CN112307828A - Count verification device, count system and method - Google Patents
Count verification device, count system and method Download PDFInfo
- Publication number
- CN112307828A CN112307828A CN201910700271.0A CN201910700271A CN112307828A CN 112307828 A CN112307828 A CN 112307828A CN 201910700271 A CN201910700271 A CN 201910700271A CN 112307828 A CN112307828 A CN 112307828A
- Authority
- CN
- China
- Prior art keywords
- counting
- weighing
- counted
- error
- image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012795 verification Methods 0.000 title claims abstract description 9
- 238000005303 weighing Methods 0.000 claims abstract description 98
- 238000009826 distribution Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000003860 storage Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 description 16
- 238000004806 packaging method and process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000003708 edge detection Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 206010049040 Weight fluctuation Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/40—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight
- G01G19/42—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight for counting by weighing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a counting and checking device, a counting system and a counting method, wherein the counting and checking device comprises: the processing unit is used for carrying out image recognition counting on the image of the counted object; the calculating unit is used for weighing and counting according to the weighing total weight of the counted object and pre-stored mass distribution information; the judging unit is used for judging whether the number of the image identification counts is within the counting error range of the number of the weighing counts according to the mass distribution information; if so, judging that the image recognition counting number is the counting number of the counted object, otherwise, the processing unit carries out image recognition counting again. By the counting verification device, the counting system and the counting method, the accuracy of counting articles can be improved.
Description
Technical Field
The invention relates to the technical field of counting, in particular to a counting checking device, a counting system and a counting method.
Background
The counting of articles is widely applied to the production statistics, the packaging operation and the like of articles in various industries such as food, medicine, daily chemical products, hardware and the like. Compared with the traditional manual counting statistics, the automatic counting system has high working efficiency and accuracy and is suitable for batch industrial operation.
The principle of weighing and counting is to calculate the total weight of an item divided by its average weight based on the average weight of that type of item measured beforehand by weighing the total weight of a number of items. For weighing counting, it is necessary to obtain an average weight of the type of article. The accuracy of the weight count may be affected by the pre-stored average weight.
The average weight of the articles is a statistic of historical average weight data, and even under the same production process, the average weight of products produced in different batches can be different. Therefore, whether the weight distribution in the statistical data is the same as that of the currently counted product will affect the accuracy of weighing and counting.
And the image counting adopts an image recognition technology to obtain the image of the counted object, and the image recognition model is used for image processing to finally calculate the counting result. Image counting can be affected by factors such as the state of distribution of the items being counted. If the counted articles touch each other, the accuracy of the counting result is also affected by the overlapping condition.
Disclosure of Invention
The invention aims to solve the technical problem of the existing weighing counting and image recognition counting, and provides a counting system capable of improving the counting accuracy of articles.
In order to solve the above technical problem, the present invention provides a counting and checking device, including: the processing unit is used for carrying out image recognition counting on the image of the counted object; the calculating unit is used for weighing and counting according to the weighing total weight of the counted object and pre-stored mass distribution information; the judging unit is used for judging whether the number of the image identification counts is within the counting error range of the number of the weighing counts according to the mass distribution information; if so, judging that the image recognition counting number is the counting number of the counted object, otherwise, the processing unit carries out image recognition counting again.
Preferably, the calculating unit is further configured to calculate an average weight AW of the object to be counted when the determination result of the determining unit is yesold+K×(AWold-AWnew) And updating the pre-stored mass distribution information; wherein the content of the first and second substances,
w is the weighed total weight of the counted objects, and N is the image identification counting number of the counted objects; AWoldK is a predetermined convergence factor, AW, for the raw average weight obtained from the mass distribution informationnewIs the average weight of the objects being counted.
Preferably, the counting error of the number of the weighing counts includes a counting error allowed by a statistical error, and the counting error allowed by the statistical error is as follows:
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1); wherein, A is a preset credibility multiple index, σ is a standard deviation obtained according to the mass distribution information, N is the image identification counting number of the counted object, AW is the original average weight obtained according to the mass distribution information, and N' is the weighing counting number of the counted object.
Preferably, the counting error of the weighing and counting number further includes an allowable counting error of the weighing error, and the allowable counting error of the weighing error is as follows: +/-C/AW; the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1); wherein, C is the weighing precision error of the weighing equipment.
