CN110009609B - Method for rapidly detecting yellow rice - Google Patents
Method for rapidly detecting yellow rice Download PDFInfo
- Publication number
- CN110009609B CN110009609B CN201910232846.0A CN201910232846A CN110009609B CN 110009609 B CN110009609 B CN 110009609B CN 201910232846 A CN201910232846 A CN 201910232846A CN 110009609 B CN110009609 B CN 110009609B
- Authority
- CN
- China
- Prior art keywords
- rice
- yellow
- image
- value
- structure element
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for rapidly detecting yellow-grained rice, and belongs to the technical field of food detection. The invention applies a detection device for detecting the appearance of rice and combines a self-designed yellow-grain rice detection method, the average detection time of a rice image is 10s, and the image identification and positioning are rapid; compared with the detection result of a manual method, the absolute error is not more than 0.01 percent. The method has the advantages of accurate identification of the yellow rice, high speed, high accuracy, strong objectivity and the like, conforms to the domestic standard and specification, and is suitable for popularization.
Description
Technical Field
The invention relates to a method for rapidly detecting yellow-grained rice, and belongs to the technical field of food detection.
Background
The rice is a daily staple food in China, the yield and the consumption are extremely high, along with the progress of the society and the continuous improvement of the living standard, people have higher requirements on the quality of the rice, and the yellow-grained rice is one of the important indexes for judging the quality of the rice in the national rice detection standard. The yellow-grained rice is defined in GB/T1354-2018 rice, and is rice grains with yellow endosperm, which is obviously different from normal rice grains in color and is consistent with or deeper than the color of a standard sample of the yellow index of rice color. The quality index of the rice requires that the content of the yellow-grained rice is not more than 1 percent, and the quality index of the high-quality rice requires that the content of the yellow-grained rice is not more than 0.5 percent.
The yellow rice is yellow and is obviously different from the transparent white of normal rice, and the yellow rice is mainly formed because the rice cannot be threshed and dried in time after being harvested and the storage condition is poor in the harvest season of the rice, so that the rice is infected by mold or biochemical reaction is generated to form the yellow rice. Due to the production of the yellow-grained rice, the quality of the rice is reduced, the quality of color, aroma and taste is deteriorated, the commercial value and the economic benefit are lost, and the yellow-grained rice can cause harm to the body after being eaten for a long time or excessively.
The traditional method for detecting the yellow-grained rice is completed by manual detection. The operator can identify the yellow rice by naked eyes, pick the yellow rice and weigh and calculate the yellow rice content. The detection result depends on the knowledge of operators on the yellow rice and the working experience thereof to a great extent, and the detection process has the defects of low speed, strong subjectivity, low accuracy and the like. Aiming at the problems existing in the current manual detection, a research method for directly and quickly identifying the yellow rice based on machine vision and image processing technology is provided.
Machine vision can replace human eyes to measure and judge, objectivity is achieved, and accuracy of recognition results can be improved due to the fact that the machine vision is high in pixel. In the process of mass repetitive industrial production, the machine vision detection method can greatly improve the production efficiency and the automation degree. The image processing is to analyze an image by a computer, generally, an image is obtained by shooting with equipment such as an industrial camera, a video camera, a scanner and the like, and the required result is achieved by processing processes such as graying, histogram equalization, image denoising, binarization, feature extraction and the like. The method is based on machine vision and image processing technology, rice images are collected, image chromaticity information is obtained through a Lab model in an image processing tool, a statistical chart is made according to the Lab chromaticity information, a chromaticity threshold value of the yellow rice is obtained, and the grain rate of the yellow rice in the rice to be detected is calculated.
Disclosure of Invention
A method for rapidly detecting yellow rice, which comprises the following steps:
(1) collecting an image of rice grains to be detected;
(2) converting the image from an RGB color space to an LAB color space;
(3) extracting three components of an image L, a and b;
(4) normalizing the L component;
(5) converting the image into a binary image;
(6) removing interference signals in the binary image;
(7) taking the value a as a judgment element, and judging the rice to be yellow when the value a is greater than a threshold value; when the value a is smaller than the threshold value, judging that the rice is normal;
(8) and outputting the result.
