WO2019101027A1 - 一种商品识别方法和设备 - Google Patents

一种商品识别方法和设备 Download PDF

Info

Publication number
WO2019101027A1
WO2019101027A1 PCT/CN2018/116127 CN2018116127W WO2019101027A1 WO 2019101027 A1 WO2019101027 A1 WO 2019101027A1 CN 2018116127 W CN2018116127 W CN 2018116127W WO 2019101027 A1 WO2019101027 A1 WO 2019101027A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
image
label
item
information
Prior art date
Application number
PCT/CN2018/116127
Other languages
English (en)
French (fr)
Inventor
斯科特·马修·罗伯特
黄鼎隆
傅恺
Original Assignee
深圳码隆科技有限公司
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 深圳码隆科技有限公司 filed Critical 深圳码隆科技有限公司
Publication of WO2019101027A1 publication Critical patent/WO2019101027A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/62Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63Scene text, e.g. street names
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/62Text, e.g. of license plates, overlay texts or captions on TV images
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/2163Partitioning the feature space
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/68Food, e.g. fruit or vegetables
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/28Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet
    • G06V30/293Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet of characters other than Kanji, Hiragana or Katakana

Definitions

  • the present application relates to the field of data identification, and in particular, to a product identification method and device.
  • the identification of goods in the area of the shopping mall is basically based on manual methods for identification, but this method can not cope with the huge amount of goods, and because it is manually identified, resulting in inefficiency, time-consuming and laborious, and artificial The cost is also increasing, and the identification by manual means will also lead to high costs and cannot effectively meet the needs of current product identification.
  • the present application proposes a product identification method and device; by acquiring an image of a product and performing multi-level detection on the image, automatic product identification is realized, efficiency is improved, and a large number of commodities can be handled. , saving costs.
  • the embodiment of the present application proposes a commodity identification method, including:
  • Determining the label area of the product by performing multi-level detection on the image; wherein, the image area corresponding to the upper level detection is larger than the image area corresponding to the next level detection;
  • Information in the tag area is identified to determine information for the item.
  • the "by performing multi-level inspection of the image to determine a label area of the item” includes:
  • An area in which the number of characters satisfies a preset value is set as a label area of the label.
  • the label area is an area in which the number of characters is the largest and the area is a preset unit area.
  • the "by multi-level inspection of the image to determine the label area of the item” includes:
  • the area is set as the label area of the label.
  • the "identifying information in the tag area to determine information of the item” includes:
  • Enhancing contrast of the label area and performing character recognition on the label area; wherein the character recognition includes Chinese character recognition and English recognition and symbol recognition;
  • Information of the item is obtained from the result of the identification.
  • the embodiment of the present application further provides a commodity identification device, including:
  • Obtaining a module configured to obtain an image of the item
  • a detecting module configured to determine a label area of the product by performing multi-level detection on the image; wherein, an image area corresponding to the upper level detection is greater than an image area corresponding to the next level detection;
  • An identification module configured to identify information in the tag area to determine information of the item.
  • the detecting module is configured to:
  • An area in which the number of characters satisfies a preset value is set as a label area of the label.
  • the label area is an area in which the number of characters is the largest and the area is a preset unit area.
  • the detecting module is configured to:
  • the area is set as the label area of the label.
  • the identification module is configured to:
  • Enhancing contrast of the label area and performing character recognition on the label area; wherein the character recognition includes Chinese character recognition and English recognition and symbol recognition;
  • Information of the item is obtained from the result of the identification.
  • the embodiment of the present application provides a product identification method and device, the method includes: acquiring an image of a product; and performing multi-level detection on the image to determine a label area of the product; wherein, the upper level The image area corresponding to the detection is larger than the image area corresponding to the next level detection; the information in the label area is identified to determine the information of the item.
  • FIG. 1 is a schematic flow chart of a product identification method according to an embodiment of the present application.
  • FIG. 2 is a schematic structural diagram of a commodity identification device according to an embodiment of the present application.
  • the term “comprising” or “including” may be used in the various embodiments of the present disclosure to indicate the existence of the disclosed function, operation or element, and does not limit one or more functions, operations or elements. increase.
  • the terms “comprising,” “having,” “,” It should not be understood that the existence or addition of one or more features, numbers, steps, operations, components or components of one or more other features, numbers, steps, operations, components, components or combinations of the foregoing are excluded. Or the possibility of a combination of the foregoing.
  • the expression “or” or “at least one of A or / and B” includes any or all combinations of the simultaneously listed characters.
  • the expression “A or B” or “at least one of A or / and B” may include A, may include B, or may include both A and B.
  • Expressions used in various embodiments of the present disclosure may modify various constituent elements in various embodiments, but the corresponding constituent elements may not be limited.
  • the above statements do not limit the order and/or importance of the elements.
  • the above statements are only used for the purpose of distinguishing one element from another.
  • the first user device and the second user device indicate different user devices, although both are user devices.
