WO2013004037A1 - 判断联系人列表中是否存在欲添加名片的方法 - Google Patents

判断联系人列表中是否存在欲添加名片的方法 Download PDF

Info

Publication number
WO2013004037A1
WO2013004037A1 PCT/CN2011/078055 CN2011078055W WO2013004037A1 WO 2013004037 A1 WO2013004037 A1 WO 2013004037A1 CN 2011078055 W CN2011078055 W CN 2011078055W WO 2013004037 A1 WO2013004037 A1 WO 2013004037A1
Authority
WO
WIPO (PCT)
Prior art keywords
business card
contact list
added
image
electronic device
Prior art date
Application number
PCT/CN2011/078055
Other languages
English (en)
French (fr)
Inventor
罗希平
Original Assignee
上海合合信息科技发展有限公司
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 上海合合信息科技发展有限公司 filed Critical 上海合合信息科技发展有限公司
Priority to JP2014517389A priority Critical patent/JP5863962B2/ja
Priority to US14/126,359 priority patent/US9147109B2/en
Priority to KR1020147000968A priority patent/KR20140066686A/ko
Priority to EP11869081.7A priority patent/EP2731019A4/en
Publication of WO2013004037A1 publication Critical patent/WO2013004037A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5846Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10File systems; File servers
    • G06F16/11File system administration, e.g. details of archiving or snapshots
    • G06F16/116Details of conversion of file system types or formats
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/432Query formulation
    • G06F16/434Query formulation using image data, e.g. images, photos, pictures taken by a user
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5862Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using texture
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • 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
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/41Analysis of document content
    • G06V30/413Classification of content, e.g. text, photographs or tables
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/41Analysis of document content
    • G06V30/418Document matching, e.g. of document images
    • 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

