WO2017101323A1 - 图像采集、信息推送方法、装置及手机 - Google Patents

图像采集、信息推送方法、装置及手机 Download PDF

Info

Publication number
WO2017101323A1
WO2017101323A1 PCT/CN2016/088535 CN2016088535W WO2017101323A1 WO 2017101323 A1 WO2017101323 A1 WO 2017101323A1 CN 2016088535 W CN2016088535 W CN 2016088535W WO 2017101323 A1 WO2017101323 A1 WO 2017101323A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
user
picture
camera
expression attribute
Prior art date
Application number
PCT/CN2016/088535
Other languages
English (en)
French (fr)
Inventor
邓凯月
Original Assignee
乐视控股（北京）有限公司
乐视移动智能信息技术（北京）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 乐视控股（北京）有限公司, 乐视移动智能信息技术（北京）有限公司 filed Critical 乐视控股（北京）有限公司
Priority to US15/241,455 priority Critical patent/US20170171462A1/en
Publication of WO2017101323A1 publication Critical patent/WO2017101323A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
    • H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body

Definitions

  • the present invention relates to the field of communication technologies, and in particular, to an image acquisition, information push method, device, and mobile phone.
  • Information push is a hot field in recent years. For example, an application involving e-commerce, social networking sites, etc., will push some information that the user may be interested in according to the browsing history, which can reduce the information overload to the user to a certain extent. Trouble.
  • the user of the mobile terminal needs to call the camera to perform photographing, photographing, scanning, etc., it can only be performed by the client software of the calling camera installed on the mobile terminal, but the activation of multiple client software is also increased.
  • the load on the soft and hardware of the mobile terminal reduces the processing speed.
  • one technical problem to be solved by the present invention is to overcome the defects that the load and the processing speed of the mobile terminal are large and the processing speed is reduced when the camera is operated in the prior art, thereby providing a software and hardware load that does not increase the mobile terminal.
  • Image acquisition method, device and mobile phone are large and the processing speed is reduced when the camera is operated in the prior art, thereby providing a software and hardware load that does not increase the mobile terminal.
  • Another technical problem to be solved by the present invention is to overcome the defects that the information pushed in the prior art is difficult to match the real needs of the user, and the experience is poor, thereby providing an information pushing method and device that match the real needs of the user.
  • Mobile phone
  • the present invention provides an image acquisition method for a mobile terminal, in which a plug-in capable of calling a camera is installed in a browser software of the mobile terminal;
  • the image collection method includes the following steps:
  • the image acquisition instruction is from trigger information generated by a user clicking a preset button in a browser.
  • the image collecting method of the present invention further includes: after step S14:
  • the invention also provides an information pushing method for the server side, comprising the following steps:
  • the step of acquiring the expression attribute of the user corresponding to the picture according to the character avatar picture includes:
  • the matched expression attribute is used as an expression attribute of the user corresponding to the picture.
  • the step of pushing the information matching the expression attribute of the user to the mobile terminal comprises:
  • the invention also provides an image collecting device for a mobile terminal, wherein a plug-in software capable of calling a camera is installed in a browser software of the mobile terminal;
  • the image collection device includes:
  • a scanning unit configured to invoke a camera to perform image scanning after receiving an instruction for image capturing
  • a character avatar recognition unit configured to determine whether the image scanned by the camera is a character avatar
  • a photographing unit configured to: when the image is a character avatar, invoke a camera to take a photo of the image;
  • a sending unit configured to acquire an image captured by the camera, and use the image of the character as a picture
  • the form is saved and sent to the server.
  • the present invention also provides an information pushing device for the server side, including;
  • a receiving unit configured to receive a picture of a character avatar
  • An expression attribute obtaining unit configured to acquire an expression attribute of a user corresponding to the picture according to the character avatar picture
  • the information pushing unit is configured to push information matching the expression attribute of the user to the mobile terminal.
  • the expression attribute acquiring unit includes:
  • a user feature point information obtaining subunit configured to acquire a plurality of user feature point information related to an expression attribute of the user in the character avatar picture
  • the comparison subunit is configured to compare the user feature point information with standard feature point information corresponding to each expression attribute in the face database to obtain a matching expression attribute;
  • An expression attribute determining subunit configured to use the matched expression attribute as an expression attribute of a user corresponding to the picture.
  • the invention also provides a mobile phone comprising the above image acquisition device.
  • the invention provides an image collecting method and device for a mobile terminal, and a plug-in software capable of calling a camera is installed in a browser software of the mobile terminal; after receiving an instruction of image capturing, the camera is called to perform image scanning, and Determine whether the image scanned by the camera is a character avatar. If the image is a character avatar, call the camera to take a picture of the image, then obtain the image captured by the camera, save the avatar in the form of a picture and send it to the server.
