CN114359882B - Method and system for detecting bottle commodity in container - Google Patents
Method and system for detecting bottle commodity in container Download PDFInfo
- Publication number
- CN114359882B CN114359882B CN202111683403.7A CN202111683403A CN114359882B CN 114359882 B CN114359882 B CN 114359882B CN 202111683403 A CN202111683403 A CN 202111683403A CN 114359882 B CN114359882 B CN 114359882B
- Authority
- CN
- China
- Prior art keywords
- image
- merchant
- straight line
- bottle body
- pattern
- 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
- 238000000034 method Methods 0.000 title claims description 32
- 235000013361 beverage Nutrition 0.000 claims abstract description 44
- 230000009191 jumping Effects 0.000 claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
Abstract
The invention discloses a detection method of bottle commodity in a container, which comprises the steps of acquiring an image of a beverage bottle, and preprocessing to obtain a preprocessed image; judging whether the beverage bottle body in the image has a cover body or not according to the preprocessed image; and judging the position of the cover body, identifying the cover body pattern, jumping to an alarming step if the identified pattern is not a preset pattern of a merchant, identifying the bottle body pattern if the identified pattern is the preset pattern of the merchant, determining that the bottle body is a merchant commodity if the identified pattern of the bottle body is judged to be the preset pattern of the merchant, jumping to counting the identified bottle body if the identified pattern of the bottle body is not the preset pattern of the merchant to obtain the number of the bottle body which is not the merchant commodity, performing category statistics on the identified non-merchant commodity and generating a bid analysis report if the detected number of the bottle body is smaller than a second preset value, and directly sending alarming information to a merchant preset terminal if the detected number of the bottle body is larger than the second value.
Description
Technical Field
The invention relates to the technical field of food detection, in particular to a method and a system for detecting bottle goods in a container.
Background
With the development of science and technology, the vending machine is used in places where people are living in schools, office buildings and the like, so that the life of people is more convenient and comfortable, and the working pressure born by supermarkets is greatly reduced due to the use of the vending machine. The beverage is taken as a quick-acting product, and the market is huge. In order to ensure the mouthfeel of beverages, the beverages are often sold in refrigerated environments. In China, beverages are usually sold in refrigerated cabinets.
In the prior art, a merchant needs to analyze the types of beverages in a container, and usually, the detection of the beverage bottle body is performed by image acquisition of the pattern of the bottle body, however, many similar bottle body advertisements lead to that the food recognition technology cannot well distinguish the merchant belonging to the beverage commodity in the container, for example, the "Master kang" and the imitation "Kang Shuaifu" similar to the Master kang can not be distinguished by the food recognition technology, but the imitation of the bottle body by the imitation is often spurious, however, the imitation of the cover body is difficult, and whether the imitation is genuine or not can be distinguished by the cover body.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention discloses a method for detecting bottle goods in a container, which further comprises the following steps:
step 1, acquiring an image of a beverage bottle body, and preprocessing the image of the beverage bottle body to obtain a preprocessed image;
step 2, judging whether the beverage bottle body in the image has a cover body or not according to the preprocessed image, if not, jumping to step 6, and if so, jumping to step 3;
detecting a cover body on a beverage body through a straight line fitting algorithm, solving a straight line equation 1 where a fixed center point of the cover body and the bottle body is located through hough conversion, solving a straight line equation 2 where a cover top of the cover body is located through a straight line fitting algorithm, judging the position of the cover body relative to the bottle body through comparing the narrative rate and intercept of the straight line equation 1 and the straight line equation 2, if the position of the cover body relative to the bottle body is judged to exceed a preset range value input by a merchant, jumping to a step 6, and if the position of the cover body relative to the bottle body is not beyond the preset range value input by the merchant, jumping to a step 4;
step 4, identifying the cover body pattern, if the identified pattern is not the preset pattern of the merchant, jumping to step 6, and if the identified pattern is the preset pattern of the merchant, jumping to step 5;
step 5, identifying the pattern of the bottle body, if the identification judges that the pattern of the bottle body is the preset pattern of the merchant, determining that the bottle body is a merchant commodity, jumping back to the step 1 to acquire the images of other bottle bodies again, and if the identification judges that the pattern of the bottle body is not the preset pattern of the merchant, jumping to the step 6;
and 6, counting the identified bottles to obtain the number of the bottles which are not merchant commodities, counting the types of the identified non-merchant commodities if the detected number of the bottles is larger than a first preset value and smaller than a second preset value, generating an analysis report of the bid commodity, and directly sending alarm information to a merchant preset terminal if the detected number of the bottles is larger than the second preset value.