In order to solve the above counting problem, the present invention further discloses a counting system, including the above counting verification apparatus, further including: an image pickup device for acquiring an image of a counted object; the weighing device is used for acquiring the weighing total weight of the counted object; and the storage device is used for storing the mass distribution data of the counted objects.
Preferably, the counting system further comprises: and the vibration device is used for vibrating the placing platform of the counted object before the processing unit carries out image recognition counting again.
Preferably, the placing platform of the counted objects is provided with a plurality of grooves suitable for the counted objects to fall into, or a plurality of bulges suitable for the counted objects to separate.
In order to solve the above technical problem, the present invention also discloses a counting method, comprising: acquiring an image of a counted object, and identifying the number of the counted object in the image; weighing and counting the counted objects; judging whether the image counting number of the counted object is within the counting error range of the weighing counting number according to the pre-stored mass distribution information; if so, taking the image counting number as the counting result of the counted object; and if not, the image recognition counting is carried out again.
Preferably, the above counting method, after determining that the counted number of images of the object to be counted is within the counting error range of the weighed number, further includes: calculating the average weight AW of the counted objectold+K×(AWold-AWnew) And updating the pre-stored mass distribution information; wherein the content of the first and second substances,
AWoldk is a predetermined convergence factor, AW, for the raw average weight obtained from the mass distribution informationnewW is the average weight of the counted objects, W is the weighed total weight of the counted objects, and N is the image recognition counting number of the counted objects.
Preferably, the counting error of the number of the weighing counts includes a counting error allowed by a statistical error, and the counting error allowed by the statistical error is as follows:
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1); wherein, A is a preset credibility multiple index, σ is a standard deviation obtained according to the mass distribution information, N is the image identification counting number of the counted object, AW is the original average weight obtained according to the mass distribution information, and N' is the weighing counting number of the counted object.
Preferably, the counting error of the weighing and counting number further includes an allowable counting error of the weighing error, and the allowable counting error of the weighing error is as follows: +/-C/AW; the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1); wherein, C is the weighing precision error of the weighing equipment.
Preferably, before the image recognition and counting are performed again, the counting method further includes: the placing platform of the counted object is vibrated.
The positive progress effects of the invention are as follows:
the counting system performs counting verification by combining two counting modes of image identification counting and weighing counting, on one hand, the image identification counting can reflect the actual condition that the current quality part condition of a counted object changes along with the change of the production condition, and the problem of weighing counting is solved; on the other hand, by using weighing counting as a comparison standard, the situation that image recognition is possibly wrong due to the influence of factors such as the spreading state of the counted object can be overcome, and the accuracy and the reliability of the counting result are ensured.
Certain terms are used throughout the description and claims to refer to particular system components. As one skilled in the art will appreciate, different usage objects may represent the same component by different names. Components that differ in name but not function are not distinguished herein and are intended to be within the scope of the present invention.
Drawings
FIG. 1 is a schematic structural diagram of a counting system according to an embodiment of the present invention;
fig. 2 is a flowchart of a counting method according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Example 1
When the packaging production line carries out counting and packaging, a plurality of products to be packaged are conveyed to the counting system through the conveying belt in sequence, and the counting system carries out weighing and counting. As shown in fig. 1, the counting system includes: the device comprises a scale, a camera, a counting and checking device, a storage device and a vibrating device. The counting and checking device comprises a processing unit, a calculating unit and a judging unit. The storage device stores the mass distribution information of each type of product. The quality distribution information is statistical data information formed according to the weight data distribution of the product collected from the production process, such as average weight of the product, standard deviation and the like, and reflects the production weight fluctuation of the product.
And the counting system shoots the images of the batch of products through the camera. After the counting and checking device obtains the shot image, the processing unit applies an image recognition technology to perform image processing on the obtained image through an image recognition model of the detected product so as to recognize the number of the products in the image, and the image processing method may include: and carrying out gray level processing on the obtained image, and carrying out image enhancement through median filtering so as to improve the image definition and the image quality. Then, the image is subjected to binarization and threshold processing, the enhanced image obtained in the previous step is converted into a black-and-white binary image, so that a clearer edge contour line can be obtained, and meanwhile, image segmentation is carried out to extract a target feature required by identification. And finally, after the edge of the product is identified through an edge detection algorithm, such as a Canny edge detection operator, calculating a counting result through an identification function, such as automatically identifying connected domains in the image by using a Bwlabel function and calculating the number, so as to obtain an image counting value N.
