CN109100350B - Flour bran star detection method - Google Patents
Flour bran star detection method Download PDFInfo
- Publication number
- CN109100350B CN109100350B CN201810956037.XA CN201810956037A CN109100350B CN 109100350 B CN109100350 B CN 109100350B CN 201810956037 A CN201810956037 A CN 201810956037A CN 109100350 B CN109100350 B CN 109100350B
- Authority
- CN
- China
- Prior art keywords
- sample
- value
- whiteness
- flour
- pixel point
- 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.)
- Active
Links
Images
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
The technical scheme of the invention comprises a flour bran star detection method, which is used for realizing the following steps: and acquiring the brightness of the reflected light of the sample and the brightness of the reflected light of the standard white board by acquiring image data, presetting the whiteness of the standard white board, and converting a corresponding formula to obtain the whiteness of the sample. The invention has the beneficial effects that: different parameters can be set according to different samples, the method has high applicability, the whiteness of the samples can be automatically calculated according to the collected image data, the calculation mode is simple, and the logical judgment of the whiteness detection of the samples is greatly simplified.
Description
Technical Field
The invention relates to a method for detecting flour bran stars, and belongs to the technical field of computer food processing.
Background
Flour bran is the seed coat of wheat, the seed of wheat, i.e., the harvested wheat grain, and is composed of the seed coat wrapped around the surface, saturated with starch and protein and endosperm, and the germ hidden in the middle. Wherein, the endosperm and germ are ground into flour which is eaten by people. The seed coat is brown, contains a large amount of cellulose, has a rough mouthfeel, and is removed before flour milling. If the flour is ground into flour without removing the seed coats, the flour is gray black, and the taste is hard and rough when being eaten. The seed coat removed before flour milling is testa Tritici.
The flour bran star is a spot which can be seen by naked eyes and is darker than flour in color in the finished product flour, and the main components of the flour bran star are wheat bran which is not separated in the processing process of wheat, buckwheat husk and grass seed husk which are not cleaned up, and even blackstone blocks, coal cinder and the like which have the size and the specific gravity similar to that of the wheat. For example, wheat flour may be mixed with wheat epidermis (bran stars), black coal briquettes, etc.; black impurities with unknown components are mixed in the white paint; the level impact of these impurity levels on product quality is significant; in some white powders, a granular material having a certain function is added, and in order to control the adding effect and the mixing uniformity, the added granules need to be dyed, so that the consumer can recognize the additive. In summary, the detection of the content of these non-white particles and the detection of the particle diameter size are very important and necessary for evaluating the quality standard of the product. The detection purpose of the content of non-white particles is different according to different products, and the less the content of the non-white particles, the better the content of the non-white particles, such as bran stars and black dots in the flour, the less the content of the non-white particles, the better the content of the non-white particles; the content of non-white detergent particles must be not less than a certain content, for example, the content of non-white detergent enzyme particles added in the laundry detergent must be not less than a certain content; meanwhile, analyzing samples of different batches, and judging the uniformity by using the difference of content data; in summary, the detection of the content of non-white particles in white powders is of great importance and significance.
The bran star of the flour not only influences the purity and whiteness of the flour, but also relates to other related indexes in the flour production process. Such as: the flour yield, the bran content in the flour, the flour grade and the like. The cleaning in the flour production process can be measured, whether the matching of the flour mill is proper or not, whether the screening matching is reasonable or not and the like. It can also be obtained whether the wheat milling process and equipment are advanced or not, whether the operation is reasonable or not, etc. Because the flour in China is mainly cooked, consumers are very concerned about the single size and the number of the flour bran stars. The content of the bran stars in the flour is an important index for evaluating the quality grade of the flour and also an important index for reflecting the production process level of the flour. Although the flour bran is small in area and large in quantity, the flour bran is quite obvious in white flour and particularly clearly visible in steamed bread, but accurate quantification of the flour bran is difficult. The wheat flour can only be evaluated for which kind of flour has high, low, high and low bran star (such as superfine flour, superfine flour and standard flour), and the high and low bran star is difficult to accurately and quantitatively express. Flour mills and flour inspection institutions all over the country use experts in national grain inspection to evaluate grade flour samples by sense organs every year (or half year) (only flour bran stars are sensed by sense organs, other parameters have detailed requirements of national standards, inspection methods, inspection equipment and the like) and flour to be inspected to compare the grade flour samples with the flour to be inspected and give whether certain flour bran stars exceed standards or not to determine the quality and grade of the flour, and the traditional bran star detection method is that operators directly search for the bran stars which can be seen in the visual field range by using a magnifying glass and count the number. The mode has the advantages of extremely low detection efficiency, low fatigue-prone speed and large error. Therefore, the accurate detection of the flour bran star is an important link in the flour processing process.
