CN110705567A - Machine learning-based identification system and method for sneakers - Google Patents
Machine learning-based identification system and method for sneakers Download PDFInfo
- Publication number
- CN110705567A CN110705567A CN201910871059.0A CN201910871059A CN110705567A CN 110705567 A CN110705567 A CN 110705567A CN 201910871059 A CN201910871059 A CN 201910871059A CN 110705567 A CN110705567 A CN 110705567A
- Authority
- CN
- China
- Prior art keywords
- sneakers
- module
- data
- identified
- genuine
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims description 15
- 238000012545 processing Methods 0.000 claims abstract description 30
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 210000002105 tongue Anatomy 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Abstract
The invention provides a machine learning-based identification system for sneakers, which comprises a database module, a user module and a data processing module, wherein the database module is used for carrying out image data acquisition on the characteristics of the genuine sneakers, carrying out machine learning and establishing a characteristic database of the genuine sneakers; the user module is used for providing a system entrance for a user, and comprises an image acquisition module and an information service module, wherein the image acquisition module is used for acquiring image data of the characteristics of the sneakers to be identified, and the information service module is used for displaying identification results and storing identification records; the data processing module is used for receiving the feature data of the genuine sneakers provided by the database module and the feature data of the sneakers to be identified provided by the image acquisition module, comparing the feature data of the genuine sneakers with the feature data of the sneakers to be identified to form an identification result, and sending the identification result to the information service module.
Description
Technical Field
The invention relates to image processing and machine learning technologies, in particular to a system and a method for identifying sneakers based on machine learning.
Background
With the explosion of the sneaker market, the phenomenon that limited supply of the sneakers is not sufficient is increasingly serious, counterfeit goods in the market are abused, the authenticity of the sneakers becomes a main concern of consumers when the sneakers are purchased, so that a sneaker appraiser for appraising the authenticity of the sneakers is generated, the characteristics of the shoes, such as the appearances, insoles, shoe logos and the like are appraised, most of the appraising methods come from the experience and summary of the appraiser, the appraising speed is low, the experience is poor, and the error rate is high. CN 108509992A discloses a seal imprint intelligent identification anti-counterfeiting method based on machine learning technology. The method comprises the steps of carrying out image acquisition of a limited area on an imprint to be detected, carrying out machine learning and data training by using an SIFT algorithm, carrying out weight addition operation on an obtained stamp specification information weight, an imprint content view weight and a background content view weight, and judging the authenticity of the imprint through a total weight, so that the aim of quickly verifying the authenticity of the stamp is fulfilled. Thereby achieving the purpose of quickly verifying the authenticity of the seal. CN 109754393 a discloses a method and device for identifying tampered images based on deep learning. The image tampering detection problem is described as an image classification problem, and data training is performed by using the images with the original resolution ratio in the training, testing and judging stages by using a neural network algorithm, so that the purpose of distinguishing whether the images are tampered or not is achieved. CN 108509992A is mainly used for processing plane images such as stamps, and the requirement for acquiring the images is generally high. CN 109754393 a performed a tamper verification on images by using deep learning, and was not a true or false verification. Therefore, there is a need for a system for identifying a soccer shoe that overcomes the above-mentioned deficiencies.
Disclosure of Invention
The invention aims to provide a system and a method for identifying sneakers based on machine learning, which are used for identifying the genuineness of the sneakers by using a computer, avoiding the instability of artificial identification results and improving the identification efficiency.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a machine learning-based identification system for a soccer shoe, comprising:
the database module is used for carrying out image data acquisition on the characteristics of the genuine sneakers and carrying out machine learning to establish a characteristic database of the genuine sneakers;
the user module is used for providing a system entrance for a user, and comprises an image acquisition module and an information service module, wherein the image acquisition module is used for acquiring image data of the characteristics of the sneakers to be identified, and the information service module is used for displaying identification results and storing identification records;
and the data processing module is used for receiving the feature data of the genuine sneakers provided by the database module and the feature data of the sneakers to be identified provided by the image acquisition module, comparing the feature data of the genuine sneakers with the feature data of the sneakers to be identified to form an identification result, and sending the identification result to the information service module.
The user module is located at the application terminal, and the database module and the data processing module are located at the cloud end.