Still further, the step 3 further includes: assuming that there is a point (xn, yn) in image space, then all straight-line equations passing through this point can be expressed as:
y n ＝αx n +β
where α is the slope of the line and β is the intercept of the line;
if the image space has a point (xk, yk) to which there is likewise a straight line in the parameter space, the two straight lines must intersect at a point (α ', β') if they are not parallel lines. The slope and intercept of the straight line represented by (xn, yn) and (xk, yk) in image space are represented at α ', β', respectively; and determining a straight line through the points (xn, yn) and the points (xk, yk), wherein the straight line corresponding to the straight line at the parameter space is through the points (alpha ', beta'), and the straight line detection in the image space is converted into the detection of the midpoint of the parameter space through the transformation of a straight line fitting algorithm.
Further, the preprocessing the image of the beverage bottle body to obtain a preprocessed image further comprises: and carrying out gray level processing on the color image, carrying out histogram equalization on the gray level image to obtain a gray level histogram of the image of the beverage bottle body, setting a preset template, and replacing gray level values of corresponding pixel points by using a template median value to filter high-frequency noise to obtain a smooth image, wherein the preset template is a median filtering template used as a neighborhood operation template, and replacing the value of any point in the digital image by using the median value of each pixel point value in one field of the point to enable adjacent numerical values to be closer to an actual value, thereby eliminating noise points of the image.
Further, the method for judging whether the images match comprises the following steps: and calculating the similarity of the characteristic values of the images to obtain the difference between the images, and judging that the images are matched when the similarity is larger than a preset threshold value.
Further, the preset threshold of the similarity is 0.8.
Still further, the step 3 may be further replaced by: the method comprises the steps of analyzing and processing an image by adopting a first neural network model, wherein the image of a beverage bottle body to be detected is firstly divided into grids of 3 multiplied by 3, and then each grid is matched with a learning label, wherein the learning label is a cover body image data label, and if the center of an object in a detected picture falls into the divided grids, the grids predict the bottle body corresponding to the cover body falling into the grids.
Further, the first neural network model is a YOLO v1 network, and the network structure has 24 convolution layers, 2 full connection layers and one output layer.
