (en) | Method and system for analyzing coatings undergoing exposure testing | |
CN105069790A (en) | Rapid imaging detection method for gear appearance defect | |
CN106796724A (en) | Automation pattern fidelity measurement setup is produced | |
CN108355987A (en) | A kind of screen printing of battery quality determining method based on piecemeal template matches | |
CN112699876A (en) | Automatic reading method for various meters of gas collecting station | |
CN113109240B (en) | Method and system for determining imperfect grains of grains implemented by computer | |
CN108955901B (en) | Infrared temperature measurement method and system and terminal equipment | |
CN104318249A (en) | Grinding surface roughness grade identification method based on multi-classification support vector machine | |
CN101793840A (en) | Diamond cutting parameter measurement method and measuring device | |
CN105319223A (en) | Detection method and system of chalky rice | |
CN103822897A (en) | White spirit appraising and source-tracing method based on infrared spectroscopy | |
CN102183500A (en) | White spirit identification method based on fluorescence characteristic parameter Euclidean distance | |
CN103839271A (en) | Method for image texture synthesis based on optimum matching | |
CN100449302C (en) | Quickly non-demage discriminating method and device for marked wine year of bottled yellow rice or millet wine | |
Zhang et al. | Water meter pointer reading recognition method based on target-key point detection | |
Wu et al. | Automatic kernel counting on maize ear using RGB images | |
CN105509657A (en) | High-precision measurement method of scratch area and grayscale parameter of IC card chip | |
Tu et al. | AIseed: An automated image analysis software for high-throughput phenotyping and quality non-destructive testing of individual plant seeds | |
CN102980536B (en) | Brake block steel back flatness detection system and method | |
CN117152461A (en) | Cigarette packaging material color difference detection method based on digital image | |
CN105841818A (en) | Color measuring apparatus and method of light column laser paper and presswork | |
CN112419244B (en) | Concrete crack segmentation method and device | |
CN114970164A (en) | Refined steel classification quantitative method and portable system | |
CN115115889A (en) | Instrument image analysis method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20081001 |