CN105319223B - The detection method and detecting system of a kind of chalk rice - Google Patents
The detection method and detecting system of a kind of chalk rice Download PDFInfo
- Publication number
- CN105319223B CN105319223B CN201510893771.2A CN201510893771A CN105319223B CN 105319223 B CN105319223 B CN 105319223B CN 201510893771 A CN201510893771 A CN 201510893771A CN 105319223 B CN105319223 B CN 105319223B
- Authority
- CN
- China
- Prior art keywords
- rice
- grain
- chalk
- points
- flase drop
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
Abstract
The present invention is applied to data processing field, there is provided a kind of detection method of chalk rice, methods described include:Grain of rice sample RGB image is pre-processed, judges whether the grain of rice in the grain of rice sample RGB image is chalk rice;If a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes flase drop;The chalk rice grain rate and chalkiness degree of chalk rice are calculated according to default formula.The embodiment of the present invention, grain of rice sample RGB image is pre-processed, judge whether the grain of rice in the grain of rice sample RGB image is chalk rice, if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes flase drop, and chalky grain rate and chalkiness degree are obtained according to default formula so that the detection of chalk rice is more accurate.
Description
Technical field
The invention belongs to the detection method and detecting system of data processing field, more particularly to a kind of chalk rice.
Background technology
China is eating rice production state maximum in the world.Monitoring of Paddy Rice Plant Area accounts for the 22.8% of world's total cultivated area,
Total output accounts for the 35% of Gross World Product.In China, rice is the first generalized grain crop, and it is total that Monitoring of Paddy Rice Plant Area accounts for cereal crops
The 30% of area, and paddy accounts for the 40% of total output of grain.The population in the whole nation more than 2/3rds is using rice as main food, people
Body daily required 60%-80% heat, 50%-70% protein and some inorganic salts and vitamin B essentially from rice.
Rice industry has very important strategic position in China.
The outward appearance of rice is a highly important index of rice quality, and influence rice market price it is important because
Element.Routine inspection such as broken rice rate at present, the chalkiness degree of rice and glutinous millet grain rate etc. are mainly carried out by being classified personnel's naked-eye observation.
Although this method is simple and cost is low.But its subjectivity is larger, less efficient, repeatability is poor, and labor intensity is very
Greatly.Therefore rice quality detect by computer vision technique of increased attention.Pass through image first
Acquisition system obtains the high-definition image of detection rice, is analyzed and calculated then in conjunction with machine vision technique and be broken to obtain
Rice rate, the chalkness ratio of rice, the performance indications such as chalkiness degree and glutinous millet grain rate, can be greatly enhanced detection quality.In these inspections
Survey in index, the chalkness ratio of Rice Chalkiness rice, the detection of chalkiness degree is exactly one and judges the very important of rice quality quality
A study hotspot in index, and Machine Vision Detection.
Rice Chalkiness is because starch in rice endosperm and protein particulate filling be not close, caused by loose inflation.Rice
The white partially protein content of chalk is relatively low, and content of starch is higher, prematurity when being due to too high rice water content or rice harvesting
Caused by and, so Rice Chalkiness degree is higher, the quality of rice is poorer, and nutritive value is also poorer;After this rice boiling, rice grain
On crackle occurs, rice is fluffy hollow, and food flavor is poor.Chalk rice commodity is poor, and the market price is low, thus planting benefit compared with
Low, on hybrid paddy rice, this problem is more prominent.Defined in fine quality rice standard GB/T/T17981-1999:" chalk is white " is
Refer to the White-opalescent part in grain of rice endosperm, location is divided into white belly, core white and the back of the body in rice endosperm in vain according to chalk
In vain, their principal characters in two-dimensional digital image are exactly Gao Bai occurred, and it is big to judge to have been presented for many methods at present
The chalk rice rate and chalkiness degree of rice.But the author has found in detection is studied, after the de- embryo of the germ fraction of normal grain of rice
A white pit can be left on the top of the grain of rice, in visual effect with as the white part of chalk be Gao Bai, so at present
Detection algorithm is substantially all the chalk that can not judge to detect, and partly which belongs to the Gao Bai of germ fraction in vain, and which belongs to chalk rice
Really chalk is white for grain, so as to cause the reduction of Detection accuracy.Thus, the author have studied the random placement grain of rice photographed first
The disposing way of sample, it is found that the grain of rice substantially there are two kinds of disposing ways, for one kind to keep flat, this mode is more common, at this moment,
Plumule pit is in the side of the grain of rice, when camera is shot from surface, shoots less than so can be refused when detection