The identification method of the sneakers of the system comprises the following steps:
(1) the identification system of the sneakers acquires image data of the characteristics of the genuine sneakers through the database module and performs machine learning to establish a characteristic database of the genuine sneakers;
(2) a user enters the sneaker identification system through the user module and selects the style of the sneaker to be identified through the information service module;
(3) the user acquires image data of the characteristics of the sneakers to be identified through the image acquisition module to obtain the characteristic data of the sneakers to be identified;
when image data is collected, the characteristics of the sneakers to be identified comprise shoe tongues, shoe marks, shoe sole routing, shoe pads, shoe box steel marks, side marks and the overall appearance of the sneakers;
when image data is collected, a user places the characteristics of the sneakers to be identified at the central position of the image;
when image data are collected, if the image is deformed due to the problem of shooting angle, the image collection module locally intercepts a central position area of the image, performs image projection transformation by using a corresponding mapping relation fitted by a function, and performs denoising processing by using a bilinear interpolation algorithm to obtain characteristic data of the sneakers to be identified;
(4) the image acquisition module sends the characteristic data of the sneakers to be identified to the data processing module at the cloud end;
(5) the data processing module requests the database module to provide characteristic data of the genuine sneakers of the styles corresponding to the sneakers to be identified, and the database module receives the request of the data processing module and sends the characteristic data of the genuine sneakers of the corresponding styles to the data processing module;
(6) the data processing module compares the characteristic data of the standard sneakers with the characteristic data of the sneakers to be identified to form an identification result, and sends the identification result to the information service module.
The invention has the advantages that:
the database module of the system carries out image data acquisition on the characteristics of the genuine sneakers and carries out machine learning, a characteristic database of the genuine sneakers is established, image data acquisition is carried out on the characteristics of the sneakers to be identified through the image acquisition module, the characteristic data of the sneakers to be identified are obtained, the characteristic data of the genuine sneakers and the characteristic data of the sneakers to be identified are compared through the data processing module to form an identification result, the instability of identification carried out by personal experience is avoided, the identification time is shortened, the identification efficiency is improved, under the condition that the accuracy of the database data is guaranteed, the pirate market can be greatly struck, the market order is maintained, and the market fairness is realized.
Drawings
FIG. 1 is a schematic diagram of the construction of a sneaker identification system according to the present invention;
FIG. 2 is a schematic diagram of the database module operation;
FIG. 3 is an image acquisition flow chart;
FIG. 4 is a flow chart of the operation of the identification system of the shoes.
Detailed Description
In order to make the technical means, the original characteristics, the achieved purposes and the effects of the invention easy to understand, the invention is further described with reference to the figures and the specific embodiments.
As shown in fig. 1, the identification system for shoes based on machine learning provided by the invention comprises a database module, a user module and a data processing module, wherein the database module is used for carrying out image data acquisition on the characteristics of the genuine shoes, carrying out machine learning and establishing a characteristic database of the genuine shoes; the user module is used for providing a system entrance for a user, and comprises an image acquisition module and an information service module, wherein the image acquisition module is used for acquiring image data of the characteristics of the sneakers to be identified, and the information service module is used for displaying identification results and storing identification records; the data processing module is used for receiving the feature data of the genuine sneakers provided by the database module and the feature data of the sneakers to be identified provided by the image acquisition module, comparing the feature data of the genuine sneakers with the feature data of the sneakers to be identified to form an identification result, and sending the identification result to the information service module. The user module is located at the application terminal, and the database module and the data processing module are located at the cloud end.
As shown in fig. 2 to 4, the identification method of the sneakers of the system comprises the following steps: the identification system of the sneakers acquires image data of the characteristics of the genuine sneakers through the database module and performs machine learning to establish a characteristic database of the genuine sneakers; a user enters the sneaker identification system through the user module and selects the style of the sneaker to be identified through the information service module; the method comprises the steps that a user acquires image data of the characteristics of the sneakers to be identified through an image acquisition module to obtain the characteristic data of the sneakers to be identified (when the image data are acquired, the characteristics of the sneakers to be identified comprise a shoe tongue, a shoe mark, a shoe sole wiring line, an insole, a shoe box steel seal, a side mark and the overall appearance of the sneakers, when the image data are acquired, the user places the characteristics of the sneakers to be identified at the central position of an image, when the image data are acquired, if the image is deformed due to shooting angle problems, the image acquisition module intercepts the central position area of the image locally, performs image projection transformation by using a corresponding mapping relation fitted by a function, and performs denoising by using a bilinear interpolation algorithm to obtain the characteristic data of the sneakers; the image acquisition module sends the characteristic data of the sneakers to be identified to the data processing module at the cloud end; the data processing module requests the database module to provide characteristic data of the genuine sneakers of the styles corresponding to the sneakers to be identified, and the database module receives the request of the data processing module and sends the characteristic data of the genuine sneakers of the corresponding styles to the data processing module; the data processing module compares the characteristic data of the standard sneakers with the characteristic data of the sneakers to be identified to form an identification result, and sends the identification result to the information service module.
The database module of the system carries out image data acquisition on the characteristics of the genuine sneakers and carries out machine learning, a characteristic database of the genuine sneakers is established, image data acquisition is carried out on the characteristics of the sneakers to be identified through the image acquisition module, the characteristic data of the sneakers to be identified are obtained, the characteristic data of the genuine sneakers and the characteristic data of the sneakers to be identified are compared through the data processing module to form an identification result, the instability of identification carried out by personal experience is avoided, the identification time is shortened, the identification efficiency is improved, under the condition that the accuracy of the database data is guaranteed, the pirate market can be greatly struck, the market order is maintained, and the market fairness is realized.
The above embodiments are merely illustrative of the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the content of the present invention and implement the present invention, and not to limit the scope of the present invention, and all equivalent changes or modifications made according to the spirit of the present invention should be covered by the scope of the present invention.
Claims (6)
1. A machine learning-based identification system for a sneaker, comprising:
the database module is used for carrying out image data acquisition on the characteristics of the genuine sneakers and carrying out machine learning to establish a characteristic database of the genuine sneakers;
the user module is used for providing a system entrance for a user, and comprises an image acquisition module and an information service module, wherein the image acquisition module is used for acquiring image data of the characteristics of the sneakers to be identified, and the information service module is used for displaying identification results and storing identification records;
and the data processing module is used for receiving the feature data of the genuine sneakers provided by the database module and the feature data of the sneakers to be identified provided by the image acquisition module, comparing the feature data of the genuine sneakers with the feature data of the sneakers to be identified to form an identification result, and sending the identification result to the information service module.
2. A machine learning-based sneaker identification system according to claim 1, wherein:
the user module is located at the application terminal, and the database module and the data processing module are located at the cloud end.
3. A method of identifying a sneaker in accordance with the system of claim 1, comprising:
(1) the identification system of the sneakers acquires image data of the characteristics of the genuine sneakers through the database module and performs machine learning to establish a characteristic database of the genuine sneakers;
(2) a user enters the sneaker identification system through the user module and selects the style of the sneaker to be identified through the information service module;
(3) the user acquires image data of the characteristics of the sneakers to be identified through the image acquisition module to obtain the characteristic data of the sneakers to be identified;
(4) the image acquisition module sends the characteristic data of the sneakers to be identified to the data processing module at the cloud end;
(5) the data processing module requests the database module to provide characteristic data of the genuine sneakers of the styles corresponding to the sneakers to be identified, and the database module receives the request of the data processing module and sends the characteristic data of the genuine sneakers of the corresponding styles to the data processing module;
(6) the data processing module compares the characteristic data of the standard sneakers with the characteristic data of the sneakers to be identified to form an identification result, and sends the identification result to the information service module.
4. A method of identifying a sneaker according to claim 3, wherein:
in the step (3), when the image data is collected, the characteristics of the sneakers to be identified comprise shoe tongues, shoe marks, shoe sole routing lines, shoe pads, shoe box steel seals, side marks and the overall appearance of the sneakers.
5. A method of identifying a sneaker according to claim 3, wherein:
in the step (3), when image data is collected, the user places the characteristics of the sneakers to be identified at the central position of the image.
6. The identification method of a sneaker according to claim 5, wherein:
in the step (3), when image data is acquired, if the image is deformed due to the problem of shooting angle, the image acquisition module locally intercepts a central position area of the image, performs image projection transformation by using a corresponding mapping relation fitted by a function, and performs denoising processing by using a bilinear interpolation algorithm to obtain characteristic data of the sneakers to be identified.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910871059.0A CN110705567A (en) | 2019-09-16 | 2019-09-16 | Machine learning-based identification system and method for sneakers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910871059.0A CN110705567A (en) | 2019-09-16 | 2019-09-16 | Machine learning-based identification system and method for sneakers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110705567A true CN110705567A (en) | 2020-01-17 |
Family
ID=69195404
