CN109100350A - A kind of flour bran speck detection method - Google Patents
A kind of flour bran speck detection method Download PDFInfo
- Publication number
- CN109100350A CN109100350A CN201810956037.XA CN201810956037A CN109100350A CN 109100350 A CN109100350 A CN 109100350A CN 201810956037 A CN201810956037 A CN 201810956037A CN 109100350 A CN109100350 A CN 109100350A
- Authority
- CN
- China
- Prior art keywords
- pixel
- value
- sample
- whiteness
- flour
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
Technical solution of the present invention includes a kind of flour bran speck detection method, for realizing: the brightness of sample reflectance lightness and standard white plate reflected light is obtained by acquiring image data, the whiteness of preset standard blank carries out corresponding formula scales and obtains sample whiteness.The invention has the benefit that different parameters can be arranged according to different samples, applicability with higher calculates the whiteness of sample according to acquired image data automatically, and calculation is simple, greatly simplified the logic judgment of sample whiteness detection.
Description
Technical field
The present invention relates to a kind of flour bran speck detection methods, belong to computer food processing technology field.
Background technique
Flour bran is the kind skin of wheat, the seed of wheat, that is, the wheat grain harvested, is the kind by being wrapped in surface
Skin is full of starch and protein and endosperm, and ensconces intermediate plumule composition.It wherein, is exactly me after endosperm and plumule are ground
The flour eaten.Kind skin is brown, and containing a large amount of cellulose, mouthfeel is very coarse, first to remove before flour milling powder.If no
Removal kind skin just wears into flour together, and flour is in grey black, and mouthfeel is very hard when eating, very coarse.It is got rid of before flour milling powder
Kind skin be exactly wheat bran.
Flour bran speck is the spot that naked eyes are visible, color is deeper than flour in final flour, and main component is wheat processing
The wheat bran that do not separate in the process, also there is a buckwheat skin that do not clean out, grass-seed skin, in addition there are also size, specific gravity with
Black stone block, cinder etc. similar in wheat.For example the epidermis (bran star) of wheat, the coal cinder of black can be mixed into wheat flour etc.；It is white
The impurity of the unknown ingredient of black is mixed into the coating of color；These impurity contents are very big on the influence of the grade of product quality；
And need to add the granule materials with certain function in some white powders, also, in order to control the effect of addition and mixing
The effect of the uniformity needs to carry out dyeing processing to the particle of addition, consumer is allowed to identify additive.In short, these
The detection of the content detection and particle diameter size of non-white coloured particles is very important for the quality standard of evaluation product
It and is necessary.The testing goal of the granule content of non-white is because of product difference, and meaning is different, and the fewer some the better, than
As the fewer bran star, stain content the better in flour；Some non-white contents must reach certain content, such as laundry clothes
The content of the washing enzyme granulate of the non-white of middle addition, it is necessary to not less than certain content；Meanwhile to the sample of different batches into
Row analysis, the judgement of uniformity is carried out using the otherness of content data；In short, in white powder non-white granule content inspection
Survey is extremely important and has very important significance.
Since flour bran speck not only influences whether the purity and whiteness of flour, also by its in relationship Flour production technical process
His index of correlation.Such as: rate containing bran, flour grade in flour extraction, powder.Whether cleaning is done during Flour production can more be measured
Only, whether flour mill collocation adjustment is proper, whether screen matching is reasonable etc..Therefrom can also obtain wheat flour milling Processes and apparatus is
It is no it is advanced, whether operation reasonable etc..It is based on boiling since the flour in China is edible, consumer also extremely takes notice of flour bran speck
Single size and number how much.In flour the content of bran star how much be flour quality ranking an important indicator,
It is the important indicator for reflecting flour production technology level.Since the area of flour bran speck is although small, quantity is more, in the flour of white
In it is fairly obvious, it is even more high-visible especially in steamed steamed bun, but we are difficult its accurate quantity.We are only
The bran star (such as a special powder, special two powder, standard flour) which kind of flour can be evaluated is high, normal, basic, mostly and few, is more as height is how many, low
It is few to be all difficult to state its accurate quantitative analysis.Flour mill and flour inspection body in all parts of the country is all to examine aspect with national food
Expert's annual (or half a year) choose that (for only flour bran speck with sense organ, other parameters have national standard, inspection party with sense organ
Method examines the detail requirements such as equipment) grade flour sample be compared with the flour to be examined, providing certain flour bran speck is
It is no it is exceeded depending on the flour quality and grade, traditional bran star detection method, which is operator, directly searches view using magnifying glass
The bran star that can see in wild range simultaneously counts number.Not only detection efficiency is extremely low for which, and vulnerable to fatigue rate slow, error compared with
Greatly.Therefore, the accurate detection of flour bran speck is the important link during flour processing.