The problem of considering flase drop, referring to the normal long-grained nonglutinous rice artwork kept flat and line drawing in accompanying drawing 5.Another kind is places vertically, in reality
When sample is placed in detection device, it is impossible to which every is checked laying state, just occurs that the grain of rice is to place vertically sometimes.Situation about placing vertically
There are two kinds, a kind of germ fraction is upward, then plumule pit has high white display on the image photographed, while can detect
Be chalk rice grain white belly area, white belly part is also displayed as Gao Bai, because plumule pit is consistent with the picture characteristics of white belly,
Causing in detection can be by such plumule pit also flase drop to be the white part of chalk, referring to the plumule area placed vertically in accompanying drawing 6 chalk upward
Rice image, contour line picture and the white parts of images of chalk for having flase drop detected.Another germ fraction down, plumule pit
It will not be photographed, what at this moment can be detected is the back of the body fine flour product of chalk rice grain, and the back of the body is typically distributed across the centre at grain of rice back in vain
Position.Meanwhile under study for action it has been found that the grain of rice kept flat, the contour line of position part corresponding to its plumule pit is substantially
There is an obvious straight line variation tendency, referring to the normal long-grained nonglutinous rice artwork and contour line schematic diagram kept flat in accompanying drawing 5.And erect
The contour line at grain of rice both ends is all substantially in smooth elliptical variation tendency in the case of putting, referring to what is placed vertically in accompanying drawing 6
Plumule area chalk rice image contour line schematic diagram upward.
Thus, we have proposed judging the disposing way of the grain of rice by analyzing the characteristics of image of the grain of rice, and it is white to combine chalk
Part and germ fraction appear in the characteristic of the different parts of the grain of rice, are partitioned into plumule area, when detecting that the grain of rice is the mode of placing vertically
Under, it is necessary to be the white part of chalk by flase drop by appear in plumule area in the grain of rice when the chalk white part of the grain of rice is calculated
Reject, so as to improve the Detection accuracy of chalk rice grain.
The content of the invention
The purpose of the embodiment of the present invention is the detection method and detecting system for providing a kind of chalk rice, to solve existing skill
The problem of detection of art chalk rice is inaccurate.
The embodiment of the present invention is achieved in that a kind of detection method of chalk rice, and methods described includes:
Grain of rice sample RGB image is pre-processed, judges whether the grain of rice in the grain of rice sample RGB image is that chalk is white
Rice;
If a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes flase drop;
The chalk rice grain rate and chalkiness degree of chalk rice are calculated according to below equation:
The embodiment of the present invention additionally provides a kind of detecting system of chalk rice, and the system includes:
Pretreatment unit, for being pre-processed to grain of rice sample RGB image, judge in the grain of rice sample RGB image
The grain of rice whether be chalk rice;
Flase drop unit, if being chalk rice for the pretreatment unit judged result, judge the grain of rice sample
Whether disposing way causes flase drop;
As a result acquiring unit, for after completing flase drop and judging, the chalk rice grain of chalk rice to be calculated according to below equation
Rate and chalkiness degree:
The embodiment of the present invention, grain of rice sample RGB image is pre-processed, judged in the grain of rice sample RGB image
Whether the grain of rice is chalk rice, if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes to miss
Inspection, and chalky grain rate and chalkiness degree are obtained according to default formula so that the detection of chalk rice is more accurate.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In the required accompanying drawing used be briefly described, it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
Fig. 1 is the flow chart of chalk rice detection method provided in an embodiment of the present invention;
Fig. 2 is the structure chart of chalk rice detecting system provided in an embodiment of the present invention;
Fig. 3 is grain of rice barycenter provided in an embodiment of the present invention and grain width, length detection schematic diagram;
Fig. 4 is delimitation grain of rice plumule area provided in an embodiment of the present invention schematic diagram;
Fig. 5 is the normal long-grained nonglutinous rice artwork provided in an embodiment of the present invention kept flat and contour line schematic diagram;
Fig. 6 is the plumule provided in an embodiment of the present invention placed vertically chalk rice artwork and contour line schematic diagram upward.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Embodiment one
It is the flow chart of chalk rice detection method provided in an embodiment of the present invention as shown in Figure 1, methods described includes following
Step:
Step S101, grain of rice sample RGB image is pre-processed, judge the grain of rice in the grain of rice sample RGB image
Whether it is chalk rice.