Definitions

  • the present invention relates to the field of character recognition and image processing, and more particularly to a method for automatically determining whether an identified business card already exists in a contact list in combination with a text recognition result and an image feature.
  • Business cards are a kind of media that people often use to record and communicate with each other. In daily business activities, a large number of business card exchanges are often involved. People use business card exchange methods to communicate and connect with others.
  • the user recognizes a business card.
  • an entry is added to the contact list, which contains the text information of the identified business card, including name, phone, E -ma il , company, department, position, address, etc., generally contains the business card images that have been taken and may be beautified. If the user enters the same business card multiple times, a new contact entry will be generated for this business card multiple times, causing unnecessary duplication. There is currently no good way to automatically determine if the identified business card already exists in the contact list.
  • the contact names such as name, phone number, and ema il are the same, but the company and the job may be different, so if the identification of the company and the position is wrong, according to The recognized text cannot determine which one of the recognized business cards is.
  • the sales cards of some companies' salespersons are the same except for other names such as company name, address, contact number, and email address. If the name of the business card is not recognized at this time, It is impossible to determine who the owner of this business card is based on other textual information.
  • an object of the present invention is to provide a method for determining whether a business card is to be added in a contact list, and to automatically determine whether the identified business card is in contact with the text recognition result and the image feature.
  • the list of people already exists to solve the problem that users who are common in the prior art add redundant entries to the contact list.
  • the present invention provides a method for determining whether a business card is to be added in a contact list, and is applied to an electronic device having at least a business card image capture, text information recognition, and image feature extraction function, and The electronic device further includes a contact list for storing contact card information, wherein the method includes at least the following steps: 1) after the electronic device captures a business card image to add a business card, the identification device Describe text information on the business card image, and extract image features; 2) retrieve all pre-stored business cards matching the text information from the contact list according to the text information, and retrieve the business cards of the pre-stored business cards The image is matched with the business card image of the business card to be added, and a similar degree of metric is generated for each pre-stored business card according to the similarity of the image features; 3) a business card with the largest metric value among all the pre-stored business cards As a candidate business card; 4) determining whether the candidate business card and the business card to be added belong
  • the business card information in the contact list includes a business card image and text information.
  • the text information is at least one of a name, a title, a telephone, a fax, an address, a zip code, an e-mail address, a website address, and product information on the business card.
  • the electronic device is pre-set with a reference value for comparison with the metric value, and the metric value and the reference value are integers.
  • step 1) of the method of the present invention the electronic device captures the business card image of the business card to be added by a digital camera or a scanning device.
  • the electronic device recognizes text information on the business card image and extracts image features using optical character recognition technology.
  • step 4) of the method of the present invention when it is determined whether the candidate business card and the business card to be added belong to the same user, determining whether the metric value is greater than the reference value, and if yes, the electronic device displays the business card information of the user The contact list already exists, and if not, the electronic device displays that the user card information does not exist in the contact list.
  • the method further includes: determining whether the candidate business card and the business card to be added belong to the same business card, and if yes, the electronic device displays that the business card information to be added is already in the contact list, if No, the electronic device displays that the business card information of the business card to be added does not exist in the contact list.
  • step 2) of the method of the present invention when all the pre-stored business cards matching the text information are not retrieved from the contact list according to the text information, the electronic device displays that the user card information does not exist. In the contact list.
  • the image feature matching is a feature point matching both the feature image of the pre-stored business card and the business card image of the business card to be added, and a feature vector corresponding to each feature point.
  • FIG. 1 is a flow chart showing the steps of a method for determining whether a business card is to be added in the judgment contact list of the present invention.
  • FIG. 1 is a flow chart showing the steps of the method for determining whether a business card is to be added in the judgment contact list of the present invention.
  • the illustrations provided in this embodiment merely illustrate the basic concept of the present invention in a schematic manner, and only the components related to the present invention are shown in the drawings, instead of the number and shape of components in actual implementation. Dimensional drawing, the actual type of implementation of each component's type, number and proportion can be a random change, and its component layout can be more complicated.
  • the present invention provides a method for determining whether a business card is to be added in a contact list, and is applied to an electronic device having at least a business card image capture, text information recognition, and image feature extraction function, and the electronic device
  • the business card information in the contact list includes a business card image and text information, wherein the text information is a name and a title on the business card.
  • the business card image corresponding to the same text information stored in the contact list may have one or more sheets, for example, the same user may have multiple business cards, and only the information of the company and the position is different among the plurality of business cards. Other information such as name, phone number, and e-mail address are the same.
  • the electronic device has a digital photographing device or a scanning device for capturing a business card image, and can recognize the text information on the business card image and extract the image feature by using an optical character recognition technology.
  • the electronic device may be an electronic device with a data processing function, such as a smart phone, a tablet computer, or a PDA.
  • the method for determining whether there is a business card to be added in the contact list includes at least the following steps:
  • step S1 the electronic device captures a business card image of a business card, identifies text information on the business card image, and extracts image features.
  • the electronic device passes the digital camera.
  • the scanning device captures the business card image of the business card to be added, and uses the optical character recognition technology to identify the text information on the business card image and extract the image feature.
  • step S2 is performed.
  • step S2 all pre-stored business cards matching the text information are retrieved from the contact list according to the text information.
  • the electronic device uses the recognized text information in the contact list.
  • the purpose of the text search is to greatly reduce the number of images that need to be image-matched according to image features in the next step, thereby improving the speed of image matching and the accuracy of matching.
  • the specific method for performing text retrieval by using the recognized text information is to search for the name, title, telephone, fax, address, zip code, and the text contained in the recognized text in the text information of the business card information pre-stored in the contact list. At least one of the e-mail, website address, and product information is a fully consistent pre-stored business card. Then step S3 is performed.
  • step S3 it is judged whether or not it is retrieved, and if so, the process proceeds to step S4, and if not, the process proceeds to step S9.
  • step S3 even after the search is performed from the contact list by using the recognized text information in step S3, a unique business card that matches the recognized text in the business card image to which the business card is to be added is obtained. It is still necessary to go to step S4 for verification, because there are cases where the electronic device cannot uniquely determine which of the business cards held by the contact list is based on the text obtained by the optical character recognition.
  • the same user may have multiple names. In the multiple business cards, only the information of the company and the position is different. The other names, telephone, and e-mail information are the same, so if the company and the job are identified incorrectly, only the name is correctly identified. Information such as telephone, e-mail, etc., electronic devices cannot uniquely determine which business card the information belongs to.
  • step S4 the retrieved business card images of the pre-stored business cards are respectively matched with the business card images of the business card to be added, and in this embodiment, the image feature matching is a business card matching the pre-stored business card. A feature point of both the image and the business card image of the business card to be added and a feature vector corresponding to each of the feature points. Then step S5 is performed.
  • step S5 a similarity measure value is generated corresponding to each pre-stored business card according to the similarity of the image features.
  • the electronic device is pre-set with a reference value for comparison with the metric value.
  • the metric value and the reference value are both integers.
  • the candidate business card corresponding to the metric value is a business card to be added. In other words, the larger the metric value, the more similar the business card corresponding to the metric value to the business card to be added.
  • step S6 is performed.
  • step S6 a business card with the largest metric value among all the pre-stored business cards is used as the candidate business card; to ensure the accuracy of the next step comparison. Then step S7 is performed.
  • step S7 it is determined whether the candidate business card and the business card to be added belong to the same user.
  • determining whether the candidate business card and the business card to be added belong to the same user determining whether the metric value is greater than the The reference value, if yes, proceeds to step S8, and if not, proceeds to step S9.
  • step S8 the electronic device displays that the user card information is already in the contact list, but since the same user may have multiple business cards, only the company and the job information are different among the multiple business cards. The other names, telephone, and e-mail information are the same. In this case, the electronic device is required to notify the operator whether to further verify whether the candidate business card and the business card to be added belong to the same business card. That is, the process goes to step S10.
  • step S9 the electronic device displays that the user card information does not exist in the contact list, and the operator of the electronic device can decide whether to add the user card according to the needs of the user. To the contact list.
  • step S10 it is judged whether the candidate business card and the business card to be added belong to the same business card, and if so, the process goes to step S11, and if no, the process goes to step S12.
  • step S11 the electronic device displays that the business card information to be added is already in the contact list, so that the operator of the electronic device does not need to repeatedly add the business card information.
  • step S12 the electronic device displays that the business card information of the business card to be added does not exist in the contact list, and the operator of the electronic device may decide whether to add different business card information of the same user according to his own needs. To the contact list.
  • the method for determining a business card in the contact list of the present invention when identifying the business card image, automatically determines whether the identified business card already exists in the contact list by combining the text recognition result and the image feature. This avoids the problem of users adding extra entries to the contact list. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.
  • the above-described embodiments are merely illustrative of the principles of the invention and its advantages, and are not intended to limit the invention. Any of the above-described embodiments may be modified or altered without departing from the spirit and scope of the invention. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and scope of the invention are still to be covered by the appended claims.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Library & Information Science (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Character Discrimination (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)
  • Telephone Function (AREA)