As described above, most of them stay in a state of sensory inspection using artificial naked eyes; the artificial naked eye sensory inspection is different from person to person, the dispute is large, and the efficiency is low; although the literature with similar functions can be analyzed by the computer image analysis technology, the literature only stays in an unrealistic theoretical state and is not converted into a really good instrument product; moreover, the non-white particles in the flour are not uniform in size, irregular in shape, and inexhaustible, as is the case with the epidermis (bran) of wheat flour, which is large, small, and even smaller, how well defined? The chromatic values of the non-white particle colors are different, and the colors are different under different illumination conditions; if the images with consistent illumination are obtained, the method is also an important influence factor influencing the image analysis effect of the computer; therefore, it is urgent to invent a device for intelligently detecting non-white particles in white powder, which has stable illumination conditions, obtains images with stable imaging effect, can use computer image analysis technology to replace artificial visual inspection and provides accurate data.
Disclosure of Invention
In order to solve the problems, the invention aims to provide a flour bran star detection method, which obtains the brightness of the reflected light of a sample and the brightness of the reflected light of a standard white board by acquiring image data, presets the whiteness of the standard white board, and carries out conversion by a corresponding formula to obtain the whiteness of the sample.
The technical scheme adopted by the invention for solving the problems is as follows: the method for detecting the bran star is characterized by comprising the following steps: s100, collecting image data of a sample to be detected, and presetting whiteness X of a standard white board; s200, analyzing the image data to obtain the brightness Y of the reflected light of the sample and the brightness V of the reflected light of the standard white board; s300, processing the obtained image data by adopting a whiteness algorithm to obtain the whiteness W of the sample.
S101, presetting an acquisition strategy comprising an image acquisition time interval; s102, collecting image data of a sample to be detected to obtain a digital image.
Further, the acquisition image time interval is from 0.5 seconds to 5 seconds.
Further, the step S200 includes the steps of: s201, carrying out statistical analysis on the acquired image data to obtain total pixel points of the whole image; s202, analyzing each pixel point one by one to obtain the RGB value of each pixel point.
Further, the method comprises the following steps: according to the RGB value of each pixel point, conversion is carried out according to the international standard, and the calculation is as follows:
obtaining a Lab value of each pixel; and according to the previous step, processing each pixel point one by one, and finally carrying out average value processing on the whole image to obtain the Lab value of the whole image.
Further, the method comprises the following steps: a100, presetting a number threshold of continuous adjacent pixel points meeting conditions; a200, selecting a reference pixel point, and taking a color corresponding to the maximum value of RGB three values as a reference color according to the RGB value of the reference pixel point; a300, traversing continuous adjacent pixel points by taking the reference pixel point as a starting point, and counting corresponding RGB value information; a400, judging whether the color corresponding to the maximum value in RGB of the continuous adjacent pixel points is a reference color, if so, counting the quantity information of the continuous adjacent pixel points which meet the condition, otherwise, executing the step A600; a500, judging whether the number of adjacent pixel points meeting the condition exceeds a preset threshold value, if so, outputting a judgment result of screen mesh damage, otherwise, executing the step A600; and A600, judging whether all pixel points are traversed or not, if so, ending the process, and otherwise, returning to execute the step A200.
Further, the method steps further comprise: setting an RGB threshold value of a single pixel point; analyzing the RGB value of each pixel point, and judging the magnitude of the three values; taking the maximum value of RGB three values in a pixel point as a reference value, and judging whether the reference value is greater than a threshold value, if so, counting the information of the pixel point, and if not, skipping the pixel point; carrying out classification statistics on the pixel point information obtained last, and comparing the pixel point information with the total pixel point number of the image to obtain the area proportion of the particles with the same color; the particles of different color types are distinguished by area ratios to account for the proportion in the sample image data.