As described above, most of states rested on using artificial eye organoleptic examination；Artificial eye organoleptic examination because
People and it is different, dispute is big, low efficiency；It can be carried out with the technology of computer image analysis in spite of the documents and materials of similar functions
Analysis, but unpractical theory state is also only resided within, it is not converted to really handy instrument product；Moreover, powder
The size of non-white particulate matter is uneven in end, in irregular shape, there is innumerable situation, such as the epidermis in wheat flour
(wheat bran), has big, has small, there are also smaller, how to define? the chromatic value thousand poor ten thousand of the grain color of these non-white
Not, and under different illumination conditions, the performance of color is also different；If obtaining the consistent image of illumination and shadow
Ring the important factor in order of computer image analysis effect；Therefore, it invents a kind of with stable illumination condition, acquisition imaging effect
The stable image of fruit, and Computer imaging analysis system can be used, artificial eye organoleptic examination is substituted, accurate data are provided
The device of non-white coloured particles, extremely urgent in intellectualized detection white powder.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide a kind of flour bran speck detection method, by acquiring image
Data obtain the brightness of sample reflectance lightness and standard white plate reflected light, and the whiteness of preset standard blank carries out corresponding public affairs
Formula converts to obtain sample whiteness.
Technical solution used by the present invention solves the problems, such as it is: a kind of flour bran speck detection method, which is characterized in that should
Method is the following steps are included: S100, acquisition sample to be tested image data, the whiteness X of preset standard blank；S200, analysis image
Data obtain the brightness V of sample reflectance lightness Y and standard white plate reflected light；S300, using whiteness algorithm to obtained figure
As data are handled, sample whiteness W is obtained.
Further, the step S100 is the following steps are included: S101, default acquisition strategies, including acquisition image temporal
Interval；S102, acquisition sample to be tested image data, obtain digital picture.
Further, the acquisition image temporal interval is from 0.5 second to 5 second.
Further, the step S200 is the following steps are included: S201, statistical analysis acquired image data, obtain
Total pixel of whole image；S202, each pixel is analyzed one by one, obtain the rgb value of each pixel.
Further, this method is further comprising the steps of: according to the rgb value of each pixel, carrying out according to international standard
Conversion calculates are as follows:
Obtain the Lab value of each pixel；According to previous step, each pixel is handled one by one, finally to whole
Image carries out average value processing, obtains the Lab value of whole image.
Further, this method is further comprising the steps of: the number of A100, the default continuous adjacent pixel for meeting condition
Threshold value；A200, one reference image vegetarian refreshments of selection take the maximum value of tri- value of RGB to correspond to color conduct according to the rgb value of reference image vegetarian refreshments
Reference color；A300, using reference image vegetarian refreshments as starting point, traverse the pixel of continuous adjacent, count corresponding rgb value information；A400,
Judge whether the corresponding color of maximum value is reference color in the RGB of the pixel of continuous adjacent, if so, statistics meets the condition
Continuous adjacent pixel quantity information, otherwise, execute step A600；A500, judgement meet the neighbor pixel of the condition
Quantity whether be more than preset threshold, if so, output sieve breakage judging result, otherwise, execute step A600；A600,
Judge whether that all pixels point has all traversed completion, if so, terminating this process, otherwise, returns to step A200.
Further, this method step further include: the RGB threshold value of setting single pixel point；Analyze the RGB of each pixel
Value, judges the size of three values；It takes the maximum value of tri- value of RGB in a pixel as reference value, and judges whether the reference value is big
In threshold value, if so, the information of the pixel is counted, if it is not, then skipping the pixel；The pixel information that upper one is obtained into
Row statistic of classification does comparison processing with the quantity of total pixel of image to get the area ratio for arriving the particle with color；Pass through
The particle of area ratio differentiation different colours type proportion in sample image data.