Abstract

本发明提供一种判断联系人列表中是否存在欲添加名片的方法,应用于具有用以储存联系人名片信息的联系人列表的电子设备中,所述方法包括:电子设备撷取一欲添加名片的名片图像后,依据该名片图像上的文字信息从联系人列表中检索出各该预存名片的名片图像,再分别与欲添加名片进行图像特征匹配,根据图像特征的相似度选出候选名片;判断该候选名片与欲添加名片是否属于同一用户,若是,则显示欲添加名片信息已存在所述联系人列表中,若否,则显示欲添加名片信息未存在所述联系人列表中,用以结合文字识别结果和图像特征来自动判断所识别的名片是否在联系人列表中已经存在,以解决现有技术中常见的用户向联系人列表中加入多余的条目的问题。

Description

判断联系人列表中是否存在欲添加名片的方法 技术领域
本发明涉及一种文字识别及图像处理领域, 特别是涉及一种结合文字识别 结果和图像特征来自动判断所识别的名片是否在联系人列表中已经存在的方 法。
背景技术
名片是人们经常使用的一种记载和传递联系方式的媒体, 在日常商务活动 中往往会涉及大量的名片交换, 人们通过名片交换的方式来传递联系方式, 跟 其他人建立联系。
目前已经在手机和微机中广泛使用的名片识别技术利用图像处理和光学字 符识另1 J ( OCR, Opt ica l Character Recogni t ion ) 的原理, 对相机拍摄或扫描 仪扫描得到的名片图像自动进行处理和识别, 然后自动提取出其中的姓名, 电 话, ema i l 等有用信息来加入到地址簿中去, 为人们在电子设备中输入名片上 记载的联系信息提供了很大的方便。 一个例子如在苹果公司的 App s tore 和 Goog le公司的 Android market中销售的名片全能王等名片识别软件。
在目前的所有名片识别软件中, 用户识别了一张名片, 保存到联系人列表 以后, 联系人列表中就会增加一个条目, 其中包含所识别出来的名片的文字信 息, 包括姓名, 电话, E-ma i l , 公司, 部门, 职务, 地址等等, 一般还包含了 所拍摄的, 可能经过美化处理的名片图像。 如果用户多次输入同一张名片, 则 会为多次为这张名片产生新的联系人条目, 造成不必要的重复。 目前的产品中 还没有好的方式来自动判断所识别的名片是否已经存在于联系人列表中了。
自动判断所识别的名片是否已经存在于联系人列表中了一个直观的办法是 将识别出来的名片的文字跟联系人列表中已有条目的文字进行比对, 从而检查 是否已经存在了。 这种方法的问题在于基于光学字符识别原理的名片识别技术 识别结果是不可能达到 100%的准确率的, 这样用经过光学字符识别获得的可能 包含错误的文字信息来跟联系人列表中的已有条目进行比对就不能保证比对结 果的可靠性。 比如说有很多人同时拥有代表多个身份的多张名片, 其中的姓 名, 电话, ema i l 等联系方式都是一样的, 只是公司和职务可能不同, 这样如 果公司和职务的识别有错, 根据识别出来的文字就不能确定所识别的名片是哪 一张了。 再比如说, 有些公司的销售人员的名片, 除了姓名不同其它的信息如 公司名称, 地址, 联系电话, 电子邮件地址等都是一样的, 这个时候如果名片 中的姓名的文字没有识别出来, 就不可能根据其它文字信息来确定这张名片的 主人是谁了。
因而, 如何提供一种结合文字识别结果和图像特征来自动判断所识别的名 片是否在联系人列表中已经存在的方法, 以解决现有技术中的种种问题, 已经 成为本技术领域从业者亟待解决的问题。 发明内容
鉴于以上所述现有技术的缺点, 本发明的目的在于提供一种判断联系人列 表中是否存在欲添加名片的方法, 用以结合文字识别结果和图像特征来自动判 断所识别的名片是否在联系人列表中已经存在, 以解决现有技术中常见的用户 向联系人列表中加入多余的条目的问题。
为实现上述目的及其他相关目的, 本发明提供一种判断联系人列表中是否 存在欲添加名片的方法, 应用于至少具有名片图像撷取、 文字信息识别及图像 特征提取功能的电子设备中, 且所述电子设备中还具有用以储存联系人名片信 息的联系人列表, 其特征在于, 所述方法至少包括以下步骤: 1 ) 所述电子设 备撷取一欲添加名片的名片图像后, 识别所述名片图像上的文字信息, 并提取 图像特征; 2 )依据所述文字信息从所述联系人列表中检索与该文字信息相匹 配的所有预存名片, 并将检索出的各该预存名片的名片图像分别与所述欲添加 名片的名片图像进行图像特征匹配, 根据图像特征的相似度, 对应每一预存名 片生成一个相似程度的度量值; 3 )将所有预存名片中度量值最大的一张名片 作为候选名片; 4 ) 判断所述候选名片与欲添加名片是否属于同一用户, 若 是, 则所述电子设备显示该用户名片信息已存在所述联系人列表中, 若否, 则 所述电子设备显示该用户名片信息未存在所述联系人列表中。
其中, 所述联系人列表中的名片信息包括名片图像及文字信息。 所述文字 信息为名片上的姓名、 职称、 电话、 传真、 地址、 邮编、 电子信箱、 网站地 址、 产品信息中的至少一种。
其中, 所述电子设备预设有用于与所述度量值相比对的参照值, 且所述度 量值与参照值均为整数。
在本发明方法的步骤 1 ) 中, 所述电子设备是通过数码拍摄装置或扫描装 置撷取所述欲添加名片的名片图像。 所述电子设备是利用光学字符识别技术识 别所述名片图像上的文字信息和提取图像特征。
在本发明方法的步骤 4 ) 中, 判断所述候选名片与欲添加名片是否属于同 一用户时, 为判断所述度量值是否大于所述参照值, 若是, 则所述电子设备显 示该用户名片信息已存在所述联系人列表中, 若否, 则所述电子设备显示该用 户名片信息未存在所述联系人列表中。
在本发明方法的步骤 4 ) 中, 还包括判断所述候选名片与欲添加名片是否 属于同一张名片, 若是, 则所述电子设备显示该欲添加名片信息已存在所述联 系人列表中, 若否, 则所述电子设备显示所述欲添加名片的名片信息未存在所 述联系人列表中。
在本发明方法的步骤 2 ) 中, 依据所述文字信息从所述联系人列表中未检 索与该文字信息相匹配的所有预存名片时, 则所述电子设备显示该用户名片信 息未存在所述联系人列表中。
在本发明方法的步骤 2 ) 中, 所述图像特征匹配是匹配所述预存名片的名 片图像和欲添加名片的名片图像二者的特征点和各该特征点对应的特征向量。
如上所述, 本发明的判断联系人列表中是否存在欲添加名片的方法, 在识 别名片图像时, 结合文字识别结果和图像特征来自动判断所识别的名片是否在 联系人列表中已经存在, 从而避免了现有技术中常见的向联系人列表中加入多 余条目的问题。 附图说明
图 1 显示为本发明的判断联系人列表中是否存在欲添加名片的方法步骤流 程图。 具体实施方式 说明书所揭示的内容轻易地了解本发明的其他优点与功效。 本发明还可以通过 另外不同的具体实施方式加以实施或应用, 本说明书中的各项细节也可以基于 不同观点与应用, 在不背离本发明的精神下进行各种修饰或改变。
请参阅图 1 , 显示为本发明的判断联系人列表中是否存在欲添加名片的方 法步骤流程图。 需要说明的是, 本实施例中所提供的图示仅以示意方式说明本 发明的基本构想, 遂图式中仅显示与本发明中有关的组件而非按照实际实施时 的组件数目、 形状及尺寸绘制, 其实际实施时各组件的型态、 数量及比例可为 一种随意的改变, 且其组件布局型态也可能更为复杂。
如图所示, 本发明提供一种判断联系人列表中是否存在欲添加名片的方 法, 应用于至少具有名片图像撷取、 文字信息识别及图像特征提取功能的电子 设备中, 且所述电子设备中还具有用以储存联系人名片信息的联系人列表, 在 本实施例中, 所述联系人列表中的名片信息包括名片图像及文字信息, 其中, 所述文字信息为名片上的姓名、 职称、 电话、 传真、 地址、 邮编、 电子信箱、 网站地址、 产品信息中的至少一种。 而且, 所述联系人列表中保存的对应同样 的文字信息的名片图像可以有一张或者多张, 例如同一个用户可能有多张名 片, 在这多张名片中只有公司和职务的信息是不同的, 其它姓名、 电话、 电子 信箱等信息都是相同的。 在本实施例中, 所述电子设备具有数码拍摄装置或扫描装置, 用以撷取名 片图像, 并可以利用光学字符识别技术识别所述名片图像上的文字信息和提取 图像特征。 在本实施例中, 所述电子设备可以是智能手机、 平板电脑、 PDA 等 具有数据处理功能的电子设备。
如图 1 所示, 所述判断联系人列表中是否存在欲添加名片的方法至少包括 以下步骤:
首先执行步骤 S1 , 所述电子设备撷取一欲添加名片的名片图像后, 识别所 述名片图像上的文字信息, 并提取图像特征; 在本实施例中, 所述电子设备是 通过数码拍摄装置或扫描装置撷取所述欲添加名片的名片图像, 并利用光学字 符识别技术识别所述名片图像上的文字信息和提取图像特征。 接着执行步骤 S2。
