CN106326852A - Commodity identification method and device based on deep learning - Google Patents
Commodity identification method and device based on deep learning Download PDFInfo
- Publication number
- CN106326852A CN106326852A CN201610692575.3A CN201610692575A CN106326852A CN 106326852 A CN106326852 A CN 106326852A CN 201610692575 A CN201610692575 A CN 201610692575A CN 106326852 A CN106326852 A CN 106326852A
- Authority
- CN
- China
- Prior art keywords
- commodity
- store
- image
- degree
- geographical position
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a commodity identification method and device based on deep learning. The commodity identification method and device are used for applying a commodity model which is obtained on the basis of deep learning training to commodity identification. The commodity identification method comprises steps of training a commodity picture according to a detection method based on deep learning, obtaining a commodity model, obtaining an image in a video program, identifying whether a commodity exists in the image according to the commodity model, matching the commodity identified from the image with a shopping mall commodity in a designated shopping mall, and choosing a specific shopping mall commodity from matched shopping mall commodities according to a preset parameter. The scheme of the commodity identification method and device applies a commodity model obtained on the basis of deep learning training to commodity identification, improves accuracy and identification efficiency of the commodity recognition and improves user experience.
Description
Technical field
The present invention relates to commodity identification field, particularly to a kind of commodity recognition method based on degree of depth study and device.
Background technology
Degree of depth study is a new field in machine learning research, and its motivation is to set up, simulation is restrained oneself and carried out point
Analysing the neutral net of study, the mechanism that it imitates human brain explains data, such as image, sound and text.And at electricity quotient system system
In, it is the conventional means improving Sales Volume of Commodity to user's Recommendations, and in recommendation process, goods model is most important, is
The core of whole electricity quotient system system；At present, goods model can be obtained by training and treat Recommendations according to goods model
It is simulated, it is thus achieved that the prediction output of commodity to be recommended, and then recommends to user.Along with science and technology development, for
The goods model accuracy that the training requirement of goods model generates is more and more higher, and training effectiveness requires more and more higher, existing
Goods model training method gradually can not meet current demand, and a kind of commodity recognition method based on degree of depth study is to work as
Required for before.
Summary of the invention
The present invention provides a kind of commodity recognition method based on degree of depth study and device, will obtain based on degree of depth learning training
Goods model application in commodity identification, and the method improves accuracy and the recognition efficiency of commodity identification, improves use
Family is experienced.
First aspect according to embodiments of the present invention, it is provided that a kind of commodity recognition method based on degree of depth study, including:
According to the detection method training commodity picture learnt based on the degree of depth, and obtain goods model；
Obtain the image in video frequency program, and whether there are commodity according in image described in described goods model identification；
The described commodity identified in described image are mated with specifying the store commodity in store；
From the described store commodity of coupling, choose specific store commodity according to parameter preset.
In one embodiment, described from the described store commodity of coupling, choose specific store business according to parameter preset
After product, also include:
The chain of the described specific store commodity chosen is received and sent to user.
In one embodiment, described detection method based on degree of depth study includes faster-based on degree of depth study
Rcnn algorithm.
In one embodiment, described by the store business in the described commodity identified in described image and appointment store
Product mate, including:
According to perception hash algorithm, by the described commodity identified in described image and the store business specified in store
Product mate, and all in described appointment store and described goods matching store commodity are set as the store business identified
Product.
In one embodiment, described from the described store commodity of coupling, choose specific store business according to parameter preset
Product, including:
The geographical position in store residing for each described store commodity of the described goods matching obtained and identify；
Obtain the distance between geographical position and the geographical position at user place in store residing for the commodity of each described store；
The store commodity choosing the distance between the geographical position in residing store and the geographical position at user place the shortest are made
For specific store commodity.
Second aspect according to embodiments of the present invention, also provides for a kind of article identification device based on degree of depth study, including:
Training module, for training commodity picture according to detection method based on degree of depth study, and obtains goods model；
Identification module, for obtaining the image in video frequency program, and according in image described in described goods model identification be
No there are commodity；
Matching module, for carrying out the described commodity identified in described image with specifying the store commodity in store
Coupling；
Choose module, for the described store commodity from coupling, choose specific store commodity according to parameter preset.
In one embodiment, described device also includes:
Sending module, for receiving and sending the chain of the described specific store commodity chosen to user.
