CN111507947B - Identification method for identifying package authenticity based on trademark or pattern reading - Google Patents
Identification method for identifying package authenticity based on trademark or pattern reading Download PDFInfo
- Publication number
- CN111507947B CN111507947B CN202010262053.6A CN202010262053A CN111507947B CN 111507947 B CN111507947 B CN 111507947B CN 202010262053 A CN202010262053 A CN 202010262053A CN 111507947 B CN111507947 B CN 111507947B
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic points
- package
- points
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 12
- 230000005477 standard model Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to the technical field of anti-counterfeiting, in particular to an identification method for identifying package authenticity based on reading a trademark or pattern.
Description
Technical Field
The invention relates to the technical field of anti-counterfeiting, in particular to a method for identifying authenticity of a package based on reading a trademark or pattern.
Background
When a user purchases a commodity, the user cannot accurately judge the authenticity of the commodity according to the package due to weak identification capability of naked eyes on the color of the pattern, the size of the trademark or the relative distance between each marking point in the pattern, and in order to solve the problem that the authenticity of the package cannot be distinguished due to individual reasons, an identification method for identifying the authenticity of the package based on reading the trademark or the pattern is designed, so that the system automatically identifies the authenticity of the package after the user uploads a picture.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the technology and provide an identification method for identifying the authenticity of the package based on reading the trademark or pattern.
In order to solve the technical problems, the technical scheme provided by the invention is an identification method for identifying the authenticity of the package based on reading a trademark or a pattern: the user shoots an external package image through a mobile phone and uploads the external package image to a back-end system, the back-end system extracts characteristic information in the image through image analysis and noise reduction processing, identifies and marks all kinds of targets in the image, establishes an internal model between image characteristics and marks, compares the model with a standard model trained in the background, and analyzes package authenticity through a target detection algorithm based on combined characteristics and a layered structure, wherein the target detection algorithm comprises the following steps:
step (1): acquiring multi-scale features of an image through a feature function with variable scales, wherein the large scale corresponds to the profile features of the image, the small scale corresponds to the detail features of the image, and for one image, establishing images of the image under different scales through noise reduction treatment to acquire feature points which can be corresponding under any scale;
step (2): determining space feature points, namely performing gridding on the image, wherein each grid is required to be associated with the adjacent grid, and comparing adjacent grid value deviations of an image domain and a scale domain in the grid, so as to determine the feature points;
step (3): rejecting bad characteristic points, accurately determining the positions and scales of the characteristic points by researching and acquiring the characteristics of symmetry, edges, shadows, colors, textures, statistical information and the like of the image, and rejecting low-contrast characteristic points and unstable edge response points;
step (4): enabling the characteristic points, combining the characteristic points on the basis of the extracted characteristic points, and combining and layering the characteristic points according to the value of each characteristic point to realize the mutual correlation among the characteristic points and realize multi-target mutual detection and multi-target mutual verification;
step (5): and (3) anti-counterfeiting identification, namely uploading a package image shot by a user to the background, carrying out algorithm processing on the background, identifying and marking all kinds of targets in the shot image, establishing an internal model between the shot image characteristics and the marks, comparing the new model with a standard model trained in the background, and analyzing package authenticity.
Compared with the prior art, the invention has the advantages that:
1. by researching and acquiring the characteristics of symmetry, edge, shadow, color, texture, statistical information and the like of an image, a target detection algorithm based on the combined characteristics and a layered structure is provided, multi-target detection and multi-target verification are realized, and the consumer uploads commodity pictures or other descriptive information to realize self-verification of package authenticity, so that the reliability of package authenticity verification is effectively improved;
2. the technology is software identification, does not need to increase any hardware cost, is non-invasive to the original production process, and is convenient and practical.
Detailed Description
The method for identifying the authenticity of the package based on the read trademark or pattern is described in further detail below.
A method for identifying package authenticity based on reading trademark or pattern includes shooting package image by user through mobile phone and uploading to back end system, extracting characteristic information in image by back end system through image analysis and noise reduction process, identifying and labeling all kinds of targets in image, setting up internal model between image characteristic and label, comparing model with standard model trained in background, analyzing package authenticity through target detection algorithm based on combined characteristic and layered structure, said target detection algorithm includes following steps:
step (1): acquiring multi-scale features of an image through a feature function with variable scales, wherein the large scale corresponds to the profile features of the image, the small scale corresponds to the detail features of the image, and for one image, establishing images of the image under different scales through noise reduction treatment to acquire feature points which can be corresponding under any scale;
step (2): determining space feature points, namely performing gridding on the image, wherein each grid is required to be associated with the adjacent grid, and comparing adjacent grid value deviations of an image domain and a scale domain in the grid, so as to determine the feature points;
step (3): rejecting bad characteristic points, accurately determining the positions and scales of the characteristic points by researching and acquiring the characteristics of symmetry, edges, shadows, colors, textures, statistical information and the like of the image, and rejecting low-contrast characteristic points and unstable edge response points;
step (4): enabling the characteristic points, combining the characteristic points on the basis of the extracted characteristic points, and combining and layering the characteristic points according to the value of each characteristic point to realize the mutual correlation among the characteristic points and realize multi-target mutual detection and multi-target mutual verification;
step (5): and (3) anti-counterfeiting identification, namely uploading a package image shot by a user to the background, carrying out algorithm processing on the background, identifying and marking all kinds of targets in the shot image, establishing an internal model between the shot image characteristics and the marks, comparing the new model with a standard model trained in the background, and analyzing package authenticity.
In the specific implementation of the invention, the multi-scale features of the image, the outline features of the large-scale corresponding image and the detail features of the small-scale corresponding image are obtained through the feature function with variable scale, and for one image, the image with different scales is established through noise reduction treatment, and the corresponding feature points can be obtained at any scale; determining space feature points, namely performing gridding on the image, wherein each grid is required to be associated with the adjacent grid, and comparing adjacent grid value deviations of an image domain and a scale domain in the grid, so as to determine the feature points; rejecting bad characteristic points, accurately determining the positions and scales of the characteristic points by researching and acquiring the characteristics of symmetry, edges, shadows, colors, textures, statistical information and the like of the image, and rejecting low-contrast characteristic points and unstable edge response points; enabling the characteristic points, combining the characteristic points on the basis of the extracted characteristic points, and combining and layering the characteristic points according to the value of each characteristic point to realize the mutual correlation among the characteristic points and realize multi-target mutual detection and multi-target mutual verification; and (3) anti-counterfeiting identification, namely uploading a package image shot by a user to the background, carrying out algorithm processing on the background, identifying and marking all kinds of targets in the shot image, establishing an internal model between the shot image characteristics and the marks, comparing the new model with a standard model trained in the background, and analyzing package authenticity.
The invention and its embodiments have been described above without limitation. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (1)
1. An identification method for identifying package authenticity based on reading trademark or pattern is characterized in that: the user shoots an external package image through a mobile phone and uploads the external package image to a back-end system, the back-end system extracts characteristic information in the image through image analysis and noise reduction processing, identifies and marks all kinds of targets in the image, establishes an internal model between image characteristics and marks, compares the model with a standard model trained in the background, and analyzes package authenticity through a target detection algorithm based on combined characteristics and a layered structure, wherein the target detection algorithm comprises the following steps:
step (1): acquiring multi-scale features of an image through a feature function with variable scales, wherein the large scale corresponds to the profile features of the image, the small scale corresponds to the detail features of the image, and for one image, establishing images of the image under different scales through noise reduction treatment to acquire feature points which can be corresponding under any scale;
step (2): determining space feature points, namely performing gridding on the image, wherein each grid is required to be associated with the adjacent grid, and comparing adjacent grid value deviations of an image domain and a scale domain in the grid, so as to determine the feature points;
step (3): rejecting bad characteristic points, accurately determining the positions and scales of the characteristic points by researching and acquiring the characteristics of symmetry, edges, shadows, colors, textures, statistical information and the like of the image, and rejecting low-contrast characteristic points and unstable edge response points;
step (4): enabling the characteristic points, combining the characteristic points on the basis of the extracted characteristic points, and combining and layering the characteristic points according to the value of each characteristic point to realize the mutual correlation among the characteristic points and realize multi-target mutual detection and multi-target mutual verification;
step (5): and (3) anti-counterfeiting identification, namely uploading a package image shot by a user to the background, carrying out algorithm processing on the background, identifying and marking all kinds of targets in the shot image, establishing an internal model between the shot image characteristics and the marks, comparing the new model with a standard model trained in the background, and analyzing package authenticity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010262053.6A CN111507947B (en) | 2020-04-06 | 2020-04-06 | Identification method for identifying package authenticity based on trademark or pattern reading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010262053.6A CN111507947B (en) | 2020-04-06 | 2020-04-06 | Identification method for identifying package authenticity based on trademark or pattern reading |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111507947A CN111507947A (en) | 2020-08-07 |
| CN111507947B true CN111507947B (en) | 2023-06-27 |
Family
ID=71864063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010262053.6A Active CN111507947B (en) | 2020-04-06 | 2020-04-06 | Identification method for identifying package authenticity based on trademark or pattern reading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507947B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012007811A2 (en) * | 2010-07-13 | 2012-01-19 | パナソニック電工Ｓｕｎｘ株式会社 | Printed medium inspection system using image processing, authenticity determination method for printed medium, and image pickup apparatus therefor |
| CN105699382A (en) * | 2016-04-20 | 2016-06-22 | 姜太平 | Packaging film grain acquiring device |
| CN107895144A (en) * | 2017-10-27 | 2018-04-10 | 重庆工商大学 | A kind of finger vein image anti-counterfeiting discrimination method and device |
| CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
| CN108921006A (en) * | 2018-05-03 | 2018-11-30 | 西北大学 | The handwritten signature image true and false identifies method for establishing model and distinguishing method between true and false |
-
2020
- 2020-04-06 CN CN202010262053.6A patent/CN111507947B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012007811A2 (en) * | 2010-07-13 | 2012-01-19 | パナソニック電工Ｓｕｎｘ株式会社 | Printed medium inspection system using image processing, authenticity determination method for printed medium, and image pickup apparatus therefor |
| CN105699382A (en) * | 2016-04-20 | 2016-06-22 | 姜太平 | Packaging film grain acquiring device |
| CN107895144A (en) * | 2017-10-27 | 2018-04-10 | 重庆工商大学 | A kind of finger vein image anti-counterfeiting discrimination method and device |
| CN108921006A (en) * | 2018-05-03 | 2018-11-30 | 西北大学 | The handwritten signature image true and false identifies method for establishing model and distinguishing method between true and false |
| CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111507947A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230206720A1 (en) | System for counting quantity of game tokens | |
| CN105518709B (en) | The method, system and computer program product of face for identification | |
| CN102521560B (en) | Instrument pointer image identification method of high-robustness rod | |
| CN108291876A (en) | System and method for the authenticity for detecting product | |
| CN103473571B (en) | Human detection method | |
| CN103617420A (en) | Commodity fast recognition method and system based on image feature matching | |
| US9754191B2 (en) | Feature image generation apparatus, classification apparatus and non-transitory computer-readable memory, and feature image generation method and classification method | |
| JP6810392B2 (en) | Individual identification device | |
| CN110084788B (en) | Compressed tea appearance texture recording and identifying method | |
| CN109409377A (en) | The detection method and device of text in image | |
| CN115244542A (en) | Method and device for verifying authenticity of product | |
| CN111507947B (en) | Identification method for identifying package authenticity based on trademark or pattern reading | |
| Ye et al. | The technology of image processing used in automatic target-scoring system | |
| Rusia et al. | A Color-Texture-Based Deep Neural Network Technique to Detect Face Spoofing Attacks | |
| CN109886212A (en) | From the method and apparatus of rolling fingerprint synthesis fingerprint on site | |
| CN107220612B (en) | Fuzzy face discrimination method taking high-frequency analysis of local neighborhood of key points as core | |
| Hsu et al. | Vision-based automatic identification tracking of steel products for intelligent steel manufacturing | |
| CN114758162A (en) | Commodity anti-counterfeiting identification method and device, electronic equipment and storage medium | |
| CN103295186A (en) | Image descriptor generation method and system and image detection method and system | |
| KR101836768B1 (en) | System and method for object recognition based automatic picture color balance, recording medium thereof | |
| Hong et al. | Saliency-based feature learning for no-reference image quality assessment | |
| Stentiford et al. | Image recognition using maximal cliques of interest points | |
| Si et al. | Person re-identification via region-of-interest based features | |
| CN117496201B (en) | Identification method for electronic cigarette, atomizer and battery rod | |
| Kesiman et al. | Benchmarking A New Dataset for Coffee Bean Defects Classification Based on SNI 01-2907-2008 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 210012 room 801-810, 8 building, 7 Ande Gate Street, Yuhuatai District, Nanjing, Jiangsu, China, 57 Patentee after: Xinlixun Technology Group Co.,Ltd. Country or region after: China Address before: 210012 room 801-810, 8 building, 7 Ande Gate Street, Yuhuatai District, Nanjing, Jiangsu, China, 57 Patentee before: New Lixun Technology Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |