CN102930264A - System and method for acquiring and analyzing commodity display information based on image identification technology - Google Patents

System and method for acquiring and analyzing commodity display information based on image identification technology Download PDF

Info

Publication number
CN102930264A
CN102930264A CN2012103768076A CN201210376807A CN102930264A CN 102930264 A CN102930264 A CN 102930264A CN 2012103768076 A CN2012103768076 A CN 2012103768076A CN 201210376807 A CN201210376807 A CN 201210376807A CN 102930264 A CN102930264 A CN 102930264A
Authority
CN
China
Prior art keywords
server
image
commodity display
commodity
feature
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.)
Granted
Application number
CN2012103768076A
Other languages
Chinese (zh)
Other versions
CN102930264B (en
Inventor
李炳华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou full latitude image Mdt InfoTech Ltd
Original Assignee
李炳华
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 李炳华 filed Critical 李炳华
Priority to CN201210376807.6A priority Critical patent/CN102930264B/en
Publication of CN102930264A publication Critical patent/CN102930264A/en
Application granted granted Critical
Publication of CN102930264B publication Critical patent/CN102930264B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a system and a method for acquiring and analyzing commodity display information based on an image identification technology. The system comprises an image acquisition terminal and an image processing center which is connected with the image acquisition terminal through Internet, wherein the image processing center comprises an image storage server, an image analysis server, a database server, a client and a router/switchboard; and the image storage server, the image analysis server, the database server and the client are respectively connected with the router/switchboard. The method comprises the following steps of: 1) establishing a feature library; 2) acquiring commodity display pictures; 3) reading the commodity display pictures, and analyzing and cutting the pictures; 4) identifying the obtained commodity information and display position information; 5) identifying the positions of price labels and acquiring price label information; and 6) associating the acquired price label information with bar codes for commodities. By the system and the method, the efficiency of entering the commodity display information can be improved substantially, and the cost of information acquisition is reduced.