In embodiments of the present invention, detecting system pre-processes to grain of rice sample RGB image first, is sentenced by pretreatment
Whether the grain of rice in the disconnected grain of rice sample RGB image is chalk rice.It is described that grain of rice sample RGB image is pre-processed, judge
Whether the grain of rice in the grain of rice sample RGB image is chalk rice, including:
1st, the grain of rice sample RGB image is converted into gray level image, and obtains adaptivenon-uniform sampling in the gray level image
Threshold value.
In embodiments of the present invention, obtaining the method for the threshold value of adaptivenon-uniform sampling can be calculated by varimax between class
The threshold value of adaptivenon-uniform sampling, it should be pointed out that after RGB image is converted into gray level image, in order that gray level image is more
Clearly, noise reduction process can be carried out to gray level image.
2nd, it is bianry image by the greyscale image transitions according to the threshold value, the bianry image is:The grain of rice for white,
Background is the black and white binary image of black.
3rd, total and every grain of rice the data of the grain of rice are obtained by regional connectivity algorithm, the data include:
The sum of all pixels m of every grain of rice, every grain of rice origin coordinates.
4th, the grain of rice sample RGB image is converted into HSI images, obtains the I component histogram of every grain of rice, obtain the I points
Measure in histogram:Peak dot number n, peak maximum max, peak-to-average aver, and according to formula
D values are obtained, by the D values compared with default standard value D1, judge whether the grain of rice is chalk rice according to comparative result, are had
Body:If D values are less than D1, the rice is judged for chalk rice, if D values are more than D1, the rice is not chalk rice.
Further, if it is determined that chalk rice, then the white portion of chalk of the chalk rice is partitioned into by maximum variance between clusters
Point and normal segments.
Step S102, if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes to miss
Inspection.
In embodiments of the present invention, it is possible to because the disposing way mistake of grain of rice sample, is by normal grain of rice flase drop
Chalk rice, therefore after chalk rice is determined whether by grain of rice image, it is also necessary to judge whether by disposing way
Flase drop is showed.It is described if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes flase drop, tool
Body is:
1st, the contour line of chalk rice grain is detected, the center of mass point of the chalk rice grain is obtained by the contour line.
In embodiments of the present invention, if the bianry image of grain of rice image is expressed as:
Then the coordinate of the center of mass point of the grain of rice can be obtained by below equation:
Wherein k and n is the line number and columns of the grain of rice contour images.
2nd, in the range of the acquisition center of mass point is 0 ° to 90 ° of end points, the center of mass point to the contour line owns
Distance, and obtain beeline, angle, the length and width of the chalk rice grain, the chalk rice grain corresponding to beeline
Angles.
3rd, two friendships of the straight line and the contour line along the chalk rice grain length direction Jing Guo the center of mass point are obtained
Whether point A, B, the disposing way for judging the grain of rice sample according to described A, B cause flase drop.
In embodiments of the present invention, a straight line along chalk rice grain length direction is done from grain of rice center of mass point first, this is straight
Line has intersection point A and B with two sections of contour lines of the grain of rice respectively, from A points and B points, point-to-point analysis they change respectively to both ends
Grain of rice contour line variation tendency, judge whether chalk rice grain is flase drop according to the variation tendency.It is described to be sentenced according to described A, B
Whether the disposing way of the disconnected grain of rice sample causes flase drop, including:
From the A points and B points, if being respectively to the track on contour line both sides a bit:The change of line-like becomes
Gesture and elliptical variation tendency, another point to the track on contour line both sides be elliptical variation tendency, then it is described
Chalk rice grain is flat condition, then does not occur flase drop;Or
From the A points and B points, if 2 points of tracks to contour line both sides are elliptical variation tendency,
Then the chalk rice grain is surveyed along its length to the chalk rice intragranular portion respectively to place state vertically from the A points and B points
The width of a grain of rice is measured, obtaining C points and D points, the width from C points and D points along the grain of rice draws straight line and rice respectively afterwards
The profile of grain intersects, and the plumule area of closing is obtained according to intersection point, if the chalk is white partly in the plumule area, and in plumule area
The similar ellipse in part, then be determined as flase drop occur, if the white part of the chalk all in the plumule area, and the white part of chalk
It is similar oval, then also there is flase drop.
