CN107454964A - A kind of commodity recognition method and device - Google Patents
A kind of commodity recognition method and device Download PDFInfo
- Publication number
- CN107454964A CN107454964A CN201680006925.4A CN201680006925A CN107454964A CN 107454964 A CN107454964 A CN 107454964A CN 201680006925 A CN201680006925 A CN 201680006925A CN 107454964 A CN107454964 A CN 107454964A
- Authority
- CN
- China
- Prior art keywords
- commodity
- image information
- text message
- obtains
- image
- 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
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
A kind of commodity recognition method and device, it is related to commodity identification technology field.Merchandise news is obtained for assisting blind.This method includes:IMAQ is carried out to commodity from least one visual angle, obtains the image information (S11) of commodity;According to the text message (S12) of the image information acquisition commodity of commodity;The text message of commodity is converted into voice messaging, and (S13) is exported to voice messaging.This method is used for assisting blind and carries out commodity identification.
Description
Technical field
The present invention relates to commodity identification technology field, more particularly to a kind of commodity recognition method and device.
Background technology
Blind is one of society serious in the world and public health problem.The information of the mankind more than 70% is all to pass through vision
Come what is obtained, visual problems largely limit blind person and carry out acquisition of information.
Due to visual problems, inconvenience in the life of blind person be present, when especially being done shopping in market, in face of market
The commodity of middle a great variety, blind person can not independently obtain the information of the commodity such as species, model, price, therefore for blind person,
The commodity of oneself needs are picked out in larger spatial dimension and various commodity, complete independently shopping, is extremely difficult.
Blind person is to obtain merchandise news by Shopping Guide's explanation in shopping in the case of one, but this not only brings to blind person's shopping
Very big inconvenience, the workload of Shopping Guide is also significantly increased, consume substantial amounts of manpower and time cost.Therefore, it is how auxiliary
It is a problem urgently to be resolved hurrily to help blind person to obtain merchandise news.
The content of the invention
Embodiments of the invention provide a kind of commodity recognition method and device, and merchandise news is obtained for assisting blind.
To reach above-mentioned purpose, embodiments of the invention adopt the following technical scheme that:
First aspect, there is provided a kind of commodity recognition method, obtain merchandise news for assisting blind, methods described includes:
IMAQ is carried out to commodity from least one visual angle, obtains the image information of the commodity;
According to the text message of commodity described in the image information acquisition of the commodity;
The text message of the commodity is converted into voice messaging, and the voice messaging is exported.
Second aspect, there is provided a kind of article identification device, obtain merchandise news for assisting blind, described device includes:
Image capture module, for carrying out IMAQ to commodity from least one visual angle, obtain the image of the commodity
Information;
Picture recognition module, the text message for commodity described in the image information acquisition according to the commodity;
Voice output module, for the text message of the commodity to be converted into voice messaging, and to the voice messaging
Exported.
The third aspect, there is provided a kind of article identification device, described device include:Processor and memory, the memory
For storing computer executable code, the computer executable code is used to control described in the computing device first aspect
Commodity recognition method.
Fourth aspect, there is provided a kind of computer-readable storage medium, for saving as the article identification device described in the third aspect
Computer software instructions used, it includes the program code designed by the commodity recognition method performed described in first aspect.
5th aspect, there is provided a kind of computer program product, can be loaded directly into the internal storage of computer, and contain
There is a software code, the computer program is loaded into via computer and can realize that the commodity described in first aspect identify after performing
Method.
The commodity recognition method that embodiments of the invention provide carries out IMAQ from least one visual angle to commodity first,
The image information of commodity is obtained, then according to the text message of the image information acquisition commodity of commodity, finally by the text of commodity
Information is converted to voice messaging, and voice messaging is exported, because article identification device provided in an embodiment of the present invention can
To obtain the text message of the image information of commodity and image information acquisition commodity according to commodity, finally by the text envelope of commodity
Breath be converted to voice messaging output, so blind person of the embodiment of the present invention can by voice by way of obtain merchandise news.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is one of step flow chart of commodity recognition method that embodiments of the invention provide;
Fig. 2 is the two of the step flow chart for the commodity recognition method that embodiments of the invention provide;
Fig. 3 is the three of the step flow chart for the commodity recognition method that embodiments of the invention provide;
Fig. 4 is the four of the step flow chart for the commodity recognition method that embodiments of the invention provide;
Fig. 5 is the five of the step flow chart for the commodity recognition method that embodiments of the invention provide;
Fig. 6 is one of schematic diagram of article identification device that embodiments of the invention provide;
Fig. 7 is the two of the schematic diagram for the article identification device that embodiments of the invention provide;
Fig. 8 is the three of the schematic diagram for the article identification device that embodiments of the invention provide.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Need
Illustrate, the part or all of technical characteristic in any number of technical schemes provided below in the case where not conflicting,
It can be used in combination, form new technical scheme.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
Go out under the premise of creative work the every other embodiment obtained, belong to the scope of protection of the invention.
Term "and/or" in embodiments of the present invention, a kind of only incidence relation for describing affiliated partner, expression can be with
In the presence of three kinds of relations, for example, A and/or B, can be represented:Individualism A, while A and B be present, these three feelings of individualism B
Condition.In addition, character "/" herein, it is a kind of relation of "or" to typically represent forward-backward correlation object.If being not added with illustrating, herein
In " multiple " refer to two or more.
In embodiments of the present invention, " exemplary " or " such as " etc. word make example, illustration or explanation for expression.This
Be described as in inventive embodiments " exemplary " or " such as " any embodiment or design be not necessarily to be construed as comparing
Other embodiments or design more preferably or more advantage.Specifically, use " exemplary " or " such as " etc. word purport
Related notion is being presented in a concrete fashion.
It should be noted that in the embodiment of the present invention, unless otherwise indicated, the implication of " multiple " refer to two or two with
On.
It should also be noted that, in the embodiment of the present invention, " (English:Of) ", " corresponding (English:
Corresponding, relevant) " and " corresponding (English:Corresponding) " can use with sometimes, it should be pointed out that
Be, when not emphasizing its difference, its is to be expressed be meant that it is consistent.
The general principle for the technical scheme that the embodiment of the present invention is provided is:It can not be obtained because of visual problems for blind person
Merchandise news, so cause that blind person can not be independent the problem of do shopping, the technical scheme that the embodiment of the present invention is provided is led to
The image information for obtaining commodity is crossed, then according to the text message of the image information acquisition commodity of commodity, finally by the text of commodity
This information be converted to voice messaging output, and then make blind person by receive voice messaging obtain commodity information, on solving
State the problem of blind person can not obtain merchandise news.
Based on the above, the embodiment of the present invention provides a kind of commodity identification side that merchandise news is obtained for assisting blind
Method.
Exemplary, the executive agent of commodity recognition method provided in an embodiment of the present invention can be to be implemented using the present invention
The terminal device that the commodity recognition method that example provides identifies to commodity row.Terminal device can be wear-type blind-guide device, guide
Glasses, mobile phone, portable computer, pocket computer, handheld computer, DPF, palm PC, navigator etc.,
Or terminal device can be to be provided with to identify commodity row using commodity recognition method provided in an embodiment of the present invention
Software client or the personal computer of software systems or software application (English full name:Personal computer, referred to as:
PC), server etc., specific hardware realize that environment can be in the form of all-purpose computer, or the integrated circuit (English specially designed
Literary full name:Application Specific Integrated Circuit, referred to as:ASIC mode) or (English
Full name:Field Programmable Gate Array, referred to as:FPGA), or some programmable expansion platforms for example
Embedded (English name:Tensilica configurable processor platform) etc..
Shown in reference picture 1, commodity recognition method provided in an embodiment of the present invention includes:
S11, from least one visual angle IMAQ is carried out to commodity, obtain the image informations of commodity.
Exemplary, can be by the one or more in monocular cam, the first-class imaging sensor of binocular camera shooting come real
IMAQ in existing above-mentioned steps S11.
Optionally, IMAQ is carried out to commodity from least one visual angle in above-mentioned S11 to be specifically as follows from a visual angle
IMAQ is carried out to commodity, or IMAQ is carried out to commodity from multiple visual angles.Exemplary, the embodiment of the present invention
In can specifically realize by the following method from multiple visual angles to commodity carry out IMAQ:
First, commodity are positioned within the acquisition range of image collecting device by user, then commodity are rotated and/or
Mobile, image collecting device carries out figure from multiple visual angles during user is rotated and/or moved to commodity to commodity
As collection.
2nd, image collecting device includes multiple and is respectively arranged at different positions, when carrying out IMAQ, Duo Geshe
The image collecting device for being placed in diverse location carries out IMAQ from a visual angle to commodity respectively, so as to realize from multiple visual angles
IMAQ is carried out to commodity.
It should also be noted that, when carrying out IMAQ to commodity from multiple visual angles, because the image information of commodity is
By carrying out IMAQ acquisition to commodity from multiple visual angles, therefore the image information of commodity includes:Multiple visual angle commodity
Image.The image information of commodity, Jin Eryou can be more comprehensively obtained by carrying out IMAQ to commodity from multiple visual angles
The sharp follow-up image information to commodity is identified.
S12, the text message according to the image information acquisition commodity of commodity.
The process of the text message of the image information acquisition commodity according to commodity in above-described embodiment can be known in image
Complete, can also assist to complete by remote service apparatus inside other device.
When the process of the text message of the image information acquisition commodity according to commodity is completed inside pattern recognition device,
Step S12 can be specifically achieved by the steps of:A, the image information of commodity is identified.B, obtained according to recognition result
The text message of commodity.Exemplary, above-mentioned step can be performed by being provided with the image processing equipment of image recognition software
Suddenly.
When the process of the text message of the image information acquisition commodity according to commodity assists to complete by remote service apparatus
When, step S12 can be specifically achieved by the steps of:C, commodity image information is sent to remote service equipment, so as to remote
The image information of commodity is identified end service equipment, and the text message of commodity is obtained according to recognition result.D, receive remote
Hold the text message of the commodity of service equipment transmission.Exemplary, remote service equipment can be cloud server etc..
In addition, the image informations of commodity, which is identified, can use any image recognition algorithm to commodity image information
Handled, analyzed and understood.The image recognition used in the image information identification process of commodity is calculated in the embodiment of the present invention
Method does not limit.
S13, the text message of commodity is converted into voice messaging, and voice messaging is exported.
Specifically, the text message of commodity can be converted to by voice messaging by speech synthesis technique, then by raising
The audio output apparatus such as sound device, power amplifier, audio amplifier, earphone export the voice messaging of synthesis.
It should be noted that the text message of commodity is converted into voice messaging, and voice messaging export specifically
Can be:The text message of commodity directly is converted into voice messaging by speech synthesis technique to export, or by commodity
Text message carry out keyword extraction, for example the keywords of the commodity stored in the text message and database of commodity is carried out
Compare, then voice output keyword comparison result.
The commodity recognition method that embodiments of the invention provide carries out IMAQ from least one visual angle to commodity first,
The image information of commodity is obtained, then according to the text message of the image information acquisition commodity of commodity, finally by the text of commodity
Information is converted to voice messaging, and voice messaging is exported, because article identification device provided in an embodiment of the present invention can
To obtain the text message of the image information of commodity and image information acquisition commodity according to commodity, finally by the text envelope of commodity
Breath be converted to voice messaging output, so blind person of the embodiment of the present invention can by voice by way of obtain merchandise news,
And then can allow blind person it is independent do shopping.
Further, the embodiment of the present invention provides following several specific implementations to realize the commodity identification shown in Fig. 1
Method:
First,
Shown in reference picture 2, above-mentioned commodity recognition method specifically comprises the following steps:
S21, from least one visual angle IMAQ is carried out to commodity, obtain the image informations of commodity.
S22, the image information to commodity carry out bar code identification, obtain the bar code of commodity.
Specifically, bar code can be bar code and/or two-dimensional bar code in above-described embodiment.Wherein, the one of commodity
Dimension bar code is made up of one group of regularly arranged bar, sky and its corresponding code.The two-dimensional bar code of commodity is with specific geometric figure
The chequered with black and white figure being distributed in the two-dimensional direction according to certain rules.It, which forms the bar code symbol of bar code, can include zero
Sell the code and bar code mark of commodity, accumulating package goods, Logistic Unit, participant position etc..The bar code print of usual commodity
In commodity packaging, or it is made into bar-code label and is attached on commodity.Therefore by carrying out bar code knowledge to the image information of commodity
The bar code of commodity can not obtained.
The bar codes of commodity is not identified and is specifically as follows:Bar code detection and positioning are first carried out, determines one
The region in the picture of bar code is tieed up, then bar code identification is carried out in the image to the region, reads in bar code
The information of goods number etc., the finally information inquiry in bar code obtain commodity text message.Equally to the two of commodity
Dimension bar code, which is identified, to be specifically as follows:First carry out two-dimensional bar code detection and positioning and then carry out two dimension in the image to the region
Bar code identifies, reads the information in two-dimensional bar code.It is with bar code difference, more letters can be included in two-dimensional bar code
Breath, therefore the text message of commodity can be directly obtained by the content of two-dimensional bar code or is further located to obtaining information
Reason obtains the text of commodity.
S23, the text message according to the bar code of commodity acquisition commodity.
The bar code of commodity is inquired about and data processing, commodity manufacturer, title, price, face can be identified immediately
The merchandise newss such as color, and these merchandise newss are shown by the form of text, it is possible to according to commodity
Bar code obtains the text message of commodity.
In addition, the bar code of commodity also follows uniqueness principle, i.e. a commodity item can only have a code, in other words one
Individual code can only identify a kind of commodity item.Different size, Different Package, different cultivars, different prices, the commodity of different colours
The bar code of different commodity can be used.Therefore the text message of the commodity obtained by the bar codes of commodity is relatively accurate, can be with
Avoid the merchandise news mistake provided a user.
S24, the text message of commodity is converted into voice messaging, and voice messaging is exported.
2nd,
Shown in reference picture 3, above-mentioned commodity recognition method specifically comprises the following steps:
S31, from least one visual angle IMAQ is carried out to commodity, obtain the image informations of commodity.
S32, the image information to commodity carry out optical character identification (English name:Optical Character
Recognition, English abbreviation:OCR), the character in the image information of commodity is obtained.
Specifically, optical character identification refers to optical character recognition equipment (such as scanner, digital camera, printer etc.)
Character on inspection paper document, image, its shape is determined by detecting dark, bright pattern, then will with character identifying method
Shape translates into the process of computword.
Optionally, as described above, the image information of the commodity in the embodiment of the present invention includes at least two images, to business
The image information of product carries out that first optical character identification can be carried out to each image respectively during optical character identification, so
The character of identification is arranged to the text message for obtaining commodity, first can also include to the image information of commodity at least two again afterwards
Image is spliced, fusion treatment, then carries out the text message that optical character identification obtains commodity again.
S33, the character in commodity image information obtain the text message of commodity.
Generally, the outer packing of commodity can all have packaging label, and packaging label can show commodity by text mode
The title and address of producer or sellers, name of product, trade mark, composition, quality characteristic, product quantity, user in packaging
Method and dosage, numbering, store the contents such as item, quality inspection number, date of manufacture and the term of validity that should be noted that, it is possible to according to commodity
Character in image information obtains the text message of commodity.
S34, the text message of commodity is converted into voice messaging, and voice messaging is exported.
3rd,
Shown in reference picture 4, above-mentioned commodity recognition method specifically comprises the following steps:
S41, from least one visual angle IMAQ is carried out to commodity, obtain the image informations of commodity.
S42, the image information to commodity carry out feature extraction, obtain the feature of commodity.
Optionally, the feature of the commodity in above-described embodiment can be obtained by the image characteristics extraction device of engineer
Feature or by machine learning method, such as by deep learning method automatically learn obtain characteristics of image.
S43, according to the feature of commodity commodity are classified, obtain the classification of commodity.
Exemplary, the classification that according to the feature of commodity commodity are classified and obtained with commodity can be by the spy of commodity
Sign input grader is classified, and obtains the classification of commodity.Wherein, grader can be traditional support vector machine classifier
(English name:Support Vector Machine, referred to as:) or traditional iteration (English name SVM:Adaboost) divide
Class device or the grader based on deep learning network.
S44, according to commodity classification obtain commodity text message.
After the classification that commodity are obtained in above-mentioned steps S43, the commodity of the category can be obtained according to the classification of commodity
Text message.
S45, the text message of commodity is converted into voice messaging, and voice messaging is exported.
4th,
Shown in reference picture 5, above-mentioned commodity recognition method specifically comprises the following steps:
S51, from least two visual angles IMAQ is carried out to commodity, obtain the image informations of commodity.
S52, the image information to commodity carry out bar code identification.
When the image information progress bar code in step S52 to commodity identifies successfully, step S53, S57 is performed, works as step
When in S52 to the image information progress bar code recognition failures of commodity, step S54 is performed.
S53, the bar code for obtaining commodity, the text message of commodity is obtained according to the bar code of commodity.
S54, the image information to commodity carry out optical character identification.
When carrying out optical character identification success to the image informations of commodity in step S54, step S55, S57 is performed, when
When carrying out optical character identification failure to the image informations of commodity in step S52, step S56, S57 is performed.
S55, character in the image informations of commodity is obtained, character in commodity image information obtains the text of commodity
Information.
S56, the image information to commodity carry out feature extraction, and commodity are classified according to the feature of commodity, obtain business
The classification of product, the text message of commodity is obtained according to the classification of commodity.
S57, the text message of commodity is converted into voice messaging, and voice messaging is exported.
It should be noted that the step of text message of commodity is provided in the commodity recognition method provided in above-described embodiment
It can also be applied in far-end server, such as:, can also be to business when remote service equipment receives the image information of commodity
The image information of product carries out bar code identification, obtains the bar code of commodity, and the text message of commodity is obtained according to the bar code of commodity, so
The text message of goods in transit again afterwards;Again for example:, can also be to business when remote service equipment receives the image information of commodity
The image information of product carries out optical character identification, obtains the character in the image information of commodity;According in commodity image information
Character obtains the text message of commodity, then with the text message of goods in transit again;I.e. far-end server can also use above-mentioned
The text message acquisition methods of commodity in any implementation obtain the text message of commodity.
Illustrate the device embodiment corresponding with embodiment of the method presented above provided in an embodiment of the present invention below.
It should be noted that in following apparatus embodiment related content explanation, may be referred to above method embodiment.
In the case where dividing each functional module using corresponding each function, Fig. 6 shows involved in above-described embodiment
And be used for assisting blind obtain merchandise news article identification device a kind of possible structural representation.Article identification device
600 include:
Image capture module 61, for carrying out IMAQ to commodity from least one visual angle, obtain the image letter of commodity
Breath.
Picture recognition module 62, the text message for the image information acquisition commodity according to commodity.
Voice output module 63, for the text message of commodity to be converted into voice messaging, and voice messaging is carried out defeated
Go out.
The article identification device that embodiments of the invention provide includes:Image capture module, picture recognition module and language
Sound output module, wherein, image capture module is used to carry out IMAQ to commodity from least one visual angle, obtains the figure of commodity
As information, picture recognition module is used to the image information of commodity be identified, and the text of commodity is obtained according to recognition result
Information, voice output module is used to the text message of commodity being converted to voice messaging, and voice messaging is exported, due to
Article identification device provided in an embodiment of the present invention can obtain the image information of commodity and according to the image information acquisition of commodity
Commodity text message, the text message of commodity is finally converted into voice messaging output, so passing through blind person of the embodiment of the present invention
Merchandise news can be obtained by way of voice.
Optionally, shown in reference picture 7, picture recognition module 62 includes:Transmitting element 621 and receiving unit 622;
Transmitting element 621 is used to send commodity image information to remote service equipment, so that remote service equipment is to business
The image information of product is identified, and the text message of commodity is obtained according to recognition result;
Receiving unit 622 is used for the text message for receiving the commodity of remote service equipment transmission.
Optionally, picture recognition module 62 is specifically used for carrying out bar code identification to commodity image information, obtains the bar of commodity
Code, the text message of commodity is obtained according to the bar code of commodity.
Optionally, picture recognition module 62 is specifically used for carrying out optical character identification to the image information of commodity, obtains business
Character in the image information of product, the character in the image information of commodity obtain the text message of commodity.
Optionally, picture recognition module 62 is specifically used for carrying out feature extraction to the image information of commodity, obtains commodity
Feature;Commodity are classified according to the feature of commodity, obtain the classification of commodity;The text of commodity is obtained according to the classification of commodity
Information.
That is, image capture module 61 is used to realize shown in step S21, Fig. 3 shown in step S11, Fig. 2 shown in Fig. 1
Step S31, the step S51 shown in the step S41 and Fig. 5 shown in Fig. 4;Picture recognition module 62 is used to realize shown in Fig. 1
Step S12, step S42, S43, S44 shown in step S32, S33, Fig. 4 shown in step S22, S23, Fig. 3 shown in Fig. 2 with
And step S52, S53, S54, S55, S56 shown in Fig. 5;Voice output module 63 is used to realize step S13, Fig. 2 shown in Fig. 1
The step S57 shown in step S45 and Fig. 5 shown in step S34, Fig. 4 shown in shown step S24, Fig. 3.
Corresponded to it should be noted that all related contents for each step that above method embodiment is related to can be quoted
The function description of functional module, will not be repeated here.
In hardware realization, above-mentioned image capture module 61 can be monocular cam, the first-class image biography of binocular camera shooting
One or more in sensor.Picture recognition module 62 can be processor;Voice output module 63 can be loudspeaker, power amplifier
The audio output apparatus such as machine, audio amplifier, earphone.The program corresponding to action performed by above-mentioned article identification device can be with soft
Part form is stored in the memory of article identification device, and behaviour corresponding to above modules is performed in order to which processor calls
Make.
In the case of using integrated unit, Fig. 8 shows article identification device involved in above-described embodiment
A kind of possible structural representation.Article identification device 800 includes:Processor 81, memory 82, system bus 83, communication connect
Mouth 84, image collecting device 85, instantaneous speech power 86.
Above-mentioned processor 81 can be the general designation of a processor or multiple treatment elements.For example, processor 81
It can be central processing unit (central processing unit, CPU).Processor 81 can also be other general processors,
Digital signal processor (digital signal processing, DSP), application specific integrated circuit (application
Specific integrated circuit, ASIC), field programmable gate array (field-programmable gate
Array, FPGA) either other PLDs, discrete gate or transistor logic, discrete hardware components etc., its
It can realize or perform the various exemplary logic blocks with reference to described by the disclosure of invention, module and circuit.It is general
Processor can be microprocessor or the processor can also be any conventional processor etc..Processor 81 can also be special
With processor, the application specific processor can include at least one in baseband processing chip, radio frequency processing chip etc..Processor
It can be the combination for realizing computing function, such as be combined comprising one or more microprocessors, combination of DSP and microprocessor etc.
Deng.Further, the application specific processor can also include the chip with other dedicated processes functions of the device.
Memory 82 is used to store computer executable code, and processor 81 is connected with memory 82 by system bus 83,
When running of mobile terminal, processor 81 is used for the computer executable code for performing the storage of memory 82, real to perform the present invention
Any one commodity recognition method of example offer is applied, e.g., processor 81 is used to support mobile terminal to perform the step shown in Fig. 1
Step S42, S43, S44 and Fig. 5 shown in step S32, S33, Fig. 4 shown in step S22, S23, Fig. 3 shown in S12, Fig. 2
Shown step S52, S53, S54, S55, S56, and/or other processes for techniques described herein, specific commodity
Recognition methods refers to the associated description in above and accompanying drawing, and here is omitted.
System bus 83 can include data/address bus, power bus, controlling bus and signal condition bus etc..The present embodiment
In for clear explanation, various buses are all illustrated as system bus 83 in fig. 8.
Communication interface 84 can be specifically the transceiver on the device.The transceiver can be wireless transceiver.For example, nothing
Line transceiver can be antenna of the device etc..Processor 81 is by communication interface 84 and other equipment, if for example, the device is
During a module or component in the terminal device, the device is used to carry out data between other modules in the terminal device
Interaction.
The step of method with reference to described by the disclosure of invention can be realized in a manner of hardware or by
The mode that reason device performs software instruction is realized.The embodiment of the present invention also provides a kind of storage medium, for saving as shown in Fig. 8
Mobile terminal used in computer software instructions, its include perform Fig. 1,2,3,4,5 shown in commodity recognition method designed by
Program code.Wherein, software instruction can be made up of corresponding software module, and software module can be stored on arbitrary access
Memory (English:Random access memory, abbreviation:RAM), flash memory, read-only storage (English:read only
Memory, abbreviation:ROM), Erasable Programmable Read Only Memory EPROM (English:Erasable programmable ROM, abbreviation:
EPROM), EEPROM (English:Electrically EPROM, abbreviation:EEPROM), register, hard
Disk, mobile hard disk, read-only optical disc (CD-ROM) or any other form well known in the art storage medium in.A kind of example
The storage medium of property is coupled to processor, so as to enable a processor to from the read information, and can be situated between to the storage
Matter writes information.Certainly, storage medium can also be the part of processor.Processor and storage medium can be located at ASIC
In.In addition, the ASIC can be located in core network interface equipment.Certainly, processor and storage medium can also be used as discrete sets
Part is present in core network interface equipment.
The embodiment of the present invention also provides a kind of computer program product, and the computer program can be loaded directly into computer
In internal storage, and contain software code, computer program is loaded into via computer and Fig. 1 can be realized after performing, 2,3,
4th, the commodity recognition method shown in 5.
Those skilled in the art are it will be appreciated that in said one or multiple examples, work(described in the invention
It is able to can be realized with hardware, software, firmware or their any combination.When implemented in software, can be by these functions
It is stored in computer-readable medium or is transmitted as one or more instructions on computer-readable medium or code.
Computer-readable medium includes computer-readable storage medium and communication media, and wherein communication media includes being easy to from a place to another
Any medium of one place transmission computer program.It is any that storage medium can be that universal or special computer can access
Usable medium.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, the change or replacement that can readily occur in, all should
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (13)
1. a kind of commodity recognition method, obtain merchandise news for assisting blind, it is characterised in that methods described includes:
IMAQ is carried out to commodity from least one visual angle, obtains the image information of the commodity;
According to the text message of commodity described in the image information acquisition of the commodity;
The text message of the commodity is converted into voice messaging, and the voice messaging is exported.
2. according to the method for claim 1, it is characterised in that the business according to the image information acquisition of the commodity
The text message of product, including:
The image information of the commodity is sent to remote service equipment, so that the remote service equipment is according to the commodity
The text message of commodity described in image information acquisition;
Receive the text message for the commodity that the remote service equipment is sent.
3. according to the method for claim 1, it is characterised in that the business according to the image information acquisition of the commodity
The text message of product includes:
Bar code identification is carried out to the image information of the commodity, obtains the bar code of the commodity;
The text message of the commodity is obtained according to the bar code of the commodity.
4. according to the method for claim 1, it is characterised in that the business according to the image information acquisition of the commodity
The text message of product includes:
Optical character identification is carried out to the image information of the commodity, obtains the character in the image information of the commodity;
Character in the commodity image information obtains the text message of commodity.
5. according to the method for claim 1, it is characterised in that the business according to the image information acquisition of the commodity
The text message of product includes:
Feature extraction is carried out to the image information of the commodity, obtains the feature of commodity;
The commodity are classified according to the feature of the commodity, obtain the classification of commodity;
The text message of the commodity is obtained according to the classification of the commodity.
6. a kind of article identification device, obtain merchandise news for assisting blind, it is characterised in that described device includes:
Image capture module, for carrying out IMAQ to commodity from least one visual angle, obtain the image information of the commodity;
Picture recognition module, the text message for commodity described in the image information acquisition according to the commodity;
Voice output module, for the text message of the commodity to be converted into voice messaging, and the voice messaging is carried out
Output.
7. device according to claim 6, it is characterised in that described image identification module includes:Transmitting element and reception
Unit;
The transmitting element is used to send the commodity image information to remote service equipment, so as to the remote service equipment
The image information of the commodity is identified, and the text message of commodity is obtained according to recognition result;
The receiving unit is used for the text message for receiving the commodity that the remote service equipment is sent.
8. device according to claim 6, it is characterised in that
Described image identification module is specifically used for carrying out bar code identification to the commodity image information, obtains the bar of the commodity
Code, the text message of the commodity is obtained according to the bar code of the commodity.
9. device according to claim 6, it is characterised in that
Described image identification module is specifically used for carrying out optical character identification to the image information of the commodity, obtains the commodity
Image information in character, character in the image information of the commodity obtains the text message of commodity.
10. device according to claim 6, it is characterised in that
Described image identification module is specifically used for carrying out feature extraction to the image information of the commodity, obtains the feature of commodity;
The commodity are classified according to the feature of the commodity, obtain the classification of commodity;Institute is obtained according to the classification of the commodity
State the text message of commodity.
11. a kind of article identification device, it is characterised in that described device includes:Processor and memory, the memory are used for
Computer executable code is stored, the computer executable code is used to control any one of described computing device claim 1-5
Described commodity recognition method.
12. a kind of computer-readable storage medium, it is characterised in that for saving as the article identification device institute described in claim 11
Computer software instructions, it includes the program designed by the commodity recognition method described in perform claim requirement any one of 1-5
Code.
13. a kind of computer program product, it is characterised in that can be loaded directly into the internal storage of computer, and contain
Software code, the computer program are loaded into via computer and can realized described in claim any one of 1-5 after performing
Commodity recognition method.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2016/111831 WO2018112930A1 (en) | 2016-12-23 | 2016-12-23 | Method and device for identifying commodities |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107454964A true CN107454964A (en) | 2017-12-08 |
Family
ID=60484713
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201680006925.4A Pending CN107454964A (en) | 2016-12-23 | 2016-12-23 | A kind of commodity recognition method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107454964A (en) |
WO (1) | WO2018112930A1 (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033985A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术(北京)有限公司 | Processing method, device, equipment, system and the storage medium of commodity identification |
CN109359706A (en) * | 2018-09-25 | 2019-02-19 | 上海合阔信息技术有限公司 | Merchandise news intelligent identifying system and method |
CN109353398A (en) * | 2018-09-20 | 2019-02-19 | 北京旷视科技有限公司 | Commodity recognition method, device and system and storage medium and shopping cart |
CN110009071A (en) * | 2018-01-04 | 2019-07-12 | 青岛海尔洗衣机有限公司 | A kind of control method and intelligence wardrobe of intelligence wardrobe |
CN110942035A (en) * | 2019-11-28 | 2020-03-31 | 浙江由由科技有限公司 | Method, system, device and storage medium for acquiring commodity information |
CN111080399A (en) * | 2019-11-22 | 2020-04-28 | 汉口北进出口服务有限公司 | Commodity information processing method and device |
CN111242712A (en) * | 2018-11-29 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Commodity display method and device |
CN111738031A (en) * | 2020-08-06 | 2020-10-02 | 江苏东大集成电路系统工程技术有限公司 | One-dimensional bar code identification method |
WO2021004386A1 (en) * | 2019-07-11 | 2021-01-14 | 上海肇观电子科技有限公司 | Information broadcasting method, circuit, broadcasting device, storage medium, and intelligent eyeglasses |
CN112698848A (en) * | 2020-12-31 | 2021-04-23 | Oppo广东移动通信有限公司 | Downloading method and device of machine learning model, terminal and storage medium |
CN113393289A (en) * | 2021-05-27 | 2021-09-14 | 阿里巴巴新加坡控股有限公司 | Method and device for processing commodity object information and modifying title |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008782A (en) * | 2019-06-06 | 2019-07-12 | 江苏东大集成电路系统工程技术有限公司 | The acquisition methods and device of bar code information |
CN117077083B (en) * | 2023-10-10 | 2024-01-05 | 上海英内物联网科技股份有限公司 | Automatic identification and statistics method for packaged articles |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN102354366A (en) * | 2011-09-23 | 2012-02-15 | 上海合合信息科技发展有限公司 | Network based image recognition method and system |
CN102798388A (en) * | 2012-06-20 | 2012-11-28 | 上海交通大学 | Blind person supermarket shopping auxiliary device based on DSP (Digital Signal Processor) |
US20140169675A1 (en) * | 2004-12-03 | 2014-06-19 | Google Inc. | Method and system for character recognition |
CN104463659A (en) * | 2014-12-23 | 2015-03-25 | 江苏天使电子科技有限公司 | Blind person shopping system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101474020B (en) * | 2009-01-08 | 2010-07-21 | 上海交通大学 | Shopping guide method and apparatus for blind in supermarket based on bar code identification |
CN101524220B (en) * | 2009-03-25 | 2010-08-18 | 胡志超 | Method for blind persons self-help shopping |
CN102495995A (en) * | 2011-12-09 | 2012-06-13 | 上海力远计算机科技有限公司 | Optical character recognition system |
CN103632588A (en) * | 2013-11-28 | 2014-03-12 | 苏州罗马冯环保科技有限公司 | Commodity reader special for blind person |
-
2016
- 2016-12-23 WO PCT/CN2016/111831 patent/WO2018112930A1/en active Application Filing
- 2016-12-23 CN CN201680006925.4A patent/CN107454964A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140169675A1 (en) * | 2004-12-03 | 2014-06-19 | Google Inc. | Method and system for character recognition |
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 |
CN102354366A (en) * | 2011-09-23 | 2012-02-15 | 上海合合信息科技发展有限公司 | Network based image recognition method and system |
CN102798388A (en) * | 2012-06-20 | 2012-11-28 | 上海交通大学 | Blind person supermarket shopping auxiliary device based on DSP (Digital Signal Processor) |
CN104463659A (en) * | 2014-12-23 | 2015-03-25 | 江苏天使电子科技有限公司 | Blind person shopping system |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110009071A (en) * | 2018-01-04 | 2019-07-12 | 青岛海尔洗衣机有限公司 | A kind of control method and intelligence wardrobe of intelligence wardrobe |
CN109033985A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术(北京)有限公司 | Processing method, device, equipment, system and the storage medium of commodity identification |
US11023717B2 (en) | 2018-06-29 | 2021-06-01 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus, device and system for processing commodity identification and storage medium |
CN109353398A (en) * | 2018-09-20 | 2019-02-19 | 北京旷视科技有限公司 | Commodity recognition method, device and system and storage medium and shopping cart |
CN109353398B (en) * | 2018-09-20 | 2020-11-10 | 北京旷视科技有限公司 | Commodity identification method, device and system, storage medium and shopping cart |
CN109359706A (en) * | 2018-09-25 | 2019-02-19 | 上海合阔信息技术有限公司 | Merchandise news intelligent identifying system and method |
CN111242712A (en) * | 2018-11-29 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Commodity display method and device |
CN111242712B (en) * | 2018-11-29 | 2023-04-28 | 阿里巴巴集团控股有限公司 | Commodity display method and device |
WO2021004386A1 (en) * | 2019-07-11 | 2021-01-14 | 上海肇观电子科技有限公司 | Information broadcasting method, circuit, broadcasting device, storage medium, and intelligent eyeglasses |
CN111080399A (en) * | 2019-11-22 | 2020-04-28 | 汉口北进出口服务有限公司 | Commodity information processing method and device |
CN110942035A (en) * | 2019-11-28 | 2020-03-31 | 浙江由由科技有限公司 | Method, system, device and storage medium for acquiring commodity information |
CN111738031A (en) * | 2020-08-06 | 2020-10-02 | 江苏东大集成电路系统工程技术有限公司 | One-dimensional bar code identification method |
CN112698848A (en) * | 2020-12-31 | 2021-04-23 | Oppo广东移动通信有限公司 | Downloading method and device of machine learning model, terminal and storage medium |
CN113393289A (en) * | 2021-05-27 | 2021-09-14 | 阿里巴巴新加坡控股有限公司 | Method and device for processing commodity object information and modifying title |
Also Published As
Publication number | Publication date |
---|---|
WO2018112930A1 (en) | 2018-06-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107454964A (en) | A kind of commodity recognition method and device | |
CN109919014B (en) | OCR (optical character recognition) method and electronic equipment thereof | |
US9002066B2 (en) | Methods, systems and processor-readable media for designing a license plate overlay decal having infrared annotation marks | |
CN109934244B (en) | Format type learning system and image processing apparatus | |
CN109416731B (en) | Document optical character recognition | |
US20210217129A1 (en) | Detection of encoded signals and icons | |
US20170286383A1 (en) | Augmented imaging assistance for visual impairment | |
CN103597500A (en) | System and method for recognizing text information in object | |
US20190012756A1 (en) | Method and system for providing information regarding with delivery article using augmented reality | |
JP7140453B2 (en) | Encoding data into symbols placed on the optically active article | |
US9946949B2 (en) | Techniques including URL recognition and applications | |
CN104603833B (en) | Method and system for linking printing object with digital content | |
US20180239981A1 (en) | Increasing dissimilarity of characters disposed on an optically active article | |
US10592580B2 (en) | Web UI builder application | |
US11257198B1 (en) | Detection of encoded signals and icons | |
CN110070081A (en) | Automatic information input method, device, storage medium and electronic equipment | |
CN103425993A (en) | Method and system for recognizing images | |
CN110647956A (en) | Invoice information extraction method combined with two-dimensional code recognition | |
CN109784339A (en) | Picture recognition test method, device, computer equipment and storage medium | |
US20140019378A1 (en) | Evaluation system, method, and computer-readable recording medium | |
US9665786B2 (en) | Confirming automatically recognized handwritten answers | |
CN112396060A (en) | Identity card identification method based on identity card segmentation model and related equipment thereof | |
US11074418B2 (en) | Information processing apparatus and non-transitory computer readable medium | |
US20150227787A1 (en) | Photograph billpay tagging | |
WO2021214540A1 (en) | Robust camera localization based on a single color component image and multi-modal learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171208 |
|
RJ01 | Rejection of invention patent application after publication |