Description

Commodity display information acquisition and analysis system and method based on image recognition technology
Technical field
The present invention relates to a kind of acquisition analysis system and method, especially a kind of commodity display information acquisition and analysis system and method based on image recognition technology belong to commodity display information discriminating technology field.
Background technology
In retail trade, especially in the retail trade of fast-moving consumer goods (such as food, personal hygiene article, tobacco and drinks and the beverage etc. of packing), the display mode of commodity and price have conclusive impact to the sale of commodity.Commodity display is in good position and poor position, and its sales volume is poor to be very obvious, and good display position is very rare in retail shops, and therefore, how by data analysis, the utilization ratio of optimization display position is very valuable research field.
In this commodity display research field, the most basic problem is the display information of product to be converted to the numerical information that computer can statistical study.Mainly be to realize that by following dual mode product display information is converted to the numerical information that computer can be analyzed in the existing market:
1) manually fill in the papery form, and then typing computer or the artificial form of directly filling in electronic format.The market research agency of the overwhelming majority all adopts this mode to process in the Chinese market.The main shortcoming of this mode is inefficiency, and mistake is difficult to control, and the limitation that is subjected to labor cost.
2) adopt the advanced technologies such as bar code (or RFID) and shelf location bar code (or RFID) to carry out the collection of merchandise news and commodity display position, then the content such as manual entry pricing information.This mode recognition value and the display position that gathers commodity are high efficiency, and bar code reading (or RFID) chance of makeing mistakes is very little.But the limitation of this mode is, it requires shelf to dispose the position that corresponding position bar code (or RFID) represents shelf, and the production cost of this shelf and maintenance cost are all higher; The simultaneously collection of bar code (or RFID) needs special terminal, and therefore, it is difficult to penetration and promotion.At present, in common supermarket environment, substantially do not possess the condition that is widely used this class technology.This technical scheme only adopts at the very high logistics warehouse shelf of some management expectancys.
In addition, also having a kind of mode is by the image recognition mode commodity display photo to be analyzed, and obtains the information such as commodity display position and merchandise classification.The disclosed a kind of image acquisition-analysis method of Chinese patent 201110098035.X has adopted this mode exactly, and the method for its design is at the commodity shelf special-purpose scale to be set, and contains coded message on the scale; The commodity display picture that contains these scales by analysis obtains the information such as shelf location and size.The display position efficient that this mode gathers commodity is higher, but its limitation is that it requires the special scale marking of shelf configuration to represent the position of shelf, can increase the complicated operation degree and increase use cost; Simultaneously, the position of labeling chi generally is used for the publicity of Commdity advertisement information on the shelf, and every layer of shelf all stick visual effect and the advertising effect that such scale can affect shelf, therefore, promotes to get up to acquire a certain degree of difficulty in common supermarket environment.
Summary of the invention
Purpose of the present invention is in order to solve the defective of above-mentioned prior art, to provide a kind of and can significantly improve the efficient of commodity display Data Enter, the commodity display information acquisition and analysis system based on image recognition technology of reduction acquisition of information cost.
Another object of the present invention is to provide a kind of commodity display analysis of information collection method based on image recognition technology.
Purpose of the present invention can reach by taking following technical scheme:
Commodity display information acquisition and analysis system based on image recognition technology is characterized in that: comprise image acquisition terminal and the image processing enter that is connected with the image acquisition terminal by the internet;
Described image acquisition terminal is used for taking the commodity display picture, and by the internet picture is sent to the image processing enter;
Described image processing enter comprises image storage server, graphical analysis server, database server, client and router/switch;
Described image storage server is used for the commodity display picture that the store images acquisition terminal sends;
Described graphical analysis server is used for the commodity display picture that the reading images storage server stores, and identifies the commodity display information that obtains;
Described database server is used for the commodity display information that the identification of store images Analysis server obtains;
Described client is used for carrying out alternately with graphical analysis server and database server;
Described image storage server, graphical analysis server, database server are connected with router/switch with client and are connected.
As a kind of preferred version, described image acquisition terminal is interconnective digital camera and PC, or band is taken pictures and the smart mobile phone/glasses of function of surfing the Net.
As a kind of preferred version, described image processing enter also comprises the firewall box that carries out authentication for to the image acquisition terminal, and described firewall box is connected with router/switch.
As a kind of preferred version, described image storage server is for supporting the server of large capacity storage and express network transmission; Described graphical analysis server is the GPU cluster server; Described client is comprised of one or more PC.
Another object of the present invention can reach by taking following technical scheme:
Commodity display analysis of information collection method based on image recognition technology is characterized in that may further comprise the steps:
1) in the graphical analysis server, sets up the feature database of a CF;
2) image acquisition terminal taking commodity display picture, the upper left corner and lower right corner dots in red of each mark to shelf position in the picture represent the position of shelf in the commodity display picture, then send to the image processing enter by the internet, and be stored in the image storage server;
3) the graphical analysis server reads the commodity display picture from image storage server, dots in red to mark in the picture is made straight line by vertical and horizontal direction, shelf in the picture are partly cut out, shelf are partly carried out printed page analysis, then press shelf plywood with the layering of shelf part, the identical goods that is displayed in every layer of shelf is together cut at a segment, and every layer of shelf obtain the segment of several different commodity;
4) extract the commodity segment CF feature that each cuts out, find matching characteristic in feature database, identification obtains the merchandise news that represents with bar code; Extract again pixels across and vertical pixel of each commodity segment that cuts out, conversion obtains height and the width of corresponding commodity display position in shelf, and the display position information storage that the merchandise news that then identification is obtained and conversion obtain is to database server;
5) the graphical analysis server reads the commodity display picture from image storage server, picture is carried out printed page analysis, identify the price tag position, and the price tag region cut out, use the OCR technology that numeral is identified, obtain the price label information of corresponding display position;
6) in client the price label information that obtains and bar code are carried out relatedly, then be stored into database server.
As a kind of preferred version, in the step 1) CF feature database set up specific as follows:
A) choose at random the commodity picture, adopt the FAST Corner Detection Algorithm to extract significant point;
B) adopt the CSIFT/OPPONENTSIFT descriptor algorithm of being expanded by SIFT, to each significant point that detects, the gradient magnitude m of the point of its peripheral part and the computing formula of direction θ are as follows:
m ( x , y ) = ( I ( x + 1 , y ) - I ( x - 1 , y ) ) 2 + ( I ( x , y + 1 ) - I ( x , y - 1 ) ) 2
θ(x,y)=tan -1((I(x,y+1)-I(x,y-1))/(I(x+1,y)-I(x-1,y)))
Wherein, the gray-scale value of I (x, y) representative point (x, y); Calculate the gradient information of the point of its peripheral part, and press the gradient direction statistic histogram as last feature, obtain 384 dimensional feature vectors;
C) adopt the kmean clustering algorithm, the proper vector that step b) obtains is encoded, the unique point of phase pairing approximation is assembled, merge the generating center point, all central points are combined makes up the Codebook dictionary;
D) add up word frequency number that each vector occurs in the Codebook dictionary, obtain at last the histogram of each word frequency, i.e. BOW word band feature;
E) with BOW word band feature and corresponding classification input SVM, training SVM model;
F) repeat above-mentioned steps, until with the BOW word band feature of extensive stock and corresponding classification input SVM model, training SVM model, generation can be carried out the feature database that pin-point accuracy is classified to the input product features.
As a kind of preferred version, step 2) in, add the MD5 check information by the commodity display picture of image acquisition terminal after to mark.
As a kind of preferred version, the layering of shelf part is after being divided into several zonules by the image with the shelf part, to extract the image border in the step 3), keeps the edge pixel of level, then adopt the Radon conversion to carry out straight-line detection, thereby with the layering of shelf part.