It is pointed out that " Chalkiness size " in national standard refers to that chalk rice grain is kept flat at present, chalk fine flour in the grain of rice
Product accounts for the percentage of whole grain rice projected area.Therefore by calculating of the current standard to chalkiness degree in detection sample, only need to count
The chalkiness degree for keeping flat the grain of rice is calculated, now it is contemplated that two ways, one kind is when it is to place state vertically to detect the grain of rice, in front panel
Position and the information of the grain of rice are prompted, notice inspector adjustment position detects, avoids causing flase drop again.It is another to calculate chalk
The grain of rice of the state of placing vertically is weeded out during whiteness, ensures all chalkiness degree data for keeping flat the grain of rice of result of detection, improves detection
Accuracy rate.
Although the grain of rice is a steric information, current detection major way is also all still to be translated into a two dimension
Image is detected, and so, many steric informations are lost, and are lost unavoidably on data accuracy, this algorithm also can be in the present
In the comprehensive detection of chalk rice grain afterwards, when it is desirable that obtaining white belly area information, for rejecting the interference in plumule area.
Step S103, the chalk rice grain rate and chalkiness degree of chalk rice are calculated according to below equation:
The embodiment of the present invention, grain of rice sample RGB image is pre-processed, judged in the grain of rice sample RGB image
Whether the grain of rice is chalk rice, if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes to miss
Inspection, and chalky grain rate and chalkiness degree are obtained according to default formula so that the detection of chalk rice is more accurate.
Embodiment two
The structure chart of chalk rice detecting system provided in an embodiment of the present invention is illustrated in figure 2, for convenience of description, is only shown
Go out the part related to the embodiment of the present invention, including:
Pretreatment unit 201, for being pre-processed to grain of rice sample RGB image, judge the grain of rice sample RGB image
In the grain of rice whether be chalk rice.
In embodiments of the present invention, detecting system pre-processes to grain of rice sample RGB image first, is sentenced by pretreatment
Whether the grain of rice in the disconnected grain of rice sample RGB image is chalk rice.The pretreatment unit 201 pre-processes, including:
1st, the grain of rice sample RGB image is converted into gray level image, and obtains adaptivenon-uniform sampling in the gray level image
Threshold value.
In embodiments of the present invention, obtaining the method for the threshold value of adaptivenon-uniform sampling can be calculated by varimax between class
The threshold value of adaptivenon-uniform sampling, it should be pointed out that after RGB image is converted into gray level image, in order that gray level image is more
Clearly, noise reduction process can be carried out to gray level image.
2nd, it is bianry image by the greyscale image transitions according to the threshold value, the bianry image is:The grain of rice for white,
Background is the black and white binary image of black.
3rd, total and every grain of rice the data of the grain of rice are obtained by regional connectivity algorithm, the data include:
The sum of all pixels m of every grain of rice, every grain of rice origin coordinates.
4th, the grain of rice sample RGB image is converted into HSI images, obtains the I component histogram of every grain of rice, obtain the I points
Measure in histogram:Peak dot number n, peak maximum max, peak-to-average aver, and according to formula
D values are obtained, by the D values compared with default standard value D1, judge whether the grain of rice is chalk rice according to comparative result, are had
Body:If D values are less than D1, the rice is judged for chalk rice, if D values are more than D1, the rice is not chalk rice.
Further, if it is determined that chalk rice, then the white portion of chalk of the chalk rice is partitioned into by maximum variance between clusters
Point and normal segments.