In one embodiment of the present invention, the removing the interference signal in the binary image includes: hole filling, deletion of image areas of interfering objects, smoothing of the contours of objects, removal of fine, prominent parts that affect object recognition.
In one embodiment of the present invention, the method specifically comprises the following steps:
(1) collecting an image of rice grains to be detected;
(2) converting the image from an RGB color space to an LAB color space;
(3) respectively obtaining three components of L, a and b;
(4) normalizing the L component; if the L value is more than 0.3, the image is regarded as a white background image, otherwise, the image is regarded as a black background image;
(5) if the image is a white background image, inverting the value of L;
(6) converting the image into a binary image;
(7) filling holes: filling the background color of the binary image;
(8) constructing an operator: creating a flat disc structure element se with the radius of 5, and creating a flat disc structure element se2 with the maximum radius of 4;
(9) performing on operation on the structure element se, deleting an object area which cannot contain the structure element, smoothing the outline of the object, disconnecting narrow connection, and removing a fine and prominent part which influences object identification;
(10) performing closed operation on the structure element se2, smoothing the outline of the object, connecting narrow gaps of the object to form a slender bent opening, and filling a hole smaller than the structure element;
(11) marking a connected domain, and taking the value a as a judgment element; in each connected domain, all pixels take the average value of a values; when the value a is larger than the threshold value, determining that the rice is yellow; when the value a is smaller than the threshold value, judging that the rice is normal;
(12) and outputting the result.
In one embodiment of the invention, the step (12) outputs a data result; the data result is specifically: respectively counting the number of normal rice and yellow rice and outputting data.
In one embodiment of the present invention, the step (12) outputs the result of an image, wherein yellow rice is marked as red and normal rice is marked as green; counting the number of the red marks, namely the number of the yellow rice; and counting the number of the green marks, namely the number of the normal rice.
In one embodiment of the present invention, the threshold is 0.2 to 0.6.
In one embodiment of the invention, the threshold is 0.4.
In one embodiment of the present invention, the method uses a rice appearance detection device, which is disclosed in patent application publication No. CN 109211740A.
The invention also claims the application of the method in grain quality control.
The invention has the advantages and effects that:
the invention provides an image processing technology for identifying and measuring yellow rice. The invention applies a detection device for detecting the appearance of rice and combines a self-designed yellow-grain rice detection method, the average detection time of a rice image is 10s, and the image identification and positioning are rapid; the interference of the experimental contrast image background on the rice identification shows that the reflection degree of the black background is extremely low, light pollution of other colors brought by actual production is not easy to show, the image background noise is reduced, and the rice image analysis and processing are easy; obtaining the chromaticity information of the rice image by adopting a Lab model, and drawing a chromaticity information graph of the yellow rice, wherein the a value is used as the judgment basis of the yellow rice; the optimal threshold value of the optimized detection system for the identification and counting of the yellow-grained rice is 0.4, the yellow-grained rice grain rate of the rice sample measured under the threshold value is not more than 0.23%, the absolute error of the comparison with the detection result of the manual method is not more than 0.01%, and the detection system can accurately identify the yellow-grained rice. The experimental method has the advantages of high speed, high accuracy, strong objectivity and the like for detecting the yellow rice, conforms to the domestic standard and specification, and is suitable for popularization.
Drawings
FIG. 1 shows the result of image processing of yellow-grained rice; (a) an original image; (b) a processed image;
FIG. 2 is a plot of the light to dark yellowrice Lab values;
FIG. 3 shows the results of the number of grains of glutinous millet at different thresholds; (a) the grain rate of the yellow-grain rice is 0 percent; (b) the grain rate of the yellow-grain rice is 50 percent; (c) the grain rate of the yellow rice is 100 percent;
FIG. 4 shows the comparison of the measured value and the actual value of the yellow rice detecting system; (a) 50 grains of yellow rice; (b) 100 yellow rice grains; (c) 150 grains of yellow rice; (d) 200 grains of yellow rice; (e) 250 grains of yellow rice; (f) 300 grains of yellow rice.
Detailed Description
Example 1 method for rapidly detecting yellow-grained rice
The detection system adopts a detection device for detecting the appearance of rice disclosed in the publication No. CN 109211740A. The device comprises a computer, a scanner, a pore plate, a glass plate, a background plate and the like. Wherein the computer is a Lenovo C560 microcomputer, the scanner is a flat-panel scanner, the optical element is CIS, and the optical resolution is 600 × 600 dpi. The pore plate is a customized pore plate, the pore diameter design that the upper pore is large and the lower pore is small is adopted, the condition that two meters are erected in one pore is avoided, the raw material is an aluminum plate, the pore plate has the advantages of light weight, good plasticity, corrosion resistance and the like, and the glass plate is float glass with high transparency, low light reflection and performance close to optics and is tightly attached to the pore plate. The background plate is a black paperboard and is attached to the inside of the upper cover of the scanner when in use, so that the background of the scanned rice image is black.
The detection method comprises the following steps:
(1) collecting an image of rice grains to be detected (as shown in FIG. 1 a);
(2) converting the image from an RGB color space to an LAB color space;
(3) respectively obtaining three components of L, a and b;
(4) normalizing the L component; if the L value is more than 0.3, the image is regarded as a white background image, otherwise, the image is regarded as a black background image;
(5) if the image is a white background image, inverting the value of L;
(6) converting the image into a binary image;
(7) filling holes: filling the background color of the binary image;
(8) constructing an operator: creating a flat disc structure element se with the radius of 5, and creating a flat disc structure element se2 with the maximum radius of 4;
(9) performing on operation on the structure element se, deleting an object area which cannot contain the structure element, smoothing the outline of the object, disconnecting narrow connection, and removing a fine and prominent part which influences object identification;
(10) performing closed operation on the structure element se2, smoothing the outline of the object, connecting narrow gaps of the object to form a slender bent opening, and filling a hole smaller than the structure element;
(11) marking a connected domain, and taking the value a as a judgment element; in each connected domain, all pixels take the average value of a values; when the value a is larger than the threshold value, determining that the rice is yellow; when the value a is smaller than the threshold value, judging that the rice is normal;
(12) and (3) generating a result picture: yellow rice is marked as red, and normal rice is marked as green (fig. 1 b); counting the number of the red marks, namely the number of the yellow rice; and counting the number of the green marks, namely the number of the normal rice.
Example 2 detection of the amount of yellow-grained Rice by Manual screening
Weighing a certain amount of rice samples 0-50 g according to GB/T5496 yellow grain and oil inspection and crack grain inspection method, and counting the total number of the rice samples; and selecting rice grains with yellow endosperm as yellow rice grains, weighing, and counting.
Example 3 detection of yellow rice in different image background colors
The equipment is the same as that in the embodiment 1, the scanner is used for obtaining an image, the upper cover plate of the scanner is white, so the background of the collected rice image is white, the color of the rice is white, the color of the yellow rice grains is yellow, in order to determine the influence of the background color of the image on the identification and counting of the yellow rice grains and the total rice grains, 10 groups of samples are selected, the images are respectively obtained under the white background and the black background, wherein the number gradient of the rice grains of the 10 groups of samples is 50, 100 and 150 and … … 500, the number of the yellow rice grains mixed in each group is 5, 10 and 15 … … 50, the image analysis, identification and counting method is the same as that in the embodiment 1, and the results are shown in the table 1, and the identification accuracy of the yellow rice grains and the normal rice grains under the black background image is higher than that of the yellow rice grains and the normal rice under the white background. The white background is similar to the color of normal rice, the adjusted chromaticity information value is approximate, image processing is interfered, incomplete identification of the rice is easily caused, yellow rice cannot be accurately positioned, and the total rice number and the counting of the yellow rice are influenced. The black background has little reflection, so that the noise of the image background is extremely low, the image processing cannot be interfered, the rapid and accurate image processing can be favorably carried out, the information of the yellow rice can be rapidly extracted, the white chromatic values of the black background and the normal rice are positioned at two extreme positions, and the influence of the black background as the background color of the rice on the calling of the chromatic information of the rice is also minimum, so that the yellow rice and the normal rice can be more accurately identified when the image is obtained by rendering the black background of the rice image.
TABLE 1 yellow-grain rice count results under different background images
Example 3 detection of yellow-grained rice in different color models
The yellow rice is rice grains with yellow endosperm, and the color information is an important basis for judging the yellow rice. Common color models are an RGB model, a CMYK model, a Lab model, and the like. Wherein, the color space of the Lab model is large, and the color information which can not be described by the RGB model and the CMYK model can be mapped. In order to determine the basis of the feature recognition of the yellow rice, 10 groups of yellow rice are selected, the yellow rice is sorted from light to deep according to the color of the yellow rice, black backgrounds are covered by a scanner to collect yellow rice images of different groups, a Lab model in an image processing tool is used for obtaining image chromaticity information, the rice images of the yellow rice from light to deep are taken as horizontal coordinates, the Lab hue value of the rice is taken as vertical coordinates, the yellow rice color information is drawn as shown in figure 2, as can be seen from figure 2, the L value represents the brightness of a picture, and the change is gentle along with the deepening of the color of the yellow rice; the positive number of the b value represents yellow, the negative number represents blue, and the unstable variation trend of the b value has no obvious correlation with the yellow degree of the yellow rice; the positive number of the value a represents red, the negative number represents green, the value a has correlation with the color of the yellow rice, and the value a is larger along with the larger color of the yellow rice, so the value a can be used as the basis for distinguishing the characteristics of the yellow rice.
Example 4 detection of yellow-grained rice at different thresholds
The detection is carried out according to the method of example 1, the threshold value of the yellow-grain rice is distinguished by colors, and the threshold value of the yellow-grain rice is the color of which the a value in the Lab channel is larger than that of normal rice. That is, when the value a is used for judging the yellow rice, the yellow rice is considered as if the chroma information is larger than the threshold value, and the normal rice is considered as if the chroma information is not larger than the threshold value. In order to accurately obtain the detection result of the yellow rice, the threshold value for detecting the yellow rice needs to be optimized.
Selecting 5 groups of samples, wherein the number of rice grains is 100, 200, 300, 400 and 500 respectively, mixing the yellow rice into the normal rice so that the rate of the mixed yellow rice grains is 100 percent, 50 percent and 0 percent, respectively adjusting the threshold value of the yellow rice detection in the step (11) to be 0,0.5,1.0,1.5,2.0,2.5,3.0,3.5 and 4.0, respectively, measuring the number of the yellow rice according to the method of the example 1, and as the result, as shown in fig. 3, the number of the detected yellow rice shows a trend along with the increase of the threshold value of the yellow rice. Meanwhile, as can be seen from fig. 3(b) and (c), when the threshold is 0, the detected amount of the yellow-grained rice exceeds the actual amount of the yellow-grained rice, because the threshold is set to be smaller, the normal rice is erroneously determined as the yellow-grained rice, and therefore the threshold for detecting the yellow-grained rice should be larger than 0; as can be seen from fig. 3(a) and (b), when the threshold is 1, the number of detected yellow-grained rice is already smaller than the actual number of yellow-grained rice, because the threshold is set to be larger, yellow-grained rice is misjudged as normal rice, and therefore the optimal threshold for detecting yellow-grained rice should be smaller than 1.
In order to determine the optimal threshold for detecting the yellow-grained rice, the grain values of the yellow-grained rice measured under different thresholds are compared with the number of the yellow-grained rice obtained by a manual screening method. 6 sets of gradient samples were selected, rice images with black backgrounds were collected using the apparatus described in example 1, wherein the number of yellow rice grains was 50, 100, 150, 200, 250, and 300, and the measurements were performed at 9 threshold points of 0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8, and 0.9, and compared with the results of the manual method as actual values, and the results of the measurements are shown in fig. 4. As can be seen from fig. 4, when the threshold is 0.4, the detected number of yellow rice grains is smaller than that of other threshold points, and the result is more accurate.