In one embodiment, described detection method based on degree of depth study includes faster-based on degree of depth study
Rcnn algorithm.
In one embodiment, described matching module includes:
Matched sub-block, for according to perception hash algorithm, by the described commodity identified in described image and finger
The store commodity determined in store mate, and are set by store commodity with described goods matching all in described appointment store
For the store commodity identified.
In one embodiment, choose module described in include:
First obtains submodule, for store residing for each described store commodity of the described goods matching obtained and identify
Geographical position；
Second obtains submodule, for obtaining the ground in the geographical position in store residing for the commodity of each described store and user place
Distance between reason position；
Choose submodule, for choosing distance between the geographical position in residing store and the geographical position at user place
Short store commodity are as specific store commodity.
The technical scheme that the embodiment of the present invention provides can produce following beneficial effect: according to the detection side learnt based on the degree of depth
Method training commodity picture, and obtain goods model；Obtain the image in video frequency program, and according to described in described goods model identification
Whether image exists commodity；The described commodity identified in described image are carried out with specifying the store commodity in store
Join；From the described store commodity of coupling, choose specific store commodity according to parameter preset.The program will be based on degree of depth study instruction
The goods model got is applied to commodity identification, and the method improves accuracy and the recognition efficiency of commodity identification, carries
Rise Consumer's Experience.
Other features and advantages of the present invention will illustrate in the following description, and, partly become from description
Obtain it is clear that or understand by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
Structure specifically noted in book, claims and accompanying drawing realizes and obtains.
Below by drawings and Examples, technical scheme is described in further detail.
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, with the reality of the present invention
Execute example together for explaining the present invention, be not intended that limitation of the present invention.
In the accompanying drawings:
Fig. 1 is the present invention stream according to a kind of based on degree of depth study the commodity recognition method shown in an exemplary embodiment
Cheng Tu.
Fig. 2 is the commodity recognition method that the present invention learns based on the degree of depth according to the another kind shown in an exemplary embodiment
Flow chart.
Fig. 3 is the present invention step according to a kind of based on degree of depth study the commodity recognition method shown in an exemplary embodiment
The flow chart of rapid S30.
Fig. 4 is the present invention step according to a kind of based on degree of depth study the commodity recognition method shown in an exemplary embodiment
The flow chart of rapid S40.
Fig. 5 is the present invention frame according to a kind of based on degree of depth study the article identification device shown in an exemplary embodiment
Figure.
Fig. 6 is the article identification device that the present invention learns based on the degree of depth according to the another kind shown in an exemplary embodiment
Block diagram.
Fig. 7 be the present invention according to a kind of based on degree of depth study the article identification device shown in an exemplary embodiment
Join the block diagram of module 63.
Fig. 8 is the present invention choosing according to a kind of based on degree of depth study the article identification device shown in an exemplary embodiment
The block diagram of delivery block 64.
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred reality described herein
Execute example be merely to illustrate and explain the present invention, be not intended to limit the present invention.
Disclosure embodiment provides a kind of commodity recognition method based on degree of depth study, for instructing based on degree of depth study
The goods model got is applied to commodity identification, and the method improves accuracy and the recognition efficiency of commodity identification, carries
Rise Consumer's Experience.As it is shown in figure 1, the method comprising the steps of S10-S40:
In step slo, according to the detection method training commodity picture learnt based on the degree of depth, and goods model is obtained；Its
In, described detection method based on degree of depth study can be set according to demand, in one embodiment, described based on the degree of depth
The detection method of study is faster-rcnn algorithm based on degree of depth study.But it is in the present invention, described based on degree of depth study
Detection method is not limited to algorithm above, as long as the effect of required goods model can be reached to train.
In step S20, obtain the image in video frequency program, and according in image described in described goods model identification whether
There are commodity；In the present embodiment, it is necessary first in video frequency program, obtain image, and (can root according to default detection method
Be set according to demand) detect in described image whether there are commodity, when detect not there are commodity in described image time, can
So that described image is abandoned and re-starts acquisition image；When detect there are commodity in described image time, can be in following step
In Zhou, it is mated with specifying the store commodity in store.
In step s 30, the described commodity identified in described image are carried out with specifying the store commodity in store
Coupling；Wherein, described appointment store can be multiple stores that user specifies, it is also possible to is the business arranged at user's default system
City.Video frequency program identifies commodity complete after, it can be compared with specifying the store commodity in store, and
After comparison, by with in video frequency program, identify the store commodity of goods matching, be set as the business identified in this store
City commodity.
In step s 40, from the described store commodity of coupling, specific store commodity are chosen according to parameter preset.That is,
Described parameter preset can be set according to user's request, such as, according to the distance in the geographical position between store and user,
Commodity price, user preferences, the frequency of commodity purchasing and positive rating etc..
In one embodiment, as in figure 2 it is shown, also include step S50 after step S40 of described method:
In step s 50, the chain of the described specific store commodity chosen is received and sent to user.That is, by described spy
Determine store commodity choose complete after, this specific store commodity are sent to user, select for user.
In one embodiment, as it is shown on figure 3, described step S30 includes:
Step S301, according to perception hash algorithm, the described commodity that will identify in described image with specify store
In store commodity mate, and be set as identifying with described goods matching store commodity by all in described appointment store
The store commodity gone out.Wherein, described appointment store can be multiple stores that user specifies, it is also possible to is at user's default system
The store arranged.Video frequency program identifies commodity complete after, it can be carried out with specifying the store commodity in store
Comparison, and after comparison, by with in video frequency program, identify the store commodity of goods matching, be set as in this store knowing
The store commodity not gone out.
In one embodiment, as shown in Figure 4, described step S40 includes:
Step S401, the described goods matching obtaining and identifying each described store commodity residing for the geographical position in store
Put；That is, in the present embodiment, the geographical position described parameter preset being set as residing for commodity between store and user away from
From, when geographical position between the two distance the most in short-term, these commodity are set as specific store commodity.
Step S402, obtain residing for the commodity of each described store between geographical position and the geographical position at user place in store
Distance；
The business that distance between step S403, the geographical position choosing residing store and the geographical position at user place is the shortest
City commodity are as specific store commodity.That is, ought geographical position between the two distance the most in short-term, these commodity are set as spy
Determine store commodity, and the connection of these specific store commodity is supplied to user.
The said method that the embodiment of the present invention provides, according to the detection method training commodity picture learnt based on the degree of depth, and
Obtain goods model；Obtain the image in video frequency program, and whether there is business according in image described in described goods model identification
Product；The described commodity identified in described image are mated with specifying the store commodity in store；From described in coupling
In the commodity of store, choose specific store commodity according to parameter preset.The commodity mould that the program will obtain based on degree of depth learning training
Type is applied to commodity identification, and the method improves accuracy and the recognition efficiency of commodity identification, improves Consumer's Experience.
The commodity recognition method based on degree of depth study that the corresponding embodiment of the present invention provides, the present invention also provides for based on the degree of depth
The article identification device of study, as it is shown in figure 5, this device comprises the steps that
Training module 61, for training commodity picture according to detection method based on degree of depth study, and obtains goods model；
Wherein, described detection method based on degree of depth study can be set according to demand, in one embodiment, described based on deeply
The detection method of degree study is faster-rcnn algorithm based on degree of depth study.But it is in the present invention, described based on degree of depth study
Detection method be not limited to algorithm above, as long as the effect of required goods model can be reached to train.
Identification module 62, for obtaining the image in video frequency program, and according in image described in described goods model identification
Whether there are commodity；In the present embodiment, it is necessary first in video frequency program, obtain image, and (can according to default detection method
To be set according to demand) detect in described image whether there are commodity, when detecting, described image does not exist commodity
Time, described image can be abandoned and re-start acquisition image；When detect there are commodity in described image time, can with
It is mated by lower step with specifying the store commodity in store.
Matching module 63, for entering the described commodity identified in described image with specifying the store commodity in store
Row coupling；Wherein, described appointment store can be multiple stores that user specifies, it is also possible to arranges at user's default system
Store.Video frequency program identifies commodity complete after, it can be compared with specifying the store commodity in store, and
After comparison, by with in video frequency program, identify the store commodity of goods matching, be set as identifying in this store
Store commodity.
Choose module 64, for the described store commodity from coupling, choose specific store commodity according to parameter preset.Also
That is, described parameter preset can be set according to user's request, such as, according to the geographical position between store and user away from
From, the frequency of commodity price, user preferences, commodity purchasing and positive rating etc..
In one embodiment, as shown in Figure 6, described device also includes:
Sending module 65, for receiving and sending the chain of the described specific store commodity chosen to user.That is, by described
Specific store commodity choose complete after, this specific store commodity are sent to user, select for user.
In one embodiment, described detection method based on degree of depth study includes faster-based on degree of depth study
Rcnn algorithm.
In one embodiment, as it is shown in fig. 7, described matching module 63 includes:
Matched sub-block 631, for according to perception hash algorithm, by the described commodity that identify in described image with
Specify the store commodity in store to mate, and the store commodity of all in described appointment store and described goods matching are set
It is set to the store commodity identified.Wherein, described appointment store can be multiple stores that user specifies, it is also possible to is user
The store that default system is arranged.Video frequency program identifies commodity complete after, can be by itself and the store specified in store
Commodity are compared, and after comparison, by with in video frequency program, identify the store commodity of goods matching, be set as at this
The store commodity identified in store.
In one embodiment, as shown in Figure 8, choose module 64 described in include:
First obtains submodule 641, for residing for each described store commodity of the described goods matching obtained and identify
The geographical position in store；That is, in the present embodiment, described parameter preset is set as residing for commodity between store and user
The distance in geographical position, when geographical position between the two distance the most in short-term, these commodity are set as specific store commodity.
Second obtains submodule 642, for obtaining the geographical position in store residing for the commodity of each described store and user place
Geographical position between distance；
Choose submodule 643, for choose between the geographical position in residing store and the geographical position at user place away from
From the shortest store commodity as specific store commodity.That is, ought geographical position between the two distance the most in short-term, by this business
Product are set as specific store commodity, and the connection of these specific store commodity is supplied to user.
The said apparatus that the embodiment of the present invention provides, applies the goods model obtained based on degree of depth learning training to commodity
In identification, and the method improves accuracy and the recognition efficiency of commodity identification, improves Consumer's Experience.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the reality in terms of the present invention can use complete hardware embodiment, complete software implementation or combine software and hardware
Execute the form of example.And, the present invention can use at one or more computers wherein including computer usable program code
The shape of the upper computer program implemented of usable storage medium (including but not limited to disk memory and optical memory etc.)
Formula.
The present invention is with reference to method, equipment (system) and the flow process of computer program according to embodiments of the present invention
Figure and/or block diagram describe.It should be understood that can by computer program request flowchart and/or block diagram in the most first-class
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
Request arrives the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable information processing equipments to produce
A raw machine so that the request performed by the processor of computer or other programmable information processing equipments is produced for real
The device of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame now.
The request of these computer programs may be alternatively stored in and computer or other programmable information processing equipments can be guided with spy
Determine in the computer-readable memory that mode works so that the request being stored in this computer-readable memory produces and includes asking
Seek the manufacture of device, this request unit realize at one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function specified in multiple square frames.
The request of these computer programs also can be loaded in computer or other programmable information processing equipments so that at meter
Perform sequence of operations step on calculation machine or other programmable devices to produce computer implemented process, thus at computer or
The request performed on other programmable devices provides for realizing at one flow process of flow chart or multiple flow process and/or block diagram one
The step of the function specified in individual square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and the modification essence without deviating from the present invention to the present invention
God and scope.So, if these amendments of the present invention and modification belong to the scope of the claims in the present invention and equivalent technologies thereof
Within, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. a commodity recognition method based on degree of depth study, it is characterised in that including:
According to the detection method training commodity picture learnt based on the degree of depth, and obtain goods model；
Obtain the image in video frequency program, and whether there are commodity according in image described in described goods model identification；
The described commodity identified in described image are mated with specifying the store commodity in store；
From the described store commodity of coupling, choose specific store commodity according to parameter preset.
2. the method for claim 1, it is characterised in that described from the described store commodity of coupling, according to default ginseng
After number chooses specific store commodity, also include:
The chain of the described specific store commodity chosen is received and sent to user.
3. the method for claim 1, it is characterised in that described detection method based on degree of depth study includes based on the degree of depth
The faster-rcnn algorithm of study.
4. the method for claim 1, it is characterised in that described by the described commodity identified in described image and finger
The store commodity determined in store mate, including:
According to perception hash algorithm, the described commodity identified in described image are entered with specifying the store commodity in store
Row coupling, and all in described appointment store and described goods matching store commodity are set as the store commodity identified.
5. method as claimed in claim 4, it is characterised in that described from the described store commodity of coupling, according to default ginseng
Number chooses specific store commodity, including:
The geographical position in store residing for each described store commodity of the described goods matching obtained and identify；
Obtain the distance between geographical position and the geographical position at user place in store residing for the commodity of each described store；
Choose the shortest store commodity of the distance between the geographical position in residing store and the geographical position at user place as spy
Determine store commodity.
6. an article identification device based on degree of depth study, it is characterised in that including:
Training module, for training commodity picture according to detection method based on degree of depth study, and obtains goods model；
Whether identification module, for obtaining the image in video frequency program, and deposit according in image described in described goods model identification
At commodity；
Matching module, for carrying out the described commodity identified in described image with specifying the store commodity in store
Join；
Choose module, for the described store commodity from coupling, choose specific store commodity according to parameter preset.
7. device as claimed in claim 6, it is characterised in that described device also includes:
Sending module, for receiving and sending the chain of the described specific store commodity chosen to user.
8. device as claimed in claim 6, it is characterised in that described detection method based on degree of depth study includes based on the degree of depth
The faster-rcnn algorithm of study.
9. device as claimed in claim 6, it is characterised in that described matching module includes:
Matched sub-block, for according to perception hash algorithm, described commodity and the appointment business that will identify in described image
Store commodity in city mate, and are set as knowing with described goods matching store commodity by all in described appointment store
The store commodity not gone out.
10. device as claimed in claim 9, it is characterised in that described in choose module and include:
First obtains submodule, for the ground in store residing for each described store commodity of the described goods matching obtained and identify
Reason position；
Second obtains submodule, for obtaining the geographical position in the geographical position in store residing for the commodity of each described store and user place
Distance between putting；
Choose submodule, the shortest for choosing the distance between the geographical position in residing store and the geographical position at user place
Store commodity are as specific store commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610692575.3A CN106326852A (en) | 2016-08-18 | 2016-08-18 | Commodity identification method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610692575.3A CN106326852A (en) | 2016-08-18 | 2016-08-18 | Commodity identification method and device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106326852A true CN106326852A (en) | 2017-01-11 |
Family
ID=57744512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610692575.3A Pending CN106326852A (en) | 2016-08-18 | 2016-08-18 | Commodity identification method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326852A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108389316A (en) * | 2018-03-02 | 2018-08-10 | 北京京东尚科信息技术有限公司 | Automatic vending method, device and computer readable storage medium |
| CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
| CN109559453A (en) * | 2017-09-27 | 2019-04-02 | 缤果可为（北京）科技有限公司 | Human-computer interaction device and its application for Automatic-settlement |
| WO2019062017A1 (en) * | 2017-09-27 | 2019-04-04 | 缤果可为（北京）科技有限公司 | Method, device, and self-service checkout counter for performing product recognition on the basis of neural network |
| CN109635705A (en) * | 2018-12-05 | 2019-04-16 | 上海交通大学 | A kind of commodity recognition method and device based on two dimensional code and deep learning |
| CN110414532A (en) * | 2019-06-21 | 2019-11-05 | 广州利科科技有限公司 | A kind of commodity image recognition methods based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201657189U (en) * | 2009-12-24 | 2010-11-24 | 深圳市同洲电子股份有限公司 | Television shopping system, digital television receiving terminal and goods information management system |
| CN103455788A (en) * | 2012-05-31 | 2013-12-18 | 东芝泰格有限公司 | Commodity recognition apparatus and commodity recognition method |
| CN103940438A (en) * | 2013-01-23 | 2014-07-23 | 清华大学 | Shopping-center positioning and crowdsourcing shopping navigation method based on bar codes |
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN105787490A (en) * | 2016-03-24 | 2016-07-20 | 南京新与力文化传播有限公司 | Commodity fashion identification method and device based on deep learning |
| CN105844283A (en) * | 2015-01-16 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Method for identifying category of image, image search method and image search device |
-
2016
- 2016-08-18 CN CN201610692575.3A patent/CN106326852A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201657189U (en) * | 2009-12-24 | 2010-11-24 | 深圳市同洲电子股份有限公司 | Television shopping system, digital television receiving terminal and goods information management system |
| CN103455788A (en) * | 2012-05-31 | 2013-12-18 | 东芝泰格有限公司 | Commodity recognition apparatus and commodity recognition method |
| CN103940438A (en) * | 2013-01-23 | 2014-07-23 | 清华大学 | Shopping-center positioning and crowdsourcing shopping navigation method based on bar codes |
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN105844283A (en) * | 2015-01-16 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Method for identifying category of image, image search method and image search device |
| CN105787490A (en) * | 2016-03-24 | 2016-07-20 | 南京新与力文化传播有限公司 | Commodity fashion identification method and device based on deep learning |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559453A (en) * | 2017-09-27 | 2019-04-02 | 缤果可为（北京）科技有限公司 | Human-computer interaction device and its application for Automatic-settlement |
| WO2019062812A1 (en) * | 2017-09-27 | 2019-04-04 | 缤果可为（北京）科技有限公司 | Human-computer interaction device for automatic payment and use thereof |
| WO2019062017A1 (en) * | 2017-09-27 | 2019-04-04 | 缤果可为（北京）科技有限公司 | Method, device, and self-service checkout counter for performing product recognition on the basis of neural network |
| CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
| US11501523B2 (en) | 2017-12-18 | 2022-11-15 | Shanghai Cloudpick Smart Technology Co., Ltd. | Goods sensing system and method for goods sensing based on image monitoring |
| CN108389316A (en) * | 2018-03-02 | 2018-08-10 | 北京京东尚科信息技术有限公司 | Automatic vending method, device and computer readable storage medium |
| WO2019165892A1 (en) * | 2018-03-02 | 2019-09-06 | 北京京东尚科信息技术有限公司 | Automatic vending method and apparatus, and computer-readable storage medium |
| US11461753B2 (en) | 2018-03-02 | 2022-10-04 | Beijing Jingdong Shangke Information Technology Co., Ltd. | Automatic vending method and apparatus, and computer-readable storage medium |
| CN109635705A (en) * | 2018-12-05 | 2019-04-16 | 上海交通大学 | A kind of commodity recognition method and device based on two dimensional code and deep learning |
| CN109635705B (en) * | 2018-12-05 | 2021-04-27 | 上海交通大学 | Commodity identification method and device based on two-dimensional code and deep learning |
| CN110414532A (en) * | 2019-06-21 | 2019-11-05 | 广州利科科技有限公司 | A kind of commodity image recognition methods based on deep learning |
| CN110414532B (en) * | 2019-06-21 | 2021-08-06 | 广州利科科技有限公司 | Commodity image identification method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326852A (en) | Commodity identification method and device based on deep learning | |
| CN108805091B (en) | Method and apparatus for generating a model | |
| EP2933780B1 (en) | Reality augmenting method, client device and server | |
| Ahmetovic et al. | Recog: Supporting blind people in recognizing personal objects | |
| US20170323158A1 (en) | Identification of Objects in a Scene Using Gaze Tracking Techniques | |
| US20180173942A1 (en) | Method and apparatus for generating facial expression and training method for generating facial expression | |
| CN109389442A (en) | Method of Commodity Recommendation and device, storage medium and electric terminal | |
| CN107424019A (en) | The art work based on Emotion identification recommends method, apparatus, medium and electronic equipment | |
| US20180189553A1 (en) | Facial expression image processing method and apparatus | |
| CN108960316A (en) | Method and apparatus for generating model | |
| CN108810619A (en) | Identify the method, apparatus and electronic equipment of watermark in video | |
| CN111666416A (en) | Method and apparatus for generating semantic matching model | |
| CN111523413A (en) | Method and device for generating face image | |
| CN110070076B (en) | Method and device for selecting training samples | |
| CN106339917A (en) | Commodity model training method and device | |
| WO2019217162A1 (en) | Computer vision and speech algorithm design service | |
| CN110046303A (en) | A kind of information recommendation method and device realized based on demand Matching Platform | |
| EP3100240B1 (en) | Evaluation of augmented reality skins | |
| JP6291041B2 (en) | Search recommendation method and apparatus | |
| RU2015145507A (en) | SUPPORT DEVICE FOR USER SUPPORT IN THE DIAGNOSTIC PROCESS | |
| CN104038489A (en) | Biological authentication method and biological authentication device | |
| US11003812B2 (en) | Experience driven development of mixed reality devices with immersive feedback | |
| US11024289B2 (en) | Cognitive recommendation engine facilitating interaction between entities | |
| CN106355184A (en) | Goods identification method and device based on picture segmentation | |
| CN104572598A (en) | Typesetting method and device for digitally published product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170111 |