Further, performing formula operation on the brightness of the reflected light of the sample, the whiteness of the standard white board and the brightness of the reflected light of the standard white board to obtain the whiteness W of the sample, wherein the formula operation is as follows:
wherein, W is the whiteness of the sample, X is the whiteness of the standard white board, Y is the brightness of the reflected light of the sample, and V is the brightness of the reflected light of the standard white board.
Further, the preliminary detection data is subjected to average value processing to obtain final detection data of the sample.
The invention has the beneficial effects that: the flour bran star detection method adopted by the invention can set different parameters according to different samples, has higher applicability, automatically calculates the whiteness of the sample according to the acquired image data, has a simple calculation mode, and greatly simplifies the logical judgment of the whiteness detection of the sample.
Drawings
FIG. 1 is a flow chart of a method according to the present invention;
FIG. 2 illustrates a first embodiment according to the present invention;
FIG. 3 illustrates a second embodiment according to the present invention;
fig. 4 shows a third embodiment according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
It is noted that, as used in this disclosure, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.
It should be understood that the use of any and all examples, or exemplary language ("e.g.," such as, "etc.), provided herein is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.
Referring to figure 1 there is shown a flow chart of a method according to the invention,
collecting image data of a sample to be detected, and presetting whiteness of a standard white board; analyzing the image data to obtain the brightness of the reflected light of the sample and the brightness of the reflected light of the standard white board; and processing the obtained image data by adopting a whiteness algorithm to obtain the whiteness of the sample, emitting light with certain brightness through a light source to irradiate the standard white board and the flour sample, wherein the brightness of the light reflected to the camera by the standard white board is a standard reference value, and calculating the whiteness of the flour sample by comparing the light reflected to the camera by the flour sample with the light reflected to the camera by the standard white board. For example, if the whiteness of the standard white board is 80, the brightness of the reflected light of the standard white board is 600, and the average brightness of the reflected light of the flour sample is 580, the whiteness of the flour sample is: 80 × 580/600 ═ 77.33.
Referring to figure 2 for a first embodiment of the present invention,
all pixel points of the whole image data are obtained by collecting the image data, and all the pixel points are analyzed one by one to obtain information of each pixel point, including RGB values.
Referring to figure 3 of the drawings showing a second embodiment according to the present invention,
the colors of the bran stars and the black dots are different from the color of the flour, so the vision system can judge whether the region is the bran stars, the black dots or the flour according to the different colors of the regions in the image. The ratio of the bran stars to the black dots in the range is determined by calculating the area occupied by the bran stars and the area occupied by the black dots in the unit area. And calculating the ratio of the bran stars to the black dots in the continuously sampled images by using the method for judging the ratio of the bran stars to the black dots, and averaging after final summation to obtain the unit area ratio of the bran stars to the black dots of the flour sample. The analysis method can reduce errors caused by uneven distribution of the bran stars and the black spots to the maximum extent. The method comprises the following specific steps:
driving the collected image part to enter a sample measurement area, continuously obtaining RGB color images of the sample, flexibly setting the time interval of the collected images, adjusting the time interval from 0.5 second to 5 seconds, analyzing each image, calculating the content of non-white particles and LAB value of each image, and performing average value processing after the measurement and analysis are finished; analysis principle of non-white particles: each pixel point in the digital image is a composite color synthesized by RGB (red, green and blue) three colors, namely each pixel is determined by an R value, a G value and a B value; analyzing the R value, the G value and the B value of each pixel, if the three values are equal, the three values are white (if the three values are equal and all 0, the three values are pure black), the three values are not equal, and the color of the pixel point is biased to the color with a larger numerical value; the area ratios of the particles with different colors can be calculated by respectively counting the number of the pixel points with the maximum R value and exceeding the set threshold, or the pixel points with the maximum G value and exceeding the set threshold, or the pixel points with the maximum B value and exceeding the set threshold, and dividing the value by the number of the total pixels of the image. And finally, carrying out average value processing on the obtained results, wherein the method is simple and convenient and can distinguish three particles with different color types from black particles.