  • the image collecting method and device of the invention call the camera to perform an image scanning every preset time interval. After determining that the image scanned by the camera is a character avatar, the camera is called to take a picture of the image, and the newly acquired character avatar is The image form is saved and sent to the server.
  • the server can obtain the updated character avatar in time to analyze the latest expression attribute of the user, so as to timely adjust and update the information pushed to the user, and push the information provided by the server to match the user's demand. Data support.
  • the present invention also provides an information pushing method and device. After receiving a picture of a person's avatar, the user obtains an expression attribute of the user corresponding to the picture according to the picture of the person's avatar; and pushes information matching the expression attribute of the user to the mobile terminal.
  • the information matching the expression attribute of the user can be pushed to the user according to the current expression attribute of the user, and the current mood of the user is matched, which meets the real needs of the user, can improve the user's attention to the push information, and achieve a good push effect.
  • the invention further discloses an image acquisition device for a mobile terminal, wherein: one or more processors; a memory; one or more programs, the one or more programs are stored in the memory, when When the one or more processors are executed, the following operations are performed: the browser software of the mobile terminal is installed with a plug-in capable of calling the camera to work; the image collection method includes the following steps: S11. When receiving an instruction for image acquisition After the camera is called to perform image scanning; S12. determining whether the image scanned by the camera is a character avatar; S13. if the image is a character avatar, calling the camera to take a picture of the image; S14. acquiring the image captured by the camera, The character avatar is saved as a picture and sent to the server.
  • the invention also discloses an information pushing device for a server side, comprising: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory, when When executed by the one or more processors, the following operations are performed: S21. receiving a character avatar picture; S22. acquiring an expression attribute of the user corresponding to the picture according to the character avatar picture; S23. The information matching the expression attributes is pushed to the mobile terminal.
  • the information pushing device wherein the step of acquiring the expression attribute of the user corresponding to the picture according to the character avatar picture comprises: S221. acquiring multiple related to the user's expression attribute in the character avatar picture User feature point information; S222. Comparing the user feature point information with standard feature point information corresponding to each expression attribute in the face database to obtain a matching expression attribute; S223. Using the matched expression attribute as The expression attribute of the user corresponding to the picture.
  • FIG. 1 is a schematic diagram of a specific example of a preset button in an image capturing method according to Embodiment 1 of the present invention
  • Embodiment 2 is a flowchart of a specific example of an image collection method in Embodiment 1 of the present invention
  • Embodiment 3 is a flowchart of a specific example of a method for pushing information in Embodiment 2 of the present invention
  • FIG. 4 is a flowchart of a specific example of acquiring an expression attribute of a user according to a picture of a person's avatar in the information pushing method according to Embodiment 2 of the present invention
  • FIG. 5 is a flowchart of a specific example of pushing information matching a user's expression attribute to a mobile terminal in an information pushing method according to Embodiment 2 of the present invention
  • FIG. 6 is a flowchart of a specific example of an image collection device in Embodiment 3 of the present invention.
  • FIG. 7 is a flowchart of a specific example of an information pushing apparatus in Embodiment 4 of the present invention.
  • FIG. 8 is a schematic structural diagram of an image capture apparatus having a processor according to Embodiment 6 of the present invention.
  • FIG. 9 is a schematic structural diagram of an image capturing apparatus with two processors according to Embodiment 6 of the present invention.
  • FIG. 10 is a schematic structural diagram of an information pushing apparatus having a processor according to Embodiment 7 of the present invention.
  • FIG. 11 is a schematic structural diagram of an information push apparatus having two processors according to Embodiment 7 of the present invention.
  • A-menu item button 11-scan unit; 12-person avatar recognition unit; 13-photograph unit; 14-send unit; 15-up unit; 21-receive unit; 22-expression attribute acquisition unit; 23-information push unit ;221-user feature point information acquisition subunit; 222-alignment subunit; 223-expression attribute determination subunit; 231-classification subunit; 232-link subunit; 233-push subunit.
  • connection or integral connection; may be mechanical connection or electrical connection; may be directly connected, may also be indirectly connected through an intermediate medium, or may be internal communication of two components, may be wireless connection, or may be wired connection.
  • connection or integral connection; may be mechanical connection or electrical connection; may be directly connected, may also be indirectly connected through an intermediate medium, or may be internal communication of two components, may be wireless connection, or may be wired connection.