  • a first element could be termed a second element, and a second element could be termed a first element, without departing from the scope of the various embodiments of the present disclosure.
  • the first constituent element can be directly connected to the second constituent element and can be “connected” between the first constituent element and the second constituent element.
  • the third component On the contrary, when a constituent element is “directly connected” to another constituent element, it is understood that there is no third constituent element between the first constituent element and the second constituent element.
  • the term "user” as used in various embodiments of the present disclosure may indicate a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).
  • Embodiment 1 of the present application discloses a commodity identification method, as shown in FIG. 1, comprising the following steps:
  • Step 101 Obtain an image of the product
  • the image acquisition may be acquired based on photographing the product, or may be extracted from the image library that has been generated by shooting.
  • Step 102 Determine a label area of the product by performing multi-level detection on the image, where an image area corresponding to the upper level detection is larger than an image area corresponding to the next level detection;
  • the specific detection may be performed on the entire image, and the area where the label information is not present is excluded, for example, in a pure blank area, or The pure picture area is excluded, and the remaining areas are identified later, thereby improving the efficiency of recognition.
  • Step 103 Identify information in the label area to determine information of the item.
  • the "by performing multi-level inspection of the image to determine a label area of the item” includes:
  • An area in which the number of characters satisfies a preset value is set as a label area of the label.
  • the label area is an area in which the number of characters is the largest and the area is a preset unit area.
  • the label area of the label corresponds to a lot of information, so the number of characters will be more, it is likely to be the most, for example, can include the manufacturer, production time, brand, model, material composition, precautions, shelf life and many more. Thereby, the label area can be determined based on the number of characters.
  • the "by performing multi-level inspection of the image to determine a label area of the item” includes:
  • the area is set as the label area of the label.
  • the "identifying information in the tag area to determine information of the item” includes:
  • Enhancing contrast of the label area and performing character recognition on the label area; wherein the character recognition includes Chinese character recognition and English recognition and symbol recognition;
  • Information of the item is obtained from the result of the identification.
  • the tag information includes Chinese characters, English characters, and symbols
  • the information in the tag can be obtained through the identification of the three, and the information of the product can be obtained.
  • other processing such as statistical sales volume and so on.
  • Embodiment 2 of the present application also discloses a commodity identification device, as shown in FIG. 2, including:
  • the obtaining module 201 is configured to acquire an image of the commodity
  • the detecting module 202 is configured to determine the label area of the product by performing multi-level detection on the image; wherein, the image area corresponding to the upper level detection is larger than the image area corresponding to the next level detection;
  • the identification module 203 is configured to identify information in the tag area to determine information of the item.
  • the detecting module 202 is configured to:
  • An area in which the number of characters satisfies a preset value is set as a label area of the label.
  • the label area is an area in which the number of characters is the largest and the area is a preset unit area.
  • the detecting module 202 is configured to:
  • the area is set as the label area of the label.
  • the identification module 203 is configured to:
  • Enhancing contrast of the label area and performing character recognition on the label area; wherein the character recognition includes Chinese character recognition and English recognition and symbol recognition;
  • Information of the item is obtained from the result of the identification.
  • Embodiment 3 of the present application further discloses a terminal, including:
  • a memory storing executable instructions of the processor
  • processor is configured to:
  • Determining the label area of the product by performing multi-level detection on the image; wherein, the image area corresponding to the upper level detection is larger than the image area corresponding to the next level detection;
  • Information in the tag area is identified to determine information for the item.
  • the "by performing multi-level inspection of the image to determine a label area of the item” includes:
  • An area in which the number of characters satisfies a preset value is set as a label area of the label.
  • the label area is an area in which the number of characters is the largest and the area is a preset unit area.
  • the "by performing multi-level inspection of the image to determine a label area of the item” includes:
  • the area is set as the label area of the label.
  • the "identifying information in the tag area to determine information of the item” includes:
  • Enhancing contrast of the label area and performing character recognition on the label area; wherein the character recognition includes Chinese character recognition and English recognition and symbol recognition;
  • Information of the item is obtained from the result of the identification.
  • the embodiment of the present application provides a product identification method and device, the method includes: acquiring an image of a product; determining a label area of the product by performing multi-level detection on the image; The corresponding image area is larger than the image area corresponding to the next level of detection; the information in the label area is identified to determine the information of the item.
  • modules in the apparatus in the implementation scenario may be distributed in the apparatus for implementing the scenario according to the implementation scenario description, or may be correspondingly changed in one or more devices different from the implementation scenario.
  • the modules of the above implementation scenarios may be combined into one module, or may be further split into multiple sub-modules.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Character Discrimination (AREA)