The counting system weighs the product to be packaged through a scale to obtain the total weight W of the product to be packaged, meanwhile, the pre-stored average weight AW of the product is obtained in the storage device, and then the weighing counting result of the product is obtained through calculation of the calculating unit
The counting system judges whether the difference between the image count N and the weighing count N' is within the counting error range through a judging unit. If the difference between the image counting number N and the weighing counting number N' of the product is larger and exceeds the counting error range determined by the standard deviation data of the mass distribution information of the product, the judging unit judges that the image counting has counting errors. For example, if the number of counts obtained by the weighing count is 30 and the determined count error range is ± 2, and the number of counts obtained by the image count is 26, it is determined that the image count is erroneous. At this moment, can pass through vibrating device vibration place the platform, it spreads the state to make through the vibration between waiting to pack the product, perhaps reports the wrong suggestion through the suggestion device on the packaging production line, by the direct product of laying flat place the platform with manual mode of operating personnel on, makes the product not contact the back each other, carries out image recognition count again to and verify each other with the count result of weighing.
The counting error of the weighing count number may include a counting error allowed by the statistical error and an allowable counting error of the weighing error. Because the mass distribution information is only statistical analysis data, components of the same type can have certain objective errors with the weighing mean AW in production, and therefore the calculation module of the object identification data processing device obtains the statistical standard deviation sigma according to the mass distribution information of the target components; and meanwhile, obtaining an error interval +/-A sigma of a single component through the credibility multiple index A multiplied by the standard deviation sigma according to a preset credibility multiple index A. Then, error intervals of a plurality of captured components are obtained by calculating the error interval multiplied by the image recognition count value N, namely +/-A sigma N, and finally, the error intervals are calculated by the method
Resulting in a count error that is allowed due to statistical errors.
Meanwhile, considering that a certain device measurement error exists in the weighing of the scale serving as the weighing device, the calculation module obtains the weighing precision error C of the scale according to the specification parameters of the scale in the storage device, for example, the precision error C of the scale is 0.05g, namely ± 0.05g, so as to further calculate the allowable counting error due to the weighing error of the weighing device itself as: + -C/AW.
The judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1), i.e., whether or not
In this equation, if the number N of image recognition counts is a true value, the equation is established, and therefore, the number N of image recognition counts can be verified. If the formula is true, then judgeDetermining the number of the image recognition counts to be within the counting error range of the number of the weighing counts; otherwise, the counting error range is judged to be out of the counting error range.
If the image counting number N of the product is within the error range of the weighing counting number N ', the condition that the mass distribution information of the product changes along with the production condition in real time can be reflected more due to the fact that the image counting number N is relative to the weighing counting number N', so that the image counting number N is judged to be the number of the product, and whether the image counting number N reaches the preset standard packaging number is detected. If so, the number of objects to be packaged is packaged by the packaging line. And if not, counting calculation is carried out after the follow-up products are supplemented through the conveyor belt.
This embodiment 1 treats the article of weighing through two kinds of counting modes of image recognition count and weighing count and carries out two count check-ups to can verify image count or weighing count's result, both avoid the problem that the detection counting performance that image recognition count exists receives the influence of object scattering state, also avoid weighing count can't change and real-time update according to product production situation and lead to the change of product weight distribution data, thereby guaranteed the accuracy of counting result in the packing production.
It can be understood by those skilled in the art that the counting system of the embodiment 1 can be applied not only to the packaging and counting operation of products, but also to the double counting verification of image counting and weighing counting in other scenes where counting and counting of articles are required, and also falls within the protection scope of the present invention.
Example 2
After the production line finishes the production of a certain batch of products, the batch of products is conveyed to the counting system, the counting system is used for weighing and counting the batch of products to calculate the average weight of the products, and then data updating is carried out on the average weight of the products which is prestored, so that the accuracy and the real-time performance of the average weight data are ensured. The counting system comprises: the device comprises a scale, a camera, a counting and checking device, a storage device and a vibrating device. The counting and checking device comprises a processing unit, a judging unit and a calculating unit. The storage device stores the mass distribution information of each type of product. The mass distribution information is statistical data information formed according to the weight data distribution condition of the product collected from the production process, such as average weight of the product, standard deviation and other data, and reflects the production weight fluctuation of the component.