Further, the brightness of sample reflectance lightness, the whiteness of standard white plate and standard white plate reflected light is carried out
Formula operation obtains the whiteness W of sample, calculates are as follows:
Wherein, W is sample whiteness, and X is the whiteness of standard white plate, and Y is sample reflectance lightness, and V is standard white plate reflection
The brightness of light.
Further, Preliminary detection data are done into average value processing, obtains the final detection data of sample.
The beneficial effects of the present invention are: a kind of flour bran speck detection method that the present invention uses, it can be according to different samples
Different parameters is set, and applicability with higher calculates the whiteness of sample according to acquired image data automatically, meter
Calculation mode is simple, greatly simplified the logic judgment of sample whiteness detection.
Detailed description of the invention
Fig. 1 show flow chart according to the method for the present invention；
Fig. 2 show according to a particular embodiment of the invention one；
Fig. 3 show according to a particular embodiment of the invention two；
Fig. 4 show according to a particular embodiment of the invention three.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments
The present invention is described in detail.
It should be noted that unless otherwise specified, in the disclosure used in the "an" of singular, " described " and
"the" is also intended to including most forms, unless the context clearly indicates other meaning.In addition, unless otherwise defined, this paper institute
All technical and scientific terms used are identical as the normally understood meaning of those skilled in the art.This paper specification
Used in term be intended merely to description specific embodiment, be not intended to be limiting of the invention.Term as used herein
"and/or" includes the arbitrary combination of one or more relevant listed items.
(" such as ", " such as ") makes it should be appreciated that provided in this article any and all example or exemplary language
With being intended merely to that the embodiment of the present invention is better described, and unless the context requires otherwise, otherwise the scope of the present invention will not be applied
Limitation.
It show flow chart according to the method for the present invention referring to Fig.1,
Acquire sample to be tested image data, the whiteness of preset standard blank；Image data is analyzed, it is bright to obtain sample reflection
The brightness of degree and standard white plate reflected light；Obtained image data is handled using whiteness algorithm, obtains sample whiteness,
The illumination for launching certain brightness by light source is reflected to the light of camera depending on standard white plate on standard white plate and flour sample
Brightness is standard reference point, and flour sample is reflected to the light of camera and standard white plate is reflected to the light of camera by comparing, thus
Calculate the whiteness of flour sample.Such as the whiteness of established standards blank is 80, the brightness of standard white plate reflected light is 600, face
The average brightness of powder sample reflected light is 580, then the whiteness of flour sample are as follows: 80*580/600=77.33.
It is shown according to a particular embodiment of the invention one referring to Fig. 2,
By acquiring image data, all pixels point of whole image data is obtained, and analyze all pixels point one by one, obtained
Obtain the information of each pixel, including rgb value.
According to a particular embodiment of the invention two are shown referring to Fig. 3,
The color of bran star, stain and flour is different, so vision system can be according to each region face in image
The difference of color, so that judging is bran star or stain either flour on earth in the region.Pass through bran star in unit of account area
Occupied area, stain occupied area, to determine the accounting of bran star and stain within the scope of this.Bran star, stain accounting more than using again
Judgment method goes to calculate the accounting of bran star, stain in the image that continuous sampling is returned, average again after final summation, must go out flour
The unit area accounting of the bran star of sample, stain.The above analysis method can reduce to the maximum extent because bran star, stain are distributed
Error caused by unevenness.Specific steps are as follows:
Driving acquisition image section enters sample measured zone, continuously acquires the RGB color image of sample, acquires image
Time interval is flexibly set, second adjustable from 0.5 second to 5, is analyzed every image, is calculated the non-white of every image
Content, the LAB value of grain object carry out average value processing after measurement analysis；The analysis principle of non-white particulate matter: digital picture
In each pixel be the tertiary colour synthesized by tri- color of RGB, i.e., each pixel is determined by R value, G value, B value；Point
Analyse the R value, G value, B value of each pixel, if three value it is equal be white (three value it is equal and all be 0, for black), three
It is worth unequal, the color deviation biggish color of numerical value of this pixel；Respectively statistics R value it is maximum and be more than given threshold,
Or G value is maximum and more than given threshold or B value is maximum and is more than the quantity of the pixel of given threshold, with this
It is worth the quantity of total pixel divided by image, it can calculate the area ratio of the particle of different colours.The knot that will finally obtain
Fruit carries out carrying out average value processing, simple and convenient with the method, and can distinguish the particle of three kinds of different colours types and black
The particle of color.