Flase drop unit 202, if being chalk rice for the judged result of pretreatment unit 201, judge the grain of rice
Whether the disposing way of sample causes flase drop.
In embodiments of the present invention, it is possible to because the disposing way mistake of grain of rice sample, is by normal grain of rice flase drop
Chalk rice, therefore after chalk rice is determined whether by grain of rice image, it is also necessary to judge whether by disposing way
Flase drop is showed.The flase drop unit 202 judges whether to cause flase drop, including:
1st, the contour line of chalk rice grain is detected, the center of mass point of the chalk rice grain is obtained by the contour line.
In embodiments of the present invention, if the bianry image of grain of rice image is expressed as:
Then the coordinate of the center of mass point of the grain of rice can be obtained by below equation:
Wherein k and n is the line number and columns of the grain of rice contour images.
2nd, in the range of the acquisition center of mass point is 0 ° to 90 ° of end points, the center of mass point to the contour line owns
Distance, and obtain beeline, angle, the length and width of the chalk rice grain, the chalk rice grain corresponding to beeline
Angles.
3rd, two friendships of the straight line and the contour line along the chalk rice grain length direction Jing Guo the center of mass point are obtained
Whether point A, B, the disposing way for judging the grain of rice sample according to described A, B cause flase drop.
In embodiments of the present invention, a straight line along chalk rice grain length direction is done from grain of rice center of mass point first, this is straight
Line has intersection point A and B with two sections of contour lines of the grain of rice respectively, from A points and B points, point-to-point analysis they change respectively to both ends
Grain of rice contour line variation tendency, judge whether chalk rice grain is flase drop according to the variation tendency.It is described to be sentenced according to described A, B
Whether the disposing way of the disconnected grain of rice sample causes flase drop, including:
From the A points and B points, if being respectively to the track on contour line both sides a bit:The change of line-like becomes
Gesture and elliptical variation tendency, another point to the track on contour line both sides be elliptical variation tendency, then it is described
Chalk rice grain is flat condition, then does not occur flase drop;Or
From the A points and B points, if 2 points of tracks to contour line both sides are elliptical variation tendency,
Then the chalk rice grain is surveyed along its length to the chalk rice intragranular portion respectively to place state vertically from the A points and B points
The width of a grain of rice is measured, obtaining C points and D points, the width from C points and D points along the grain of rice draws straight line and rice respectively afterwards
The profile of grain intersects, and the plumule area of closing is obtained according to intersection point, if the chalk is white partly in the plumule area, and in plumule area
The similar ellipse in part, then be determined as flase drop occur, if the white part of the chalk all in the plumule area, and the white part of chalk
It is similar oval, then also there is flase drop.
It is pointed out that " Chalkiness size " in national standard refers to that chalk rice grain is kept flat at present, chalk fine flour in the grain of rice
Product accounts for the percentage of whole grain rice projected area.Therefore by calculating of the current standard to chalkiness degree in detection sample, only need to count
The chalkiness degree for keeping flat the grain of rice is calculated, now it is contemplated that two ways, one kind is when it is to place state vertically to detect the grain of rice, in front panel
Position and the information of the grain of rice are prompted, notice inspector adjustment position detects, avoids causing flase drop again.It is another to calculate chalk
The grain of rice of the state of placing vertically is weeded out during whiteness, ensures all chalkiness degree data for keeping flat the grain of rice of result of detection, improves detection
Accuracy rate.
Although the grain of rice is a steric information, current detection major way is also all still to be translated into a two dimension
Image is detected, and so, many steric informations are lost, and are lost unavoidably on data accuracy, this algorithm also can be in the present
In the comprehensive detection of chalk rice grain afterwards, when it is desirable that obtaining white belly area information, for rejecting the interference in plumule area.
As a result acquiring unit 203, for after completing flase drop and judging, the chalk rice of chalk rice to be calculated according to below equation
Grain rate and chalkiness degree:
The embodiment of the present invention, grain of rice sample RGB image is pre-processed, judged in the grain of rice sample RGB image
Whether the grain of rice is chalk rice, if a determination be made that chalk rice, then judge whether the disposing way of the grain of rice sample causes to miss
Inspection, and chalky grain rate and chalkiness degree are obtained according to default formula so that the detection of chalk rice is more accurate.
