CN114066810A - Method and device for detecting concave-convex point defects of packaging box - Google Patents
Method and device for detecting concave-convex point defects of packaging box Download PDFInfo
- Publication number
- CN114066810A CN114066810A CN202111182335.6A CN202111182335A CN114066810A CN 114066810 A CN114066810 A CN 114066810A CN 202111182335 A CN202111182335 A CN 202111182335A CN 114066810 A CN114066810 A CN 114066810A
- Authority
- CN
- China
- Prior art keywords
- image
- concave
- convex point
- detection
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004806 packaging method and process Methods 0.000 title claims description 64
- 238000001514 detection method Methods 0.000 claims abstract description 90
- 238000012856 packing Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000004927 fusion Effects 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000006835 compression Effects 0.000 claims abstract description 7
- 238000007906 compression Methods 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for detecting concave-convex point defects of a packing box, which are characterized in that a packing box sample with concave-convex point defects is collected, processing modes such as image compression, feature fusion, image segmentation and the like are carried out on the sample to obtain a regional feature image set, a lightweight deep neural network is designed based on an FCNN (fuzzy C neural network) frame, a detection model is constructed, the regional feature image of the sample is utilized for model training to obtain a high-precision concave-convex point defect detection model, the packing box is detected according to the high-precision detection model, and the complex and multi-scale concave-convex point defects in the packing box are rapidly detected.
Description
Technical Field
The invention relates to the field of detection of packaging boxes, in particular to a method and a device for detecting concave-convex point defects of a packaging box.
Background
The commodity packing box can prevent commodities from being damaged, polluted, leaked or deteriorated in the circulation process, and is the most powerful and convenient means for selling commodities by manufacturers. For example, an aesthetically pleasing tablet computer outer package can improve the public acceptance of tablet computer brands. However, due to the influence of the manufacturing process and the transportation environment, the tablet computer packaging box inevitably has many defects in the production and transportation processes, wherein concave and convex points on the inner surface and the outer surface of the tablet computer packaging box are the most common product defects. The existence of the concave-convex points seriously affects the brand benefit of the tablet computer, so manufacturers must strictly detect products with the concave-convex point defect problem, and the negative influence on the brand of the tablet computer is avoided. At present, most manufacturers adopt a manual detection method for the defect problems because the types of the concave-convex point defects appearing on the surface of the tablet personal computer packaging box are complex and have different sizes and scales. The manual detection is not only high in cost, but also easy to fatigue due to long-time detection of detection personnel, so that the error rate is too high, and the computer vision detection is an innovative technology which is eagerly introduced by current manufacturers.
The computer vision detection technology is widely applied in various fields along with the rapid development of artificial intelligence, a corresponding conventional detection technical scheme is formed, and machine vision technology is widely adopted for a plurality of product outer package flaw and product defect detection tasks at present. However, the defects of concave-convex points of the packaging box of the intelligent device such as the tablet personal computer are essentially different from the defects of the conventional product, belong to a micro defect, have the characteristics of high complexity, diversity and the like, and cause the existing technical scheme to be difficult to apply.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a method and a device for detecting the concave-convex point defects of a packaging box.
The invention provides a method for detecting concave-convex point defects of a packaging box, which comprises the following steps:
s1: acquiring a detection image of the packaging box; processing the detection image to obtain a characteristic image;
s2: extracting a binary image of the characteristic image, and performing closed operation on the binary image to obtain an image mask;
s3: multiplying the image mask and the characteristic image to obtain a regional characteristic image of the packing box;
s4: collecting a packing box sample with concave-convex point defects, and acquiring a regional characteristic image set of the packing box according to the steps S1-S3;
s5: designing a lightweight deep neural network based on an FCNN (fuzzy C-means network) frame, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to an area characteristic image set;
s6: and detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
Preferably, the step S1 specifically includes:
s101: acquiring two detection images of the packing box with the same size, wherein the two detection images are a high light exposure mode shooting image and a low light exposure mode shooting image of the same packing surface of the packing box;
s102: respectively carrying out same-scale nearest neighbor interpolation compression on the two detection images to obtain two compressed images;
s103: combining with high-pass filtering to respectively calculate the gradients of the two compressed images to obtain two gradient images;
s104: and performing highlight fusion on the two gradient images by using wiener filtering to obtain a characteristic image.
Preferably, the detection image is a grayscale image.
Preferably, the extracting a binary image of the feature image in step S2 specifically includes: and carrying out median filtering on the characteristic image and extracting the characteristics by adopting a canny operator to obtain a binary image of the characteristic image.