As a kind of preferred version, specific as follows to the identification of each commodity segment in the step 4):
At first adopt the FAST Corner Detection Algorithm to extract the significant point of segment, then calculate the feature of this point by CSIFT/OPPONENTSIFT descriptor algorithm, with each vector of the feature that obtains and Codebook dictionary relatively, it is classified as the most close numbering corresponding to that vector, the word frequency number that each vector occurs in the statistics Codebook dictionary obtains BOW word band feature; With BOW word band feature input SVM model, judge that according to feature database classification under the final output identifies merchandise news, represents with bar code.
As a kind of preferred version, in the step 4), if when the CF feature that has segment to extract can't find matching characteristic in feature database, by client segment is processed, and then the recognition result of correction image Analysis server, and upgrade the merchandise news that stores in the database server.
The present invention has following beneficial effect with respect to prior art:
1, the present invention analyzes the image information that gathers at shelf display photo and by the graphical analysis server by image acquisition terminal collection commodity, greatly improved the efficient of commodity display Data Enter, reduce the cost of acquisition of information, its popularization is better than bar code (or RFID) and adds that specialized equipment realizes the mode of product display information conversion.
2, the present invention can adopt the MD5 algorithm that the picture that gathers is added check information in the image acquisition terminal, guarantees that picture can not distort after gathering, and is conducive to the accuracy of guarantee information, and the information of accomplishing can review and check.
3, the present invention analyzes and processes commodity display information by the graphical analysis server that has adopted image recognition technology, can reasonably realize large-scale image processing and image recognition computing in the cost scope, effectively overcome and manually filled in the papery form, and then typing computer or manually directly fill in the form inefficiency of electronic format, produce the defective of mistake easily, and solved the stress problems of human cost.
4, the present invention is can be in the upper left corner and dots in red of each mark of the lower right corner of the picture shelf position that gathers, then shelf are partly cut out, look like to carry out printed page analysis at the planogram of commodity shelf and identify the shelf plywood position, thereby realize the layering to the commodity display shelf image, can convert simultaneously and obtain height and the width of corresponding commodity display position in shelf, and need not to depend on the special scale that arranges at shelf, can be more widely applicable for common commodity display shelf; The color and the local shape facility that adopt the extraction of FAST algorithm and CSIFT/OPPONENTSIFT to describe commodity come recognition value information, can reach accurate effect.
Description of drawings
Fig. 1 is the structured flowchart of acquisition analysis system of the present invention.
Fig. 2 is the collection analysis schematic flow sheet of acquisition analysis system of the present invention.
Fig. 3 is the schematic flow sheet that feature database of the present invention is set up.
Fig. 4 is the schematic flow sheet of commodity graphic blocks identifying of the present invention.
Embodiment
Embodiment 1:
As shown in Figure 1, the acquisition analysis system of present embodiment comprises image acquisition terminal 1 and image processing enter 2, and described image acquisition terminal 1 is connected with image processing enter 2 by the internet; Described image processing enter 2 comprises image storage server 2-1, graphical analysis server 2-2, database server 2-3, client 2-4, router/switch 2-5 and firewall box 2-6; Described image storage server 2-1, graphical analysis server 2-2, database server 2-3, client 2-4 are connected with router/switch 2-5 with firewall box 2-6 and are connected, and consist of a LAN (Local Area Network).
Wherein, described image acquisition terminal 1 is taken pictures for band and the smart mobile phone of function of surfing the Net.Described image storage server 2-1 is for supporting the server of large capacity storage and express network transmission; Described graphical analysis server 2-2 is the GPU cluster server; Described client 2-4 is comprised of one or more PC.
As depicted in figs. 1 and 2, the capturing analysis method of present embodiment is as follows:
1) in graphical analysis server 2-2, sets up the feature database of a CF;
2) image acquisition terminal 1 is taken the commodity display picture, the upper left corner and lower right corner dots in red of each mark to shelf position in the picture represent the position of shelf in the commodity display picture, commodity display picture behind the mark is added the MD5 check information, then send to image processing enter 2 by the internet, after the authentication of firewall box 2-6 to image acquisition terminal 1, the commodity display picture is stored among the image storage server 2-1;
3) graphical analysis server 2-2 reads the commodity display picture from image storage server 2-1, dots in red to mark in the picture is made straight line by vertical and horizontal direction, shelf in the picture are partly cut out, shelf are partly carried out printed page analysis, after the image of shelf parts is divided into several zonules, extract the image border, the edge pixel of reservation level, then adopt the Radon conversion to carry out straight-line detection, thereby with the layering of shelf part, the identical goods that is displayed in every layer of shelf is together cut at a segment, and every layer of shelf obtain the segment of several different commodity;
4) extract the commodity segment CF feature that each cuts out, find matching characteristic in feature database, identification obtains the merchandise news that represents with bar code; Extract again pixels across and vertical pixel of each commodity segment that cuts out, conversion obtains height and the width of corresponding commodity display position in shelf, and the display position information storage that the merchandise news that then identification is obtained and conversion obtain is to database server 2-3;
5) if when the CF feature that has segment to extract can't find matching characteristic in feature database, 2-4 processes segment by client, and then the recognition result of correction image Analysis server 2-2, and upgrade the merchandise news that stores among the database server 2-3; Otherwise, direct execution in step 6).
6) graphical analysis server 2-2 reads the commodity display picture from image storage server 2-1, picture is carried out printed page analysis, identify the price tag position, and the price tag region cut out, use the OCR technology that numeral is identified, obtain the price label information of corresponding display position;
7) at client 2-4 the price label information that obtains and bar code are carried out relatedly, then be stored into database server 2-3.
As shown in Figure 3, in the step 1) CF feature database set up specific as follows:
A) choose the commodity picture, adopt the FAST Corner Detection Algorithm to extract significant point;
B) adopt the CSIFT/OPPONENTSIFT descriptor algorithm of being expanded by SIFT, to each significant point that detects, the gradient magnitude m of the point of its peripheral part and the computing formula of direction θ are as follows:
m ( x , y ) = ( I ( x + 1 , y ) - I ( x - 1 , y ) ) 2 + ( I ( x , y + 1 ) - I ( x , y - 1 ) ) 2
θ(x,y)=tan -1((I(x,y+1)-I(x,y-1))/(I(x+1,y)-I(x-1,y)))
Wherein, the gray-scale value of I (x, y) representative point (x, y); Calculate the gradient information of the point of its peripheral part, and press the gradient direction statistic histogram as last feature, obtain 384 dimensional feature vectors;
C) adopt the kmean clustering algorithm, the proper vector that step b) obtains is encoded, the unique point of phase pairing approximation is assembled, merge the generating center point, all central points are combined makes up the Codebook dictionary;
D) add up word frequency number that each vector occurs in the Codebook dictionary, obtain at last the histogram of each word frequency, i.e. BOW word band feature;
E) with BOW word band feature and corresponding classification input SVM, training SVM model;
F) repeat above-mentioned steps, until with the BOW word band feature of extensive stock and corresponding classification input SVM model, training SVM model, generation can be carried out the feature database that pin-point accuracy is classified to the input product features.
As shown in Figure 4, specific as follows to the identification of each commodity segment in the step 4):
At first adopt the FAST Corner Detection Algorithm to extract the significant point of segment, then press the feature of CSIFT/OPPONENTSIFT descriptor algorithm calculating significant point, with each vector of the feature that obtains and Codebook dictionary relatively, it is classified as the most close numbering corresponding to that vector, the word frequency number that each vector occurs in the statistics Codebook dictionary obtains BOW word band feature; With BOW word band feature input SVM model, judge that according to feature database classification under the final output identifies merchandise news, represents with bar code.
Embodiment 2:
The characteristics of present embodiment are: described image acquisition terminal 1 is interconnective digital camera and PC, or band is taken pictures and the intelligent glasses of function of surfing the Net.All the other are with embodiment 1.
The above; it only is the preferred embodiment of the invention; but protection scope of the present invention is not limited to this; anyly be familiar with those skilled in the art in scope disclosed in this invention; be equal to replacement or change according to technical scheme of the present invention and inventive concept thereof, all belonged to protection scope of the present invention.