Example 5 detection of the amount of yellow-grained Rice
Grouping rice samples, collecting rice images with consistent black background specification size by using the detection system of example 1, adjusting the threshold value of yellow rice to be 0.4 by testing the detection program, and comparing the detection system measurement result with the manual method measurement result of example 2, the results are shown in table 2. The results show that 7 groups of 10 groups of rice samples have no yellow-particle rice detected, and 3 groups of rice samples have yellow-particle rice detected with the quantity of 1, and compared with the detection results of the manual method, the absolute error of the quantity of the detected yellow-particle rice is 0; for counting the total amount of rice, the absolute error of the two methods is not more than 3 every x hundred samples are detected; the grain rate of the yellow-grained rice obtained by single measurement is not more than 0.23 percent, the absolute error of the grain rate of the yellow-grained rice obtained by the two methods is not more than 0.01 percent, and the detection system can accurately identify the yellow-grained rice.
TABLE 2 yellow rice testing System and human engineering method for determining yellow rice results
Although the present invention has been described with reference to the preferred embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A method for rapidly detecting yellow rice is characterized by comprising the following specific steps:
(1) collecting an image of rice grains to be detected;
(2) converting the image from an RGB color space to an LAB color space;
(3) respectively obtaining three components of L, a and b;
(4) normalizing the L component; if the L value is more than 0.3, the image is regarded as a white background image, otherwise, the image is regarded as a black background image;
(5) if the image is a white background image, inverting the value of L;
(6) converting the image into a binary image;
(7) filling holes: filling the background color of the binary image;
(8) constructing an operator: creating a flat disc structure element se with the radius of 5, and creating a flat disc structure element se2 with the maximum radius of 4;
(9) performing on operation on the structure element se, deleting an object area which cannot contain the structure element, smoothing the outline of the object, disconnecting narrow connection, and removing a fine and prominent part which influences object identification;
(10) performing closed operation on the structure element se2, smoothing the outline of the object, connecting narrow gaps of the object to form a slender bent opening, and filling a hole smaller than the structure element;
(11) marking a connected domain, and taking the value a as a judgment element; in each connected domain, all pixels take the average value of a values; when the value a is larger than the threshold value, determining that the rice is yellow; when the value a is smaller than the threshold value, judging that the rice is normal;
(12) and outputting the result.
2. The method of claim 1, wherein the output result is an output data result or an image result.
3. The method of claim 1, wherein the threshold is 0.2-0.6.
4. The method of claim 1, wherein the threshold is set to 0.4.
5. The method according to any one of claims 1 to 4, wherein the detection is performed by using a detection device for detecting appearance of rice.
6. An apparatus for rapidly detecting yellow-grained rice, characterized by implementing the method of any one of claims 1 to 5.