It is in simple terms to set the RGB threshold value of single pixel point；The rgb value for analyzing each pixel judges three values
Size；It takes the maximum value of tri- value of RGB in a pixel as reference value, and judges whether the reference value is greater than threshold value, if so,
The information of the pixel is counted, if it is not, then skipping the pixel；Obtained pixel information carries out statistic of classification, with image
The quantity of total pixel does comparison processing to get the area ratio for arriving the particle with color；Different face are distinguished by area ratio
The particle of color type proportion in sample image data.Using the method, non-white particulate matter can be identified with flexible modulation
Detection accuracy threshold value, calculate the content of non-white coloured particles and the integral color of powder-product automatically.It can also be according to larger
Particle diameter, judge automatically product particle diameter whether qualification in addition, using above-mentioned conversion formula, moreover it is possible to by rgb value turn
It is changed to Lab value, for opposite RGB, Lab possesses broader colour gamut, it not only contains RGB, and all colour gamuts of CMY are gone back
The color that they cannot be showed can be showed.
According to a particular embodiment of the invention three are shown referring to Fig. 4,
It calculates R value in image maximum (or G value is maximum or B value is maximum) and the number of the pixel of continuous adjacent is more than
When setting value, it is judged as sieve breakage.It is described in detail i.e.: the number threshold value of the default continuous adjacent pixel for meeting condition；Choosing
A reference image vegetarian refreshments is taken, according to the rgb value of reference image vegetarian refreshments, the maximum value of tri- value of RGB is taken to correspond to color as reference color；With reference
Pixel is starting point, traverses the pixel of continuous adjacent, counts corresponding rgb value information；Judge the pixel of continuous adjacent
Whether the corresponding color of maximum value is reference color in RGB, and statistics meets the quantity information of the continuous adjacent pixel of the condition；Sentence
It is disconnected to meet whether the quantity of the neighbor pixel of the condition is more than preset threshold, if so, the judging result of output sieve breakage.
Using the method, can determine whether the sieve of screen equipment is damaged, testing result caused by avoiding because of screen unit exception is inaccurate
Really.
The above, only presently preferred embodiments of the present invention, the invention is not limited to above embodiment, as long as
It reaches technical effect of the invention with identical means, all should belong to protection scope of the present invention.In protection model of the invention
Its technical solution and/or embodiment can have a variety of different modifications and variations in enclosing.
Claims (9)
1. a kind of flour bran speck detection method, which is characterized in that method includes the following steps:
S100, acquisition sample to be tested image data, the whiteness X of preset standard blank；
S200, analysis image data, obtain the brightness V of sample reflectance lightness Y and standard white plate reflected light；
S300, obtained image data is handled using whiteness algorithm, obtains sample whiteness W.
2. flour bran speck detection method according to claim 1, which is characterized in that the step S100 includes following step
It is rapid:
S101, default acquisition strategies, including acquisition image temporal interval；
S102, acquisition sample to be tested image data, obtain digital picture.
3. flour bran speck detection method according to claim 2, which is characterized in that the acquisition image temporal interval from
0.5 second to 5 seconds.
4. according to flour bran speck detection method described in claim 1, which is characterized in that the step S200 the following steps are included:
S201, statistical analysis acquired image data, obtain total pixel of whole image；
S202, each pixel is analyzed one by one, obtain the rgb value of each pixel.
5. flour bran speck detection method according to claim 4, which is characterized in that this method is further comprising the steps of:
According to the rgb value of each pixel, by weight of international standard carries out, calculate are as follows:
Obtain the Lab value of each pixel；
According to previous step, each pixel is handled one by one, average value processing finally is carried out to whole image, is obtained whole
Open the Lab value of image.