Claims (10)

1. based on the commodity display information acquisition and analysis system of image recognition technology, it is characterized in that: comprise image acquisition terminal (1) and the image processing enter (2) that is connected with image acquisition terminal (1) by the internet;
Described image acquisition terminal (1) is used for taking the commodity display picture, and by the internet picture is sent to image processing enter (2);
Described image processing enter (2) comprises image storage server (2-1), graphical analysis server (2-2), database server (2-3), client (2-4) and router/switch (2-5);
Described image storage server (2-1) is used for the commodity display picture that store images acquisition terminal (1) sends;
Described graphical analysis server (2-2) is used for the commodity display picture that reading images storage server (2-1) stores, and identifies the commodity display information that obtains;
Described database server (2-3) is used for the commodity display information that store images Analysis server (2-2) identification obtains;
Described client (2-4) is used for carrying out alternately with graphical analysis server (2-2) and database server (2-3);
Described image storage server (2-1), graphical analysis server (2-2), database server (2-3) are connected 2-4 with client) be connected with router/switch (2-5) respectively.
2. the commodity display information acquisition and analysis system based on image recognition technology according to claim 1 is characterized in that: described image acquisition terminal (1) is interconnective digital camera and PC, or band is taken pictures and the smart mobile phone/glasses of function of surfing the Net.
3. the commodity display information acquisition and analysis system based on image recognition technology according to claim 1 and 2, it is characterized in that: described image processing enter (2) comprises that also described firewall box (2-6) is connected with router/switch (2-5) for the firewall box (2-6) that image acquisition terminal (1) is carried out authentication.
4. the commodity display information acquisition and analysis system based on image recognition technology according to claim 3 is characterized in that: the server of described image storage server (2-1) for supporting that large capacity storage and express network transmit; Described graphical analysis server (2-2) is the GPU cluster server; Described client (2-4) is comprised of one or more PC.
5. based on the commodity display analysis of information collection method of the described system of claim 1, it is characterized in that may further comprise the steps:
1) in graphical analysis server (2-2), sets up the feature database of a CF;
2) image acquisition terminal (1) is taken the commodity display picture, the upper left corner and lower right corner dots in red of each mark to shelf position in the picture represent the position of shelf in the commodity display picture, then send to image processing enter (2) by the internet, and be stored in the image storage server (2-1);
3) graphical analysis server (2-2) reads the commodity display picture from image storage server (2-1), dots in red to mark in the picture is made straight line by vertical and horizontal direction, shelf in the picture are partly cut out, shelf are partly carried out printed page analysis, then press shelf plywood with the layering of shelf part, the identical goods that is displayed in every layer of shelf is together cut at a segment, and every layer of shelf obtain the segment of several different commodity;
4) extract the commodity segment CF feature that each cuts out, find matching characteristic in feature database, identification obtains the merchandise news that represents with bar code; Extract again pixels across and vertical pixel of each commodity segment that cuts out, conversion obtains height and the width of corresponding commodity display position in shelf, and the display position information storage that the merchandise news that then identification is obtained and conversion obtain is to database server (2-3);
5) graphical analysis server (2-2) reads the commodity display picture from image storage server (2-1), picture is carried out printed page analysis, identify the price tag position, and the price tag region cut out, use the OCR technology that numeral is identified, obtain the price label information of corresponding display position;
6) in client (2-4) price label information that obtains and bar code are carried out relatedly, then be stored into database server (2-3).
6. the shopping saving system analytical approach based on image recognition technology according to claim 5 is characterized in that: in the step 1) CF feature database set up specific as follows:
A) choose the commodity picture, adopt the FAST Corner Detection Algorithm to extract significant point;
B) adopt the CSIFT/OPPONENTSIFT descriptor algorithm of being expanded by SIFT, to each significant point that detects, the gradient magnitude m of the point of its peripheral part and the computing formula of direction θ are as follows:
θ(x,y)=tan -1((I(x,y+1)-I(x,y-1))/(I(x+1,y)-I(x-1,y)))
Wherein, the gray-scale value of I (x, y) representative point (x, y); Calculate the gradient information of the point of its peripheral part, and press the gradient direction statistic histogram as last feature, obtain 384 dimensional feature vectors;
C) adopt the kmean clustering algorithm, the proper vector that step b) obtains is encoded, the unique point of phase pairing approximation is assembled, merge the generating center point, all central points are combined makes up the Codebook dictionary;
D) add up word frequency number that each vector occurs in the Codebook dictionary, obtain at last the histogram of each word frequency, i.e. BOW word band feature;
E) with BOW word band feature and corresponding classification input SVM, training SVM model;
F) repeat above-mentioned steps, until BOW word band feature and the corresponding classification of extensive stock are inputted the SVM model, training SVM model, generation can be carried out the feature database that pin-point accuracy is classified to the input product features.
7. the shopping saving system analytical approach based on image recognition technology according to claim 6 is characterized in that: step 2) in, by image acquisition terminal (1) the commodity display picture behind the mark is added the MD5 check information.
8. the shopping saving system analytical approach based on image recognition technology according to claim 7, it is characterized in that: the layering of shelf part is after being divided into several zonules by the image with the shelf part in the step 3), extract the image border, the edge pixel of reservation level, then adopt the Radon conversion to carry out straight-line detection, thereby with the layering of shelf part.
9. the shopping saving system analytical approach based on image recognition technology according to claim 8 is characterized in that: specific as follows to the identification of each commodity segment in the step 4):
At first adopt the FAST Corner Detection Algorithm to extract the significant point of segment, then calculate the feature of this point by CSIFT/OPPONENTSIFT descriptor algorithm, with each vector of the feature that obtains and Codebook dictionary relatively, it is classified as the most close numbering corresponding to that vector, the word frequency number that each vector occurs in the statistics Codebook dictionary obtains BOW word band feature; With BOW word band feature input SVM model, judge that according to feature database classification under the final output identifies merchandise news, represents with bar code.
10. the shopping saving system analytical approach based on image recognition technology according to claim 9, it is characterized in that: in the step 4), when if the CF feature that has segment to extract can't find matching characteristic in feature database, (2-4) processes segment by client, and then the recognition result of correction image Analysis server (2-2), and upgrade the merchandise news that stores in the database server (2-3).
CN201210376807.6A 2012-09-29 2012-09-29 Based on commodity display information acquisition and analysis system and the method for image recognition technology Expired - Fee Related CN102930264B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210376807.6A CN102930264B (en) 2012-09-29 2012-09-29 Based on commodity display information acquisition and analysis system and the method for image recognition technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210376807.6A CN102930264B (en) 2012-09-29 2012-09-29 Based on commodity display information acquisition and analysis system and the method for image recognition technology

Publications (2)

Publication Number Publication Date
CN102930264A true CN102930264A (en) 2013-02-13
CN102930264B CN102930264B (en) 2015-10-28

Family

ID=47645061

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210376807.6A Expired - Fee Related CN102930264B (en) 2012-09-29 2012-09-29 Based on commodity display information acquisition and analysis system and the method for image recognition technology

Country Status (1)

Country Link
CN (1) CN102930264B (en)