It is illustrated in figure 3 grain of rice barycenter and grain width, length detection schematic diagram;
It is illustrated in figure 4 and delimit grain of rice plumule area schematic diagram.
Those of ordinary skill in the art are further appreciated that all or part of step realized in above-described embodiment method is can
To instruct the hardware of correlation to complete by program, described program can be stored in a computer read/write memory medium
In, described storage medium, including ROM/RAM, disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (6)
1. a kind of detection method of chalk rice, it is characterised in that methods described includes:
Grain of rice sample RGB image is pre-processed, judges whether the grain of rice in the grain of rice sample RGB image is chalk rice;
If a determination be made that chalk rice, then be partitioned into the white part of chalk of the chalk rice and normal portion by maximum variance between clusters
Point;Judge whether the disposing way of the grain of rice sample causes flase drop again;Concretely comprise the following steps;
The contour line of chalk rice grain is detected, the center of mass point of the chalk rice grain is obtained by the contour line;
Obtain in the range of the center of mass point is 0 ° to 90 ° of end points, all distances of the center of mass point to the contour line, and
Angle, the length and width of the chalk rice grain, the putting angle of the chalk rice grain corresponding to acquisition beeline, beeline
Degree;
Two intersection points A, B of the straight line and the contour line along the chalk rice grain length direction Jing Guo the center of mass point are obtained,
Judge whether the disposing way of the grain of rice sample causes flase drop according to described A, B, and flase drop region is rejected according to testing result;
The chalk rice grain rate and chalkiness degree of chalk rice are calculated according to below equation:
2. the method as described in claim 1, it is characterised in that it is described that grain of rice sample RGB image is pre-processed, judge institute
Whether the grain of rice stated in grain of rice sample RGB image is chalk rice, including:
The grain of rice sample RGB image is converted into gray level image, and obtains the threshold value of adaptivenon-uniform sampling in the gray level image;
By the greyscale image transitions it is bianry image according to the threshold value, the bianry image is:The grain of rice is white, background is
The black and white binary image of black;
Total and every grain of rice the data of the grain of rice are obtained by regional connectivity algorithm, the data include:Every rice
The sum of all pixels m of grain, the origin coordinates of every grain of rice;
The grain of rice sample RGB image is converted into HSI images, the I component histogram of every grain of rice is obtained, it is straight to obtain the I component
In square figure:Peak dot number n, peak maximum max, peak-to-average a v e r, and according to formula
D values are obtained, by the D values compared with default standard value D1, judge whether the grain of rice is chalk rice according to comparative result, are had
Body:If D values are less than D1, the rice is judged for chalk rice, if D values are more than D1, the rice is not chalk rice.
3. the method as described in claim 1, it is characterised in that described that putting for the grain of rice sample is judged according to described A, B
Whether mode causes flase drop, including:
From the A points and B points, if being respectively to the track on contour line both sides a bit:The variation tendency of line-like and
Elliptical variation tendency, another point are elliptical variation tendency to the track on contour line both sides, then the chalk is white
The grain of rice is flat condition, then does not occur flase drop;Or
From the A points and B points, if 2 points of tracks to contour line both sides are elliptical variation tendency, institute
Chalk rice grain is stated to place state vertically, one is measured along its length to the chalk rice intragranular portion respectively from the A points and B points
The width of the individual grain of rice, obtain after C points and D points the width from C points and D points along the grain of rice respectively and draw straight line and the grain of rice
Profile intersects, and the plumule area of closing is obtained according to intersection point, if the chalk is white partly in the plumule area, and in the portion in plumule area
Classification is then determined as flase drop occur, if the white part of the chalk is all in the plumule area, and the white part of chalk is similar like ellipse
Ellipse, then also there is flase drop.
4. a kind of detecting system of chalk rice, it is characterised in that the system includes:
Pretreatment unit, for being pre-processed to grain of rice sample RGB image, judge the rice in the grain of rice sample RGB image
Whether grain is chalk rice;
Flase drop unit, if being chalk rice for the pretreatment unit judged result, split by maximum variance between clusters
Go out the white part of chalk and the normal segments of the chalk rice;Judge whether the disposing way of the grain of rice sample causes flase drop again;Specifically
Step is;
The contour line of chalk rice grain is detected, the center of mass point of the chalk rice grain is obtained by the contour line;
Obtain in the range of the center of mass point is 0 ° to 90 ° of end points, all distances of the center of mass point to the contour line, and
Angle, the length and width of the chalk rice grain, the putting angle of the chalk rice grain corresponding to acquisition beeline, beeline
Degree;
Two intersection points A, B of the straight line and the contour line along the chalk rice grain length direction Jing Guo the center of mass point are obtained,
Judge whether the disposing way of the grain of rice sample causes flase drop according to described A, B, and flase drop region is rejected according to testing result;
As a result acquiring unit, for calculating the chalk rice grain rate and chalkiness degree of chalk rice according to below equation:
5. system as claimed in claim 4, it is characterised in that the pretreatment unit pretreatment, including:
The grain of rice sample RGB image is converted into gray level image, and obtains the threshold value of adaptivenon-uniform sampling in the gray level image;
By the greyscale image transitions it is bianry image according to the threshold value, the bianry image is:The grain of rice is white, background is
The black and white binary image of black;
Total and every grain of rice the data of the grain of rice are obtained by regional connectivity algorithm, the data include:Every rice
The sum of all pixels m of grain, the origin coordinates of every grain of rice;
The grain of rice sample RGB image is converted into HSI images, the I component histogram of every grain of rice is obtained, it is straight to obtain the I component
In square figure:Peak dot number n, peak maximum max, peak-to-average a v e r, and according to formula
D values are obtained, by the D values compared with default standard value D1, judge whether the grain of rice is chalk rice according to comparative result, are had
Body:If D values are less than D1, the rice is judged for chalk rice, if D values are more than D1, the rice is not chalk rice.
6. system as claimed in claim 4, it is characterised in that described that putting for the grain of rice sample is judged according to described A, B
Whether mode causes flase drop, including:
From the A points and B points, if being respectively to the track on contour line both sides a bit:The variation tendency of line-like and
Elliptical variation tendency, another point are elliptical variation tendency to the track on contour line both sides, then the chalk is white
The grain of rice is flat condition, then does not occur flase drop;Or
From the A points and B points, if 2 points of tracks to contour line both sides are elliptical variation tendency, institute
Chalk rice grain is stated to place state vertically, one is measured along its length to the chalk rice intragranular portion respectively from the A points and B points
The width of the individual grain of rice, obtain after C points and D points the width from C points and D points along the grain of rice respectively and draw straight line and the grain of rice
Profile intersects, and the plumule area of closing is obtained according to intersection point, if the chalk is white partly in the plumule area, and in the portion in plumule area
Classification is then determined as flase drop occur, if the white part of the chalk is all in the plumule area, and the white part of chalk is similar like ellipse
Ellipse, then also there is flase drop.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510893771.2A CN105319223B (en) | 2015-12-07 | 2015-12-07 | The detection method and detecting system of a kind of chalk rice |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510893771.2A CN105319223B (en) | 2015-12-07 | 2015-12-07 | The detection method and detecting system of a kind of chalk rice |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105319223A CN105319223A (en) | 2016-02-10 |
CN105319223B true CN105319223B (en) | 2018-03-20 |
Family
ID=55247083
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510893771.2A Expired - Fee Related CN105319223B (en) | 2015-12-07 | 2015-12-07 | The detection method and detecting system of a kind of chalk rice |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105319223B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109781730B (en) * | 2019-01-28 | 2020-06-09 | 江南大学 | Method for quickly identifying chalky rice |