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910871059.0A Pending CN110705567A (en) | 2019-09-16 | 2019-09-16 | Machine learning-based identification system and method for sneakers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110705567A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111882015A (en) * | 2020-07-15 | 2020-11-03 | 拍拍看(海南)人工智能有限公司 | Genuine insurance anti-counterfeiting method, marker, device and related equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009266082A (en) * | 2008-04-28 | 2009-11-12 | Bloom Co Ltd | System for determining authenticity |
CN104361056A (en) * | 2014-10-30 | 2015-02-18 | 蒲重良 | Automatic ancient ceramic authenticity identification system and method |
CN107463962A (en) * | 2017-08-08 | 2017-12-12 | 张天君 | A kind of method and system of micro- artificial intelligence identification suitcase |
CN108573205A (en) * | 2017-09-26 | 2018-09-25 | 中科智文(北京)科技有限公司 | A kind of Khotan jade seed material micro-image intelligent identifying system |
CN108876402A (en) * | 2018-05-30 | 2018-11-23 | 于东升 | For the method for anti-counterfeit and device of leather and fur products, anti-fake traceability system |
CN109146517A (en) * | 2018-08-02 | 2019-01-04 | 惠龙 | A kind of fake products data identification method based on online dictionary learning Data Matching model |
CN109389192A (en) * | 2018-09-30 | 2019-02-26 | 安徽职业技术学院 | A kind of art work authentication method based on RFID coding |
CN109948713A (en) * | 2019-03-22 | 2019-06-28 | 邓斌 | A kind of authentication approach of painting and calligraphy pieces |
WO2019148729A1 (en) * | 2018-02-01 | 2019-08-08 | 平安科技(深圳)有限公司 | Luxury goods identification method, electronic device, and storage medium |
-
2019
- 2019-09-16 CN CN201910871059.0A patent/CN110705567A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009266082A (en) * | 2008-04-28 | 2009-11-12 | Bloom Co Ltd | System for determining authenticity |
CN104361056A (en) * | 2014-10-30 | 2015-02-18 | 蒲重良 | Automatic ancient ceramic authenticity identification system and method |
CN107463962A (en) * | 2017-08-08 | 2017-12-12 | 张天君 | A kind of method and system of micro- artificial intelligence identification suitcase |
CN108573205A (en) * | 2017-09-26 | 2018-09-25 | 中科智文(北京)科技有限公司 | A kind of Khotan jade seed material micro-image intelligent identifying system |
WO2019148729A1 (en) * | 2018-02-01 | 2019-08-08 | 平安科技(深圳)有限公司 | Luxury goods identification method, electronic device, and storage medium |
CN108876402A (en) * | 2018-05-30 | 2018-11-23 | 于东升 | For the method for anti-counterfeit and device of leather and fur products, anti-fake traceability system |
CN109146517A (en) * | 2018-08-02 | 2019-01-04 | 惠龙 | A kind of fake products data identification method based on online dictionary learning Data Matching model |
CN109389192A (en) * | 2018-09-30 | 2019-02-26 | 安徽职业技术学院 | A kind of art work authentication method based on RFID coding |
CN109948713A (en) * | 2019-03-22 | 2019-06-28 | 邓斌 | A kind of authentication approach of painting and calligraphy pieces |
Non-Patent Citations (1)
Title |
---|
王存睿等: "基于人脸检测的教室信息智能采集系统", 《大连民族学院学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111882015A (en) * | 2020-07-15 | 2020-11-03 | 拍拍看(海南)人工智能有限公司 | Genuine insurance anti-counterfeiting method, marker, device and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10210423B2 (en) | Image match for featureless objects | |
CN110874746B (en) | Product traceability system based on block chain | |
Ferrer et al. | Robustness of offline signature verification based on gray level features | |
WO2018095142A1 (en) | Livestream interaction method and apparatus | |
US8934734B1 (en) | Video identification through detection of proprietary rights logos in media | |
CN108416902B (en) | Real-time object identification method and device based on difference identification | |
Ortega-Delcampo et al. | Border control morphing attack detection with a convolutional neural network de-morphing approach | |
CN105631272B (en) | A kind of identity identifying method of multiple security | |
US10127310B2 (en) | Search method and system | |
WO2019067310A1 (en) | System and method for entity recognition | |
US20160335490A1 (en) | Method and apparatus for detecting persons, and non-transitory computer-readable recording medium | |
CN103617420A (en) | Commodity fast recognition method and system based on image feature matching | |
EP4109332A1 (en) | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device | |
CN106250958A (en) | With hiding mark combination tag and generate method with generate system | |
WO2021179157A1 (en) | Method and device for verifying product authenticity | |
CN111046889A (en) | Method and device for processing pressed tea information and electronic equipment | |
CN110705567A (en) | Machine learning-based identification system and method for sneakers | |
CN112437946A (en) | Illegal action estimation system, illegal action estimation method, and program | |
CN105868815A (en) | Superposed-type combined identification based on same identification equipment, and generation method and system | |
TWI766408B (en) | A method for verifying product authenticity and establishing authorized product data by fabric characteristics | |
CN114758162A (en) | Commodity anti-counterfeiting identification method and device, electronic equipment and storage medium | |
Yuan et al. | Footwear for gender recognition | |
Rabasse et al. | A method for the synthesis of dynamic biometric signature data | |
CN107240184B (en) | Method, device and equipment for identifying versions of plastic coins | |
WO2020072664A1 (en) | Vision based recognition of gaming chips |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |
|
RJ01 | Rejection of invention patent application after publication |