Preferably, the step S5 specifically includes:
s501: designing a lightweight deep neural network Model based on an FCNN framework;
s502: sequentially marking concave-convex point information of the regional characteristic images of the regional characteristic image set, selecting two thirds of the regional characteristic images to form a model training set, and forming a model testing set by the remaining one third of the regional characteristic images;
s503: setting corresponding network parameters and training parameters based on the Model, inputting the Model training set into the Model for training, and obtaining a concave-convex point defect detection Model PreModel;
s504: inputting the model test set into a concave-convex point defect detection model PreModel for detection, comparing a detection result with marked concave-convex point information, and calculating a model error epsilon;
s505: judging whether epsilon is less than c, if so, obtaining a high-precision concave-convex point defect detection Model Pre-Model; if the judgment result is no, returning to the step S503; where c represents the industry standard error.
Preferably, the network depth of the deep neural network Model is 35 layers.
The invention also provides a device for detecting the concave-convex point defects of the packaging box, which comprises:
the characteristic fusion module is used for acquiring a detection image of the packaging box; processing the detection image to obtain a characteristic image;
the image processing module is used for extracting a binary image of the characteristic image and performing closed operation on the binary image to obtain an image mask; multiplying the image mask and the characteristic image to obtain a regional characteristic image of the packing box;
the data acquisition module is used for acquiring a packing box sample with concave-convex point defects and acquiring a regional characteristic image set of the packing box;
the model training module is used for designing a lightweight deep neural network based on the FCNN framework, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to the regional characteristic image set;
and the detection module is used for detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
The invention also proposes a computer-readable storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method for detecting defects of bumps and dips of a packaging box.
According to the invention, a region characteristic image set is obtained by collecting a packaging box sample with concave-convex point flaws and processing the packaging box sample in image compression, characteristic fusion, image segmentation and the like, a lightweight deep neural network is designed based on an FCNN frame, a detection model is constructed, the packaging box is trained through the sample region characteristic image to obtain a high-precision concave-convex point defect detection model, and the packaging box is detected according to the high-precision detection model, so that the complex and multi-scale concave-convex point defects in a target can be rapidly detected.
In the invention, when the packaging surface of the packaging box is shot, a gray high-definition industrial camera is adopted to shoot images, which is beneficial to the acquisition of information of micro concave-convex points; nearest neighbor interpolation compression is carried out on the obtained high-definition image, so that the characteristic structure information is ensured, and meanwhile, the input scale and the calculation complexity are greatly reduced; calculating the gradient of a compressed image by combining high-pass filtering to obtain a gradient image, eliminating low-noise interference and simultaneously keeping low-scale concave-convex point information; highlight fusion is carried out on the gradient image by utilizing wiener filtering to obtain a characteristic image, so that concave-convex point information is effectively enhanced; the canny operator is used for extracting the characteristic image binary image, so that the complete characteristics of the packaging box can be simply and effectively obtained; by performing closed operation on the characteristic image binary image, a complete information mask of the closed area of the packaging box can be quickly obtained.
According to the invention, a 35-layer lightweight network based on the FCNN framework is constructed, the detection precision and the training speed can be ensured simultaneously, the training verification is carried out by using sample data, the low-scale concave-convex point information can be effectively enhanced, and the high-precision detection model is ensured to be finally obtained.
The detection method provided by the invention is based on local positioning and local segmentation, a lightweight learning network and a non-end-to-end training application strategy are adopted, mixed-type and multi-scale micro-defect concave-convex points can be quickly and efficiently detected, and the designed deep network model has high expansibility and can be applied to other types of problem migration learning.
Drawings
Fig. 1 is a flow chart of a method for detecting defects of concave-convex points of a packaging box provided by the invention.
Detailed Description
As shown in fig. 1, fig. 1 is a flowchart of a method for detecting a concave-convex point defect of a packaging box according to an embodiment of the present invention.
Referring to fig. 1, a method for detecting a concave-convex point defect of a packaging box according to an embodiment of the present invention, which takes a packaging box of a tablet personal computer as an example, specifically includes:
s1: acquiring a detection image of the packaging box; processing the detection image to obtain a characteristic image;
in this embodiment, the step S1 specifically includes:
s101: obtaining two packing box detection images I with the same size1、I2;
The two detection images are two images obtained by shooting the same packaging surface of the packaging box in a high light exposure mode and a low light exposure mode respectively;
specifically, the gray scale industrial camera is fixed to be perpendicular to a tablet personal computer packaging shooting surface, strip-shaped parallel light sources for controlling high light exposure and low light exposure are selected respectively, parallel light emitted by the light sources is perpendicular to the tablet personal computer packaging box surface, and then shooting is carried out to obtain a detection image.