The invention further discloses a detection system of the bottle commodity in the container, the image acquisition unit acquires the image of the beverage bottle, and the image of the beverage bottle is preprocessed to obtain a preprocessed image, wherein the preprocessing of the image of the beverage bottle to obtain the preprocessed image further comprises the following steps: performing gray level processing on the color image, performing gray level range 0255, performing histogram equalization on the gray level image to obtain a gray level histogram of the image of the beverage bottle, setting a preset template, replacing gray level values of corresponding pixel points by using a template median value to filter high-frequency noise to obtain a smooth image, wherein the preset template is a median filtering template used as a neighborhood operation template, and replacing the value of any point in the digital image by using the median value of each pixel point value in one field of the point to enable adjacent numerical values to be closer to an actual value, so that noise points of the image are eliminated; a cap judging unit for judging whether the beverage bottle body in the image has a cap or not according to the preprocessed image;
the cover body detection and identification unit detects the cover body on the beverage body through a straight line fitting algorithm, a straight line equation 1 where a fixed center point of the cover body and the bottle body is located is obtained through hough conversion, a straight line equation 2 where the cover top of the cover body is located is obtained through a straight line fitting algorithm, the positions of the cover body relative to the bottle body are judged through comparing the narration and intercept of the straight line equation 1 and the straight line equation 2, whether the positions of the cover body relative to the bottle body exceed a preset range value input by a merchant is judged, wherein, assuming that one point (xn, yn) exists in an image space, all straight line equations passing through the point can be expressed as:
y n ＝αx n +β
where α is the slope of the line and β is the intercept of the line;
if the image space has a point (xk, yk) to which there is likewise a straight line in the parameter space, the two straight lines must intersect at a point (α ', β') if they are not parallel lines. The slope and intercept of the straight line represented by (xn, yn) and (xk, yk) in image space are represented at α ', β', respectively; determining a straight line through points (xn, yn) and points (xk, yk), enabling the straight line corresponding to the straight line in the parameter space to pass through points (alpha ', beta'), and converting the detection of the straight line in the image space to the detection of the midpoint in the parameter space through the transformation of a straight line fitting algorithm; identifying the cover body pattern, and if the identified pattern is not the preset pattern of the merchant, jumping to a statistical analysis and alarm unit;
the bottle body identification unit is used for identifying the pattern of the bottle body, determining that the bottle body is a commodity of a merchant if the pattern of the bottle body is identified and judged to be a preset pattern of the merchant, and jumping to the statistical analysis and alarm unit if the pattern of the bottle body is judged not to be the preset pattern of the merchant;
the statistical analysis and alarm unit counts the identified bottles to obtain the number of the bottles which are not merchant commodities, if the detected number of the bottles is larger than a first preset value and smaller than a second preset value, the identified non-merchant commodities are subjected to category statistics, an analysis report of the bid commodity is generated, and if the detected number of the bottles is larger than the second preset value, alarm information is directly sent to a merchant preset terminal.
The invention also discloses an electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps of the above-described method.
The invention also discloses a computer readable storage medium for storing a computer program for execution by a processor to implement the above method.
Compared with the prior art, the invention solves the problems that ' beverage maker puts in refrigeration equipment, beverage maker products are placed on each layer of shelves, and comparison is carried out through images, bottle shapes and the like by adopting an image analysis mode and combining the analysis of bottle caps with the identification and analysis of bottle bodies ', and if too many products other than the products exist, the invention can not well distinguish imitations or the competing goods with the bottle shapes and the close figures during alarming '. Meanwhile, two analysis methods aiming at the bottle cap are adopted, so that the problem of overlong recognition time caused by multi-level (overlong time for two times of pattern recognition) image recognition in the image recognition process is greatly reduced, and the time for image recognition processing can be well compressed through a linear algorithm and a neural network prediction.
Drawings
The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. In the figures, like reference numerals designate corresponding parts throughout the different views.
FIG. 1 is a flow chart of a method for detecting a bottle commodity in a container according to the present invention.
Detailed Description
Example 1
A method for detecting a bottle commodity in a container as shown in fig. 1, the method further comprising:
step 1, acquiring an image of a beverage bottle body, and preprocessing the image of the beverage bottle body to obtain a preprocessed image;
step 2, judging whether the beverage bottle body in the image has a cover body or not according to the preprocessed image, if not, jumping to step 6, and if so, jumping to step 3;
detecting a cover body on a beverage body through a straight line fitting algorithm, solving a straight line equation 1 where a fixed center point of the cover body and the bottle body is located through hough conversion, solving a straight line equation 2 where a cover top of the cover body is located through a straight line fitting algorithm, judging the position of the cover body relative to the bottle body through comparing the narrative rate and intercept of the straight line equation 1 and the straight line equation 2, if the position of the cover body relative to the bottle body is judged to exceed a preset range value input by a merchant, jumping to a step 6, and if the position of the cover body relative to the bottle body is not beyond the preset range value input by the merchant, jumping to a step 4;
step 4, identifying the cover body pattern, if the identified pattern is not the preset pattern of the merchant, jumping to step 6, and if the identified pattern is the preset pattern of the merchant, jumping to step 5;
step 5, identifying the pattern of the bottle body, if the identification judges that the pattern of the bottle body is the preset pattern of the merchant, determining that the bottle body is a merchant commodity, jumping back to the step 1 to acquire the images of other bottle bodies again, and if the identification judges that the pattern of the bottle body is not the preset pattern of the merchant, jumping to the step 6;
and 6, counting the identified bottles to obtain the number of the bottles which are not merchant commodities, counting the types of the identified non-merchant commodities if the detected number of the bottles is larger than a first preset value and smaller than a second preset value, generating an analysis report of the bid commodity, and directly sending alarm information to a merchant preset terminal if the detected number of the bottles is larger than the second preset value.
Still further, the step 3 further includes: assuming that there is a point (xn, yn) in image space, then all straight-line equations passing through this point can be expressed as:
y n ＝αx n +β
where α is the slope of the line and β is the intercept of the line;
if the image space has a point (xk, yk) to which there is likewise a straight line in the parameter space, the two straight lines must intersect at a point (α ', β') if they are not parallel lines. The slope and intercept of the straight line represented by (xn, yn) and (xk, yk) in image space are represented at α ', β', respectively; and determining a straight line through the points (xn, yn) and the points (xk, yk), wherein the straight line corresponding to the straight line at the parameter space is through the points (alpha ', beta'), and the straight line detection in the image space is converted into the detection of the midpoint of the parameter space through the transformation of a straight line fitting algorithm.
Further, the preprocessing the image of the beverage bottle body to obtain a preprocessed image further comprises: and carrying out gray level processing on the color image, carrying out gray level range 0255, carrying out histogram equalization on the gray level image to obtain a gray level histogram of the image of the beverage bottle, setting a preset template, and replacing gray level values of corresponding pixel points by using a template median value to filter high-frequency noise to obtain a smooth image, wherein the preset template is a median filtering template used as a neighborhood operation template, and replacing the value of any point in the digital image by using the median value of each pixel point value in one field of the point to enable adjacent numerical values to be closer to an actual value, so that noise points of the image are eliminated.
Further, the method for judging whether the images match comprises the following steps: and calculating the similarity of the characteristic values of the images to obtain the difference between the images, and judging that the images are matched when the similarity is larger than a preset threshold value.
Further, the preset threshold of the similarity is 0.8.
Still further, the step 3 may be further replaced by: the method comprises the steps of analyzing and processing an image by adopting a first neural network model, wherein the image of a beverage bottle body to be detected is firstly divided into grids of 3 multiplied by 3, and then each grid is matched with a learning label, wherein the learning label is a cover body image data label, and if the center of an object in a detected picture falls into the divided grids, the grids predict the bottle body corresponding to the cover body falling into the grids.
Further, the first neural network model is a YOLO v1 network, and the network structure has 24 convolution layers, 2 full connection layers and one output layer.