Cited By (72)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103927399A (en) * 2014-05-07 2014-07-16 苏州搜客信息技术有限公司 Information push method and device
CN103984967A (en) * 2014-05-08 2014-08-13 杭州同尊信息技术有限公司 Automatic detection system and automatic detection method applied to commodity label detection
CN104318251A (en) * 2014-10-29 2015-01-28 广州视源电子科技股份有限公司 Method and device for processing photo in real time
CN104599269A (en) * 2015-01-16 2015-05-06 王虓栋 Camera shooting technology based grid positioning processing system and method
CN104616131A (en) * 2015-02-16 2015-05-13 北京任我在线电子商务有限公司 Shelf management system and method
CN105809094A (en) * 2014-12-31 2016-07-27 研祥智能科技股份有限公司 Bar code identification method based on machine vision
CN105809690A (en) * 2016-03-09 2016-07-27 联想(北京)有限公司 Data processing method, device and electronic device
CN106570510A (en) * 2016-11-07 2017-04-19 南京航空航天大学 Supermarket commodity identification method
CN107077686A (en) * 2014-10-23 2017-08-18 日本电气株式会社 Image processing apparatus, display control unit, image processing method and recording medium
CN107256500A (en) * 2017-06-28 2017-10-17 太仓苏易信息科技有限公司 A kind of processing method of supermarket's express checkout
CN107292248A (en) * 2017-06-05 2017-10-24 广州诚予国际市场信息研究有限公司 A kind of merchandise control method and system based on image recognition technology
CN107305675A (en) * 2016-04-20 2017-10-31 上海恒名软件有限公司 One kind shopping software display ordering method
CN107463945A (en) * 2017-07-12 2017-12-12 浙江大学 A kind of type of merchandize recognition methods based on depth matching network
CN107578582A (en) * 2017-08-31 2018-01-12 昆山中骏博研互联网科技有限公司 A kind of batch commodity charge system and charging method
CN107705066A (en) * 2017-09-15 2018-02-16 广州唯品会研究院有限公司 Information input method and electronic equipment during a kind of commodity storage
CN108182406A (en) * 2017-12-28 2018-06-19 仝西鲁 The article display recognition methods of retail terminal and system
CN108334912A (en) * 2017-01-19 2018-07-27 浙江汉朔电子科技有限公司 Article display aided management system
CN108364205A (en) * 2018-01-18 2018-08-03 北京居然设计家家居连锁集团有限公司 It generates the method for commodity mark point and generates the device of commodity mark point
CN108416403A (en) * 2018-03-08 2018-08-17 上海扩博智能技术有限公司 The automatic correlation method of commodity and label, system, equipment and storage medium
CN108509879A (en) * 2018-03-19 2018-09-07 北京学之途网络科技有限公司 A kind of method and device for realizing information processing
CN108550002A (en) * 2018-01-17 2018-09-18 桂林电子科技大学 A kind of bank's noble metal intelligence inventory making system and method
CN108615015A (en) * 2018-04-28 2018-10-02 海信（山东）冰箱有限公司 A kind of recognition methods, equipment and the image identification system of refrigerator inside food materials
CN108647553A (en) * 2018-05-10 2018-10-12 上海扩博智能技术有限公司 Rapid expansion method, system, equipment and the storage medium of model training image
CN108665617A (en) * 2018-05-16 2018-10-16 安徽机电职业技术学院 Intelligence is automatic to pawn machine
CN108846401A (en) * 2018-05-30 2018-11-20 京东方科技集团股份有限公司 Commodity detect terminal, method, system and computer equipment, readable medium
CN108875831A (en) * 2018-06-22 2018-11-23 广州图匠数据科技有限公司 A kind of refrigerator-freezer commodity information identification method, system and device based on image recognition
CN109034067A (en) * 2018-07-27 2018-12-18 上海扩博智能技术有限公司 Commodity image reproduction detection method, system, equipment and storage medium
CN109086938A (en) * 2018-08-09 2018-12-25 北京朗镜科技有限责任公司 Product SKU recognition methods, device and computer readable storage medium
CN109102329A (en) * 2018-07-27 2018-12-28 索信市场咨询(北京)有限公司 A kind of data sampling and processing and analysis application method and device
CN109191546A (en) * 2018-09-18 2019-01-11 北京无线体育俱乐部有限公司 Map method of formation, information acquisition method, apparatus and system
CN109190644A (en) * 2018-09-20 2019-01-11 深圳市联新移动医疗科技有限公司 A kind of recognition methods of injection similar drug, equipment and storage medium based on color
CN109242060A (en) * 2018-08-30 2019-01-18 上海扩博智能技术有限公司 New restocking product fast searching method, system, equipment and storage medium
CN109271935A (en) * 2018-09-17 2019-01-25 北京旷视科技有限公司 The matching method of article and electronic tag, apparatus and system
CN109446883A (en) * 2018-09-05 2019-03-08 北京三快在线科技有限公司 Condition of merchandise recognition methods, device, electronic equipment and readable storage medium storing program for executing
CN109509304A (en) * 2017-09-14 2019-03-22 阿里巴巴集团控股有限公司 Automatic vending machine and its control method, device and computer system
CN109522780A (en) * 2017-09-19 2019-03-26 东芝泰格有限公司 Shelf information estimating device, information processing method and terminal device
CN109697445A (en) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 Image processing method and device
CN109697481A (en) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 Method and apparatus for determining article tag
CN109740649A (en) * 2018-12-21 2019-05-10 创新奇智(重庆)科技有限公司 A kind of long commodity on shelf recognition methods, storage medium and identifying system
CN109767265A (en) * 2018-12-21 2019-05-17 创新奇智(广州)科技有限公司 A kind of business suspended method, storage medium and business suspended system
CN109902636A (en) * 2019-03-05 2019-06-18 上海扩博智能技术有限公司 Commodity identification model training method, system, equipment and storage medium
CN109961053A (en) * 2018-09-18 2019-07-02 北京无线体育俱乐部有限公司 Reminding method, apparatus and system
CN110020080A (en) * 2017-12-08 2019-07-16 北京京东尚科信息技术有限公司 Information processing method and system
CN110245580A (en) * 2019-05-24 2019-09-17 北京百度网讯科技有限公司 A kind of method, apparatus of detection image, equipment and computer storage medium
CN110321769A (en) * 2019-03-25 2019-10-11 浙江工业大学 A kind of more size commodity on shelf detection methods
CN110364084A (en) * 2019-07-01 2019-10-22 苏宁云计算有限公司 A kind of display control method and device of electronic tag
CN110414559A (en) * 2019-06-26 2019-11-05 武汉大学 The construction method and commodity recognition method of intelligence retail cabinet commodity target detection Unified frame
CN110533028A (en) * 2019-07-31 2019-12-03 北京三快在线科技有限公司 Detection method, device, electronic equipment and the storage medium of commodity display state
CN110569789A (en) * 2019-09-06 2019-12-13 创新奇智(重庆)科技有限公司 Commodity combined sku identification method and device
CN110659642A (en) * 2018-06-29 2020-01-07 北京京东尚科信息技术有限公司 Image processing method, apparatus, system and computer readable medium
CN110705424A (en) * 2019-09-25 2020-01-17 广州市玄武无线科技股份有限公司 Method and device for positioning commodity display position and storage medium
CN110705744A (en) * 2019-08-26 2020-01-17 苏宁云计算有限公司 Planogram generation method, planogram generation apparatus, computer device, and storage medium
CN110705559A (en) * 2019-10-09 2020-01-17 杭州高达软件系统股份有限公司 Steel information recording method, device and equipment based on steel label image recognition
WO2020015340A1 (en) * 2018-07-20 2020-01-23 浙江汉朔电子科技有限公司 Shelf short supply checking method and apparatus, and device and storage medium
WO2020048376A1 (en) * 2018-09-07 2020-03-12 杭州海康威视数字技术股份有限公司 Shelf analysis method and apparatus, system, and electronic device
CN110895747A (en) * 2018-09-13 2020-03-20 阿里巴巴集团控股有限公司 Commodity information identification, display, information association and settlement method and system
CN110944147A (en) * 2018-09-25 2020-03-31 阿里巴巴集团控股有限公司 Resource bit monitoring system, method and device and electronic equipment
CN110991372A (en) * 2019-12-09 2020-04-10 河南中烟工业有限责任公司 Method for identifying cigarette brand display condition of retail merchant
CN111274845A (en) * 2018-12-04 2020-06-12 杭州海康威视数字技术股份有限公司 Method, device and system for identifying shelf display situation of store and electronic equipment
CN111295684A (en) * 2017-10-30 2020-06-16 松下知识产权经营株式会社 Shelf monitoring device, shelf monitoring method, and shelf monitoring program
CN111507253A (en) * 2020-04-16 2020-08-07 腾讯科技（深圳）有限公司 Method and device for auditing displayed articles based on artificial intelligence
CN111724188A (en) * 2019-03-22 2020-09-29 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for optimizing commodity display position
CN111814628A (en) * 2020-06-29 2020-10-23 北京百度网讯科技有限公司 Display cabinet identification method, device, equipment and storage medium
CN111931674A (en) * 2020-08-18 2020-11-13 创新奇智(成都)科技有限公司 Article identification management method, device, server and readable storage medium
CN112149450A (en) * 2019-06-26 2020-12-29 浙江汉朔电子科技有限公司 Noodle arrangement inspection system and method
CN112489240A (en) * 2020-11-09 2021-03-12 上海汉时信息科技有限公司 Commodity display inspection method, inspection robot and storage medium
CN112990115A (en) * 2021-04-21 2021-06-18 广州市玄武无线科技股份有限公司 Shooting method and system for freezer display identification
CN113222705A (en) * 2021-05-21 2021-08-06 支付宝(杭州)信息技术有限公司 Commodity display optimization method, device and equipment
WO2021179138A1 (en) * 2020-03-09 2021-09-16 图灵通诺（北京）科技有限公司 Method and system for analyzing commodities on supermarket shelf
TWI769420B (en) * 2019-12-11 2022-07-01 財團法人工業技術研究院 Intelligent planogram producing method and system
CN115661624A (en) * 2022-11-07 2023-01-31 浙江莲荷科技有限公司 Digital method and device for goods shelf and electronic equipment
CN117152540A (en) * 2023-10-27 2023-12-01 浙江由由科技有限公司 Intelligent pricing method for fresh goods considering display position, sales volume and classification precision