The placing platform of the product is provided with a plurality of grooves. The counting system firstly vibrates the placing platform where the batch of products are located through the vibrating device, so that the products are not touched with each other due to vibration, and the grooves formed in the placing platform can fall into the placing platform when the single product is vibrated to move, so that the products are further prevented from being touched with each other. And after the vibration is finished, the counting system performs subsequent identification and counting on the product.
As a modification, a plurality of protrusions may be provided on the placement platform of the products, so as to achieve the same separation and dispersion among the products when the products are vibrated and moved by the vibration device during the vibration operation.
And the counting system shoots the images of the batch of products through the camera. After the counting and checking device acquires the shot images, the processing unit applies an image recognition technology to perform image processing on the acquired images through an image recognition model of the detected products so as to recognize the number of the products in the images, and the method comprises the following steps: and carrying out gray level processing on the obtained image, and carrying out image enhancement through median filtering so as to improve the image definition and the image quality. Then, the image is subjected to binarization and threshold processing, the enhanced image obtained in the previous step is converted into a black-and-white binary image, so that a clearer edge contour line can be obtained, and meanwhile, image segmentation is carried out to extract a target feature required by identification. And finally, after the edge recognition of the product is finished through an edge detection algorithm, such as a Canny edge detection operator, calculating a counting result through a recognition function, such as automatically recognizing connected domains in the image by using a Bwlabel function and calculating the number.
The counting system weighs the product to be packaged through a scale to obtain the product to be packagedThe total weight W of the product is obtained, and meanwhile, the prestored original average weight AWold of the product is obtained in the storage device, and then the weighing counting result of the product is obtained through calculation
The counting system judges whether the difference between the image counting number N and the weighing counting number N' is within the counting error range through a judging unit. If the image count number N and the weighing count number N' of the product are greatly different, for example, beyond the count error range determined by the standard deviation data of the mass distribution information of the product, it is determined that there is an abnormality in the image count. For example, if the number of counts obtained by the weight counting is 30 and the range of the error of the count is ± 2 is determined from the standard deviation σ, and the number of counts obtained by the image counting is 26, it is determined that the image counting is erroneous. At this time, the placing platform can be vibrated again through the vibrating device, or the products on the placing platform are directly paved in a manual mode by an operator, so that the products are not contacted with each other, and then the image recognition counting is carried out again.
If the judging unit judges that the image count N is within the counting error range of the weighing count N', the calculating unit calculates the average weight of the batch of products according to the obtained weight W of the batch of products and the image counting result N
And based on the average weight AWnewCalculating the average weight AW of the type of product stored in said storage means, making AW equal to AWold+K×(AWold-AWnew). Wherein K is a preset convergence coefficient. After calculating the average weight AW of the type of product, the original average weight AW in the storage device is updatedoldAnd corresponding mass distribution information.
This example is carried out on the average weight AWoldAfter updating, the counting system can calculate the weighing count number according to the latest average weight calculation AW when the subsequent weighing count of the product of the type is carried out. Thus, mean weight AW data can be guaranteedThe real-time updating can be carried out according to the fluctuation condition of actual production, so that the accuracy of weighing and counting is improved.
It can be understood by those skilled in the art that the present embodiment 2 and the embodiment 1 are based on the same inventive concept, and the corresponding contents of the embodiment 1 can be referred to with respect to the present embodiment 2, and the two can be combined and supplemented with each other.
Example 3
The counting method of this embodiment can be applied to the counting system of the above embodiment 1 or 2 to complete counting statistics of the objects to be counted. As shown in fig. 2, the counting method includes:
in step S101, an image of the counted object is acquired.
The counting system takes images of the batch of products through a camera therein. Before image shooting, the placing platform of the objects to be counted can be vibrated by the vibrating device of the counting system, so that the objects to be counted are in a scattered state without contacting each other.
In step S102, the number of objects to be counted in the image to be counted is identified.
After the captured image is obtained, image recognition technology is applied, and image processing is performed on the obtained image through an image recognition model of the detected product so as to identify the number of products in the image, wherein the image recognition technology comprises the following steps: and carrying out gray level processing on the obtained image, and carrying out image enhancement through median filtering so as to improve the image definition and the image quality. Then, the image is subjected to binarization and threshold processing, the enhanced image obtained in the previous step is converted into a black-and-white binary image, so that a clearer edge contour line can be obtained, and meanwhile, image segmentation is carried out to extract a target feature required by identification. And finally, after edge recognition of the product is finished through an edge detection algorithm, such as a Canny edge detection operator, calculating a counting result through a recognition function, such as automatically recognizing a connected domain in the image by using a Bwlabel function and calculating the number, and obtaining an image counting value N.
And step S103, weighing and counting the objects to be counted.
The counting system passes through the balance pairAnd weighing the product to be packaged to obtain the total weight W of the product to be packaged. Meanwhile, the mass distribution data of the product prestored in the storage device of the counting system can obtain corresponding statistical information such as the average weight AW and the standard deviation sigma of the counted object through the mass distribution data, so that the weighing and counting result of the product is calculated
And step S104, judging whether the image counting number of the counted object is within the counting error range of the weighing counting number.
The standard deviation sigma can be obtained according to the mass distribution information of the counted object, so as to determine the counting error of the object, and whether N is in the range of the counting error of N' is compared. If so, the process proceeds to step S105, otherwise, the process proceeds to step S106.
In step S105, the counted number of images is used as the counting result of the counted object.
After determining the image count number as the final count result, the packaging operation can be further performed as in embodiment 1 or 2, or the average weight of the counted object can be calculated for data update.
Step S106, vibrating the placing platform or prompting to pave the counted object.
If the image counting number N is not within the range of the counting error of the weighing counting number N', the image counting has a high probability of errors, at the moment, the placing platform can be vibrated again through the vibrating device, or a paving prompt is sent through the prompting device, the products on the placing platform are directly paved in a manual mode by an operator, and after the products are not contacted with each other, the image recognition counting is started again in the step S101.
Since this embodiment 3 is based on the same inventive concept as embodiments 1 and 2, the content of this embodiment can refer to the corresponding content of embodiments 1 and 2, and is not described herein again.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored on a computer readable medium, which may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
While the invention has been described with reference to a number of specific embodiments, it will be understood by those skilled in the art that the foregoing embodiments are merely illustrative of the invention, and various changes in and substitutions of equivalents may be made without departing from the spirit of the invention. Therefore, changes and modifications to the above-described embodiments within the spirit and scope of the present invention will fall within the scope of the claims of the present application.
Claims (12)
1. A count verification device, comprising:
the processing unit is used for carrying out image recognition counting on the image of the counted object;
the calculating unit is used for weighing and counting according to the weighing total weight of the counted object and pre-stored mass distribution information;
the judging unit is used for judging whether the number of the image identification counts is within the counting error range of the number of the weighing counts according to the mass distribution information; if so, judging that the image recognition counting number is the counting number of the counted object, otherwise, the processing unit carries out image recognition counting again.
2. The count verification apparatus according to claim 1, wherein the calculation unit is further configured to calculate an average weight AW of the counted object when the determination result of the determination unit is yesold+K×(AWold-AWnew) And updating the pre-stored mass distribution information;
wherein the content of the first and second substances,
w is the total weight of the objects to be counted and N is the weight of the objects to be countedIdentifying and counting the number of the images; AWoldK is a predetermined convergence factor, AW, for the raw average weight obtained from the mass distribution informationnewIs the average weight of the objects being counted.
3. The count checking apparatus of claim 1,
the counting error of the weighing counting number comprises a counting error allowed by a statistical error, and the counting error allowed by the statistical error is as follows:
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1);
wherein, A is a preset credibility multiple index, σ is a standard deviation obtained according to the mass distribution information, N is the image identification counting number of the counted object, AW is the original average weight obtained according to the mass distribution information, and N' is the weighing counting number of the counted object.
4. The count checking apparatus of claim 3,
the counting error of the weighing and counting number further comprises an allowable counting error of the weighing error, and the allowable counting error of the weighing error is as follows: +/-C/AW;
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1);
wherein, C is the weighing precision error of the weighing equipment.
5. A counting system comprising the count verification apparatus as claimed in any one of claims 1 to 4, further comprising:
an image pickup device for acquiring an image of a counted object;
the weighing device is used for acquiring the weighing total weight of the counted object;
and the storage device is used for storing the mass distribution data of the counted objects.
6. The counting system of claim 5, further comprising: and the vibration device is used for vibrating the placing platform of the counted object before the processing unit carries out image recognition counting again.
7. The counting system of claim 5, wherein the placing platform of the counted objects is provided with a plurality of grooves adapted for the counted objects to fall into or a plurality of protrusions adapted for being separated by the counted objects.
8. A counting method, comprising:
acquiring an image of a counted object, and identifying the number of the counted object in the image;
weighing and counting the counted objects;
judging whether the image counting number of the counted object is within the counting error range of the weighing counting number according to the pre-stored mass distribution information; if so, taking the image counting number as the counting result of the counted object; and if not, the image recognition counting is carried out again.
9. The counting method of claim 8, further comprising, after determining that the counted number of images of the object to be counted is within a count error of the counted number of weighing,:
calculating the average weight AW of the counted objectold+K×(AWold-AWnew) And updating the pre-stored mass distribution information;
wherein，
AWoldK is a predetermined convergence factor, AW, for the raw average weight obtained from the mass distribution informationnewW is the average weight of the counted objects, W is the weighed total weight of the counted objects, and N is the image recognition counting number of the counted objects.
10. The counting method of claim 8,
the counting error of the weighing counting number comprises a counting error allowed by a statistical error, and the counting error allowed by the statistical error is as follows:
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1);
wherein, A is a preset credibility multiple index, σ is a standard deviation obtained according to the mass distribution information, N is the image identification counting number of the counted object, AW is the original average weight obtained according to the mass distribution information, and N' is the weighing counting number of the counted object.
11. The counting method of claim 10,
the counting error of the weighing and counting number further comprises an allowable counting error of the weighing error, and the allowable counting error of the weighing error is as follows: +/-C/AW;
the judging whether the image identification counting number is within the counting error range of the weighing counting number comprises the following steps: calculating whether N' falls on
Within the range of (1);
wherein, C is the weighing precision error of the weighing equipment.
12. The counting method of claim 8, further comprising, before resuming image recognition counting: the placing platform of the counted object is vibrated.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910700271.0A CN112307828A (en) | 2019-07-31 | 2019-07-31 | Count verification device, count system and method |
| PCT/CN2020/101599 WO2021017797A1 (en) | 2019-07-31 | 2020-07-13 | Counting check device,counting system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910700271.0A CN112307828A (en) | 2019-07-31 | 2019-07-31 | Count verification device, count system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112307828A true CN112307828A (en) | 2021-02-02 |
Family
ID=74228543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910700271.0A Pending CN112307828A (en) | 2019-07-31 | 2019-07-31 | Count verification device, count system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112307828A (en) |
| WO (1) | WO2021017797A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407571A (en) * | 2021-06-30 | 2021-09-17 | 重庆博尔德医疗科技股份有限公司 | Counting method based on weighing principle |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937791B (en) * | 2023-01-10 | 2023-05-16 | 华南农业大学 | Poultry counting method and device suitable for multiple cultivation modes |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012173901A (en) * | 2011-02-21 | 2012-09-10 | Midori Seimitsu:Kk | Method and device for counting number of steel material in bound steel material bundle |
| JP2012232075A (en) * | 2011-05-09 | 2012-11-29 | Sankyo Co Ltd | Commodity transaction device |
| CN103308430A (en) * | 2013-06-03 | 2013-09-18 | 浙江大学 | Method and device for measuring weight of thousand of seeds |
| JP2015118630A (en) * | 2013-12-19 | 2015-06-25 | 株式会社寺岡精工 | Article-of-commerce sales data processing device |
| CN107300408A (en) * | 2017-08-07 | 2017-10-27 | 赵思俨 | A kind of combination image procossing and the examination paper counting equipment and examination paper method of counting of weight calculation |
| CN207352653U (en) * | 2017-10-17 | 2018-05-11 | 天津市农业科学院信息研究所 | Kind grain based on intelligent mobile terminal counts metering device |
| CN108537994A (en) * | 2018-03-12 | 2018-09-14 | 深兰科技（上海）有限公司 | View-based access control model identifies and the intelligent commodity settlement system and method for weight induction technology |
| CN108876268A (en) * | 2018-09-12 | 2018-11-23 | 严丽君 | A kind of weighing of smart electronics counts system of examining goods |
| CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
| CN109636824A (en) * | 2018-12-20 | 2019-04-16 | 巢湖学院 | A kind of multiple target method of counting based on image recognition technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8459092B2 (en) * | 2011-05-09 | 2013-06-11 | Mettler-Toledo, LLC | Checkweigher performance validation |
| CN107820010B (en) * | 2017-11-17 | 2020-11-06 | 英业达科技有限公司 | Photographic counting device |
-
2019
- 2019-07-31 CN CN201910700271.0A patent/CN112307828A/en active Pending
-
2020
- 2020-07-13 WO PCT/CN2020/101599 patent/WO2021017797A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012173901A (en) * | 2011-02-21 | 2012-09-10 | Midori Seimitsu:Kk | Method and device for counting number of steel material in bound steel material bundle |
| JP2012232075A (en) * | 2011-05-09 | 2012-11-29 | Sankyo Co Ltd | Commodity transaction device |
| CN103308430A (en) * | 2013-06-03 | 2013-09-18 | 浙江大学 | Method and device for measuring weight of thousand of seeds |
| JP2015118630A (en) * | 2013-12-19 | 2015-06-25 | 株式会社寺岡精工 | Article-of-commerce sales data processing device |
| CN107300408A (en) * | 2017-08-07 | 2017-10-27 | 赵思俨 | A kind of combination image procossing and the examination paper counting equipment and examination paper method of counting of weight calculation |
| CN207352653U (en) * | 2017-10-17 | 2018-05-11 | 天津市农业科学院信息研究所 | Kind grain based on intelligent mobile terminal counts metering device |
| CN108537994A (en) * | 2018-03-12 | 2018-09-14 | 深兰科技（上海）有限公司 | View-based access control model identifies and the intelligent commodity settlement system and method for weight induction technology |
| CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
| CN108876268A (en) * | 2018-09-12 | 2018-11-23 | 严丽君 | A kind of weighing of smart electronics counts system of examining goods |
| CN109636824A (en) * | 2018-12-20 | 2019-04-16 | 巢湖学院 | A kind of multiple target method of counting based on image recognition technology |
Non-Patent Citations (3)
| Title |
|---|
| LIZHENG LIU等: "A Smart Unstaffed Retail Shop Based on Artificial Intelligence and IoT", 《2018 IEEE 23RD INTERNATIONAL WORKSHOP ON COMPUTER AIDED MODELING AND DESIGN OF COMMUNICATION LINKS AND NETWORKS (CAMAD)》, 1 November 2018 (2018-11-01), pages 1 - 4 * |
| 王文静等: "基于计算机视觉的鱼苗自动计数系统研究", 《渔业现代化》, vol. 43, no. 3, 20 June 2016 (2016-06-20), pages 34 - 38 * |
| 薛彦冰: "基于机器视觉的棒材计数系统研究与实现", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 10, 15 October 2014 (2014-10-15), pages 138 - 1127 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407571A (en) * | 2021-06-30 | 2021-09-17 | 重庆博尔德医疗科技股份有限公司 | Counting method based on weighing principle |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021017797A1 (en) | 2021-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111861306B (en) | Robot system with automated package registration mechanism and automated inspection assembly line | |
| CN108335408B (en) | Article identification method, device and system for vending machine and storage medium | |
| CN110980197B (en) | Material detection method and device and electronic equipment | |
| CN112036755B (en) | Supervision method and system for quality detection of building engineering | |
| US20240157566A1 (en) | Post-detection refinement based on edges and multi-dimensional corners | |
| CN105205431A (en) | Two-dimensional code automatic correction system and method in packaging process | |
| CN106584800A (en) | Formed product on-line quality detection method | |
| CN112307828A (en) | Count verification device, count system and method | |
| CN107063099A (en) | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system | |
| US11783471B2 (en) | Method and device for determining whether object includes defect | |
| WO2021017796A1 (en) | Object recognition apparatus, system and method | |
| CN107263830B (en) | Forming system | |
| CN116846162B (en) | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium | |
| CN113850244B (en) | Coal conveying quantity monitoring method, device and equipment based on image recognition and storage medium | |
| CN108091584A (en) | For checking the method, apparatus and system of semiconductor core flake products stacking | |
| CN115218790A (en) | Bar detection method, device and system | |
| CN114972234B (en) | Edible fungus quality monitoring method and system | |
| WO2019210297A1 (en) | System and method for egg quality control | |
| CN111640096B (en) | Method, device and terminal for detecting appearance of electronic product | |
| CN115744092A (en) | Flexible vibration disc based on voice coil motor and material screening method | |
| CN115147236A (en) | Processing method, processing device and electronic equipment | |
| CN111783529B (en) | Post-detection improvement based on edges and multi-dimensional corners | |
| CN112070473A (en) | Data processing method and device based on engineering project | |
| CN105930851A (en) | Method for carrying out target contour identification on video image of moving object | |
| CN112785100A (en) | Product detection threshold setting device, method and computer readable 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 |