The invention further discloses a detection system of the bottle commodity in the container, the image acquisition unit acquires the image of the beverage bottle, and the image of the beverage bottle is preprocessed to obtain a preprocessed image, wherein the preprocessing of the image of the beverage bottle to obtain the preprocessed image further comprises the following steps: carrying out gray level processing on a color image, carrying out gray level range 0-255, carrying out histogram equalization on the gray level image to obtain a gray level histogram of the image of the beverage bottle, setting a preset template, and replacing gray level values of corresponding pixel points by using a template median value to filter high-frequency noise to obtain a smooth image, wherein the preset template is a median filter serving as a template for neighborhood operation, and replacing the value of any point in a digital image by using the median value of each pixel point value in one field of the point to enable adjacent numerical values to be closer to an actual value, so that noise points of the image are eliminated; a cap judging unit for judging whether the beverage bottle body in the image has a cap or not according to the preprocessed image;
the cover body detection and identification unit detects the cover body on the beverage body through a straight line fitting algorithm, a straight line equation 1 where a fixed center point of the cover body and the bottle body is located is obtained through hough conversion, a straight line equation 2 where the cover top of the cover body is located is obtained through a straight line fitting algorithm, the positions of the cover body relative to the bottle body are judged through comparing the narration and intercept of the straight line equation 1 and the straight line equation 2, whether the positions of the cover body relative to the bottle body exceed a preset range value input by a merchant is judged, wherein, assuming that one point (xn, yn) exists in an image space, all straight line equations passing through the point can be expressed as:
y n ＝αx n +β
where α is the slope of the line and β is the intercept of the line;
if the image space has a point (xk, yk) to which there is likewise a straight line in the parameter space, the two straight lines must intersect at a point (α ', β') if they are not parallel lines. The slope and intercept of the straight line represented by (xn, yn) and (xk, yk) in image space are represented at α ', β', respectively; determining a straight line through points (xn, yn) and points (xk, yk), enabling the straight line corresponding to the straight line in the parameter space to pass through points (alpha ', beta'), and converting the detection of the straight line in the image space to the detection of the midpoint in the parameter space through the transformation of a straight line fitting algorithm; identifying the cover body pattern, and if the identified pattern is not the preset pattern of the merchant, jumping to a statistical analysis and alarm unit;
the bottle body identification unit is used for identifying the pattern of the bottle body, determining that the bottle body is a commodity of a merchant if the pattern of the bottle body is identified and judged to be a preset pattern of the merchant, and jumping to the statistical analysis and alarm unit if the pattern of the bottle body is judged not to be the preset pattern of the merchant;
the statistical analysis and alarm unit counts the identified bottles to obtain the number of the bottles which are not merchant commodities, if the detected number of the bottles is larger than a first preset value and smaller than a second preset value, the identified non-merchant commodities are subjected to category statistics, an analysis report of the bid commodity is generated, and if the detected number of the bottles is larger than the second preset value, alarm information is directly sent to a merchant preset terminal.
The invention also discloses an electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps of the above-described method.
The invention also discloses a computer readable storage medium for storing a computer program for execution by a processor to implement the above method.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
While the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the invention. It is therefore intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that it is the following claims, including all equivalents, that are intended to define the spirit and scope of this invention. The above examples should be understood as illustrative only and not limiting the scope of the invention. Various changes and modifications to the present invention may be made by one skilled in the art after reading the teachings herein, and such equivalent changes and modifications are intended to fall within the scope of the invention as defined in the appended claims.