Abstract

一种商品识别方法和设备,该方法包括:获取商品的图像(101);通过对所述图像进行多级检测,以确定所述商品的标签区域(102);其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;对所述标签区域中的信息进行识别,以确定所述商品的信息(103)。通过获取商品的图像以及对图像进行多级检测,实现了自动化的商品识别,提高效率,且可以应对海量的商品数量,节约了成本。

Description

一种商品识别方法和设备
相关申请的交叉引用
本申请要求于2017年11月23日提交中国专利局的申请号为CN201711180389.2、名称为“一种商品识别方法和设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据识别领域,特别涉及一种商品识别方法和设备。
背景技术
目前,在商场的区域的商品识别,基本都是依赖人工的方式来进行识别,但是这种方式无法应对海量的商品数量,且由于是人工的方式进行识别,导致效率低下,费时费力,而人工的成本也越来越高,以人工的方式来进行识别也将导致成本高企,无法有效应对目前的商品识别的需要。
由此,目前拯待一种更高效的商品识别方法。
发明内容
针对现有技术中的缺陷,本申请提出了一种商品识别方法和设备;通过获取商品的图像以及对图像进行多级检测,实现了自动化的商品识别,提高效率,且可以应对海量的商品数量,节约了成本。
具体的,本申请提出了以下具体的实施例:
本申请实施例提出了一种商品识别方法,包括:
获取商品的图像;
通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
对所述标签区域中的信息进行识别,以确定所述商品的信息。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
在一个具体的实施例中,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标 签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
判断确定的各区域中的字符是否存在有预设字符;
若判断结果为是,则将所述区域设置为所述标签的标签区域。
在一个具体的实施例中,所述“对所述标签区域中的信息进行识别,以确定所述商品的信息”包括:
提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
从所述识别的结果的中获取所述商品的信息。
本申请实施例还提出了一种商品识别设备,包括:
获取模块,配置成获取商品的图像;
检测模块,配置成通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
识别模块,配置成对所述标签区域中的信息进行识别,以确定所述商品的信息。
在一个具体的实施例中,所述检测模块,配置成:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
在一个具体的实施例中,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
在一个具体的实施例中,所述检测模块,配置成:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
判断确定的各区域中的字符是否存在有预设字符;
若判断结果为是,则将所述区域设置为所述标签的标签区域。
在一个具体的实施例中,所述识别模块,配置成:
提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
从所述识别的结果的中获取所述商品的信息。
以此,本申请实施例提出了一种商品识别方法和设备,该方法包括:获取商品的图像;通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的 图像区域大于下一级检测所对应的图像区域;对所述标签区域中的信息进行识别,以确定所述商品的信息。通过获取商品的图像以及对图像进行多级检测,实现了自动化的商品识别,提高效率,且可以应对海量的商品数量,节约了成本。
附图说明