Simply, that is, setting the RGB threshold of a single pixel point; analyzing the RGB value of each pixel point, and judging the magnitude of the three values; taking the maximum value of RGB three values in a pixel point as a reference value, and judging whether the reference value is greater than a threshold value, if so, counting the information of the pixel point, and if not, skipping the pixel point; carrying out classification statistics on the obtained pixel point information, and comparing the obtained pixel point information with the total number of pixel points of the image to obtain the area proportion of the particles with the same color; the particles of different color types are distinguished by area ratios to account for the proportion in the sample image data. By adopting the method, the threshold value of the detection precision for identifying the non-white particles can be flexibly adjusted, and the content of the non-white particles and the whole color of the powder product can be automatically calculated. The grain diameter of the product can be automatically judged whether to be qualified or not according to the larger grain diameter, and moreover, the RGB value can be converted into the Lab value by adopting the conversion formula, and compared with the RGB value, the Lab has a wider color gamut and not only contains all the color gamuts of RGB and CMY, but also can express colors which cannot be expressed by the RGB value and the CMY value.
Referring to figure 4 showing a third embodiment according to the present invention,
when the R value (or the G value or the B value) in the calculated image is maximum and the number of the continuous adjacent pixels exceeds a set value, the screen is judged to be damaged. The detailed description is as follows: presetting a number threshold value of continuous adjacent pixel points meeting the condition; selecting a reference pixel point, and taking the color corresponding to the maximum value of RGB three values as a reference color according to the RGB value of the reference pixel point; traversing continuous adjacent pixel points by taking the reference pixel point as a starting point, and counting corresponding RGB value information; judging whether the color corresponding to the maximum value in the RGB of the continuous adjacent pixel points is a reference color or not, and counting the number information of the continuous adjacent pixel points which meet the condition; and judging whether the number of the adjacent pixel points meeting the condition exceeds a preset threshold value or not, and if so, outputting a judgment result of the damage of the screen. By adopting the method, whether the screen of the screening device is damaged or not can be judged, and the inaccuracy of the detection result caused by the abnormality of the screening device is avoided.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (4)
1. The method for detecting the bran star is characterized by comprising the following steps:
s100, collecting image data of a sample to be detected, and presetting whiteness X of a standard white board;
s200, analyzing the image data to obtain the brightness Y of the reflected light of the sample and the brightness V of the reflected light of the standard white board, wherein the method comprises the following steps: s201, carrying out statistical analysis on the acquired image data to obtain total pixel points of the whole image; s202, analyzing each pixel point one by one to obtain the RGB value of each pixel point; converting according to international standard according to RGB value of each pixel point to obtain Lab value of each pixel, wherein the calculation method comprises the following steps:
carrying out average value processing on the whole image to obtain a Lab value of the whole image;
s300, processing the obtained image data by adopting a whiteness algorithm to obtain whiteness W of the sample;
s400, carrying out average value processing on the whiteness data W of the sample obtained by the primary detection to obtain the final detection data of the sample;
further comprising:
a100, presetting a number threshold of continuous adjacent pixel points meeting conditions;
a200, selecting a reference pixel point, and taking a color corresponding to the maximum value of RGB three values as a reference color according to the RGB value of the reference pixel point;
a300, traversing continuous adjacent pixel points by taking the reference pixel point as a starting point, and counting corresponding RGB value information;
a400, judging whether the color corresponding to the maximum value in RGB of the continuous adjacent pixel points is a reference color, if so, counting the quantity information of the continuous adjacent pixel points which meet the condition, otherwise, executing the step A600;
a500, judging whether the number of adjacent pixel points meeting the condition exceeds a preset threshold value, if so, outputting a judgment result of screen mesh damage, otherwise, executing the step A600;
a600, judging whether all pixel points are traversed or not, if so, ending the process, otherwise, returning to execute the step A200;
acquiring the maximum value of RGB three values in a pixel point as a reference value, judging whether the reference value is greater than a threshold value, and if so, carrying out classified statistics on the information of the pixel point; comparing the number of the total pixel points of the image to obtain the area proportion of the particles with the same color; the particles of different color types are distinguished by area ratios to account for the proportion in the sample image data.
2. The method for detecting the bran stars as claimed in claim 1, wherein the step S100 comprises the steps of:
s101, presetting an acquisition strategy, including an image acquisition time interval;
s102, collecting image data of a sample to be detected to obtain a digital image.
3. The flour bran star detection method as claimed in claim 2, wherein the acquisition image time interval is from 0.5 seconds to 5 seconds.
4. The method for detecting the bran stars as claimed in claim 1, said step S300 further comprising a step S301, wherein: performing formula operation on the brightness of the reflected light of the sample, the whiteness of the standard white board and the brightness of the reflected light of the standard white board to obtain the whiteness W of the sample, wherein the formula operation is as follows:
wherein, W is the whiteness of the sample, X is the whiteness of the standard white board, Y is the brightness of the reflected light of the sample, and V is the brightness of the reflected light of the standard white board.
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 CN109100350A (en) | 2018-12-28 |
| CN109100350B true 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) |
Families Citing this family (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 |
| CN115862006B (en) * | 2023-03-01 | 2023-05-16 | 山东长有面粉有限公司 | Bran star detection method in flour milling process |
| 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 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3576076B2 (en) * | 2000-06-30 | 2004-10-13 | 松下電器産業株式会社 | Whiteness evaluation method and illumination light source / illumination device |
| CN1536523A (en) * | 2003-04-12 | 2004-10-13 | 李同强 | Method for identifying wheat fluor bran content by using computer |
| JP5679564B2 (en) * | 2011-03-09 | 2015-03-04 | 株式会社 日立産業制御ソリューションズ | Surface foreign matter inspection device |
| CN202057610U (en) * | 2011-03-29 | 2011-11-30 | 蒋衍恩 | Wheat flour processing precision detecting device |
| KR102623403B1 (en) * | 2015-11-08 | 2024-01-12 | 어그로잉 리미티드 | Methods for aerial image acquisition and analysis |
| CN107491731B (en) * | 2017-07-17 | 2019-12-20 | 南京航空航天大学 | Ground moving target detection and identification method for accurate striking |
| 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 |
-
2018
- 2018-08-21 CN CN201810956037.XA patent/CN109100350B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109100350A (en) | 2018-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Colour measurements by computer vision for food quality control–A review | |
| CN109100350B (en) | Flour bran star detection method | |
| CN107144353B (en) | A kind of textile chromatism measurement method based on digital camera | |
| Miller et al. | A color vision system for peach grading | |
| Afshari-Jouybari et al. | Evaluation of Photoshop software potential for food colorimetry | |
| Eissa et al. | Understanding color image processing by machine vision for biological materials | |
| CN101085442B (en) | Method for treating and classifying orange image based on RGB composite model | |
| Zhang et al. | A transformation technique from RGB signals to the Munsell system for color analysis of tobacco leaves | |
| WO2007068056A1 (en) | Stain assessment for cereal grains | |
| CN110646354A (en) | Color testing device and method for cotton fibers | |
| CN102782481A (en) | Method for calculating weight ratio by quality in grain appearance quality discrimination device | |
| JPH08297054A (en) | Color sensation measuring system | |
| CN112697682B (en) | Method for detecting color fastness to light of furniture based on machine vision | |
| CN113426709A (en) | Intelligent detection robot for grain material purchase and grain material classification method | |
| Çınar et al. | Determination of effective and specific physical features of rice varieties by computer vision in exterior quality inspection | |
| CN104749126A (en) | Wheat hardness prediction method based on near infrared hyperspectral image analysis | |
| Shahraki et al. | Development and application of a computer vision system for the measurement of the colour of Iranian sweet bread | |
| CN112098415B (en) | Nondestructive testing method for quality of waxberries | |
| CN109682817A (en) | Degree of whiteness detection device and method based on computer vision technique | |
| CN115880282A (en) | Monitoring method and monitoring device for uniform charging of hotpot condiment | |
| CN105628206A (en) | Method for measuring colors of tea leaves at different positions | |
| Udayakumar | Visible light imaging | |
| Saito et al. | Eggplant classification using artificial neural network | |
| Manamohana et al. | Applications of colour models in the food processing industry: A systematic review | |
| Symons et al. | Quality evaluation of corn/maize |
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 |