6. flour bran speck detection method according to claim 4, which is characterized in that this method is further comprising the steps of:
The number threshold value of A100, the default continuous adjacent pixel for meeting condition；
A200, a reference image vegetarian refreshments is chosen, according to the rgb value of reference image vegetarian refreshments, the maximum value of tri- value of RGB is taken to correspond to color as ginseng
Examine color；
A300, using reference image vegetarian refreshments as starting point, traverse the pixel of continuous adjacent, count corresponding rgb value information；
A400, judge continuous adjacent pixel RGB in the corresponding color of maximum value whether be reference color, if so, statistics
Meet the quantity information of the continuous adjacent pixel of the condition, otherwise, executes step A600；
A500, judgement meet whether the quantity of the neighbor pixel of the condition is more than preset threshold, if so, output sieve breakage
Judging result, otherwise, execute step A600；
A600, judge whether that all pixels point has all traversed completion, if so, terminating this process, otherwise, return to step
A200。
7. flour bran speck detection method according to claim 4, which is characterized in that this method step further include:
Set the RGB threshold value of single pixel point；
The rgb value for analyzing each pixel judges the size of three values；
It takes the maximum value of tri- value of RGB in a pixel as reference value, and judges whether the reference value is greater than threshold value, if so,
The information of the pixel is counted, if it is not, then skipping the pixel；
Upper one obtained pixel information is subjected to statistic of classification, with the quantity of total pixel of image do comparison processing to get
To the area ratio of the particle of same color；
By area ratio distinguish different colours type particle in sample image data proportion.
8. flour bran speck detection method according to claim 1, the step S300 further includes step S301, and feature exists
In: the brightness of sample reflectance lightness, the whiteness of standard white plate and standard white plate reflected light is subjected to formula operation, obtains sample
The whiteness W of product is calculated are as follows:
Wherein, W is sample whiteness, and X is the whiteness of standard white plate, and Y is sample reflectance lightness, and V is standard white plate reflected light
Brightness.
9. flour bran speck detection method according to claim 1, this method further includes step S400, it is characterised in that: will
Preliminary detection data do average value processing, obtain the final detection data of sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810956037.XA CN109100350B (en) | 2018-08-21 | 2018-08-21 | Flour bran star detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810956037.XA CN109100350B (en) | 2018-08-21 | 2018-08-21 | Flour bran star detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109100350A true CN109100350A (en) | 2018-12-28 |
| CN109100350B CN109100350B (en) | 2022-01-28 |
Family
ID=64850588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810956037.XA Active CN109100350B (en) | 2018-08-21 | 2018-08-21 | Flour bran star detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109100350B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109682817A (en) * | 2019-02-22 | 2019-04-26 | 哈尔滨工程大学 | Degree of whiteness detection device and method based on computer vision technique |
| CN115862006A (en) * | 2023-03-01 | 2023-03-28 | 山东长有面粉有限公司 | Method for detecting bran stars in flour milling process |
| CN116071351A (en) * | 2023-03-06 | 2023-05-05 | 山东金利康面粉有限公司 | Flour quality visual detection system based on flour bran star identification |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1334449A (en) * | 2000-06-30 | 2002-02-06 | 松下电器产业株式会社 | Method for estimating whiteness, method for estimating relative whiteness, and light source and illuminator |
| CN1536523A (en) * | 2003-04-12 | 2004-10-13 | 李同强 | Method for identifying wheat fluor bran content by using computer |
| CN202057610U (en) * | 2011-03-29 | 2011-11-30 | 蒋衍恩 | Wheat flour processing precision detecting device |
| JP2012189351A (en) * | 2011-03-09 | 2012-10-04 | Hitachi Information & Control Solutions Ltd | Surface foreign matter inspection apparatus |
| CN107491731A (en) * | 2017-07-17 | 2017-12-19 | 南京航空航天大学 | A kind of Ground moving target detection and recognition methods towards precision strike |