为了更清楚地说明本申请实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本申请的某些实施例,因此不应被看作是对范围的限定,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相关的附图。
图1为本申请的一个实施例提出的一种商品识别方法的流程示意图;
图2为本申请的一个实施例提出的一种商品识别设备的结构示意图。
具体实施方式
在下文中,将更全面地描述本公开的各种实施例。本公开可具有各种实施例,并且可在其中做出调整和改变。然而,应理解:不存在将本公开的各种实施例限于在此公开的特定实施例的意图,而是应将本公开理解为涵盖落入本公开的各种实施例的精神和范围内的所有调整、等同物和/或可选方案。
在下文中,可在本公开的各种实施例中使用的术语“包括”或“可包括”指示所公开的功能、操作或元件的存在,并且不限制一个或更多个功能、操作或元件的增加。此外,如在本公开的各种实施例中所使用,术语“包括”、“具有”及其同源词仅意在表示特定特征、数字、步骤、操作、元件、组件或前述项的组合,并且不应被理解为首先排除一个或更多个其它特征、数字、步骤、操作、元件、组件或前述项的组合的存在或增加一个或更多个特征、数字、步骤、操作、元件、组件或前述项的组合的可能性。
在本公开的各种实施例中,表述“或”或“A或/和B中的至少一个”包括同时列出的文字的任何组合或所有组合。例如,表述“A或B”或“A或/和B中的至少一个”可包括A、可包括B或可包括A和B二者。
在本公开的各种实施例中使用的表述(诸如“第一”或“第二”等)可修饰在各种实施例中的各种组成元件,不过可不限制相应组成元件。例如,以上表述并不限制所述元件的顺序和/或重要性。以上表述仅用于将一个元件与其它元件区别开的目的。例如,第一用户装置和第二用户装置指示不同用户装置,尽管二者都是用户装置。例如,在不脱离本公开的各种实施例的范围的情况下,第一元件可被称为第二元件,同样地,第二元件也可被称为第一元件。
应注意到:如果描述将一个组成元件“连接”到另一组成元件,则可将第一组成元件直接连接到第二组成元件,并且可在第一组成元件和第二组成元件之间“连接”第三组成元件。相反地,当将一个组成元件“直接连接”到另一组成元件时,可理解为在第一组成元件和第二组成元件之间不存在第三组成元件。
在本公开的各种实施例中使用的术语“用户”可指示使用电子装置的人或使用电子装置的装置(例如,人工智能电子装置)。
在本公开的各种实施例中使用的术语仅用于描述特定实施例的目的并且并非意在限制本公开的各种实施例。如在此所使用,单数形式意在也包括复数形式,除非上下文清楚地另有指示。除非另有限定,否则在这里使用的所有术语(包括技术术语和科学术语)具有与本公开的各种实施例所属领域普通技术人员通常理解的含义相同的含义。所述术语(诸如在一般使用的词典中限定的术语)将被解释为具有与在相关技术领域中的语境含义相同的含义并且将不被解释为具有理想化的含义或过于正式的含义,除非在本公开的各种实施例中被清楚地限定。
实施例1
本申请实施例1公开了一种商品识别方法,如图1所示,包括以下步骤:
步骤101、获取商品的图像;
具体的,图像获取可以是基于对商品进行拍摄而获取的,还可以是从已经拍摄生成的图片库中进行提取获取。
步骤102、通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
具体的,在一个具体的实施例中,通过对图片进行多级检测,具体的可以先在整体图像上进行检测,将确定不存在标签信息的区域进行排除,具体的例如在纯空白区域,或者纯图片区域进行排除,后续再对剩下的区域进行识别,以此提高识别的效率。
步骤103、对所述标签区域中的信息进行识别,以确定所述商品的信息。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
在一个具体的实施例中,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
具体的,标签的标签区域所对应的信息时很多的,因此对于的字符个数会比较多,很 可能是最多,例如可以包括生产厂家,生产时间,品牌,型号,材料组成,注意事项,保质期等等。由此可以基于字符个数来确定标签区域。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
判断确定的各区域中的字符是否存在有预设字符;
若判断结果为是,则将所述区域设置为所述标签的标签区域。
正如上述的内容,标签中会存在有预设的一些固定的信息,例如可以包括生产厂家,生产时间,品牌,型号,材料组成,注意事项,保质期等等,因此在排除掉空白区域,或者字符数量明显很少的区域时,对剩下的区域进行识别,当识别出固定的信息时,即可认为该区域即为标签区域。
在一个具体的实施例中,所述“对所述标签区域中的信息进行识别,以确定所述商品的信息”包括:
提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
从所述识别的结果的中获取所述商品的信息。
具体的,考虑到标签信息中包含有汉字,英文以及符号,因此可以通过这三者的识别可以获取到标签中的信息,进而可以获取到商品的信息。以便后续进行其他的处理,例如统计销售量等等。
实施例2
本申请实施例2还公开了一种商品识别设备,如图2所示,包括:
获取模块201,配置成获取商品的图像;
检测模块202,配置成通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
识别模块203,配置成对所述标签区域中的信息进行识别,以确定所述商品的信息。
在一个具体的实施例中,所述检测模块202,配置成:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
在一个具体的实施例中,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
在一个具体的实施例中,所述检测模块202,配置成:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
判断确定的各区域中的字符是否存在有预设字符;
若判断结果为是,则将所述区域设置为所述标签的标签区域。
在一个具体的实施例中,所述识别模块203,配置成:
提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
从所述识别的结果的中获取所述商品的信息。
实施例3
本申请实施例3还公开了一种终端,包括:
处理器;
存储有所述处理器的可执行指令的存储器;
其中,所述处理器配置成:
获取商品的图像;
通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
对所述标签区域中的信息进行识别,以确定所述商品的信息。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
在一个具体的实施例中,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
在一个具体的实施例中,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
对所述图像划分为多个区域;
对各个区域进行字符识别,以确定识别处字符的区域;
判断确定的各区域中的字符是否存在有预设字符;
若判断结果为是,则将所述区域设置为所述标签的标签区域。
在一个具体的实施例中,所述“对所述标签区域中的信息进行识别,以确定所述商品 的信息”包括:
提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
从所述识别的结果的中获取所述商品的信息。
以此,本申请实施例提出了一种商品识别方法和设备,该方法包括:获取商品的图像;通过对所述图像进行多级检测,以确定所述商品的标签区域;上一级检测所对应的图像区域大于下一级检测所对应的图像区域;对所述标签区域中的信息进行识别,以确定所述商品的信息。通过获取商品的图像以及对图像进行多级检测,实现了自动化的商品识别,提高效率,且可以应对海量的商品数量,节约了成本。
本领域技术人员可以理解附图只是一个优选实施场景的示意图,附图中的模块或流程并不一定是实施本申请所必须的。
本领域技术人员可以理解实施场景中的装置中的模块可以按照实施场景描述进行分布于实施场景的装置中,也可以进行相应变化位于不同于本实施场景的一个或多个装置中。上述实施场景的模块可以合并为一个模块,也可以进一步拆分成多个子模块。
上述本申请序号仅仅为了描述,不代表实施场景的优劣。
以上公开的仅为本申请的几个具体实施场景,但是,本申请并非局限于此,任何本领域的技术人员能思之的变化都应落入本申请的保护范围。

Claims (10)

  1. 一种商品识别方法,其特征在于,包括:
    获取商品的图像;
    通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
    对所述标签区域中的信息进行识别,以确定所述商品的信息。
  2. 如权利要求1所述的方法,其特征在于,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
    对所述图像划分为多个区域;
    对各个区域进行字符识别,以确定识别处字符的区域;
    将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
  3. 如权利要求2所述的方法,其特征在于,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
  4. 如权利要求1所述的方法,其特征在于,所述“通过对所述图像进行多级检测,以确定所述商品的标签区域”包括:
    对所述图像划分为多个区域;
    对各个区域进行字符识别,以确定识别处字符的区域;
    判断确定的各区域中的字符是否存在有预设字符;
    若判断结果为是,则将所述区域设置为所述标签的标签区域。
  5. 如权利要求1所述的方法,其特征在于,所述“对所述标签区域中的信息进行识别,以确定所述商品的信息”包括:
    提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
    从所述识别的结果的中获取所述商品的信息。
  6. 一种商品识别设备,其特征在于,包括:
    获取模块,配置成获取商品的图像;
    检测模块,配置成通过对所述图像进行多级检测,以确定所述商品的标签区域;其中,上一级检测所对应的图像区域大于下一级检测所对应的图像区域;
    识别模块,配置成对所述标签区域中的信息进行识别,以确定所述商品的信息。
  7. 如权利要求6所述的设备,其特征在于,所述检测模块,配置成:
    对所述图像划分为多个区域;
    对各个区域进行字符识别,以确定识别处字符的区域;
    将所述字符的个数满足预设数值的区域设置为所述标签的标签区域。
  8. 如权利要求7所述的设备,其特征在于,所述标签区域为所述字符个数最多,且面积为预设单位面积的区域。
  9. 如权利要求6所述的设备,其特征在于,所述检测模块,配置成:
    对所述图像划分为多个区域;
    对各个区域进行字符识别,以确定识别处字符的区域;
    判断确定的各区域中的字符是否存在有预设字符;
    若判断结果为是,则将所述区域设置为所述标签的标签区域。
  10. 如权利要求6所述的设备,其特征在于,所述识别模块,配置成:
    提高所述标签区域的对比度,并对所述标签区域进行文字识别;其中,所述文字识别包括汉字识别和英文识别以及符号识别;
    从所述识别的结果的中获取所述商品的信息。
PCT/CN2018/116127 2017-11-23 2018-11-19 一种商品识别方法和设备 WO2019101027A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711180389.2A CN107958252A (zh) 2017-11-23 2017-11-23 一种商品识别方法和设备
CN201711180389.2 2017-11-23

Publications (1)

Publication Number Publication Date
WO2019101027A1 true WO2019101027A1 (zh) 2019-05-31

Family

ID=61961900

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/116127 WO2019101027A1 (zh) 2017-11-23 2018-11-19 一种商品识别方法和设备

Country Status (3)

