CN113780074A - Method and device for detecting quality of wrapping paper and storage medium - Google Patents
Method and device for detecting quality of wrapping paper and storage medium Download PDFInfo
- Publication number
- CN113780074A CN113780074A CN202110889489.2A CN202110889489A CN113780074A CN 113780074 A CN113780074 A CN 113780074A CN 202110889489 A CN202110889489 A CN 202110889489A CN 113780074 A CN113780074 A CN 113780074A
- Authority
- CN
- China
- Prior art keywords
- image
- roll paper
- package
- image recognition
- recognition model
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 29
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for detecting the quality of a roll paper package, and a storage medium, wherein the method comprises the steps of acquiring a first image of the roll paper package in the roll paper, wherein the first image comprises a circular surface of the roll paper in the roll paper package in the roll paper; performing feature extraction on the first image to obtain image features, and performing image identification according to the image features to obtain the number of circular surfaces; comparing the number of the circular surfaces with the number standard value to obtain a quality detection result of the roll paper middle package; the image recognition technology can be used for intelligently and quickly detecting the quality of the paper in the roll paper, so that the manpower resource is saved, and the production efficiency is improved.
Description
Technical Field
The invention relates to the field of intelligent detection, in particular to a method and a device for detecting the quality of a package in roll paper and a storage medium.
Background
In current stock form automated production workshop, need pack into through the stock form chartered plane or artifical with a plurality of stock forms packing into and carry out shipment, in packaging process, can appear stock form figure lack or the stock form and place the incorrect quality problem of orientation. At present, quality detection in the roll paper mainly detects through manual work, and the workman can only detect package in the roll paper on two transmission belts simultaneously usually, and the transmission speed on the transmission belt can not be too fast, otherwise people's eye is difficult to see clearly package in the roll paper, and the method of manual work detection has extravagant manpower resources, the shortcoming of inefficiency.
Disclosure of Invention
The present invention has been made to solve at least one of the problems occurring in the prior art, and an object of the present invention is to provide a method and an apparatus for detecting the quality of a package in roll paper, and a storage medium.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect of the present invention, a method for detecting a quality of a package in roll paper includes:
acquiring a first image of a roll paper middle package, wherein the first image comprises the round surfaces of all roll paper in the roll paper middle package;
performing feature extraction on the first image to obtain image features, and performing image identification according to the image features to obtain the number of the circular surfaces contained in the first image;
and comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the middle package in the roll paper.
According to the first aspect of the present invention, before the step of extracting the feature of the first image to obtain the image feature, the method further includes:
performing data enhancement on the first image, the data enhancement comprising one or more of random cropping, random rotation, and color dithering.
According to the first aspect of the present invention, the extracting the feature of the first image to obtain the image feature, and performing image recognition according to the image feature to obtain the number of the circular surfaces included in the first image includes:
inputting the first image to an image recognition model constructed based on a deep neural network;
performing feature extraction on the first image through a convolution layer of the image recognition model to obtain image features;
obtaining a plurality of candidate regions according to the image characteristics through a region generation layer of the image recognition model;
compressing the candidate region through the region-of-interest pooling layer of the image recognition model, and obtaining target characteristics according to the compressed candidate region;
and classifying the target features through a full connection layer of the image recognition model to obtain the number of the circular surfaces contained in the first image.
According to the first aspect of the present invention, before the step of extracting the feature of the first image to obtain the image feature and performing image recognition according to the image feature to obtain the number of the circular surfaces included in the first image, the method further includes:
manually marking the plurality of first images to obtain a plurality of marked images corresponding to the first images, wherein the marked images are marked with the type and the position information of the circular surface;
dividing the labeled image into a training data set, a test data set and a verification data set;
training the image recognition model through the training data set and the testing data set to optimize parameters of the image recognition model, and verifying the image recognition model through the verification data set.
In a second aspect of the present invention, a package-in-roll quality detection apparatus includes:
an image acquisition unit configured to acquire a first image of a roll paper wrapper, the first image including circular faces of all roll papers in the roll paper wrapper;
the image recognition unit is used for performing feature extraction on the first image to obtain image features, and performing image recognition according to the image features to obtain the number of the circular surfaces contained in the first image;
and the detection unit is used for comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the roll paper.
According to a second aspect of the present invention, the package-in-roll quality detection apparatus further includes a data enhancement unit configured to perform data enhancement on the first image in a process of training the image recognition model, the data enhancement including one or more of random cropping, random rotation, and color dithering.
According to a second aspect of the present invention, the image recognition unit includes an image recognition model constructed based on a deep neural network, the image recognition model including an input layer, a convolutional layer, a region generation layer, a region-of-interest pooling layer, and a full-link layer;
the input layer is used for inputting the first image;
the convolution layer is used for carrying out feature extraction on the first image to obtain image features;
the region generation layer is used for obtaining a plurality of candidate regions according to the image features;
the interested region pooling layer is used for compressing the candidate region and obtaining target characteristics according to the compressed candidate region;
the full-connection layer is used for classifying the target features to obtain the number of the circular surfaces contained in the first image.
According to a second aspect of the present invention, the package quality detection apparatus in roll paper further includes a training unit including a marking unit, a diversity unit, and a training subunit;
the marking unit is used for manually marking the plurality of first images to obtain a plurality of marked images corresponding to the first images, and the marked images are marked with the type and the position information of the circular surface;
the diversity unit is used for dividing the marked image into a training data set, a test data set and a verification data set;
the training subunit is configured to train the image recognition model through the training data set and the test data set to optimize parameters of the image recognition model, and verify the image recognition model through the verification data set.
In a third aspect of the present invention, a quality detection apparatus for wrapping in roll paper includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the quality detection method for wrapping in roll paper according to the first aspect of the present invention when executing the computer program.
In a fourth aspect of the present invention, a storage medium having stored therein executable instructions that when executed by a processor implement the method for detecting a quality of a package in roll paper according to the first aspect of the present invention.
The scheme at least has the following beneficial effects: because the circular surface of the roll paper is easier to detect and identify relative to the arc-shaped side surface of the roll paper, the identification efficiency and the identification accuracy can be improved by detecting the circular surface of the roll paper; the number of the circular surfaces can be identified according to a first image containing the circular surfaces of all the roll paper in the roll paper package by using an image identification technology, and whether the roll paper package is increased or omitted is judged according to the number of the identified circular surfaces; it can detect package quality in the stock form intelligently, swiftly, has saved manpower resources, has improved production efficiency.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flowchart of a package quality detection method in roll paper according to an embodiment of the present invention;
FIG. 2 is a structural view of a package quality detecting apparatus in roll paper according to an embodiment of the present invention;
fig. 3 is a structural diagram of an image recognition model.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
Referring to fig. 1, an embodiment of a first aspect of the present invention provides a method for detecting a quality of a package in roll paper.
The quality detection method for the roll paper package comprises the following steps:
s100, acquiring a first image of a roll paper package in the roll paper, wherein the first image comprises the circular surfaces of all roll paper in the roll paper package in the roll paper;
s200, extracting the features of the first image to obtain image features, and identifying the image according to the image features to obtain the number of circular surfaces contained in the first image;
and S300, comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the roll paper middle package.
In this embodiment, since the circular face of the roll paper is easier to detect and recognize with respect to the arc-shaped side face of the roll paper, the recognition efficiency and recognition accuracy can be improved by detecting the circular face of the roll paper; the number of the circular surfaces can be identified according to a first image containing the circular surfaces of all the roll paper in the roll paper package by using an image identification technology, and whether the roll paper package is increased or omitted or the placement direction is incorrect is judged according to the number of the identified circular surfaces; the quality detection method for the roll paper tundish can intelligently and quickly detect the quality of the roll paper tundish, saves manpower resources and improves production efficiency.
Certain embodiments of the first aspect of the present invention, for step S100, in the step of acquiring the first image of the package-in-roll paper, a conveying belt of the package-in-roll paper machine is photographed by a photographing apparatus. A photoelectric switch electrically connected with the photographic equipment is arranged on a conveying belt for conveying the roll paper package, and the photoelectric switch is used for sensing the roll paper package; the photoelectric switch is triggered once every time a new roll paper middle package passes through the photoelectric switch, and then the photographing device photographs images of the roll paper middle package.
Certain embodiments of the first aspect of the present invention, in training the image recognition model, after inputting the first image to the image recognition model, perform data enhancement on the first image, the data enhancement including one or more of random cropping, random rotation, and color dithering. Through data enhancement, the robustness of the image recognition model is improved, and the detection accuracy is improved.
In some embodiments of the first aspect of the present invention, in the training of the image recognition model, after the data enhancement is performed on the first image, the expert performs manual labeling on the plurality of first images to obtain a plurality of labeled images corresponding to the first images. The expert adds manual marks on the first image through Labellmg software by an input device such as a mouse according to own experience, the marked image is marked with the manual marks of the type and the position information of the circular faces and the number of all the circular faces, and the marked image is converted into an xml file. Dividing the labeled image into a training data set, a test data set and a verification data set; training the image recognition model through the training data set and the testing data set to optimize parameters of the image recognition model, and verifying the image recognition model through the verification data set.
It should be noted that, in the real-time detection process, after the first image is input to the image recognition model, data enhancement and manual marking are not required, and the image recognition model performs feature extraction to perform image recognition according to image features.
In some embodiments of the first aspect of the present invention, for step S200, performing feature extraction on the first image to obtain an image feature, and performing image recognition according to the image feature to obtain the number of circular surfaces included in the first image, includes:
inputting the first image into an image recognition model constructed based on a deep neural network, wherein the image recognition model can adopt fast-RCNN, and the image recognition model is trained and parameter optimization is completed;
performing feature extraction on the first image through the convolution layer 42 of the image recognition model to obtain image features;
a plurality of candidate regions are obtained from the image features by the region generation layer 43 of the image recognition model;
compressing the candidate region through the region-of-interest pooling layer 44 of the image recognition model, and obtaining target characteristics according to the compressed candidate region;
the target features are classified by the full-connected layer 45 of the image recognition model to obtain the number of circular surfaces included in the first image.
In some embodiments of the first aspect of the present invention, for step S300, comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the roll paper package, specifically:
comparing the number of the circular surfaces with a preset number standard value, and when the number of the circular surfaces is smaller than or larger than the preset number standard value, determining that the quality detection result of the package in the roll paper is a defective product, and removing the defective product; and when the number of the circular surfaces is equal to a preset number standard value, the quality detection result of the package in the roll paper is a qualified product, and the qualified product passes through.
Referring to fig. 2, an embodiment of a second aspect of the present invention provides a package-in-roll quality detection apparatus.
The package quality detection device in stock form includes:
an image acquisition unit 10 for acquiring a first image of a package in roll paper, the first image including a circular face of all roll paper in the package in roll paper;
the image recognition unit 20 is used for performing feature extraction on the first image to obtain image features, and performing image recognition according to the image features to obtain the number of circular surfaces contained in the first image;
and the detection unit 30 is used for comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the roll paper package.
In this embodiment, since the circular face of the roll paper is easier to detect and recognize with respect to the arc-shaped side face of the roll paper, the recognition efficiency and recognition accuracy can be improved by detecting the circular face of the roll paper; the image recognition unit 20 can recognize the number of circular faces from a first image containing the circular faces of all the roll papers in the roll paper package captured by the image acquisition unit 10 by using an image recognition technique, and the detection unit 30 judges whether the roll paper package is increased or omitted or the placement direction is incorrect according to the recognized number of circular faces; the quality detection method for the roll paper tundish can intelligently and quickly detect the quality of the roll paper tundish, saves manpower resources and improves production efficiency.
In certain embodiments of the second aspect of the present invention, the package-in-roll quality detection apparatus further includes a data enhancement unit for performing data enhancement on the first image, the data enhancement including one or more of random cropping, random rotation, and color dithering.
Referring to fig. 3, some embodiments of the second aspect of the present invention, the image recognition unit 20 comprises an image recognition model constructed based on a deep neural network, the image recognition model comprising an input layer 41, a convolution layer 42, a region generation layer 43, a region of interest pooling layer 44 and a full-connectivity layer 45;
the input layer 41 is used for inputting a first image;
the convolution layer 42 is used for performing feature extraction on the first image to obtain image features;
the region generation layer 43 is used to obtain a plurality of candidate regions from the image features;
the region-of-interest pooling layer 44 is used for compressing the candidate region and obtaining a target feature according to the compressed candidate region;
the full-connected layer 45 is used for classifying the target features to obtain the number of circular surfaces included in the first image.
In some embodiments of the second aspect of the present invention, the package quality detection apparatus in roll paper further includes a training unit, the training unit including a marking unit, a diversity unit, and a training subunit;
the marking unit is used for manually marking the plurality of first images to obtain a plurality of marking images corresponding to the first images, and the marking images are marked with the type and the position information of the circular surface;
the diversity unit is used for dividing the marked image into a training data set, a test data set and a verification data set;
the training subunit is configured to train the image recognition model through the training data set and the test data set to optimize parameters of the image recognition model, and verify the image recognition model through the verification data set.
It should be noted that the quality detection device in the roll paper package adopted by the embodiment of the second aspect of the present invention adopts the quality detection method in the roll paper package as the embodiment of the first aspect of the present invention, and each unit in the quality detection device in the roll paper package adopted by the embodiment of the second aspect of the present invention corresponds to each step in the quality detection method in the embodiment of the first aspect of the present invention, and the same technical solutions are adopted, so that the same technical effects are achieved, and detailed description is omitted here.
In a third embodiment of the invention, a package quality detection device in roll paper is provided. The quality detection device for the roll paper medium package comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the quality detection method for the roll paper medium package according to the first aspect of the invention.
The processor and memory may be connected by a bus or other means.
An embodiment of a fourth aspect of the present invention provides a storage medium having stored therein executable instructions that, when executed by a processor, implement the method for detecting a quality of a package in roll paper according to the first aspect of the present invention.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means.
Claims (10)
1. The quality detection method for the roll paper package is characterized by comprising the following steps:
acquiring a first image of a roll paper middle package, wherein the first image comprises the round surfaces of all roll paper in the roll paper middle package;
performing feature extraction on the first image to obtain image features, and performing image identification according to the image features to obtain the number of the circular surfaces contained in the first image;
and comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the middle package in the roll paper.
2. The method for detecting the packet quality in the roll paper according to claim 1, further comprising, before the step of extracting the feature of the first image to obtain the image feature:
performing data enhancement on the first image, the data enhancement comprising one or more of random cropping, random rotation, and color dithering.
3. The method for detecting the quality of the wrapping paper in the roll paper according to claim 1, wherein the extracting the feature of the first image to obtain the image feature, and performing image recognition according to the image feature to obtain the number of the circular surfaces included in the first image comprises:
inputting the first image to an image recognition model constructed based on a deep neural network;
performing feature extraction on the first image through a convolution layer of the image recognition model to obtain image features;
obtaining a plurality of candidate regions according to the image characteristics through a region generation layer of the image recognition model;
compressing the candidate region through the region-of-interest pooling layer of the image recognition model, and obtaining target characteristics according to the compressed candidate region;
and classifying the target features through a full connection layer of the image recognition model to obtain the number of the circular surfaces contained in the first image.
4. The roll paper package quality detection method according to claim 3, further comprising, before the step of extracting the feature of the first image to obtain an image feature and performing image recognition based on the image feature to obtain the number of circular faces included in the first image:
manually marking the plurality of first images to obtain a plurality of marked images corresponding to the first images, wherein the marked images are marked with the type and the position information of the circular surface;
dividing the labeled image into a training data set, a test data set and a verification data set;
training the image recognition model through the training data set and the testing data set to optimize parameters of the image recognition model, and verifying the image recognition model through the verification data set.
5. Package quality detection device in stock form, its characterized in that includes:
an image acquisition unit configured to acquire a first image of a roll paper wrapper, the first image including circular faces of all roll papers in the roll paper wrapper;
the image recognition unit is used for performing feature extraction on the first image to obtain image features, and performing image recognition according to the image features to obtain the number of the circular surfaces contained in the first image;
and the detection unit is used for comparing the number of the circular surfaces with a preset number standard value to obtain a quality detection result of the roll paper.
6. The package-in-roll quality detection device according to claim 5, further comprising a data enhancement unit configured to perform data enhancement on the first image during training of the image recognition model, wherein the data enhancement includes one or more of random cropping, random rotation, and color dithering.
7. The package-in-roll quality detection device according to claim 5, wherein the image recognition unit includes an image recognition model constructed based on a deep neural network, the image recognition model including an input layer, a convolution layer, a region generation layer, a region-of-interest pooling layer, and a full-link layer;
the input layer is used for inputting the first image;
the convolution layer is used for carrying out feature extraction on the first image to obtain image features;
the region generation layer is used for obtaining a plurality of candidate regions according to the image features;
the interested region pooling layer is used for compressing the candidate region and obtaining target characteristics according to the compressed candidate region;
the full-connection layer is used for classifying the target features to obtain the number of the circular surfaces contained in the first image.
8. The quality detection device for a package in roll paper according to claim 7, further comprising a training unit including a marking unit, a diversity unit, and a training subunit;
the marking unit is used for manually marking the plurality of first images to obtain a plurality of marked images corresponding to the first images, and the marked images are marked with the type and the position information of the circular surface;
the diversity unit is used for dividing the marked image into a training data set, a test data set and a verification data set;
the training subunit is configured to train the image recognition model through the training data set and the test data set to optimize parameters of the image recognition model, and verify the image recognition model through the verification data set.
9. The quality detection device for the roll paper packet is characterized by comprising a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the quality detection method for the roll paper packet according to any one of claims 1 to 4.
10. Storage medium, characterized in that it has stored therein executable instructions which, when executed by a processor, implement the method of detecting the quality of a package in roll paper according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889489.2A CN113780074A (en) | 2021-08-04 | 2021-08-04 | Method and device for detecting quality of wrapping paper and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889489.2A CN113780074A (en) | 2021-08-04 | 2021-08-04 | Method and device for detecting quality of wrapping paper and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113780074A true CN113780074A (en) | 2021-12-10 |
Family
ID=78836804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110889489.2A Pending CN113780074A (en) | 2021-08-04 | 2021-08-04 | Method and device for detecting quality of wrapping paper and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780074A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767238A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product discriminating method, device, equipment and storage medium based on image recognition |
| CN109978868A (en) * | 2019-03-29 | 2019-07-05 | 北京百度网讯科技有限公司 | Toy appearance quality determining method and its relevant device |
| CN109978867A (en) * | 2019-03-29 | 2019-07-05 | 北京百度网讯科技有限公司 | Toy appearance quality determining method and its relevant device |
| WO2019232831A1 (en) * | 2018-06-06 | 2019-12-12 | 平安科技（深圳）有限公司 | Method and device for recognizing foreign object debris at airport, computer apparatus, and storage medium |
| CN110647912A (en) * | 2019-08-15 | 2020-01-03 | 深圳久凌软件技术有限公司 | Fine-grained image recognition method and device, computer equipment and storage medium |
| CN111717618A (en) * | 2020-06-04 | 2020-09-29 | 上海燕汐软件信息科技有限公司 | Express delivery bubble counting method and device, computer equipment and storage medium |
| CN112613581A (en) * | 2020-12-31 | 2021-04-06 | 广州大学华软软件学院 | Image recognition method, system, computer equipment and storage medium |
-
2021
- 2021-08-04 CN CN202110889489.2A patent/CN113780074A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019232831A1 (en) * | 2018-06-06 | 2019-12-12 | 平安科技（深圳）有限公司 | Method and device for recognizing foreign object debris at airport, computer apparatus, and storage medium |
| CN109767238A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product discriminating method, device, equipment and storage medium based on image recognition |
| CN109978868A (en) * | 2019-03-29 | 2019-07-05 | 北京百度网讯科技有限公司 | Toy appearance quality determining method and its relevant device |
| CN109978867A (en) * | 2019-03-29 | 2019-07-05 | 北京百度网讯科技有限公司 | Toy appearance quality determining method and its relevant device |
| CN110647912A (en) * | 2019-08-15 | 2020-01-03 | 深圳久凌软件技术有限公司 | Fine-grained image recognition method and device, computer equipment and storage medium |
| CN111717618A (en) * | 2020-06-04 | 2020-09-29 | 上海燕汐软件信息科技有限公司 | Express delivery bubble counting method and device, computer equipment and storage medium |
| CN112613581A (en) * | 2020-12-31 | 2021-04-06 | 广州大学华软软件学院 | Image recognition method, system, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王胜;吕林涛;杨宏才;: "卷积神经网络在印刷品缺陷检测的应用", 包装工程, no. 11, pages 213 - 221 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2754091B1 (en) | Measurement of belt wear through edge detection of a raster image | |
| EP3751976B1 (en) | System for creating learned model for component image recognition, and method for creating learned model for component image recognition | |
| CN110276257B (en) | Face recognition method, device, system, server and readable storage medium | |
| CN103366176B (en) | Optical element defect batch automatic identification equipment and method | |
| CN113820333B (en) | Battery pole piece abnormality detection method, device, upper computer and detection system | |
| CN111862057A (en) | Picture labeling method and device, sensor quality detection method and electronic equipment | |
| CN116519707A (en) | Lithium battery defect detection method and device based on machine vision and electronic equipment | |
| CN111597857A (en) | Logistics package detection method, device and equipment and readable storage medium | |
| CN112465910B (en) | Target shooting distance obtaining method and device, storage medium and electronic equipment | |
| KR102253385B1 (en) | detecting system of multi-packaging error | |
| CN113780074A (en) | Method and device for detecting quality of wrapping paper and storage medium | |
| CN112016533A (en) | Material detection method and device, electronic equipment and computer readable storage medium | |
| CN113516625A (en) | Method, device and equipment for detecting abnormity of photovoltaic module image | |
| CN112733864B (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN112785595A (en) | Target attribute detection, neural network training and intelligent driving method and device | |
| CN111460198A (en) | Method and device for auditing picture timestamp | |
| CN109449096B (en) | Method for identifying and detecting wafer chip | |
| CN113420579A (en) | Method and device for training and positioning identification code position positioning model and electronic equipment | |
| CN112990028A (en) | Method for classifying coal and gangue based on classifier and gangue sorting device | |
| WO2001014928A9 (en) | Print inspection system | |
| CN217332186U (en) | Plank AI visual defect detection device | |
| CN114529733A (en) | Package damage detection method and device, electronic equipment and storage medium | |
| CN117764963A (en) | Packaging bag defect detection method, device, terminal and medium based on machine vision | |
| CN116883484A (en) | Method, system and storage medium for identifying size of tray | |
| CN117853390A (en) | Logistics object detection method, device, electronic equipment and readable 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 |