7. The apparatus of claim 6, comprising a scanner and an image processing device.
8. Use of the method according to any one of claims 1 to 5 for controlling grain quality, wherein the quality of rice is evaluated by detecting the amount of yellow-grained rice in rice according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910232846.0A CN110009609B (en) | 2019-03-26 | 2019-03-26 | Method for rapidly detecting yellow rice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910232846.0A CN110009609B (en) | 2019-03-26 | 2019-03-26 | Method for rapidly detecting yellow rice |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110009609A CN110009609A (en) | 2019-07-12 |
| CN110009609B true CN110009609B (en) | 2021-03-30 |
Family
ID=67168205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910232846.0A Active CN110009609B (en) | 2019-03-26 | 2019-03-26 | Method for rapidly detecting yellow rice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009609B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111986130B (en) * | 2020-07-16 | 2024-03-15 | 南京航空航天大学 | Method for removing impurity particles in XCT slice data of woven ceramic matrix composite |
| 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 |
| CN112730273B (en) * | 2021-01-06 | 2021-10-12 | 淮阴工学院 | Portable rice quality detection device and detection method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271522A (en) * | 2008-05-21 | 2008-09-24 | 中国农业大学 | Automatic recognition method for yellow-colored rice in rice |
| CN102495068A (en) * | 2011-12-01 | 2012-06-13 | 浙江工商大学 | Method and system for detecting chalky rice on line |
| CN103674957A (en) * | 2013-12-25 | 2014-03-26 | 浙江工商大学 | Method and system for detecting yellow rice grains |
| CN107679535A (en) * | 2017-09-16 | 2018-02-09 | 西安电子科技大学 | A kind of pointer-type water meter automatic indication recognition system and method based on template matches |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6074272B2 (en) * | 2013-01-17 | 2017-02-01 | キヤノン株式会社 | Image processing apparatus and image processing method |
| CN104651462B (en) * | 2015-01-29 | 2017-02-22 | 华南农业大学 | Method for detecting magnaporthe grisea spore based on microscopic image analysis |
| CN108460780A (en) * | 2018-02-28 | 2018-08-28 | 哈尔滨工程大学 | A kind of adhesion grain of rice image partition method based on background framework characteristic |
-
2019
- 2019-03-26 CN CN201910232846.0A patent/CN110009609B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271522A (en) * | 2008-05-21 | 2008-09-24 | 中国农业大学 | Automatic recognition method for yellow-colored rice in rice |
| CN102495068A (en) * | 2011-12-01 | 2012-06-13 | 浙江工商大学 | Method and system for detecting chalky rice on line |
| CN103674957A (en) * | 2013-12-25 | 2014-03-26 | 浙江工商大学 | Method and system for detecting yellow rice grains |
| CN107679535A (en) * | 2017-09-16 | 2018-02-09 | 西安电子科技大学 | A kind of pointer-type water meter automatic indication recognition system and method based on template matches |
Non-Patent Citations (1)
| Title |
|---|
| Concentrations of heavy metals and arsenic in market rice grain and their potential health risks to the population of Fuzhou;Fu QL et al.;《Human ＆ Ecological risk Assessment an International Journal》;20151231;第117－128页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110009609A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109269951B (en) | Image-based flotation tailing ash content, concentration and coarse particle content detection method | |
| CN110415181B (en) | Intelligent identification and grade judgment method for RGB (red, green and blue) images of flue-cured tobacco in open environment | |
| CN110009609B (en) | Method for rapidly detecting yellow rice | |
| CN109978822B (en) | Banana maturity judging modeling method and judging method based on machine vision | |
| CN103076288B (en) | A kind of flesh of fish self-grading device based on computer vision and method | |
| CN101701916B (en) | Method for quickly identifying and distinguishing variety of corn | |
| CN114170208A (en) | Paper product defect detection method based on artificial intelligence | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| CN102288606B (en) | Pollen viability measuring method based on machine vision | |
| CN109766909B (en) | Analysis method for aging behavior of shore environment microplastic based on spectrogram fusion | |
| CN101059452A (en) | Fruit quality damage-free detection method and system based on multiple spectral imaging technique | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| Wah et al. | Analysis on feature extraction and classification of rice kernels for Myanmar rice using image processing techniques | |
| Birla et al. | An efficient method for quality analysis of rice using machine vision system | |
| CN109115775B (en) | Betel nut grade detection method based on machine vision | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
| CN106940292A (en) | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology | |
| CN201041553Y (en) | Fruit quality non-damage detection system base on multi-spectrum imaging technology | |
| CN110044485B (en) | Image type fabric color measuring method | |
| CN117636334B (en) | Pork quality classification method based on image processing | |
| CN110929787A (en) | Apple objective grading system based on images | |
| CN107886497A (en) | A kind of wheat flag leaf automatic nondestructive detection and measuring method based on image | |
| CN113838081A (en) | Method and device for distinguishing color uniformity of flue-cured tobacco leaves based on machine vision | |
| CN107991307A (en) | A kind of soft material face crack automatic detection device and method |
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 |