The detection image is an image shot by a gray-scale high-definition industrial camera; when the packaging surface of the packaging box is shot, a monochromatic gray-scale high-definition industrial camera is used for shooting images, so that the information acquisition of micro concave-convex points is facilitated; meanwhile, a pure color background which has a larger difference with the characteristic color of the tablet computer packaging box is used as a shooting background, so that the interference of the peripheral background can be eliminated as much as possible, and the regional information of the tablet computer packaging box can be completely extracted.
S102: respectively carrying out same-scale nearest neighbor interpolation compression on the two detection images to obtain two compressed images J1、J2;
S103: combining high-pass filtering to respectively calculate the gradients of the two compressed images to obtain two gradient images C1、C2;
S104: highlight fusion is carried out on the two gradient images by utilizing wiener filtering, and a characteristic image G is obtained.
S2: extracting a binary image of the characteristic image, and performing closed operation on the binary image to obtain an image mask L;
specifically, the method comprises the following steps: performing median filtering on the G, and extracting the structural edge by adopting a canny operator to obtain a characteristic binary image EdgeI of the G; it should be noted that, the canny operator is used to extract the binary image of the feature image, so that the complete features of the tablet personal computer box can be simply extracted.
S3: multiplying the image mask L and the characteristic image G to obtain a regional characteristic image G of the packing box0;
S4: collecting a packing box sample with concave-convex point defects, and acquiring a regional characteristic image set F ═ G { G } of the packing box according to the steps S1-S30,G1,…,Gn};
S5: designing a lightweight deep neural network based on an FCNN (fuzzy C-means network) frame, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to an area characteristic image set;
in this embodiment, the step S5 specifically includes:
s501: designing a lightweight deep neural network Model based on an FCNN framework; it should be noted that the depth of the deep neural network Model is preferably 35 layers, which can ensure the detection precision and the training speed at the same time;
s502: sequentially marking concave-convex point information of the regional characteristic images of the regional characteristic image set, selecting two thirds of the regional characteristic images to form a model training set, and forming a model testing set by the remaining one third of the regional characteristic images;
s503: setting corresponding network parameters and training parameters based on the Model, inputting the Model training set into the Model for training, and obtaining a concave-convex point defect detection Model PreModel;
s504: inputting the model test set into a concave-convex point defect detection model PreModel for detection, comparing a detection result with marked concave-convex point information, and calculating a model error epsilon;
s505: judging whether epsilon is less than c, if so, obtaining a high-precision concave-convex point defect detection Model Pre-Model; if the judgment result is no, returning to the step S503; where c represents the industry standard error.
In this embodiment, when the determination result is negative, the process returns to step S503, adjusts the network parameters and the training parameters, and performs training and detection again according to the training set and the test set until the error of the detection model is within the standard error range, so as to obtain a high-precision detection model.
In this embodiment, the high-precision concave-convex point defect detection Model Pre-Model is a detection Model Premodel which is obtained by continuously training the detection Model and meets the error standard, namely epsilon < c.
S6: and detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
The embodiment of the invention also provides a device for detecting the concave-convex point defects of the packaging box, which comprises:
the characteristic fusion module is used for acquiring a detection image of the packaging box; processing the detection image to obtain a characteristic image;
the detection images are two images obtained by shooting the same packaging surface of the packaging box in a high light exposure mode and a low light exposure mode respectively; specifically, nearest neighbor interpolation compression is carried out through a detection image, and the gradient of the compressed image is calculated to obtain a gradient image; and performing highlight fusion on the gradient image by using wiener filtering to obtain a characteristic image.
The image processing module is used for extracting a binary image of the characteristic image and performing closed operation on the binary image to obtain an image mask; multiplying the image mask and the characteristic image to obtain a regional characteristic image of the packing box;
specifically, the method comprises the following steps: performing median filtering on the characteristic image, and extracting the structural edge by adopting a canny operator to obtain a characteristic binary image of the characteristic image; it should be noted that, the canny operator is used to extract the binary image of the feature image, so that the complete features of the tablet personal computer box can be simply extracted.
The data acquisition module is used for acquiring a packing box sample with concave-convex point defects and acquiring a regional characteristic image set of the packing box;
the model training module is used for designing a lightweight deep neural network based on the FCNN framework, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to the regional characteristic image set; (ii) a
Specifically, the model training module constructs a high-precision concave-convex point detection model according to the specific steps described in step S5 in the above embodiment.
And the detection module is used for detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to realize the steps of the method for detecting the concave-convex point defects of the packaging box.