Claims (7)
1. A method for detecting a bottle commodity in a container, the method further comprising:
step 1, acquiring an image of a beverage bottle body, and preprocessing the image of the beverage bottle body to obtain a preprocessed image;
step 2, judging whether the beverage bottle body in the image has a cover body or not according to the preprocessed image, if not, jumping to step 6, and if so, jumping to step 3;
detecting a cover body on a beverage body through a straight line fitting algorithm, solving a straight line equation 1 where a fixed center point of the cover body and the bottle body is located through hough conversion, solving a straight line equation 2 where a cover top of the cover body is located through a straight line fitting algorithm, judging the position of the cover body relative to the bottle body through comparing the narrative rate and intercept of the straight line equation 1 and the straight line equation 2, jumping to the step 6 if judging that the position of the cover body relative to the bottle body exceeds a preset range value input by a merchant, and jumping to the step 4 if the position of the cover body relative to the bottle body does not exceed the preset range value input by the merchant, wherein the step 3 further comprises: assuming that there is a point (xn, yn) in image space, then all straight-line equations passing through this point can be expressed as:
y n ＝αx n +β
where α is the slope of the line and β is the intercept of the line;
providing an image space with a point (xk, yk), and also having a straight line corresponding to the point in the parameter space, if the two straight lines are not parallel lines, the two straight lines certainly intersect at a point (alpha ', beta'), and alpha ', beta' respectively represent the slope and intercept of the straight line represented by (xn, yn) and (xk, yk) in the image space; determining a straight line through points (xn, yn) and points (xk, yk), wherein the straight line corresponding to the straight line through points (alpha ', beta') of the points on the straight line in a parameter space is converted into detection of points in the parameter space through straight line fitting algorithm transformation, and before/after the straight line fitting algorithm positioning, an image is analyzed and processed through a first neural network model, wherein the image of a beverage bottle body to be detected is firstly divided into grids divided into 3X 3, and then each grid is matched with a learning label, the learning label is a cover body image data label, if the center of an object in a detected image falls in the divided grids, the grids predict the bottle body corresponding to the cover body in the detected image, so that double algorithm identification is realized, and a more accurate cover body identification result is obtained;
step 4, identifying the cover body pattern, if the identified pattern is not the preset pattern of the merchant, jumping to step 6, and if the identified pattern is the preset pattern of the merchant, jumping to step 5;
step 5, identifying the pattern of the bottle body, if the identification judges that the pattern of the bottle body is the preset pattern of the merchant, determining that the bottle body is a merchant commodity, jumping back to the step 1 to acquire the images of other bottle bodies again, and if the identification judges that the pattern of the bottle body is not the preset pattern of the merchant, jumping to the step 6;
and 6, counting the identified bottles to obtain the number of the bottles which are not merchant commodities, counting the types of the identified non-merchant commodities if the detected number of the bottles is larger than a first preset value and smaller than a second preset value, generating an analysis report of the bid commodity, and directly sending alarm information to a merchant preset terminal if the detected number of the bottles is larger than the second preset value.
2. The method of claim 1, wherein the preprocessing the image of the beverage bottle to obtain a preprocessed image further comprises: and carrying out gray level processing on the color image, carrying out histogram equalization on the gray level image to obtain a gray level histogram of the image of the beverage bottle body, setting a preset template, and replacing gray level values of corresponding pixel points by using a template median value to filter high-frequency noise to obtain a smooth image, wherein the preset template is a median filtering template used as a neighborhood operation template, and replacing the value of any point in the digital image by using the median value of each pixel point value in one field of the point to enable adjacent numerical values to be closer to an actual value, thereby eliminating noise points of the image.
3. The method for detecting a bottle commodity in a container according to claim 2, wherein the method for judging whether the images match comprises: and calculating the similarity of the characteristic values of the images to obtain the difference between the images, and judging that the images are matched when the similarity is larger than a preset threshold value.
4. A method for detecting a bottle commodity in a container according to claim 3, wherein said predetermined threshold value of similarity is 0.8.
5. The method of claim 4, wherein the first neural network model is a YOLO v1 network having 24 convolutional layers, 2 fully-connected layers, and an output layer.
6. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-5.
7. A computer readable storage medium for storing a computer program for execution by a processor to implement the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111683403.7A CN114359882B (en) | 2021-12-31 | 2021-12-31 | Method and system for detecting bottle commodity in container |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111683403.7A CN114359882B (en) | 2021-12-31 | 2021-12-31 | Method and system for detecting bottle commodity in container |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114359882A CN114359882A (en) | 2022-04-15 |
| CN114359882B true CN114359882B (en) | 2024-04-02 |
Family
ID=81105705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111683403.7A Active CN114359882B (en) | 2021-12-31 | 2021-12-31 | Method and system for detecting bottle commodity in container |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114359882B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034442A (en) * | 2006-03-08 | 2007-09-12 | 刘欣融 | System for judging between identical and proximate goods appearance design based on pattern recognition |
| CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
| CN108985305A (en) * | 2018-06-26 | 2018-12-11 | 武汉科技大学 | A kind of positioning of laser-induced thermal etching industrial detonator coded image and bearing calibration |
| WO2019228063A1 (en) * | 2018-05-30 | 2019-12-05 | 京东方科技集团股份有限公司 | Product inspection terminal, method and system, computer apparatus and readable medium |
| CN113239862A (en) * | 2021-05-31 | 2021-08-10 | 艾的梦 | Commodity identification method and device based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11288472B2 (en) * | 2011-08-30 | 2022-03-29 | Digimarc Corporation | Cart-based shopping arrangements employing probabilistic item identification |
-
2021
- 2021-12-31 CN CN202111683403.7A patent/CN114359882B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034442A (en) * | 2006-03-08 | 2007-09-12 | 刘欣融 | System for judging between identical and proximate goods appearance design based on pattern recognition |
| CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
| WO2019228063A1 (en) * | 2018-05-30 | 2019-12-05 | 京东方科技集团股份有限公司 | Product inspection terminal, method and system, computer apparatus and readable medium |
| CN108985305A (en) * | 2018-06-26 | 2018-12-11 | 武汉科技大学 | A kind of positioning of laser-induced thermal etching industrial detonator coded image and bearing calibration |
| CN113239862A (en) * | 2021-05-31 | 2021-08-10 | 艾的梦 | Commodity identification method and device based on artificial intelligence |
Non-Patent Citations (3)
| Title |
|---|
| 吴兰兰 ; 陈硕 ; 黄祥斌 ; 陆华 ; .PET瓶封盖缺陷视觉检测算法研究.机电工程.2018,(第05期),全文. * |
| 王斌 ; 汪云路 ; .基于图形识别技术的商品保质提醒技术研究.科技创新与应用.2016,(第29期),全文. * |
| 王睿 ; 武秋敏 ; 李晶 ; 武吉梅 ; .啤酒生产包装中电子监管码的定位算法.包装工程.2017,(第01期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114359882A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985359B (en) | Commodity identification method, unmanned vending machine and computer-readable storage medium | |
| CN109003390B (en) | Commodity identification method, unmanned vending machine and computer-readable storage medium | |
| US10452707B2 (en) | Product auditing in point-of-sale images | |
| US10949665B2 (en) | Reducing scale estimate errors in shelf images | |
| CN111415461A (en) | Article identification method and system and electronic equipment | |
| CN111915572B (en) | Adaptive gear pitting quantitative detection system and method based on deep learning | |
| CN109961101A (en) | Shelf state determines method and device, electronic equipment, storage medium | |
| CN106372564A (en) | Gesture identification method and apparatus | |
| CN111523421B (en) | Multi-person behavior detection method and system based on deep learning fusion of various interaction information | |
| CN115302963B (en) | Bar code printing control method, system and medium based on machine vision | |
| CN112001362A (en) | Image analysis method, image analysis device and image analysis system | |
| CN116910752B (en) | Malicious code detection method based on big data | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| JP2021012692A (en) | Object identification method, system, and electronic apparatus | |
| CN115063084A (en) | Inventory checking method and system for cigarette retail merchants | |
| CN110930087A (en) | Inventory checking method and device | |
| CN114359882B (en) | Method and system for detecting bottle commodity in container | |
| Bai et al. | A hierarchical face recognition method based on local binary pattern | |
| CN116434266A (en) | Automatic extraction and analysis method for data information of medical examination list | |
| CN111199228A (en) | License plate positioning method and device | |
| CN115690514A (en) | Image recognition method and related equipment | |
| CN111414930A (en) | Deep learning model training method and device, electronic equipment and storage medium | |
| CN114332602A (en) | Commodity identification method of intelligent container | |
| CN110110594B (en) | Product distribution identification method and device | |
| CN113298100A (en) | Data cleaning method, self-service equipment and storage medium |
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 |