在步骤 S2 中, 依据所述文字信息从所述联系人列表中检索与该文字信息 相匹配的所有预存名片, 在本实施例中, 所述电子设备利用识别出来的文字信 息在该联系人列表中进行检索, 文字检索的目的是大幅度减少在下一步中需要 依据图像特征来进行图像匹配的图像的数量, 从而提高图像匹配的速度和匹配 的准确率。 所述利用识别出来的文字信息进行文字检索具体的做法就是在该联 系人列表中预存之名片信息的文字信息中查找跟识别出来的文字中包含的姓 名、 职称、 电话、 传真、 地址、 邮编、 电子信箱、 网站地址、 产品信息中的至 少一种完全一致的预存名片。 接着执行步骤 S3。
在步骤 S3 中, 判断是否检索到, 若是, 则进至步骤 S4 , 若否, 则进至步 骤 S9。
需要说明的是, 即使在步骤 S3 中利用识别出来的文字信息从所述联系人 列表中进行检索之后, 得到的是唯一的一张与欲添加名片的名片图像中识别出 来的文字一致的名片, 也仍然需要到步骤 S4 中去进行验证, 这是因为存在某 些情况下电子设备不能根据由光学字符识别得到的文字来唯一确定这些文字属 于联系人列表所保存的名片中的哪一张。 比如说, 同一个用户可能有多张名 片, 在这多张名片中只有公司和职务的信息是不同的, 其它姓名, 电话, 电子 信箱这些信息都是相同的, 这样如果对公司和职务的识别有误, 只是正确的识 别出了姓名, 电话, 电子信箱等信息, 电子设备就不能唯一确定这些信息属于 用户的哪一张名片。
在步骤 S4 中, 将检索出的各该预存名片的名片图像分别与所述欲添加名 片的名片图像进行图像特征匹配, 在本实施例中, 所述图像特征匹配是匹配所 述预存名片的名片图像和欲添加名片的名片图像二者的特征点和各该特征点对 应的特征向量。 接着执行步骤 S5。
在步骤 S5 中, 根据图像特征的相似度, 对应每一预存名片生成一个相似 程度的度量值; 在本实施例中, 所述电子设备预设有用于与所述度量值相比对 的参照值, 且所述度量值与参照值均为整数, 当所述度量值大于所述参照值 时, 则表示所述度量值对应的那种候选名片为欲添加名片。 换言之, 所述度量 值越大, 则表示所述度量值对应的那种名片与欲添加名片越相似。 接着执行步 骤 S6。
在步骤 S6 中, 将所有预存名片中度量值最大的一张名片作为候选名片; 以确保下一步骤比对的精确度。 接着执行步骤 S7。
在步骤 S7 中, 判断所述候选名片与欲添加名片是否属于同一用户, 在本 实施例中, 判断所述候选名片与欲添加名片是否属于同一用户时, 为判断所述 度量值是否大于所述参照值, 若是, 进至步骤 S8 , 若否, 进至步骤 S9。
在步骤 S8 中, 所述电子设备显示该用户名片信息已存在所述联系人列表 中, 但是, 由于同一个用户可能有多张名片, 在这多张名片中只有公司和职务 的信息是不同的, 其它姓名, 电话, 电子信箱这些信息都是相同的, 此时就需 要该电子设备通知操作者要不要进一步验证所述候选名片与欲添加名片是否属 于同一张名片。 即转至步骤 S10。
在步骤 S9 中, 所述电子设备显示该用户名片信息未存在所述联系人列表 中, 此时该电子设备的操作者可以根据自身需求决定要不要将该用户名片添加 至联系人列表中。
在步骤 S10 中, 判断所述候选名片与欲添加名片是否属于同一张名片, 若 是, 则进至步骤 S11 , 若否, 则进至步骤 S12。
在步骤 S11 中, 所述电子设备显示该欲添加名片信息已存在所述联系人列 表中, 以提示该电子设备的操作者无需再重复添加名片信息。
在步骤 S12 中, 所述电子设备显示所述欲添加名片的名片信息未存在所述 联系人列表中, 此时该电子设备的操作者可以根据自身需求决定要不要将同一 用户的不同名片信息添加至联系人列表中。
综上所述, 本发明的判断联系人列表中是否存在欲添加名片的方法, 在识 别名片图像时, 结合文字识别结果和图像特征来自动判断所识别的名片是否在 联系人列表中已经存在, 从而避免用户向联系人列表中加入多余条目的问题。 所以, 本发明有效克服了现有技术中的种种缺点而具高度产业利用价值。 上述实施例仅例示性说明本发明的原理及其功效, 而非用于限制本发明。 任 何熟悉此技术的人士皆可在不违背本发明的精神及范畴下, 对上述实施例进行 修饰或改变。 因此, 举凡所属技术领域中具有通常知识者在未脱离本发明所揭 示的精神与技术思想下所完成的一切等效修饰或改变, 仍应由本发明的权利要 求所涵盖。

Claims

权利要求书 、 一种判断联系人列表中是否存在欲添加名片的方法, 应用于至少具有名片 图像撷取、 文字信息识别及图像特征提取功能的电子设备中, 且所述电子 设备中还具有用以储存联系人名片信息的联系人列表, 其特征在于, 所述 方法至少包括以下步骤:
1 ) 所述电子设备撷取一欲添加名片的名片图像后, 识别所述名片图像 上的文字信息, 并提取图像特征;
2 )依据所述文字信息从所述联系人列表中检索与该文字信息相匹配的 所有预存名片, 并将检索出的各该预存名片的名片图像分别与所述欲添加名 片的名片图像进行图像特征匹配, 根据图像特征的相似度, 对应每一预存名 片生成一个相似程度的度量值;
3 )将所有预存名片中度量值最大的一张名片作为候选名片;
4 )判断所述候选名片与欲添加名片是否属于同一用户, 若是, 则所述 电子设备显示该用户名片信息已存在所述联系人列表中, 若否, 则所述电子 设备显示该用户名片信息未存在所述联系人列表中。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 所述联系人列表中的名片信息包括名片图像及文字信息。 、 根据权利要求 2 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 所述文字信息为名片上的姓名、 职称、 电话、 传真、 地址、 邮 编、 电子信箱、 网站地址、 产品信息中的至少一种。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 1 ) 中, 所述电子设备是通过数码拍摄装置或扫描装置 撷取所述欲添加名片的名片图像。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 1 ) 中, 所述电子设备是利用光学字符识别技术识别所 述名片图像上的文字信息和提取图像特征。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 所述电子设备预设有用于与所述度量值相比对的参照值, 且所 述度量值与参照值均为整数。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 4 ) 中, 判断所述候选名片与欲添加名片是否属于同一 用户时, 为判断所述度量值是否大于所述参照值, 若是, 则所述电子设备 显示该用户名片信息已存在所述联系人列表中, 若否, 则所述电子设备显 示该用户名片信息未存在所述联系人列表中。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 4 ) 中, 还包括判断所述候选名片与欲添加名片是否属 于同一张名片, 若是, 则所述电子设备显示该欲添加名片信息已存在所述 联系人列表中, 若否, 则所述电子设备显示所述欲添加名片的名片信息未 存在所述联系人列表中。 、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 2 ) 中, 依据所述文字信息从所述联系人列表中未检索 与该文字信息相匹配的所有预存名片时, 则所述电子设备显示该用户名片 信息未存在所述联系人列表中。 10、 根据权利要求 1 所述的判断联系人列表中是否存在欲添加名片的方法, 其 特征在于: 于步骤 2 ) 中, 所述图像特征匹配是匹配所述预存名片的名片图像 和欲添加名片的名片图像二者的特征点和各该特征点对应的特征向量。
PCT/CN2011/078055 2011-07-05 2011-08-05 判断联系人列表中是否存在欲添加名片的方法 WO2013004037A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2014517389A JP5863962B2 (ja) 2011-07-05 2011-08-05 追加を希望する名刺が連絡先リストに存在しているか否かを判断する方法
US14/126,359 US9147109B2 (en) 2011-07-05 2011-08-05 Method for adding business card information into contact list
KR1020147000968A KR20140066686A (ko) 2011-07-05 2011-08-05 주소록에 추가하고자 하는 명함이 존재하는지 여부를 판단하는 방법
EP11869081.7A EP2731019A4 (en) 2011-07-05 2011-08-05 METHOD FOR DETERMINING THE PRESENCE OF A BUSINESS CARD TO BE ADDED TO A CONTACT LIST

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2011101872780A CN102393847B (zh) 2011-07-05 2011-07-05 判断联系人列表中是否存在欲添加名片的方法
CN201110187278.0 2011-07-05

Publications (1)

Publication Number Publication Date
WO2013004037A1 true WO2013004037A1 (zh) 2013-01-10

Family

ID=45861171

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2011/078055 WO2013004037A1 (zh) 2011-07-05 2011-08-05 判断联系人列表中是否存在欲添加名片的方法

Country Status (6)

Country Link
US (1) US9147109B2 (zh)
EP (1) EP2731019A4 (zh)
JP (1) JP5863962B2 (zh)
KR (1) KR20140066686A (zh)
CN (1) CN102393847B (zh)
WO (1) WO2013004037A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103888576B (zh) * 2012-12-21 2017-10-31 比亚迪股份有限公司 基于图像扫描的联系人信息添加方法及终端设备
JP6427964B2 (ja) * 2013-11-28 2018-11-28 株式会社リコー 画像処理システム、情報処理装置及びプログラム
JP2016143142A (ja) * 2015-01-30 2016-08-08 富士ゼロックス株式会社 画像管理システム、画像管理装置、及びプログラム
US20170046668A1 (en) * 2015-08-16 2017-02-16 Google Inc. Comparing An Extracted User Name with Stored User Data
CN105657122A (zh) * 2016-03-30 2016-06-08 北京农信互联科技有限公司 一种将名片资料保存到手机电话通讯录的方法及系统
CN106067019A (zh) * 2016-05-27 2016-11-02 北京旷视科技有限公司 针对图像进行文字识别的方法及装置
CN108537659B (zh) * 2018-04-18 2021-03-30 京东数字科技控股有限公司 用于输出信息的方法和装置
JP2024080024A (ja) * 2022-12-01 2024-06-13 株式会社東芝 情報処理システム、情報処理方法及びプログラム

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1716234A (zh) * 2005-07-27 2006-01-04 王晓琦 手持终端电子名片自动识别和管理系统
JP3738088B2 (ja) * 1996-08-28 2006-01-25 松下電器産業株式会社 名刺読取装置
EP1796019A1 (en) * 2005-12-12 2007-06-13 Xerox Corporation Personal information retrieval using knowledge bases for optical character recognition correction
CN101808046A (zh) * 2009-02-17 2010-08-18 北京携友聚信信息技术有限公司 名片信息管理方法和系统
CN101882227A (zh) * 2010-07-13 2010-11-10 上海合合信息科技发展有限公司 基于图像匹配和网络查询的识别方法及系统

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5465353A (en) * 1994-04-01 1995-11-07 Ricoh Company, Ltd. Image matching and retrieval by multi-access redundant hashing
US6061478A (en) * 1997-05-21 2000-05-09 Ricoh Company, Ltd. Content-based filing and retrieval system for name cards and hankos
US6816725B1 (en) 2001-01-31 2004-11-09 Palm Source, Inc. Method and apparatus for selection of one data set from among multiple related data sets and beaming the selected data set
CN1120782C (zh) 2002-06-07 2003-09-10 北京龙浩亚安智能数码科技有限公司 车牌自动识别方法
JP2004013813A (ja) * 2002-06-11 2004-01-15 Megasoft Kk 情報管理システムおよび情報管理方法
US20070149208A1 (en) 2002-12-27 2007-06-28 Hanno Syrbe Location based services for mobile communication terminals
WO2007064896A2 (en) * 2005-12-01 2007-06-07 Shahriar Sarkeshik Data exchange system and method
US8125508B2 (en) * 2006-01-24 2012-02-28 Lifesize Communications, Inc. Sharing participant information in a videoconference
CN1848115B (zh) * 2006-05-10 2010-05-12 南京大学 数字图像检索中的主观相似度度量方法
US7925620B1 (en) * 2006-08-04 2011-04-12 Hyoungsoo Yoon Contact information management
US20080134030A1 (en) 2006-12-05 2008-06-05 Palm, Inc. Device for providing location-based data
KR20080075297A (ko) 2007-02-12 2008-08-18 삼성전자주식회사 휴대용 단말기의 블루투스 연결 장치 및 방법
US8520981B2 (en) * 2007-11-08 2013-08-27 Nec Corporation Document retrieval of feature point groups using a geometrical transformation
US8914024B2 (en) 2008-01-10 2014-12-16 Ximoxi, Inc. Discovery of network members by personal attributes
US20100255861A1 (en) 2009-04-03 2010-10-07 Tal Shlomo Raviv System and Method for Transferring Contact Information to a Recipient
CN101827317A (zh) 2009-09-07 2010-09-08 上海银贵网络科技服务有限公司 一种通过移动终端寻找目标对象的控制方法以及控制装置
US20110276602A1 (en) * 2010-05-10 2011-11-10 Chikahiro Terada Business card exchange information processing apparatus, business card exchange information processing method, and program
US20120087537A1 (en) * 2010-10-12 2012-04-12 Lisong Liu System and methods for reading and managing business card information
US9591061B2 (en) * 2011-01-26 2017-03-07 Hewlett-Packard Development Company, L.P. Document workflow architecture
WO2012168942A1 (en) * 2011-06-08 2012-12-13 Hewlett-Packard Development Company Image triggered transactions

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3738088B2 (ja) * 1996-08-28 2006-01-25 松下電器産業株式会社 名刺読取装置
CN1716234A (zh) * 2005-07-27 2006-01-04 王晓琦 手持终端电子名片自动识别和管理系统
EP1796019A1 (en) * 2005-12-12 2007-06-13 Xerox Corporation Personal information retrieval using knowledge bases for optical character recognition correction
CN101808046A (zh) * 2009-02-17 2010-08-18 北京携友聚信信息技术有限公司 名片信息管理方法和系统
CN101882227A (zh) * 2010-07-13 2010-11-10 上海合合信息科技发展有限公司 基于图像匹配和网络查询的识别方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2731019A4 *

Also Published As

Publication number Publication date
EP2731019A1 (en) 2014-05-14
US9147109B2 (en) 2015-09-29
EP2731019A4 (en) 2015-01-21
CN102393847A (zh) 2012-03-28
US20140119662A1 (en) 2014-05-01
KR20140066686A (ko) 2014-06-02
JP2014521134A (ja) 2014-08-25
CN102393847B (zh) 2013-04-17
JP5863962B2 (ja) 2016-02-17

Similar Documents

Publication Publication Date Title
WO2013004037A1 (zh) 判断联系人列表中是否存在欲添加名片的方法
WO2013004036A1 (zh) 结合文字识别和图像匹配的名片识别方法
WO2013004035A1 (zh) 结合文字识别和图像匹配交换名片信息的方法
EP2874383B1 (en) System and method for controlling slide operation auxiliary input in portable terminal devices
US9665959B2 (en) Composite image creation assist apparatus using images of users other than target user, and non-transitory computer readable recording medium
US20140348394A1 (en) Photograph digitization through the use of video photography and computer vision technology
US10929461B2 (en) Automatic detection and transfer of relevant image data to content collections
US9239961B1 (en) Text recognition near an edge
WO2012019513A1 (zh) 自动获取联系人头像的方法及系统
TW201339863A (zh) 圖像識別搜索方法及裝置
CN102855298A (zh) 图像检索方法及系统
WO2014086277A1 (zh) 方便电子化的专业笔记本及其页码自动识别方法
CN102945377B (zh) 获取纸质笔记本中内容的方法及装置
CN103607512A (zh) 一种备忘提醒的方法及终端
WO2014086272A1 (zh) 方便电子化的专业笔记本及其添加到电子日历中的方法
WO2014082528A1 (zh) 自动查找纸质笔记本中页面的方法及装置
US10579653B2 (en) Apparatus, method, and computer-readable medium for recognition of a digital document
US9665574B1 (en) Automatically scraping and adding contact information
US20200186668A1 (en) Method and device for recommending watermark for electronic terminal
JP2012053519A (ja) 画像処理装置および画像処理システム
CN111783786B (zh) 图片的识别方法、系统、电子设备及存储介质
CN103870473A (zh) 一种更新联系人信息的方法及电子设备
CN105791503A (zh) 一种将名片信息存储到通讯录的方法及装置
CN109084750B (zh) 一种导航方法及电子设备
KR101216436B1 (ko) 명함을 이용한 개인 정보 제공 방법 및 그 방법이 기록된 기록매체

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: 11869081

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14126359

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2014517389

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20147000968

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2011869081

Country of ref document: EP