The detection method provided by the invention is based on local positioning and local segmentation, a lightweight learning network and a non-end-to-end training application strategy are adopted, mixed-type and multi-scale micro-defect concave-convex points can be quickly and efficiently detected, and the designed deep network model has high expansibility and can be applied to other types of problem migration learning.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (8)
1. A method for detecting concave-convex point defects of a packaging box is characterized by comprising the following steps:
s1: acquiring a detection image of the packaging box; processing the detection image to obtain a characteristic image;
s2: extracting a binary image of the characteristic image, and performing closed operation on the binary image to obtain an image mask;
s3: multiplying the image mask and the characteristic image to obtain a regional characteristic image of the packing box;
s4: collecting a packing box sample with concave-convex point defects, and acquiring a regional characteristic image set of the packing box according to the steps S1-S3;
s5: designing a lightweight deep neural network based on an FCNN (fuzzy C-means network) frame, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to an area characteristic image set;
s6: and detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
2. The method for detecting the concave-convex point defects of the packaging box according to claim 1, wherein the step S1 specifically comprises the following steps:
s101: acquiring two detection images of the packing box with the same size, wherein the two detection images are a high light exposure mode shooting image and a low light exposure mode shooting image of the same packing surface of the packing box;
s102: respectively carrying out same-scale nearest neighbor interpolation compression on the two detection images to obtain two compressed images;
s103: combining with high-pass filtering to respectively calculate the gradients of the two compressed images to obtain two gradient images;
s104: and performing highlight fusion on the two gradient images by using wiener filtering to obtain a characteristic image.
3. The method for detecting concave-convex point defects of a packing box according to claim 2, wherein the detection image is a gray scale image.
4. The method for detecting concave-convex point defects of packaging boxes according to claim 1, wherein the extracting the binary image of the feature image in the step S2 specifically comprises: and carrying out median filtering on the characteristic image and extracting the characteristics by adopting a canny operator to obtain a binary image of the characteristic image.
5. The method for detecting the concave-convex point defects of the packaging box according to claim 1, wherein the step S5 specifically comprises the following steps:
s501: designing a lightweight deep neural network Model based on an FCNN framework;
s502: sequentially marking concave-convex point information of the regional characteristic images of the regional characteristic image set, selecting two thirds of the regional characteristic images to form a model training set, and forming a model testing set by the remaining one third of the regional characteristic images;
s503: setting corresponding network parameters and training parameters based on the Model, inputting the Model training set into the Model for training, and obtaining a concave-convex point defect detection Model PreModel;
s504: inputting the model test set into a concave-convex point defect detection model PreModel for detection, comparing a detection result with marked concave-convex point information, and calculating a model error epsilon;
s505: judging whether epsilon is less than c, if so, obtaining a high-precision concave-convex point defect detection Model Pre-Model; if the judgment result is no, returning to the step S503; where c represents the industry standard error.
6. The method for detecting concave-convex point defects of a packing box according to claim 5, wherein the depth of the deep neural network Model is 35 layers.
7. The utility model provides a packing carton concave convex point defect detecting device which characterized in that includes:
the characteristic fusion module is used for acquiring a detection image of the packaging box and processing the detection image to acquire a characteristic image;
the image processing module is used for extracting a binary image of the characteristic image and performing closed operation on the binary image to obtain an image mask; multiplying the image mask and the characteristic image to obtain a regional characteristic image of the packing box;
the data acquisition module is used for acquiring a packing box sample with concave-convex point defects and acquiring a regional characteristic image set of the packing box;
the model training module is used for designing a lightweight deep neural network based on the FCNN framework, constructing a detection model of the concave-convex point defects of the packaging box, and training the detection model according to the regional characteristic image set;
and the detection module is used for detecting the packaging box according to the trained detection model for the concave-convex point defects of the packaging box.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for detecting the presence of defects in the presence of bumps of a package according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111182335.6A CN114066810A (en) | 2021-10-11 | 2021-10-11 | Method and device for detecting concave-convex point defects of packaging box |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111182335.6A CN114066810A (en) | 2021-10-11 | 2021-10-11 | Method and device for detecting concave-convex point defects of packaging box |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114066810A true CN114066810A (en) | 2022-02-18 |
Family
ID=80234506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111182335.6A Pending CN114066810A (en) | 2021-10-11 | 2021-10-11 | Method and device for detecting concave-convex point defects of packaging box |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114066810A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114463327A (en) * | 2022-04-08 | 2022-05-10 | 深圳市睿阳精视科技有限公司 | Multi-shooting imaging detection equipment and method for watermark defect of electronic product lining package |
CN117152415A (en) * | 2023-09-01 | 2023-12-01 | 北京奥乘智能技术有限公司 | Method, device, equipment and storage medium for detecting marker of medicine package |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111862092A (en) * | 2020-08-05 | 2020-10-30 | 复旦大学 | Express delivery outer package defect detection method and device based on deep learning |
CN111914622A (en) * | 2020-06-16 | 2020-11-10 | 北京工业大学 | Character interaction detection method based on deep learning |
CN111932501A (en) * | 2020-07-13 | 2020-11-13 | 太仓中科信息技术研究院 | Seal ring surface defect detection method based on semantic segmentation |
CN113240626A (en) * | 2021-04-08 | 2021-08-10 | 西安电子科技大学 | Neural network-based method for detecting and classifying concave-convex flaws of glass cover plate |
-
2021
- 2021-10-11 CN CN202111182335.6A patent/CN114066810A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111914622A (en) * | 2020-06-16 | 2020-11-10 | 北京工业大学 | Character interaction detection method based on deep learning |
CN111932501A (en) * | 2020-07-13 | 2020-11-13 | 太仓中科信息技术研究院 | Seal ring surface defect detection method based on semantic segmentation |
CN111862092A (en) * | 2020-08-05 | 2020-10-30 | 复旦大学 | Express delivery outer package defect detection method and device based on deep learning |
CN113240626A (en) * | 2021-04-08 | 2021-08-10 | 西安电子科技大学 | Neural network-based method for detecting and classifying concave-convex flaws of glass cover plate |
Non-Patent Citations (1)
Title |
---|
柳锋;李俊峰;戴文战;: "基于深度学习语义分割的导光板缺陷检测方法", 计算机系统应用, no. 06, 15 June 2020 (2020-06-15) * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114463327A (en) * | 2022-04-08 | 2022-05-10 | 深圳市睿阳精视科技有限公司 | Multi-shooting imaging detection equipment and method for watermark defect of electronic product lining package |
CN117152415A (en) * | 2023-09-01 | 2023-12-01 | 北京奥乘智能技术有限公司 | Method, device, equipment and storage medium for detecting marker of medicine package |
CN117152415B (en) * | 2023-09-01 | 2024-04-23 | 北京奥乘智能技术有限公司 | Method, device, equipment and storage medium for detecting marker of medicine package |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112085735B (en) | Aluminum material image defect detection method based on self-adaptive anchor frame | |
CN109829893B (en) | Defect target detection method based on attention mechanism | |
KR102166458B1 (en) | Defect inspection method and apparatus using image segmentation based on artificial neural network | |
JP5546317B2 (en) | Visual inspection device, visual inspection discriminator generation device, visual inspection discriminator generation method, and visual inspection discriminator generation computer program | |
CN113658176A (en) | Ceramic tile surface defect detection method based on interactive attention and convolutional neural network | |
CN113240626B (en) | Glass cover plate concave-convex type flaw detection and classification method based on neural network | |
CN108520273A (en) | A kind of quick detection recognition method of dense small item based on target detection | |
Eshkevari et al. | Automatic dimensional defect detection for glass vials based on machine vision: A heuristic segmentation method | |
CN114066810A (en) | Method and device for detecting concave-convex point defects of packaging box | |
CN106355579A (en) | Defect detecting method of cigarette carton surface wrinkles | |
Adem et al. | Defect detection of seals in multilayer aseptic packages using deep learning | |
CN109060838B (en) | Product surface scratch detection method based on machine vision | |
CN115775236B (en) | Visual detection method and system for surface micro defects based on multi-scale feature fusion | |
CN116012291A (en) | Industrial part image defect detection method and system, electronic equipment and storage medium | |
CN115452842A (en) | Fold detection method for valve bag packaging machine | |
CN113869211A (en) | Automatic image annotation and automatic annotation quality evaluation method and system | |
CN111754502A (en) | Method for detecting surface defects of magnetic core based on fast-RCNN algorithm of multi-scale feature fusion | |
CN113807378A (en) | Training data increment method, electronic device and computer readable recording medium | |
CN114972316A (en) | Battery case end surface defect real-time detection method based on improved YOLOv5 | |
CN117576095A (en) | Metal surface defect detection and classification method for multi-scale learning task | |
Gupta et al. | Deep learning model for defect analysis in industry using casting images | |
CN113538342B (en) | Convolutional neural network-based aluminum aerosol can coating quality detection method | |
CN113808099A (en) | Aluminum product surface defect detection device and method | |
Chetoui et al. | Object detection model-based quality inspection using a deep CNN | |
CN113313678A (en) | Automatic sperm morphology analysis method based on multi-scale feature fusion |
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 |