Country Link
US (1) US10635942B2 (zh)
CN (1) CN107958252A (zh)
WO (1) WO2019101027A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107958252A (zh) * 2017-11-23 2018-04-24 深圳码隆科技有限公司 一种商品识别方法和设备
CN109035630A (zh) * 2018-08-21 2018-12-18 深圳码隆科技有限公司 商品信息识别方法和系统
CN108986357A (zh) * 2018-08-21 2018-12-11 深圳码隆科技有限公司 商品信息确定方法、系统和无人售货系统
CN111222377B (zh) * 2018-11-27 2023-09-08 杭州海康威视数字技术股份有限公司 一种商品信息确定方法、装置及电子设备
CN112766250B (zh) * 2020-12-28 2021-12-21 合肥联宝信息技术有限公司 一种图像处理方法、设备及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103123683A (zh) * 2011-09-08 2013-05-29 三星电子株式会社 同时识别字符和条形码的装置及其控制方法
CN105631393A (zh) * 2014-11-06 2016-06-01 阿里巴巴集团控股有限公司 信息识别方法及装置
CN107016387A (zh) * 2016-01-28 2017-08-04 苏宁云商集团股份有限公司 一种识别标签的方法及装置
US20170293820A1 (en) * 2016-04-07 2017-10-12 Toshiba Tec Kabushiki Kaisha Image processing device
CN107958252A (zh) * 2017-11-23 2018-04-24 深圳码隆科技有限公司 一种商品识别方法和设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5909509A (en) * 1996-05-08 1999-06-01 Industrial Technology Research Inst. Statistical-based recognition of similar characters
EP0947937B1 (en) * 1998-04-02 2010-11-03 Canon Kabushiki Kaisha Image search apparatus and method
JP4641414B2 (ja) * 2004-12-07 2011-03-02 キヤノン株式会社 文書画像検索装置、文書画像検索方法、プログラム、記憶媒体
US7660468B2 (en) * 2005-05-09 2010-02-09 Like.Com System and method for enabling image searching using manual enrichment, classification, and/or segmentation
JP5034398B2 (ja) * 2006-09-14 2012-09-26 富士通株式会社 文字認識プログラム、文字認識方法および文字認識装置
US7949191B1 (en) * 2007-04-04 2011-05-24 A9.Com, Inc. Method and system for searching for information on a network in response to an image query sent by a user from a mobile communications device
JP4590433B2 (ja) * 2007-06-29 2010-12-01 キヤノン株式会社 画像処理装置、画像処理方法、コンピュータプログラム
CN106446889B (zh) * 2015-08-10 2019-09-17 Tcl集团股份有限公司 一种台标的本地识别方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103123683A (zh) * 2011-09-08 2013-05-29 三星电子株式会社 同时识别字符和条形码的装置及其控制方法
CN105631393A (zh) * 2014-11-06 2016-06-01 阿里巴巴集团控股有限公司 信息识别方法及装置
CN107016387A (zh) * 2016-01-28 2017-08-04 苏宁云商集团股份有限公司 一种识别标签的方法及装置
US20170293820A1 (en) * 2016-04-07 2017-10-12 Toshiba Tec Kabushiki Kaisha Image processing device
CN107958252A (zh) * 2017-11-23 2018-04-24 深圳码隆科技有限公司 一种商品识别方法和设备

Also Published As

Publication number Publication date
US20190156152A1 (en) 2019-05-23
US10635942B2 (en) 2020-04-28
CN107958252A (zh) 2018-04-24

Similar Documents

Publication Publication Date Title
WO2019101027A1 (zh) 一种商品识别方法和设备
US20220172157A1 (en) Information processing apparatus, control method, and program
TWI608369B (zh) 分類方法、分類模組及電腦程式產品
CN110378420A (zh) 一种图像检测方法、装置及计算机可读存储介质
US9911033B1 (en) Semi-supervised price tag detection
WO2019101088A1 (zh) 一种无人售货方法和设备
US10824832B2 (en) Barcode tag detection in side view sample tube images for laboratory automation
US11087172B2 (en) Systems and methods for creating training data
US10438165B2 (en) Planogram generation
US9811537B2 (en) Product identification via image analysis
WO2020253508A1 (zh) 异常细胞检测方法、装置及计算机可读存储介质
WO2019019595A1 (zh) 图片匹配方法及电子设备方法、装置、电子设备及介质
US11354549B2 (en) Method and system for region proposal based object recognition for estimating planogram compliance
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
CN110728198B (zh) 图像处理方法、装置、电子设备及可读存储介质
CN111310826A (zh) 样本集的标注异常检测方法、装置及电子设备
WO2019000746A1 (zh) 控件的文字颜色变换方法、系统、电子装置及存储介质
CN113378958A (zh) 自动标注方法、装置、设备、存储介质及计算机程序产品
CN116580390A (zh) 价签内容获取方法、装置、存储介质和计算机设备
WO2019096201A1 (zh) 一种基于有源标签与无源标签的无人售货方法和设备
CN113673344B (zh) 一种智能塔吊物料挂载位置识别方法和装置
GB2614170A (en) Action-object recognition in cluttered video scenes using text
CN112464946A (zh) 一种基于大数据的垃圾图像收集方法及系统
JP7049587B2 (ja) 画像処理装置、画像処理プログラム、及び画像処理方法
US20170161529A1 (en) Object recognition encoder

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: 18880458

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18880458

Country of ref document: EP

Kind code of ref document: A1