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107527096B (en) * 2017-08-18 2018-08-28 余佩佩 A method of verification oil gas vehicle
CN107562099A (en) * 2017-08-24 2018-01-09 武汉理工大学 A kind of novel intelligent cabinet and its management method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101160576A (en) * 2005-04-13 2008-04-09 斯德艾斯有限公司 Method and system for measuring retail store conditions
CN102063616A (en) * 2010-12-30 2011-05-18 上海电机学院 Automatic identification system and method for commodities based on image feature matching
CN102184405A (en) * 2011-04-19 2011-09-14 清华大学 Image acquisition-analysis method
CN202976125U (en) * 2012-09-29 2013-06-05 李炳华 Commodity display information acquisition analyzing system based on image identification technology

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101160576A (en) * 2005-04-13 2008-04-09 斯德艾斯有限公司 Method and system for measuring retail store conditions
CN102063616A (en) * 2010-12-30 2011-05-18 上海电机学院 Automatic identification system and method for commodities based on image feature matching
CN102184405A (en) * 2011-04-19 2011-09-14 清华大学 Image acquisition-analysis method
CN202976125U (en) * 2012-09-29 2013-06-05 李炳华 Commodity display information acquisition analyzing system based on image identification technology

Cited By (105)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103927399A (en) * 2014-05-07 2014-07-16 苏州搜客信息技术有限公司 Information push method and device
CN103984967A (en) * 2014-05-08 2014-08-13 杭州同尊信息技术有限公司 Automatic detection system and automatic detection method applied to commodity label detection
CN103984967B (en) * 2014-05-08 2016-12-07 杭州同尊信息技术有限公司 A kind of automatic checkout system being applied to Commercial goods labels detection and automatic testing method
CN107077686B (en) * 2014-10-23 2020-11-06 日本电气株式会社 Image processing apparatus, image processing method, and program
CN107077686A (en) * 2014-10-23 2017-08-18 日本电气株式会社 Image processing apparatus, display control unit, image processing method and recording medium
US11403843B2 (en) 2014-10-23 2022-08-02 Nec Corporation Image processing apparatus, display control apparatus, image processing method and recording medium
CN104318251A (en) * 2014-10-29 2015-01-28 广州视源电子科技股份有限公司 Method and device for processing photo in real time
CN104318251B (en) * 2014-10-29 2018-05-01 广州视源电子科技股份有限公司 A kind of photograph real-time processing method and device
CN105809094A (en) * 2014-12-31 2016-07-27 研祥智能科技股份有限公司 Bar code identification method based on machine vision
CN104599269A (en) * 2015-01-16 2015-05-06 王虓栋 Camera shooting technology based grid positioning processing system and method
CN104599269B (en) * 2015-01-16 2018-03-27 上海汉京知识产权服务有限公司 Grid location processing system and method based on camera technique
CN104616131A (en) * 2015-02-16 2015-05-13 北京任我在线电子商务有限公司 Shelf management system and method
CN104616131B (en) * 2015-02-16 2018-12-21 北京任我在线电子商务有限公司 shelf management system and method
CN105809690A (en) * 2016-03-09 2016-07-27 联想(北京)有限公司 Data processing method, device and electronic device
CN107305675A (en) * 2016-04-20 2017-10-31 上海恒名软件有限公司 One kind shopping software display ordering method
CN107305675B (en) * 2016-04-20 2021-07-13 上海恒名软件有限公司 Shopping software display ordering method
CN106570510B (en) * 2016-11-07 2019-06-25 南京航空航天大学 A kind of supermarket's commodity recognition method
CN106570510A (en) * 2016-11-07 2017-04-19 南京航空航天大学 Supermarket commodity identification method
CN108334912B (en) * 2017-01-19 2020-10-27 浙江汉朔电子科技有限公司 Auxiliary management system for article display
CN108334912A (en) * 2017-01-19 2018-07-27 浙江汉朔电子科技有限公司 Article display aided management system
CN107292248B (en) * 2017-06-05 2023-04-07 广州诚予国际市场信息研究有限公司 Commodity management method and system based on image recognition technology
CN107292248A (en) * 2017-06-05 2017-10-24 广州诚予国际市场信息研究有限公司 A kind of merchandise control method and system based on image recognition technology
CN107256500A (en) * 2017-06-28 2017-10-17 太仓苏易信息科技有限公司 A kind of processing method of supermarket's express checkout
CN107463945A (en) * 2017-07-12 2017-12-12 浙江大学 A kind of type of merchandize recognition methods based on depth matching network
CN107578582A (en) * 2017-08-31 2018-01-12 昆山中骏博研互联网科技有限公司 A kind of batch commodity charge system and charging method
CN109509304A (en) * 2017-09-14 2019-03-22 阿里巴巴集团控股有限公司 Automatic vending machine and its control method, device and computer system
CN107705066A (en) * 2017-09-15 2018-02-16 广州唯品会研究院有限公司 Information input method and electronic equipment during a kind of commodity storage
CN107705066B (en) * 2017-09-15 2022-01-07 唯品会(海南)电子商务有限公司 Information input method and electronic equipment during commodity warehousing
CN109522780B (en) * 2017-09-19 2023-08-25 东芝泰格有限公司 Shelf information estimating device, information processing method, and terminal device
CN109522780A (en) * 2017-09-19 2019-03-26 东芝泰格有限公司 Shelf information estimating device, information processing method and terminal device
CN109697481A (en) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 Method and apparatus for determining article tag
CN109697445A (en) * 2017-10-23 2019-04-30 北京京东尚科信息技术有限公司 Image processing method and device
CN111295684A (en) * 2017-10-30 2020-06-16 松下知识产权经营株式会社 Shelf monitoring device, shelf monitoring method, and shelf monitoring program
CN110020080A (en) * 2017-12-08 2019-07-16 北京京东尚科信息技术有限公司 Information processing method and system
CN108182406A (en) * 2017-12-28 2018-06-19 仝西鲁 The article display recognition methods of retail terminal and system
CN108550002A (en) * 2018-01-17 2018-09-18 桂林电子科技大学 A kind of bank's noble metal intelligence inventory making system and method
CN108550002B (en) * 2018-01-17 2021-06-08 桂林电子科技大学 Intelligent bank precious metal inventory system and method
CN108364205A (en) * 2018-01-18 2018-08-03 北京居然设计家家居连锁集团有限公司 It generates the method for commodity mark point and generates the device of commodity mark point
CN108364205B (en) * 2018-01-18 2020-12-18 躺平设计家(上海)科技有限公司 Method and device for generating commodity labeling point
CN108416403A (en) * 2018-03-08 2018-08-17 上海扩博智能技术有限公司 The automatic correlation method of commodity and label, system, equipment and storage medium
CN108509879A (en) * 2018-03-19 2018-09-07 北京学之途网络科技有限公司 A kind of method and device for realizing information processing
CN108509879B (en) * 2018-03-19 2021-12-24 北京学之途网络科技有限公司 Method and device for realizing information processing
CN108615015A (en) * 2018-04-28 2018-10-02 海信（山东）冰箱有限公司 A kind of recognition methods, equipment and the image identification system of refrigerator inside food materials
CN108647553B (en) * 2018-05-10 2022-01-25 上海扩博智能技术有限公司 Method, system, device and storage medium for rapidly expanding images for model training
CN108647553A (en) * 2018-05-10 2018-10-12 上海扩博智能技术有限公司 Rapid expansion method, system, equipment and the storage medium of model training image
CN108665617A (en) * 2018-05-16 2018-10-16 安徽机电职业技术学院 Intelligence is automatic to pawn machine
CN108846401A (en) * 2018-05-30 2018-11-20 京东方科技集团股份有限公司 Commodity detect terminal, method, system and computer equipment, readable medium
CN108875831A (en) * 2018-06-22 2018-11-23 广州图匠数据科技有限公司 A kind of refrigerator-freezer commodity information identification method, system and device based on image recognition
CN110659642A (en) * 2018-06-29 2020-01-07 北京京东尚科信息技术有限公司 Image processing method, apparatus, system and computer readable medium
CN110738085A (en) * 2018-07-20 2020-01-31 浙江汉朔电子科技有限公司 shelf out-of-stock checking method, device and equipment and storage medium
WO2020015340A1 (en) * 2018-07-20 2020-01-23 浙江汉朔电子科技有限公司 Shelf short supply checking method and apparatus, and device and storage medium
CN109102329A (en) * 2018-07-27 2018-12-28 索信市场咨询(北京)有限公司 A kind of data sampling and processing and analysis application method and device
CN109034067B (en) * 2018-07-27 2021-08-24 上海扩博智能技术有限公司 Method, system, equipment and storage medium for commodity image reproduction detection
CN109034067A (en) * 2018-07-27 2018-12-18 上海扩博智能技术有限公司 Commodity image reproduction detection method, system, equipment and storage medium
CN109086938A (en) * 2018-08-09 2018-12-25 北京朗镜科技有限责任公司 Product SKU recognition methods, device and computer readable storage medium
CN109242060A (en) * 2018-08-30 2019-01-18 上海扩博智能技术有限公司 New restocking product fast searching method, system, equipment and storage medium
CN109446883A (en) * 2018-09-05 2019-03-08 北京三快在线科技有限公司 Condition of merchandise recognition methods, device, electronic equipment and readable storage medium storing program for executing
WO2020048376A1 (en) * 2018-09-07 2020-03-12 杭州海康威视数字技术股份有限公司 Shelf analysis method and apparatus, system, and electronic device
CN110895747B (en) * 2018-09-13 2024-04-02 阿里巴巴集团控股有限公司 Commodity information identification, display, information association and settlement method and system
CN110895747A (en) * 2018-09-13 2020-03-20 阿里巴巴集团控股有限公司 Commodity information identification, display, information association and settlement method and system
CN109271935A (en) * 2018-09-17 2019-01-25 北京旷视科技有限公司 The matching method of article and electronic tag, apparatus and system
CN109191546A (en) * 2018-09-18 2019-01-11 北京无线体育俱乐部有限公司 Map method of formation, information acquisition method, apparatus and system
CN109191546B (en) * 2018-09-18 2023-06-20 北京智游意动科技有限公司 Map generation method, information acquisition method, device and system
CN109961053A (en) * 2018-09-18 2019-07-02 北京无线体育俱乐部有限公司 Reminding method, apparatus and system
CN109190644B (en) * 2018-09-20 2021-06-08 深圳市联新移动医疗科技有限公司 Injection medicine identification method and device based on colors and storage medium
CN109190644A (en) * 2018-09-20 2019-01-11 深圳市联新移动医疗科技有限公司 A kind of recognition methods of injection similar drug, equipment and storage medium based on color
CN110944147A (en) * 2018-09-25 2020-03-31 阿里巴巴集团控股有限公司 Resource bit monitoring system, method and device and electronic equipment
CN110944147B (en) * 2018-09-25 2021-11-23 阿里巴巴集团控股有限公司 Resource bit monitoring system, method and device and electronic equipment
CN111274845A (en) * 2018-12-04 2020-06-12 杭州海康威视数字技术股份有限公司 Method, device and system for identifying shelf display situation of store and electronic equipment
CN111274845B (en) * 2018-12-04 2023-09-05 杭州海康威视数字技术股份有限公司 Method, device and system for identifying display condition of store shelf and electronic equipment
CN109767265A (en) * 2018-12-21 2019-05-17 创新奇智(广州)科技有限公司 A kind of business suspended method, storage medium and business suspended system
CN109740649A (en) * 2018-12-21 2019-05-10 创新奇智(重庆)科技有限公司 A kind of long commodity on shelf recognition methods, storage medium and identifying system
CN109902636A (en) * 2019-03-05 2019-06-18 上海扩博智能技术有限公司 Commodity identification model training method, system, equipment and storage medium
CN111724188A (en) * 2019-03-22 2020-09-29 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for optimizing commodity display position
CN111724188B (en) * 2019-03-22 2024-04-19 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for optimizing commodity display position
CN110321769A (en) * 2019-03-25 2019-10-11 浙江工业大学 A kind of more size commodity on shelf detection methods
CN110321769B (en) * 2019-03-25 2022-06-17 浙江工业大学 Multi-size goods shelf commodity detection method
CN110245580A (en) * 2019-05-24 2019-09-17 北京百度网讯科技有限公司 A kind of method, apparatus of detection image, equipment and computer storage medium
CN112149450A (en) * 2019-06-26 2020-12-29 浙江汉朔电子科技有限公司 Noodle arrangement inspection system and method
CN110414559A (en) * 2019-06-26 2019-11-05 武汉大学 The construction method and commodity recognition method of intelligence retail cabinet commodity target detection Unified frame
CN110364084B (en) * 2019-07-01 2022-02-25 苏宁云计算有限公司 Display control method and device for electronic tag
CN110364084A (en) * 2019-07-01 2019-10-22 苏宁云计算有限公司 A kind of display control method and device of electronic tag
CN110533028A (en) * 2019-07-31 2019-12-03 北京三快在线科技有限公司 Detection method, device, electronic equipment and the storage medium of commodity display state
CN110705744A (en) * 2019-08-26 2020-01-17 苏宁云计算有限公司 Planogram generation method, planogram generation apparatus, computer device, and storage medium
CN110569789B (en) * 2019-09-06 2023-05-05 创新奇智(重庆)科技有限公司 Commodity combined sku identification method and device
CN110569789A (en) * 2019-09-06 2019-12-13 创新奇智(重庆)科技有限公司 Commodity combined sku identification method and device
CN110705424A (en) * 2019-09-25 2020-01-17 广州市玄武无线科技股份有限公司 Method and device for positioning commodity display position and storage medium
CN110705559A (en) * 2019-10-09 2020-01-17 杭州高达软件系统股份有限公司 Steel information recording method, device and equipment based on steel label image recognition
CN110705559B (en) * 2019-10-09 2022-07-08 杭州高达软件系统股份有限公司 Steel information recording method, device and equipment based on steel label image recognition
CN110991372A (en) * 2019-12-09 2020-04-10 河南中烟工业有限责任公司 Method for identifying cigarette brand display condition of retail merchant
TWI769420B (en) * 2019-12-11 2022-07-01 財團法人工業技術研究院 Intelligent planogram producing method and system
WO2021179138A1 (en) * 2020-03-09 2021-09-16 图灵通诺（北京）科技有限公司 Method and system for analyzing commodities on supermarket shelf
US11748787B2 (en) 2020-03-09 2023-09-05 Yi Tunnel (Beijing) Technology Co., Ltd. Analysis method and system for the item on the supermarket shelf
CN111507253B (en) * 2020-04-16 2023-06-30 腾讯科技（深圳）有限公司 Display article auditing method and device based on artificial intelligence
CN111507253A (en) * 2020-04-16 2020-08-07 腾讯科技（深圳）有限公司 Method and device for auditing displayed articles based on artificial intelligence
CN111814628A (en) * 2020-06-29 2020-10-23 北京百度网讯科技有限公司 Display cabinet identification method, device, equipment and storage medium
CN111814628B (en) * 2020-06-29 2024-02-27 北京百度网讯科技有限公司 Display cabinet identification method, device, equipment and storage medium
CN111931674A (en) * 2020-08-18 2020-11-13 创新奇智(成都)科技有限公司 Article identification management method, device, server and readable storage medium
CN111931674B (en) * 2020-08-18 2024-04-02 创新奇智(成都)科技有限公司 Article identification management method, device, server and readable storage medium
CN112489240A (en) * 2020-11-09 2021-03-12 上海汉时信息科技有限公司 Commodity display inspection method, inspection robot and storage medium
CN112990115A (en) * 2021-04-21 2021-06-18 广州市玄武无线科技股份有限公司 Shooting method and system for freezer display identification
CN113222705A (en) * 2021-05-21 2021-08-06 支付宝(杭州)信息技术有限公司 Commodity display optimization method, device and equipment
CN115661624A (en) * 2022-11-07 2023-01-31 浙江莲荷科技有限公司 Digital method and device for goods shelf and electronic equipment
CN117152540A (en) * 2023-10-27 2023-12-01 浙江由由科技有限公司 Intelligent pricing method for fresh goods considering display position, sales volume and classification precision
CN117152540B (en) * 2023-10-27 2024-01-09 浙江由由科技有限公司 Intelligent pricing method for fresh goods considering display position, sales volume and classification precision