| CN107807126A (en) * | 2017-10-25 | 2018-03-16 | 宝鸡金昱食品机械制造有限公司 | A kind of flour bran speck detection method based on PCNN |
| CN108369635A (en) * | 2015-11-08 | 2018-08-03 | 阿格洛英公司 | The method with analysis is obtained for aerial image |
-
2018
- 2018-08-21 CN CN201810956037.XA patent/CN109100350B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1334449A (en) * | 2000-06-30 | 2002-02-06 | 松下电器产业株式会社 | Method for estimating whiteness, method for estimating relative whiteness, and light source and illuminator |
| CN1536523A (en) * | 2003-04-12 | 2004-10-13 | 李同强 | Method for identifying wheat fluor bran content by using computer |
| JP2012189351A (en) * | 2011-03-09 | 2012-10-04 | Hitachi Information & Control Solutions Ltd | Surface foreign matter inspection apparatus |
| CN202057610U (en) * | 2011-03-29 | 2011-11-30 | 蒋衍恩 | Wheat flour processing precision detecting device |
| CN108369635A (en) * | 2015-11-08 | 2018-08-03 | 阿格洛英公司 | The method with analysis is obtained for aerial image |
| CN107491731A (en) * | 2017-07-17 | 2017-12-19 | 南京航空航天大学 | A kind of Ground moving target detection and recognition methods towards precision strike |
| CN107807126A (en) * | 2017-10-25 | 2018-03-16 | 宝鸡金昱食品机械制造有限公司 | A kind of flour bran speck detection method based on PCNN |
Non-Patent Citations (4)
| Title |
|---|
| 博恩科技: "麸星仪", 《HTTP://WWW.ZHBNKJ.COM/?SERVICE/ARTICLE13/36.HTML》 * |
| 戴常军: "面粉麸星计算机检测系统", 《电子技术应用》 * |
| 李同强: "面粉麸星的计算机检测", 《中国粮油学报》 * |
| 百度文库: "面粉麸星和白度的图像检测方法的研究", 《HTTPS://WENKU.BAIDU.COM/VIEW/09C4C11B227916888486D725.HTML#》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109682817A (en) * | 2019-02-22 | 2019-04-26 | 哈尔滨工程大学 | Degree of whiteness detection device and method based on computer vision technique |
| CN115862006A (en) * | 2023-03-01 | 2023-03-28 | 山东长有面粉有限公司 | Method for detecting bran stars in flour milling process |
| CN116071351A (en) * | 2023-03-06 | 2023-05-05 | 山东金利康面粉有限公司 | Flour quality visual detection system based on flour bran star identification |
| CN116071351B (en) * | 2023-03-06 | 2023-06-30 | 山东金利康面粉有限公司 | Flour quality visual detection system based on flour bran star identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109100350B (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Miller et al. | A color vision system for peach grading | |
| Rodríguez-Pulido et al. | Ripeness estimation of grape berries and seeds by image analysis | |
| Afshari-Jouybari et al. | Evaluation of Photoshop software potential for food colorimetry | |
| Leon et al. | Color measurement in L∗ a∗ b∗ units from RGB digital images | |
| US8031910B2 (en) | Method and apparatus for analyzing quality traits of grain or seed | |
| CN104871175B (en) | Food quality is scored and is controlled | |
| CN107144353B (en) | A kind of textile chromatism measurement method based on digital camera | |
| CN109100350A (en) | A kind of flour bran speck detection method | |
| Rodríguez-Pulido et al. | Analysis of food appearance properties by computer vision applying ellipsoids to colour data | |
| Hidalgo et al. | Wheat flour granulometry determines colour perception | |
| US5917541A (en) | Color sense measuring device | |
| WO2007068056A1 (en) | Stain assessment for cereal grains | |
| Zhang et al. | A transformation technique from RGB signals to the Munsell system for color analysis of tobacco leaves | |
| Lai et al. | Application of pattern recognition techniques in the analysis of cereal grains | |
| Cinar et al. | Determination of effective and specific physical features of rice varieties by computer vision in exterior quality inspection | |
| Black et al. | Accurate technique for measuring color values of grain and grain products using a visible‐NIR instrument | |
| Shahraki et al. | Development and application of a computer vision system for the measurement of the colour of Iranian sweet bread | |
| US11060918B2 (en) | Evaluator, measurement apparatus, evaluating method, and non-transitory recording medium | |
| CN109781730A (en) | A kind of method of quick identification chalk rice | |
| CN104749126A (en) | Wheat hardness prediction method based on near infrared hyperspectral image analysis | |
| Wu et al. | Food colour measurement using computer vision | |
| CN106404792B (en) | A kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology | |
| CN105628206B (en) | A kind of method for the color for determining diverse location tea leaf | |
| CN108885169B (en) | Method and device for evaluating grain fineness | |
| Chherawala et al. | Food grading/sorting based on color appearance trough machine vision: The case of fresh cranberries |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |