WO2018112930A1 - 一种商品识别方法和装置 - Google Patents

一种商品识别方法和装置 Download PDF

Info

Publication number
WO2018112930A1
WO2018112930A1 PCT/CN2016/111831 CN2016111831W WO2018112930A1 WO 2018112930 A1 WO2018112930 A1 WO 2018112930A1 CN 2016111831 W CN2016111831 W CN 2016111831W WO 2018112930 A1 WO2018112930 A1 WO 2018112930A1
Authority
WO
WIPO (PCT)
Prior art keywords
commodity
product
information
image
image information
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.)
Ceased
Application number
PCT/CN2016/111831
Other languages
English (en)
French (fr)
Inventor
刘兆祥
廉士国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cloudminds Shenzhen Robotics Systems Co Ltd
Original Assignee
Cloudminds Shenzhen Robotics Systems Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Cloudminds Shenzhen Robotics Systems Co Ltd filed Critical Cloudminds Shenzhen Robotics Systems Co Ltd
Priority to PCT/CN2016/111831 priority Critical patent/WO2018112930A1/zh
Priority to CN201680006925.4A priority patent/CN107454964A/zh
Publication of WO2018112930A1 publication Critical patent/WO2018112930A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 provisions for transferring data to distant stations, e.g. from a sensing device
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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

Definitions

  • the present invention relates to the field of commodity identification technology, and in particular, to a commodity identification method and apparatus.
  • Blindness is one of the serious social and public health problems in the world. More than 70% of human information is obtained through vision, and vision problems largely limit access to information for blind people.
  • blind people Due to vision problems, there are many inconveniences in the lives of blind people. Especially when shopping in shopping malls, in the face of a wide variety of goods in the mall, blind people cannot independently obtain information on the types, models, prices, etc., so for blind people, It is very difficult to select the products that you need from a large space and a large number of products, and complete the shopping independently. In a case, the blind person obtains the product information through the shopping guide when shopping, but this not only brings great inconvenience to the blind shopping, but also greatly increases the workload of the shopping guide, and consumes a lot of manpower and time. cost. Therefore, how to assist blind people to obtain product information is an urgent problem to be solved.
  • Embodiments of the present invention provide a product identification method and apparatus for assisting a blind person to obtain product information.
  • a method for identifying a product for assisting a blind person to obtain product information comprising:
  • the text information of the commodity is converted into voice information, and the voice information is output.
  • a merchandise identification device for assisting a blind person to obtain merchandise information, and the apparatus includes:
  • An image acquisition module configured to perform image collection on the commodity from at least one viewing angle, and acquire image information of the commodity
  • An image recognition module configured to acquire text information of the commodity according to image information of the commodity
  • a voice output module configured to convert text information of the commodity into voice information, and output the voice information.
  • a merchandise identification apparatus comprising: a processor and a memory, the memory for storing computer execution code, the computer execution code for controlling the processor to perform the first aspect Product identification method.
  • a computer storage medium for storing computer software instructions for use in the article identification device of the third aspect, comprising program code designed to perform the article identification method of the first aspect.
  • a computer program product can be directly loaded into an internal memory of a computer and contains software code, and the computer program can be implemented by the computer and can implement the product identification method described in the first aspect.
  • the product identification method provided by the embodiment of the present invention firstly collects images from at least one perspective, acquires image information of the commodity, and then acquires text information of the commodity according to the image information of the commodity, and finally converts the text information of the commodity into voice information. And outputting the voice information, because the product identification device provided by the embodiment of the present invention can acquire the image information of the product and obtain the text information of the product according to the image information of the product, and finally convert the text information of the product into the voice information output, so
  • the blind person can obtain the commodity information by means of voice.
  • FIG. 1 is a flow chart of steps of a product identification method according to an embodiment of the present invention.
  • FIG. 2 is a second flowchart of steps of a product identification method according to an embodiment of the present invention.
  • FIG. 3 is a third flowchart of steps of a product identification method according to an embodiment of the present invention.
  • FIG. 4 is a fourth flowchart of steps of a product identification method according to an embodiment of the present invention.
  • FIG. 5 is a fifth flowchart of steps of a product identification method according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a product identification device according to an embodiment of the present invention.
  • Figure 7 is a second schematic structural diagram of a product identification device according to an embodiment of the present invention.
  • FIG. 8 is a third schematic structural diagram of a product identification device according to an embodiment of the present invention.
  • the term “and/or” is merely an association relationship describing an association object, indicating that there may be three relationships, for example, A and/or B, which may indicate that A exists separately, and A and B, there are three cases of B alone.
  • the character "/" in this article generally indicates that the contextual object is an "or” relationship. Unless otherwise stated, "multiple" in this document refers to two or more.
  • the words “exemplary” or “such as” are used to mean an example, illustration, or illustration. Any embodiment or design described as “exemplary” or “for example” in the embodiments of the invention should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the words “exemplary” or “such as” is intended to present the concepts in a particular manner.
  • the basic principle of the technical solution provided by the embodiment of the present invention is: the problem that the blind person cannot obtain the product information due to the vision problem, and the blind person cannot purchase the product independently.
  • the technical solution provided by the embodiment of the present invention obtains the image of the product. The information then obtains the text information of the product according to the image information of the product, and finally converts the text information of the product into the voice information output, thereby enabling the blind person to obtain the information of the product by receiving the voice information, thereby solving the problem that the blind person cannot obtain the product information.
  • an embodiment of the present invention provides a product identification method for assisting a blind person to obtain product information.
  • the executive body of the product identification method provided by the embodiment of the present invention may A terminal device for identifying a product line by using the product identification method provided by the embodiment of the present invention.
  • the terminal device may be a head-mounted blind guide device, a guide blind glasses, a mobile phone, a portable computer, a pocket computer, a handheld computer, a digital photo frame, a palmtop computer, a navigator, etc., or the terminal device may be installed and implemented by the present invention.
  • the product identification method provided by the example is a software client for identifying a product line or a personal computer for a software system or software application (English name: personal computer, PC for short), a server, etc., and the specific hardware implementation environment may be a general computer form, or
  • the specially designed integrated circuit (English name: Application Specific Integrated Circuit, ASIC for short) can also be (English full name: Field Programmable Gate Array, referred to as: FPGA), or some programmable expansion platform such as embedded ( English name: Tensilica) configurable processor platform, etc.
  • a product identification method provided by an embodiment of the present invention includes:
  • the image acquisition in the above step S11 can be implemented by one or more of an image sensor such as a monocular camera, a binocular camera, or the like.
  • the image collection of the product from at least one perspective may be an image collection of the product from one perspective, or an image collection of the product from multiple perspectives.
  • the image collection of the commodity from multiple perspectives can be specifically implemented by the following method:
  • the user places the product within the collection range of the image capture device, and then rotates and/or moves the product, and the image capture device images the product from multiple perspectives during the user's rotation and/or movement of the product. collection.
  • the image acquisition device includes a plurality of images and is respectively disposed at different positions.
  • a plurality of image collection devices disposed at different positions respectively perform image collection on the products from one perspective, thereby realizing the goods from multiple perspectives. Perform image acquisition.
  • the image information of the product is obtained by image capturing the product from a plurality of viewing angles, and thus the image information of the product includes an image of a plurality of viewing angle products.
  • the image information of the products can be more comprehensively obtained, thereby facilitating the subsequent recognition of the image information of the products.
  • the process of acquiring the text information of the product according to the image information of the commodity in the above embodiment may be completed inside the image recognition device or may be assisted by the remote service device.
  • step S12 can be specifically implemented by the following steps: a. Identifying the image information of the product. b. Obtain text information of the product according to the recognition result.
  • the above steps can be performed by an image processing device equipped with image recognition software.
  • step S12 can be specifically implemented by: c. transmitting the product image information to the remote service device, so that the remote service device can be used for the product.
  • the image information is identified, and the text information of the product is obtained according to the recognition result.
  • d. Receive text information of the goods sent by the remote service device.
  • the remote service device can be a cloud server or the like.
  • the image information of the product can be identified, and the image image information can be processed, analyzed, and understood using any image recognition algorithm.
  • the image recognition algorithm used in the process of identifying the image information of the commodity is not limited.
  • the text information of the commodity can be converted into voice information by using a voice synthesis technology, and then the synthesized voice information is output through an audio output device such as a speaker, a power amplifier, a speaker, or a headphone.
  • an audio output device such as a speaker, a power amplifier, a speaker, or a headphone.
  • the text information of the commodity is converted into the voice information, and the voice information is outputted, which may be: directly converting the text information of the commodity into the voice information output through the voice synthesis technology, or performing the text information of the commodity.
  • Keyword extraction for example, comparing the text information of the product with the keywords of the product stored in the database, and then outputting the keyword comparison result by voice.
  • the product identification method provided by the embodiment of the present invention firstly collects images from at least one perspective, acquires image information of the commodity, and then acquires text information of the commodity according to the image information of the commodity, and finally converts the text information of the commodity into voice information. And outputting the voice information, because the product identification device provided by the embodiment of the present invention can acquire the image information of the product and obtain the text information of the product according to the image information of the product, and finally convert the text information of the product into the voice information output, so
  • the blind person can obtain the product information by means of voice, thereby enabling the blind person to independently purchase the product.
  • the embodiment of the present invention provides the following specific implementation manners to implement the product identification method shown in FIG. 1:
  • the above product identification method specifically includes the following steps:
  • S21 Perform image collection on the commodity from at least one perspective to obtain image information of the commodity.
  • the commodity barcode in the above embodiment may be a one-dimensional barcode and/or a two-dimensional barcode.
  • the one-dimensional barcode of the commodity is composed of a set of regularly arranged bars, spaces and corresponding codes.
  • the two-dimensional bar code of the product is a black and white graphic that is distributed in a two-dimensional direction by a certain geometric pattern.
  • the bar code symbols that form the bar code of the merchandise may include code and bar code identification of the retail merchandise, the storage and packaging package merchandise, the logistics unit, the location of the party, and the like.
  • the bar code of the merchandise is printed on the merchandise package or attached to the merchandise as a bar code label. Therefore, by performing bar code recognition on the image information of the product, the product can be obtained. Bar code.
  • the identification of the one-dimensional barcode of the commodity may be: firstly performing one-dimensional barcode detection and positioning, determining a region of the one-dimensional barcode in the image, and then performing one-dimensional barcode recognition on the image of the region, and reading one-dimensional
  • the information such as the product number in the barcode is finally obtained by querying the information in the one-dimensional barcode.
  • the identification of the two-dimensional barcode of the product may be: first performing two-dimensional barcode detection and positioning, and then performing two-dimensional barcode recognition on the image of the area, and reading the information in the two-dimensional barcode.
  • the difference from the one-dimensional barcode is that the two-dimensional barcode can include more information, so the text information of the commodity can be directly obtained through the content of the two-dimensional barcode or the obtained information can be further processed to obtain the text of the commodity.
  • the product information of the product manufacturer, name, price, color, etc. can be immediately recognized, and the product information is displayed in the form of text, so the product can be obtained according to the bar code of the product. Text information.
  • the barcode of the product also follows the principle of uniqueness, that is, a commodity item can only have one code, or one code can only identify one commodity item. Barcodes of different products will be used for different specifications, different packaging, different varieties, different prices, and different colors. Therefore, the text information of the commodity obtained by the barcode of the commodity is relatively accurate, and the error of the commodity information provided to the user can be avoided.
  • the above product identification method specifically includes the following steps:
  • S31 Perform image collection on the commodity from at least one perspective to obtain image information of the commodity.
  • optical character recognition refers to an optical character recognition device (such as a scanner, a digital camera, a printer, etc.) inspecting paper documents and characters on an image, determining the shape by detecting a dark and bright mode, and then using a character recognition method. The process of translating shapes into computer text.
  • an optical character recognition device such as a scanner, a digital camera, a printer, etc.
  • the image information of the product in the embodiment of the present invention includes at least two images, and each of the images may be optically recognized in the process of performing optical character recognition on the image information of the product. Then, the recognized characters are sorted to obtain the text information of the product, and at least two images included in the image information of the product may be first spliced and fused, and then the optical character recognition is performed to obtain the text information of the product.
  • the outer packaging of the product is accompanied by a packaging label
  • the packaging label will indicate the name and address of the manufacturer or seller of the product, the product name, the trademark, the composition, the quality characteristics, the number of products in the package, and the method of use. The amount, number, storage note, quality inspection number, production date and expiration date, etc., so the text information of the product can be obtained according to the characters in the product image information.
  • the above product identification method specifically includes the following steps:
  • S42 Feature extraction of image information of the product, and acquiring features of the product.
  • the feature of the commodity in the above embodiment may be a manually designed image.
  • Features acquired by the feature extractor may also be automatically learned by a machine learning method, such as by deep learning methods.
  • classifying the products according to the characteristics of the products and obtaining the classification of the products may be to classify the features of the products into a classifier to obtain the classification of the products.
  • the classifier may be a traditional support vector machine classifier (English name: Support Vector Machine, SVM for short) or a traditional iterative (English name: adaboost) classifier, or a classifier based on a deep learning network.
  • the text information of the merchandise of the merchandise can be obtained according to the classification of the merchandise.
  • the above product identification method specifically includes the following steps:
  • S51 Perform image collection on the commodity from at least two perspectives to obtain image information of the commodity.
  • step S52 When the barcode identification of the image information of the product is successful in step S52, steps S53 and S57 are performed. When the barcode identification of the image information of the product fails in step S52, step S54 is performed.
  • step S54 When the optical character recognition of the image information of the product is successful in step S54, steps S55, S57 are performed, and the optical character of the image information of the product is performed in step S52. When the recognition fails, steps S56 and S57 are performed.
  • S56 Feature extraction of image information of the product, classifying the product according to the characteristics of the product, acquiring the classification of the product, and acquiring the text information of the product according to the classification of the product.
  • the step of acquiring the text information of the product in the product identification method provided in the above embodiment may also be applied to the remote server, for example, when the remote service device receives the image information of the product, the product may also be The image information is barcoded, the barcode of the commodity is obtained, and the text information of the commodity is obtained according to the barcode of the commodity, and then the text information of the commodity is sent; for example, when the remote service device receives the image information of the commodity, it may also The image information of the product is optically recognized, the characters in the image information of the product are obtained; the text information of the product is obtained according to the characters in the product image information, and then the text information of the product is re-issued; that is, the remote server may also adopt any of the above The text information acquisition method of the commodity in the implementation manner obtains the text information of the commodity.
  • FIG. 6 is a schematic diagram showing a possible structure of the product identification device for assisting the blind person to acquire the product information in the above embodiment.
  • the item identification device 600 includes:
  • the image acquisition module 61 is configured to perform image collection on the commodity from at least one viewing angle to acquire image information of the commodity.
  • the image recognition module 62 is configured to acquire text information of the product according to the image information of the product.
  • the voice output module 63 is configured to convert text information of the commodity into voice information, and output the voice information.
  • the product identification device includes: an image acquisition module, an image recognition module, and a voice output module, wherein the image acquisition module is configured to perform image collection on the commodity from at least one perspective, and acquire image information of the commodity, and the image recognition module The image information of the product is identified, and the text information of the product is obtained according to the recognition result.
  • the voice output module is configured to convert the text information of the product into voice information, and output the voice information, because the product provided by the embodiment of the present invention
  • the identification device can acquire the image information of the product and obtain the product text information according to the image information of the product, and finally convert the text information of the product into the voice information output. Therefore, the blind person can obtain the product information by means of the voice according to the embodiment of the present invention.
  • the image recognition module 62 includes: a sending unit 621 and a receiving unit 622;
  • the sending unit 621 is configured to send the product image information to the remote service device, so that the remote service device identifies the image information of the product, and acquires the text information of the product according to the recognition result;
  • the receiving unit 622 is configured to receive text information of an item sent by the remote service device.
  • the image recognition module 62 is specifically configured to perform barcode identification on the product image information, obtain a barcode of the commodity, and obtain text information of the commodity according to the barcode of the commodity.
  • the image recognition module 62 is specifically configured to perform optical character recognition on the image information of the product, acquire characters in the image information of the product, and obtain text information of the product according to the characters in the image information of the product.
  • the image recognition module 62 is specifically configured to perform feature extraction on the image information of the product, acquire the feature of the product, classify the product according to the feature of the product, obtain a classification of the product, and obtain text information of the product according to the classification of the product.
  • the image acquisition module 61 is configured to implement step S11 shown in FIG. 1, step S21 shown in FIG. 2, step S31 shown in FIG. 3, step S41 shown in FIG. Step S51 shown in FIG. 5;
  • image recognition module 62 is used to implement step S12 shown in FIG. 1, steps S22 and S23 shown in FIG. 2, steps S32 and S33 shown in FIG. 3, and step S42 shown in FIG. S43, S44 and steps S52, S53, S54, S55, S56 shown in FIG. 5;
  • the voice output module 63 is used to implement step S13 shown in FIG. 1, step S24 shown in FIG. 2, and step S34 shown in FIG. Step S45 shown in FIG. 4 and step S57 shown in FIG.
  • the image capturing module 61 may be one or more of an image sensor such as a monocular camera or a binocular camera.
  • the image recognition module 62 may be a processor; the voice output module 63 may be an audio output device such as a speaker, a power amplifier, a speaker, a headphone, or the like.
  • the programs corresponding to the operations performed by the product identification device described above may be stored in the memory of the article identification device in software, so that the processor invokes the operations corresponding to the above respective modules.
  • FIG. 8 shows a possible structural diagram of the article identification device involved in the above embodiment.
  • the product identification device 800 includes a processor 81, a memory 82, a system bus 83, a communication interface 84, an image acquisition device 85, and a voice output device 86.
  • the processor 81 may be a processor or a collective name of a plurality of processing elements.
  • the processor 81 can be a central processing unit (CPU).
  • the processor 81 can also be another general purpose processor, a digital signal processing (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or Other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the like, can implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the present disclosure.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the processor 81 may also be a dedicated processor, which may include at least one of a baseband processing chip, a radio frequency processing chip, and the like.
  • the processor can also be a combination of computing functions, such as one or more microprocessor combinations, DSP and A combination of microprocessors and so on.
  • the dedicated processor may also include a chip having other specialized processing functions of the device.
  • the memory 82 is used to store computer execution code, and the processor 81 is connected to the memory 82 through the system bus 83.
  • the processor 81 is configured to execute the computer execution code stored in the memory 82 to execute any of the embodiments provided by the embodiments of the present invention.
  • a product identification method for example, the processor 81 is configured to support the mobile terminal to perform step S12 shown in FIG. 1 , steps S22 and S23 shown in FIG. 2 , steps S32 and S33 shown in FIG. 3 , and FIG. Steps S42, S43, S44 and steps S52, S53, S54, S55, S56 shown in Fig. 5, and/or other processes for the techniques described herein, the specific article identification method can be referred to above and in the drawings The related description is not repeated here.
  • the system bus 83 can include a data bus, a power bus, a control bus, and a signal status bus. For the sake of clarity in the present embodiment, various buses are illustrated as the system bus 83 in FIG.
  • Communication interface 84 may specifically be a transceiver on the device.
  • the transceiver can be a wireless transceiver.
  • the wireless transceiver can be an antenna or the like of the device.
  • the processor 81 communicates with other devices via the communication interface 84, for example, if the device is a module or component of the terminal device, the device is for data interaction with other modules in the terminal device.
  • the steps of the method described in connection with the present disclosure may be implemented in a hardware manner, or may be implemented by a processor executing software instructions.
  • the embodiment of the present invention further provides a storage medium for storing computer software instructions used by the mobile terminal shown in FIG. 8 , which is designed to execute the product identification method shown in FIG. 1 , 2 , 3 , 4 , and 5 . code.
  • the software instructions may be composed of corresponding software modules, and the software modules may be stored in a random access memory (English: random access memory, abbreviation: RAM), flash memory, read only memory (English: read only memory, abbreviation: ROM) , erasable programmable read-only memory (English: erasable programmable ROM, abbreviation: EPROM), electrically erasable programmable read-only memory (English: electrical EPROM, abbreviation: EEPROM), registers, hard disk, mobile hard disk, CD-ROM (CD-ROM) or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor to enable the processor to read information from the storage medium and Write information to the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and the storage medium can be located in an ASIC.
  • the ASIC can be located in a core network interface device.
  • the processor and the storage medium may also exist as discrete components in the core network interface device.
  • the embodiment of the invention further provides a computer program product, which can be directly loaded into the internal memory of the computer and contains software code, and the computer program can be loaded and executed by the computer to implement the figures 1, 2, 3, and 4.
  • the functions described herein can be implemented in hardware, software, firmware, or any combination thereof.
  • the functions may be stored in a computer readable medium or transmitted as one or more instructions or code on a computer readable medium.
  • Computer readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one location to another.
  • a storage medium may be any available media that can be accessed by a general purpose or special purpose computer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种商品识别方法和装置，涉及商品识别技术领域。用于辅助盲人获取商品信息。该方法包括：从至少一个视角对商品进行图像采集，获取商品的图像信息(S11)；根据商品的图像信息获取商品的文本信息(S12)；将商品的文本信息转换为语音信息，并对语音信息进行输出(S13)。该方法用于辅助盲人进行商品识别。

Description

一种商品识别方法和装置 技术领域
本发明涉及商品识别技术领域，尤其涉及一种商品识别方法和装置。
背景技术
盲是世界上严重的社会和公共卫生问题之一。人类70％以上的信息都是通过视觉来获取的，视力问题很大程度上限制了盲人进行信息获取。
由于视力问题，盲人的生活中存在诸多不便，尤其是在商场进行购物时，面对商场中品类繁多的商品，盲人无法独立获取种类、型号、价格等商品的信息，因此对于盲人而言，在较大的空间范围和繁多的商品中挑选出自己需要的商品，独立完成购物，是非常困难的。一情况下盲人在购物时是通过导购员讲解来获取商品信息的，但这不仅给盲人购物带来了很大的不便，也大大增大了导购员的工作量，耗费了大量的人力和时间成本。因此，如何辅助盲人获取商品信息是亟待解决的一个问题。
发明内容
本发明的实施例提供一种商品识别方法和装置，用于辅助盲人获取商品信息。
为达到上述目的，本发明的实施例采用如下技术方案：
第一方面，提供一种商品识别方法，用于辅助盲人获取商品信息，所述方法包括：
从至少一个视角对商品进行图像采集，获取所述商品的图像信息；
根据所述商品的图像信息获取所述商品的文本信息；
将所述商品的文本信息转换为语音信息，并对所述语音信息进行输出。
第二方面，提供一种商品识别装置，用于辅助盲人获取商品信息，所述装置包括：
图像采集模块，用于从至少一个视角对商品进行图像采集，获取所述商品的图像信息；
图像识别模块，用于根据所述商品的图像信息获取所述商品的文本信息；
语音输出模块，用于将所述商品的文本信息转换为语音信息，并对所述语音信息进行输出。
第三方面，提供一种商品识别装置，所述装置包括：处理器和存储器，所述存储器用于存储计算机执行代码，所述计算机执行代码用于控制所述处理器执行第一方面所述的商品识别方法。
第四方面，提供一种计算机存储介质，用于储存为第三方面所述的商品识别装置所用的计算机软件指令，其包含执行第一方面所述的商品识别方法所设计的程序代码。
第五方面，提供一种计算机程序产品，可直接加载到计算机的内部存储器中，并含有软件代码，所述计算机程序经由计算机载入并执行后能够实现第一方面所述的商品识别方法。
本发明的实施例提供的商品识别方法首先从至少一个视角对商品进行图像采集，获取商品的图像信息，然后根据商品的图像信息获取商品的文本信息，最后将商品的文本信息转换为语音信息，并对语音信息进行输出，由于本发明实施例提供的商品识别装置可以获取商品的图像信息并根据商品的图像信息获取商品的文本信息，最后将商品的文本信息转换为语音信息输出，所以通过本发明实施例盲人可以通过语音的方式获取商品信息。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明的实施例提供的商品识别方法的步骤流程图之一；
图2为本发明的实施例提供的商品识别方法的步骤流程图之二；
图3为本发明的实施例提供的商品识别方法的步骤流程图之三；
图4为本发明的实施例提供的商品识别方法的步骤流程图之四；
图5为本发明的实施例提供的商品识别方法的步骤流程图之五；
图6为本发明的实施例提供的商品识别装置的示意性结构图之一；
图7为本发明的实施例提供的商品识别装置的示意性结构图之二；
图8为本发明的实施例提供的商品识别装置的示意性结构图之三。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。需要说明的是，下文所提供 的任意多个技术方案中的部分或全部技术特征在不冲突的情况下，可以结合使用，形成新的技术方案。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
在本发明实施例中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。如果不加说明，本文中的“多个”是指两个或两个以上。
在本发明实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本发明实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
需要说明的是，本发明实施例中，除非另有说明，“多个”的含义是指两个或两个以上。
还需要说明的是，本发明实施例中，“的(英文：of)”，“相应的(英文：corresponding，relevant)”和“对应的(英文：corresponding)”有时可以混用，应当指出的是，在不强调其区别时，其所要表达的含义是一致的。
本发明实施例所提供的技术方案的基本原理为：针对盲人因视力问题而无法获取商品信息，进而导致盲人不能独立的进行购物的问题，本发明实施例所提供的技术方案通过获取商品的图像信息，然后根据商品的图像信息获取商品的文本信息，最后将商品的文本信息转换为语音信息输出，进而使盲人通过接收语音信息获取商品的信息，从而解决上述盲人无法获取商品信息的问题。
基于上述内容，本发明实施例提供一种用于辅助盲人获取商品信息的商品识别方法。
示例性的，本发明实施例提供的商品识别方法的执行主体可以 为采用本发明实施例提供的商品识别方法对商品行识别的终端设备。终端设备可以为头戴式导盲装置、导盲眼镜、手机、便携式计算机、袖珍式计算机、手持式计算机、数码相框、掌上电脑、导航仪等，或者终端设备可以为安装有可以采用本发明实施例提供的商品识别方法对商品行识别的软件客户端或软件系统或软件应用的个人计算机(英文全称：personal computer,简称：PC)、服务器等，具体的硬件实现环境可以通用计算机形式，或者是专门设计的集成电路(英文全称：Application Specific Integrated Circuit，简称：ASIC)的方式，也可以是(英文全称：Field Programmable Gate Array，简称：FPGA)，或者是一些可编程的扩展平台例如嵌入式(英文名称：Tensilica)的可配置处理器平台等。
参照图1所示，本发明实施例提供的商品识别方法包括：
S11、从至少一个视角对商品进行图像采集，获取商品的图像信息。
示例性的，可以通过单目摄像头、双目摄像头等图像传感器中的一种或多种来实现上述步骤S11中的图像采集。
可选的，上述S11中从至少一个视角对商品进行图像采集具体可以为从一个视角对商品进行图像采集，也可以为从多个视角对商品进行图像采集。示例性的，本发明实施例中具体可以通过如下方法实现从多个视角对商品进行图像采集：
一、用户将商品放置于图像采集装置的采集范围之内，然后对商品进行转动和/或移动，图像采集装置在用户对商品进行转动和/或移动的过程中从多个视角对商品进行图像采集。
二、图像采集装置包括多个且分别设置于不同的位置，当进行图像采集时，多个设置于不同位置的图像采集装置分别从一个视角对商品进行图像采集，从而实现从多个视角对商品进行图像采集。
还需要说明的是，当从多个视角对商品进行图像采集时，由于 商品的图像信息是通过从多个视角对商品进行图像采集获取的，因此商品的图像信息包括：多个视角商品的图像。通过从多个视角对商品进行图像采集可以更加全面的获取商品的图像信息，进而有利后继对商品的图像信息进行识别。
S12、根据商品的图像信息获取商品的文本信息。
上述实施例中的根据商品的图像信息获取商品的文本信息的过程可以在图像识别装置内部完成，也可以通过远程服务设备协助完成。
当根据商品的图像信息获取商品的文本信息的过程在图像识别装置内部完成时，步骤S12具体可以通过如下步骤实现：a、对商品的图像信息进行识别。b、根据识别结果获取商品的文本信息。示例性的，可以通过安装有图像识别软件的图像处理设备来执行上述步骤。
当根据商品的图像信息获取商品的文本信息的过程通过远程服务设备协助完成时，步骤S12具体可以通过如下步骤实现：c、将商品图像信息发送至远端服务设备，以便远端服务设备对商品的图像信息进行识别，并根据识别结果获取商品的文本信息。d、接收远端服务设备发送的商品的文本信息。示例性的，远端服务设备可以为云端服务器等。
此外，对商品的图像信息进行识别可以采用任一种图像识别算法对商品图像信息进行处理、分析和理解。本发明实施例中对商品的图像信息识别过程中采用的图像识别算法不做限定。
S13、将商品的文本信息转换为语音信息，并对语音信息进行输出。
具体的，可以通过语音合成技术将商品的文本信息转换为语音信息，然后通过扬声器、功放机、音箱、耳机等音频输出设备将合成的语音信息输出。
需要说明的是，将商品的文本信息转换为语音信息，并对语音信息进行输出具体可以为：直接通过语音合成技术将商品的文本信息转换为语音信息输出，也可以为将商品的文本信息进行关键字提取，比如将商品的文本信息与数据库中存储的商品的关键字进行比对，然后语音输出关键字比对结果。
本发明的实施例提供的商品识别方法首先从至少一个视角对商品进行图像采集，获取商品的图像信息，然后根据商品的图像信息获取商品的文本信息，最后将商品的文本信息转换为语音信息，并对语音信息进行输出，由于本发明实施例提供的商品识别装置可以获取商品的图像信息并根据商品的图像信息获取商品的文本信息，最后将商品的文本信息转换为语音信息输出，所以通过本发明实施例盲人可以通过语音的方式获取商品信息，进而可以使盲人可以独立的进行购物。
进一步的，本发明实施例提供如下几种具体实现方式来实现图1所示的商品识别方法：
一、
参照图2所示，上述商品识别方法具体包括如下步骤：
S21、从至少一个视角对商品进行图像采集，获取商品的图像信息。
S22、对商品的图像信息进行条码识别，获取商品的条码。
具体的，上述实施例中商品条码可以为一维条码和/或二维条码。其中，商品的一维条码由一组规则排列的条、空及其对应代码组成。商品的二维条码是用特定的几何图形按一定规律在二维方向上分布的黑白相间的图形。其形成商品条码的条码符号可以包括零售商品、储运包装商品、物流单元、参与方位置等等的代码与条码标识。通常商品的条码印在商品包装上，或将其制成条码标签附在商品上。因此通过对商品的图像信息进行条码识别可以获取商品的 条码。
对商品的一维条码别进行识别具体可以为：先进行一维条码检测和定位，确定一维条码的在图像中的区域，然后在对该区域的图像进行一维条码识别，读取一维条码中的商品编号等的信息，最后根据一维条码中的信息查询获取商品文本信息。同样对商品的二维条码进行识别具体可以为：先进行二维条码检测和定位然后在对该区域的图像进行二维条码识别，读取二维条码中的信息。与一维条码不同之处在于，二维条码中可以包括更多信息，因此可以通过二维条码的内容直接获取商品的文本信息或者对获得信息进行进一步处理获得商品的文本。
S23、根据商品的条码获取商品的文本信息。
对商品的条码进行查询和数据处理，可立即识别出商品制造厂商、名称、价格、颜色等商品信息，并且这些商品信息都是通过文本的形式显示出来的，所以可以根据商品的条码获取商品的文本信息。
此外，商品的条码还遵循唯一性原则，即一个商品项目只能有一个代码，或者说一个代码只能标识一种商品项目。不同规格、不同包装、不同品种、不同价格、不同颜色的商品均会使用不同的商品的条码。因此通过商品的条码获取的商品的文本信息相对准确，可以避免向用户提供的商品信息错误。
S24、将商品的文本信息转换为语音信息，并对语音信息进行输出。
二、
参照图3所示，上述商品识别方法具体包括如下步骤：
S31、从至少一个视角对商品进行图像采集，获取商品的图像信息。
S32、对商品的图像信息进行光学字符识别(英文名称：Optical  Character Recognition，英文简称：OCR)，获取商品的图像信息中的字符。
具体的，光学字符识别是指光学字符识别设备(例如扫描仪、数码相机、打印机等)检查纸质文档、图像上的字符，通过检测暗、亮的模式确定其形状，然后用字符识别方法将形状翻译成计算机文字的过程。
可选的，如上所述，本发明实施例中的商品的图像信息包括至少两张图像，在对商品的图像信息进行光学字符识别的过程中可以先分别对每一张图像进行光学字符识别，然后再将识别的字符整理获取商品的文本信息，也可以先对商品的图像信息中包括的至少两张图像进行拼接、融合处理，然后再进行光学字符识别获取商品的文本信息。
S33、根据商品图像信息中的字符获取商品的文本信息。
通常，商品的外包装都会附有包装标签，而包装标签会通过文字方式表明商品的制造者或销售者的名称和地址、产品名称、商标、成分、品质特点、包装内产品数量、使用方法及用量、编号、贮藏应注意的事项、质检号、生产日期和有效期等内容，所以可以根据商品图像信息中的字符获取商品的文本信息。
S34、将商品的文本信息转换为语音信息，并对语音信息进行输出。
三、
参照图4所示，上述商品识别方法具体包括如下步骤：
S41、从至少一个视角对商品进行图像采集，获取商品的图像信息。
S42、对商品的图像信息进行特征提取，获取商品的特征。
可选的，上述实施例中的商品的特征可以是通过人工设计的图 像特征提取器获取的特征，也可以是通过机器学习方法，比如通过深度学习方法自动学习获取的图像特征。
S43、根据商品的特征对商品进行分类，获取商品的分类。
示例性的，根据商品的特征对商品进行分类并获取商品的分类可以为将商品的特征输入分类器进行分类，获取商品的分类。其中，分类器可以是传统的支持向量机分类器(英文名称：Support Vector Machine，简称：SVM)或者传统的迭代(英文名称：adaboost)分类器，也可以是基于深度学习网络的分类器。
S44、根据商品的分类获取商品的文本信息。
在上述步骤S43中获取商品的分类后，可以根据商品的分类获取该类别的商品的文本信息。
S45、将商品的文本信息转换为语音信息，并对语音信息进行输出。
四、
参照图5所示，上述商品识别方法具体包括如下步骤：
S51、从至少两个视角对商品进行图像采集，获取商品的图像信息。
S52、对商品的图像信息进行条码识别。
当步骤S52中对商品的图像信息进行条码识别成功时，执行步骤S53、S57，当步骤S52中对商品的图像信息进行条码识别失败时，执行步骤S54。
S53、获取商品的条码，根据商品的条码获取商品的文本信息。
S54、对商品的图像信息进行光学字符识别。
当步骤S54中对商品的图像信息进行光学字符识别成功时，执行步骤S55、S57，当步骤S52中对商品的图像信息进行光学字符 识别失败时，执行步骤S56、S57。
S55、获取商品的图像信息中的字符，根据商品图像信息中的字符获取商品的文本信息。
S56、对商品的图像信息进行特征提取,根据商品的特征对商品进行分类,获取商品的分类，根据商品的分类获取商品的文本信息。
S57、将商品的文本信息转换为语音信息，并对语音信息进行输出。
需要说明的是，上述实施例中提供的商品识别方法中获取商品的文本信息的步骤还可以应用于远端服务器中，例如：当远端服务设备接收到商品的图像信息时，也可以对商品的图像信息进行条码识别，获取商品的条码，并根据商品的条码获取商品的文本信息，然后再发出商品的文本信息；再例如：当远端服务设备接收到商品的图像信息时，也可以对商品的图像信息进行光学字符识别，获取商品的图像信息中的字符；根据商品图像信息中的字符获取商品的文本信息，然后用再发出商品的文本信息；即远端服务器也可以采用上述任一种实现方式中的商品的文本信息获取方法来获取商品的文本信息。
下面说明本发明实施例提供的与上文所提供的方法实施例相对应的装置实施例。需要说明的是，下述装置实施例中相关内容的解释，均可以参考上述方法实施例。
在采用对应各个功能划分各个功能模块的情况下，图6示出了上述实施例中所涉及的用于辅助盲人获取商品信息的商品识别装置的一种可能的结构示意图。商品识别装置600包括：
图像采集模块61，用于从至少一个视角对商品进行图像采集，获取商品的图像信息。
图像识别模块62，用于根据商品的图像信息获取商品的文本信息。
语音输出模块63，用于将商品的文本信息转换为语音信息，并对语音信息进行输出。
本发明的实施例提供的商品识别装置包括：图像采集模块、图像识别模块以及语音输出模块，其中，图像采集模块用于从至少一个视角对商品进行图像采集，获取商品的图像信息，图像识别模块用于对商品的图像信息进行识别，并根据识别结果获取商品的文本信息，语音输出模块用于将商品的文本信息转换为语音信息，并对语音信息进行输出，由于本发明实施例提供的商品识别装置可以获取商品的图像信息并根据商品的图像信息获取商品文本信息，最后将商品的文本信息转换为语音信息输出，所以通过本发明实施例盲人可以通过语音的方式获取商品信息。
可选的，参照图7所示，图像识别模块62包括：发送单元621和接收单元622；
发送单元621用于将商品图像信息发送至远端服务设备，以便远端服务设备对商品的图像信息进行识别，并根据识别结果获取商品的文本信息；
接收单元622用于接收远端服务设备发送的商品的文本信息。
可选的，图像识别模块62具体用于对商品图像信息进行条码识别，获取商品的条码，根据商品的条码获取商品的文本信息。
可选的，图像识别模块62具体用于对商品的图像信息进行光学字符识别，获取商品的图像信息中的字符，根据商品的图像信息中的字符获取商品的文本信息。
可选的，图像识别模块62具体用于对商品的图像信息进行特征提取，获取商品的特征；根据商品的特征对商品进行分类，获取商品的分类；根据商品的分类获取商品的文本信息。
即，图像采集模块61用于实现图1所示的步骤S11、图2所示的步骤S21、图3所示的步骤S31、图4所示的步骤S41以及图 5所示的步骤S51；图像识别模块62用于实现图1所示的步骤S12、图2所示的步骤S22、S23、图3所示的步骤S32、S33、图4所示的步骤S42、S43、S44以及图5所示的步骤S52、S53、S54、S55、S56；语音输出模块63用于实现图1所示的步骤S13、图2所示的步骤S24、图3所示的步骤S34、图4所示的步骤S45以及图5所示的步骤S57。
还需说明的是，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
在硬件实现上，上述的图像采集模块61可以是单目摄像头、双目摄像头等图像传感器中的一种或多种。图像识别模块62可以是处理器；语音输出模块63可以是扬声器、功放机、音箱、耳机等音频输出设备。上述商品识别装置所执行的动作所对应的程序均可以以软件形式存储于商品识别装置的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在采用集成的单元的情况下，图8示出了上述实施例中所涉及的商品识别装置的一种可能的结构示意图。商品识别装置800包括：处理器81、存储器82、系统总线83、通信接口84、图像采集装置85、语音输出装置86。
上述处理器81可以是一个处理器，也可以是多个处理元件的统称。例如，处理器81可以为中央处理器(central processing unit，CPU)。处理器81也可以为其他通用处理器、数字信号处理器(digital signal processing，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field-programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等，其可以实现或执行结合本发明公开内容所描述的各种示例性的逻辑方框，模块和电路。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。处理器81还可以为专用处理器，该专用处理器可以包括基带处理芯片、射频处理芯片等中的至少一个。处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和 微处理器的组合等等。进一步地，该专用处理器还可以包括具有该装置其他专用处理功能的芯片。
存储器82用于存储计算机执行代码，处理器81与存储器82通过系统总线83连接，当移动终端运行时，处理器81用于执行存储器82存储的计算机执行代码，以执行本发明实施例提供的任意一种商品识别方法，如，处理器81用于支持移动终端执行图1所示的步骤S12、图2所示的步骤S22、S23、图3所示的步骤S32、S33、图4所示的步骤S42、S43、S44以及图5所示的步骤S52、S53、S54、S55、S56，和/或用于本文所描述的技术的其它过程，具体的商品识别方法可参考上文及附图中的相关描述，此处不再赘述。
系统总线83可以包括数据总线、电源总线、控制总线和信号状态总线等。本实施例中为了清楚说明，在图8中将各种总线都示意为系统总线83。
通信接口84具体可以是该装置上的收发器。该收发器可以为无线收发器。例如，无线收发器可以是该装置的天线等。处理器81通过通信接口84与其他设备，例如，若该装置为该终端设备中的一个模块或组件时，该装置用于与该终端设备中的其他模块之间进行数据交互。
结合本发明公开内容所描述的方法的步骤可以硬件的方式来实现，也可以是由处理器执行软件指令的方式来实现。本发明实施例还提供一种存储介质，用于储存为图8所示的移动终端所用的计算机软件指令，其包含执行图1、2、3、4、5所示的商品识别方法所设计的程序代码。其中，软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器(英文：random access memory，缩写：RAM)、闪存、只读存储器(英文：read only memory，缩写：ROM)、可擦除可编程只读存储器(英文：erasable programmable ROM，缩写：EPROM)、电可擦可编程只读存储器(英文：electrically EPROM，缩写：EEPROM)、寄存器、硬盘、移动硬盘、只读光盘(CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可 向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于核心网接口设备中。当然，处理器和存储介质也可以作为分立组件存在于核心网接口设备中。
本发明实施例还提供一种计算机程序产品，该计算机程序可直接加载到计算机的内部存储器中，并含有软件代码，计算机程序经由计算机载入并执行后能够实现图1、2、3、4、5所示的商品识别方法。
本领域技术人员应该可以意识到，在上述一个或多个示例中，本发明所描述的功能可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时，可以将这些功能存储在计算机可读介质中或者作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (13)

  1. 一种商品识别方法，用于辅助盲人获取商品信息，其特征在于，所述方法包括：
    从至少一个视角对商品进行图像采集，获取所述商品的图像信息；
    根据所述商品的图像信息获取所述商品的文本信息；
    将所述商品的文本信息转换为语音信息，并对所述语音信息进行输出。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述商品的图像信息获取所述商品的文本信息，包括：
    将所述商品的图像信息发送至远端服务设备，以便所述远端服务设备根据所述商品的图像信息获取所述商品的文本信息；
    接收所述远端服务设备发送的所述商品的文本信息。
  3. 根据权利要求1所述的方法，其特征在于，所述根据所述商品的图像信息获取所述商品的文本信息包括：
    对所述商品的图像信息进行条码识别，获取所述商品的条码；
    根据所述商品的条码获取所述商品的文本信息。
  4. 根据权利要求1所述的方法，其特征在于，所述根据所述商品的图像信息获取所述商品的文本信息包括：
    对所述商品的图像信息进行光学字符识别，获取所述商品的图像信息中的字符；
    根据所述商品图像信息中的字符获取商品的文本信息。
  5. 根据权利要求1所述的方法，其特征在于，所述根据所述商品的图像信息获取所述商品的文本信息包括：
    对所述商品的图像信息进行特征提取，获取商品的特征；
    根据所述商品的特征对所述商品进行分类，获取商品的分类；
    根据所述商品的分类获取所述商品的文本信息。
  6. 一种商品识别装置，用于辅助盲人获取商品信息，其特征在于，所述装置包括：
    图像采集模块，用于从至少一个视角对商品进行图像采集，获取所述商品的图像信息；
    图像识别模块，用于根据所述商品的图像信息获取所述商品的文本信息；
    语音输出模块，用于将所述商品的文本信息转换为语音信息，并对所述语音信息进行输出。
  7. 根据权利要求6所述的装置，其特征在于，所述图像识别模块包括：发送单元和接收单元；
    所述发送单元用于将所述商品图像信息发送至远端服务设备，以便所述远端服务设备对所述商品的图像信息进行识别，并根据识别结果获取商品的文本信息；
    所述接收单元用于接收所述远端服务设备发送的商品的文本信息。
  8. 根据权利要求6所述的装置，其特征在于，
    所述图像识别模块具体用于对所述商品图像信息进行条码识别，获取所述商品的条码，根据所述商品的条码获取所述商品的文本信息。
  9. 根据权利要求6所述的装置，其特征在于，
    所述图像识别模块具体用于对所述商品的图像信息进行光学字符识别，获取所述商品的图像信息中的字符，根据所述商品的图像 信息中的字符获取商品的文本信息。
  10. 根据权利要求6所述的装置，其特征在于，
    所述图像识别模块具体用于对所述商品的图像信息进行特征提取，获取商品的特征；根据所述商品的特征对所述商品进行分类，获取商品的分类；根据所述商品的分类获取所述商品的文本信息。
  11. 一种商品识别装置，其特征在于，所述装置包括：处理器和存储器，所述存储器用于存储计算机执行代码，所述计算机执行代码用于控制所述处理器执行权利要求1-5任一项所述的商品识别方法。
  12. 一种计算机存储介质，其特征在于，用于储存为权利要求11所述的商品识别装置所用的计算机软件指令，其包含执行权利要求1-5任一项所述的商品识别方法所设计的程序代码。
  13. 一种计算机程序产品，其特征在于，可直接加载到计算机的内部存储器中，并含有软件代码，所述计算机程序经由计算机载入并执行后能够实现权利要求1-5任一项所述的商品识别方法。
PCT/CN2016/111831 2016-12-23 2016-12-23 一种商品识别方法和装置 Ceased WO2018112930A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/111831 WO2018112930A1 (zh) 2016-12-23 2016-12-23 一种商品识别方法和装置
CN201680006925.4A CN107454964A (zh) 2016-12-23 2016-12-23 一种商品识别方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/111831 WO2018112930A1 (zh) 2016-12-23 2016-12-23 一种商品识别方法和装置

Publications (1)

Publication Number Publication Date
WO2018112930A1 true WO2018112930A1 (zh) 2018-06-28

Family

ID=60484713

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/111831 Ceased WO2018112930A1 (zh) 2016-12-23 2016-12-23 一种商品识别方法和装置

Country Status (2)

Country Link
CN (1) CN107454964A (zh)
WO (1) WO2018112930A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110008782A (zh) * 2019-06-06 2019-07-12 江苏东大集成电路系统工程技术有限公司 条码信息的获取方法及装置
CN116301311A (zh) * 2022-12-13 2023-06-23 北京字跳网络技术有限公司 交互式信息获取方法、装置、电子设备及存储介质
CN117077083A (zh) * 2023-10-10 2023-11-17 上海英内物联网科技股份有限公司 装箱物品自动识别统计方法

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009071B (zh) * 2018-01-04 2022-07-01 青岛海尔洗衣机有限公司 一种智能衣橱的控制方法和智能衣橱
CN109033985B (zh) 2018-06-29 2020-10-09 百度在线网络技术（北京）有限公司 商品识别的处理方法、装置、设备、系统及存储介质
CN109353398B (zh) * 2018-09-20 2020-11-10 北京旷视科技有限公司 商品识别方法、装置和系统及存储介质及购物车
CN109359706A (zh) * 2018-09-25 2019-02-19 上海合阔信息技术有限公司 商品信息智能识别系统和方法
CN111242712B (zh) * 2018-11-29 2023-04-28 阿里巴巴集团控股有限公司 一种商品展示方法及其装置
CN110222550B (zh) * 2019-07-11 2024-10-29 上海肇观电子科技有限公司 信息播报方法、电路、播报设备、存储介质、智能眼镜
CN111080399A (zh) * 2019-11-22 2020-04-28 汉口北进出口服务有限公司 一种商品信息处理方法和装置
CN110942035A (zh) * 2019-11-28 2020-03-31 浙江由由科技有限公司 一种用于获取商品信息的方法、系统、装置和存储介质
CN111738031B (zh) * 2020-08-06 2021-03-02 江苏东大集成电路系统工程技术有限公司 一种一维条码识别方法
CN112698848B (zh) * 2020-12-31 2024-07-26 Oppo广东移动通信有限公司 机器学习模型的下载方法、装置、终端及存储介质
CN113393289A (zh) * 2021-05-27 2021-09-14 阿里巴巴新加坡控股有限公司 商品对象信息处理、标题修改的方法及装置
CN114387534B (zh) * 2021-12-03 2025-09-19 浙江大华技术股份有限公司 辅助盲人购物的方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101474020A (zh) * 2009-01-08 2009-07-08 上海交通大学 基于条形码标识的盲人超市导购方法和装置
CN101524220A (zh) * 2009-03-25 2009-09-09 胡志超 盲人自助购物的方法与装置
CN102495995A (zh) * 2011-12-09 2012-06-13 上海力远计算机科技有限公司 光学字符识别系统
CN102798388A (zh) * 2012-06-20 2012-11-28 上海交通大学 基于dsp的盲人超市购物辅助装置
CN103632588A (zh) * 2013-11-28 2014-03-12 苏州罗马冯环保科技有限公司 盲人专用商品阅读器

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8620083B2 (en) * 2004-12-03 2013-12-31 Google Inc. Method and system for character recognition
CN102063616A (zh) * 2010-12-30 2011-05-18 上海电机学院 一种基于图像特征匹配的商品自动识别系统及方法
CN102354366A (zh) * 2011-09-23 2012-02-15 上海合合信息科技发展有限公司 基于网络来识别图像的方法及系统
CN104463659A (zh) * 2014-12-23 2015-03-25 江苏天使电子科技有限公司 盲人购物系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101474020A (zh) * 2009-01-08 2009-07-08 上海交通大学 基于条形码标识的盲人超市导购方法和装置
CN101524220A (zh) * 2009-03-25 2009-09-09 胡志超 盲人自助购物的方法与装置
CN102495995A (zh) * 2011-12-09 2012-06-13 上海力远计算机科技有限公司 光学字符识别系统
CN102798388A (zh) * 2012-06-20 2012-11-28 上海交通大学 基于dsp的盲人超市购物辅助装置
CN103632588A (zh) * 2013-11-28 2014-03-12 苏州罗马冯环保科技有限公司 盲人专用商品阅读器

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110008782A (zh) * 2019-06-06 2019-07-12 江苏东大集成电路系统工程技术有限公司 条码信息的获取方法及装置
CN116301311A (zh) * 2022-12-13 2023-06-23 北京字跳网络技术有限公司 交互式信息获取方法、装置、电子设备及存储介质
CN117077083A (zh) * 2023-10-10 2023-11-17 上海英内物联网科技股份有限公司 装箱物品自动识别统计方法
CN117077083B (zh) * 2023-10-10 2024-01-05 上海英内物联网科技股份有限公司 装箱物品自动识别统计方法

Also Published As

Publication number Publication date
CN107454964A (zh) 2017-12-08

Similar Documents

Publication Publication Date Title
WO2018112930A1 (zh) 一种商品识别方法和装置
US12586107B2 (en) Document optical character recognition
US20210217129A1 (en) Detection of encoded signals and icons
US11257198B1 (en) Detection of encoded signals and icons
US9002066B2 (en) Methods, systems and processor-readable media for designing a license plate overlay decal having infrared annotation marks
US20190311422A1 (en) Methods and arrangements including data migration among computing platforms, e.g. through use of audio encoding
US10832047B2 (en) Systems and methods for obtaining product information in real-time
US20170046593A1 (en) Identification of items depicted in images
US20150026074A1 (en) Consumer-centric product warranty management system
WO2020077877A1 (zh) 平台商品入驻方法、装置、计算机设备及存储介质
US10803272B1 (en) Detection of encoded signals and icons
WO2021018241A1 (zh) 信息处理
US9349046B2 (en) Smart optical input/output (I/O) extension for context-dependent workflows
CN108416403A (zh) 商品与标签的自动关联方法、系统、设备及存储介质
CN107430691A (zh) 识别图像中描绘的物品
US12242809B2 (en) Techniques for pretraining document language models for example-based document classification
CN110210478A (zh) 一种商品外包装文字识别方法
WO2019096222A1 (zh) 一种基于身份识别和商品识别的无人售货方法和设备
WO2021169207A1 (zh) 基于机器学习的物品识别方法及装置
CN107729791A (zh) 信息处理方法及电子设备
US20140330619A1 (en) Methods and systems for automatic, pre-sale price matching
CN111753608A (zh) 信息处理方法及装置、电子设备及存储介质
US20210357883A1 (en) Payment method capable of automatically recognizing payment amount
CN108090728A (zh) 一种基于智能终端的快递信息录入方法及录入系统
CN114445724B (zh) 图像识别方法及装置、电子设备、存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16924223

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 15/10/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16924223

Country of ref document: EP

Kind code of ref document: A1