CN110186924B (en) * | 2019-07-24 | 2019-11-05 | 长沙荣业智能制造有限公司 | A kind of rice variety intelligent detecting method, system and device |
CN111879735B (en) * | 2020-07-22 | 2021-11-09 | 武汉大学 | Rice appearance quality detection method based on image |
CN112070741B (en) * | 2020-09-07 | 2024-02-23 | 浙江师范大学 | Rice chalkiness degree detecting system based on image salient region extracting method |
CN114486877B (en) * | 2020-10-23 | 2024-01-19 | 合肥美亚光电技术股份有限公司 | Rice quality detection method, rice quality detection device and storage medium |
CN113109240B (en) * | 2021-04-08 | 2022-09-09 | 国家粮食和物资储备局标准质量中心 | Method and system for determining imperfect grains of grains implemented by computer |
CN114689527A (en) * | 2022-05-31 | 2022-07-01 | 合肥安杰特光电科技有限公司 | Rice chalkiness detection method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102495068A (en) * | 2011-12-01 | 2012-06-13 | 浙江工商大学 | Method and system for detecting chalky rice on line |
CN103674816A (en) * | 2013-12-25 | 2014-03-26 | 浙江工商大学 | Detection method for detecting rice grains with chalkiness and detection system adopting same |
CN104458747A (en) * | 2014-12-22 | 2015-03-25 | 扬州大学 | Rice chalkiness measurement and calculation method |
CN104483243A (en) * | 2014-11-21 | 2015-04-01 | 浙江工商大学 | Adhered-rice detection and segmentation method, device and system |
CN204255873U (en) * | 2014-12-22 | 2015-04-08 | 扬州大学 | A kind of paddy rice chalk calculates device in vain |
-
2015
- 2015-12-07 CN CN201510893771.2A patent/CN105319223B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102495068A (en) * | 2011-12-01 | 2012-06-13 | 浙江工商大学 | Method and system for detecting chalky rice on line |
CN103674816A (en) * | 2013-12-25 | 2014-03-26 | 浙江工商大学 | Detection method for detecting rice grains with chalkiness and detection system adopting same |
CN104483243A (en) * | 2014-11-21 | 2015-04-01 | 浙江工商大学 | Adhered-rice detection and segmentation method, device and system |
CN104458747A (en) * | 2014-12-22 | 2015-03-25 | 扬州大学 | Rice chalkiness measurement and calculation method |
CN204255873U (en) * | 2014-12-22 | 2015-04-08 | 扬州大学 | A kind of paddy rice chalk calculates device in vain |
Also Published As
Publication number | Publication date |
---|---|
CN105319223A (en) | 2016-02-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105319223B (en) | The detection method and detecting system of a kind of chalk rice | |
Li et al. | Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method | |
Khojastehnazhand et al. | Maturity detection and volume estimation of apricot using image processing technique | |
Lu et al. | Histogram-based automatic thresholding for bruise detection of apples by structured-illumination reflectance imaging | |
TW201604797A (en) | Method and device for inspecting specific logo images in predetermined areas | |
CN104483243B (en) | Adhered-rice detection and segmentation method, device and system | |
Corkidi et al. | Assessing mango anthracnose using a new three‐dimensional image‐analysis technique to quantify lesions on fruit | |
Tan et al. | Segmentation and counting algorithm for touching hybrid rice grains | |
CN103106668B (en) | The method and system of image-region is described based on color histogram | |
CN107369136A (en) | Composite polycrystal-diamond face crack visible detection method | |
CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
CN114219794B (en) | Method and system for evaluating surface quality of shaving board based on machine vision | |
CN103674816B (en) | Chalk whitened rice grains detection method and system | |
CN106940791B (en) | A kind of pedestrian detection method based on low-dimensional histograms of oriented gradients | |
CN109671058A (en) | A kind of defect inspection method and system of big image in different resolution | |
CN104458747A (en) | Rice chalkiness measurement and calculation method | |
CN103344577A (en) | Non-destructive detection method for freshness of livestock meat based on multispectral imaging technology | |
CN105334228A (en) | Bottled liquid impurity and liquid level detection method based on image processing | |
CN106485252B (en) | Dot matrix target image Feature point recognition method is tested in image registration | |
CN105404866B (en) | A kind of implementation method of multi-mode automatic implementation body state perception | |
Wang et al. | Improved rotation kernel transformation directional feature for recognition of wheat stripe rust and powdery mildew | |
CN104598914A (en) | Skin color detecting method and device | |
CN105488798B (en) | SAR image method for measuring similarity based on point set contrast | |
CN102435316A (en) | Image detail energy-based printing color uniformity measurement method | |
CN108416304B (en) | Three-classification face detection method using context information |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180320 Termination date: 20191207 |