Also Published As

Publication number Publication date
CN102930264B (en) 2015-10-28

Similar Documents

Publication Publication Date Title
CN102930264B (en) Based on commodity display information acquisition and analysis system and the method for image recognition technology
CN107016387B (en) Method and device for identifying label
Wei et al. Deep learning for retail product recognition: Challenges and techniques
US9524486B2 (en) System and method for retail store promotional price tag detection and maintenance via heuristic classifiers
TWI631514B (en) Method and system for marking recognition based on mobile terminal
CN101763516B (en) Character recognition method based on fitting functions
CN202976125U (en) Commodity display information acquisition analyzing system based on image identification technology
CN107403128B (en) Article identification method and device
CN103310256A (en) Methods for preparing and identifying continuous-real-object anti-counterfeit label based on image contrast
CN109635705B (en) Commodity identification method and device based on two-dimensional code and deep learning
CN202615416U (en) Multimedia food traceability query terminal
CN102799848B (en) Commodity information identification method and merchandise news identification device
US11409977B1 (en) Universal product labeling for vision-based commerce
US20200327557A1 (en) Electronic detection of products and arrangement of products in a display structure, electronic detection of objects and arrangement of objects on and around the display structure, electronic detection of conditions of and around the display structure, and electronic scoring of the detected product and object arrangements and of the detected conditions
CN110114781B (en) Method for detecting and identifying remote high density visual indicia
CN103236007A (en) On-line poster generation system and on-line poster generation method
CN107766862A (en) Item price label digit recognition method
CN112966681B (en) Method, equipment and storage medium for intelligent recognition, filing and retrieval of commodity photographing
CN110992103A (en) Intelligent counter commodity sales promotion method based on face interaction
CN108509879B (en) Method and device for realizing information processing
WO2021169207A1 (en) Object identification method and apparatus based on machine learning
CN105913104A (en) Calligraphy code generating method, calligraphy code generating system, calligraphy code analyzing method, calligraphy code analyzing system and calligraphy code label
CN107798070A (en) A kind of web data acquisition methods and terminal device
CN103116952A (en) Intelligent catering settlement system based on internet of things technology application
CN204390285U (en) A kind of Quick Response Code scan-type medicine management system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20130213

Assignee: Guangzhou Ashidi Information Science & Technology Co., Ltd.

Assignor: Li Binghua

Contract record no.: 2015990001031

Denomination of invention: System and method for acquiring and analyzing commodity display information based on image identification technology

Granted publication date: 20151028

License type: Exclusive License

Record date: 20151211

LICC Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model
C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20160318

Address after: 510765, 6, building 3, three, Jianye Road, 206 East Zone, Guangzhou economic and Technological Development Zone, Guangdong, China

Patentee after: Guangzhou Ashidi Information Science & Technology Co., Ltd.

Address before: 510630 Guangdong city of Guangzhou province huajingxincheng Xinhua garden room 1-1403

Patentee before: Li Binghua

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20180312

Address after: 510665 room 310, No. 108, Tianhe District Ke Yun North Road, Guangzhou, Guangdong

Patentee after: Guangzhou full latitude image Mdt InfoTech Ltd

Address before: 510765, 6, building 3, three, Jianye Road, 206 East Zone, Guangzhou economic and Technological Development Zone, Guangdong, China

Patentee before: Guangzhou Ashidi Information Science & Technology Co., Ltd.

CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20151028

Termination date: 20190929