  • the embodiment provides an image collection method for a mobile terminal, and a plug-in capable of calling a camera to work is installed in the browser software of the mobile terminal.
  • the mobile terminal includes, but is not limited to, a mobile phone, a personal digital assistant (PDA), a palmtop computer, or a tablet computer.
  • the mobile terminal can install a browser software supporting htm15, and install a plug-in such as a scan plug-in, a photo plug-in, and the like that can call the camera to perform scanning, photographing, and the like in the browser software.
  • a menu item button capable of triggering the above plug-in can be set on the browser as an interface for triggering the plug-in.
  • the image collection method includes the following steps:
  • the camera After receiving the instruction of image acquisition, the camera is called to perform image scanning.
  • the image acquisition instruction is from trigger information generated by the user clicking a preset button in the browser.
  • the menu item button of the scan plug-in can be triggered as a preset button, and the trigger information generated by clicking the preset button is received, and the camera can be called to perform image scanning.
  • the preset camera may be preferentially invoked or the corresponding camera may be invoked according to the user's selection.
  • mobile phones some include front camera and rear camera, generally call the front camera for image scanning, so that when the user uses the browser to browse the web, click the preset button displayed by the browser to call the front camera. Image scanning of the user's face does not interrupt the user's browsing process, and the experience is higher.
  • S12. Determine whether the image scanned by the camera is a character avatar. Specifically, in the process of image scanning, by the Facial Recognition algorithm saved locally by the mobile terminal, it can be determined whether the image scanned by the camera temporarily cached locally on the mobile terminal is a character avatar.
  • the camera is called to take a picture of the image. Specifically, after the image is determined to be a character avatar, the camera can be automatically photographed by an internal thread, and the user is not required to perform additional operations.
  • the image collecting method in this embodiment does not need to install a special video processing client software to call the camera to perform scanning, photographing, cameraing, etc., and only needs to respond to the user's image capturing instruction through the browser software of the mobile terminal, and call the camera.
  • Corresponding operations reduce the number of client software installed on the mobile terminal, reduce the load on the software and hardware of the mobile terminal, and improve the response speed.
  • the camera is called to take a picture, and the character avatar is saved in the form of a picture and sent to the server, avoiding It is also beneficial to improve the response speed by avoiding frequent calls of threads and excessive use of memory on the mobile terminal.
  • the camera is called to perform an image scan every preset time interval, and then returns to step S12.
  • the camera is called to perform an image scanning, and after determining that the image scanned by the camera is a character avatar, the camera is called.
  • Take a picture of the image save the newly acquired character avatar as a picture and send it to the server.
  • the server can obtain the updated character avatar in time to analyze the latest expression attribute of the user, and timely adjust and update the information pushed to the user, and push the server to match the current demand of the user. Data support is provided.
  • the embodiment provides an information pushing method, which is used for the server end, and the server end can be a cloud server, which has a fast computing speed and can respond to the user's needs in time.
  • the information pushing method in this embodiment includes the following steps:
  • step S22 includes:
  • the server may obtain a plurality of user feature point information related to the expression attribute of the user in the character avatar picture, such as eyebrows, eyes, and nose, by the face++ face recognition algorithm. Characteristics of the corresponding parts of the face such as the mouth Point information, through the above user feature point information, can fully describe the user's current facial expression, which lays a foundation for later analysis to obtain accurate user expression attributes.
  • the most significant number of expression attributes of the same or similar feature point information of the user feature point information in all the expression attributes may be used as the matching expression attributes.
  • the standard feature point information in each expression attribute can be obtained the same or similar to the user feature point information. The greater the number, the more the user's expression attribute is closer to the expression attribute in the face database.
  • the standard feature point information in the expression attribute of sadness is the same or similar to the user feature point information. Determine the user's expression attribute is sad.
  • the expression attribute having the most or the same number of the same or the same as the user feature point information in all the expression attributes is determined as the matching expression attribute, and the matched expression attribute is used as the expression attribute of the user corresponding to the picture,
  • the user's expression attributes are accurately divided.
  • S23 Push information matching the expression attribute of the user to the mobile terminal. Specifically, for example, after judging that the user's expression attribute is sad, the user may be pushed to push some information that can alleviate his sadness, and match the current needs of the user as much as possible.
  • step S23 includes:
  • each expression attribute may correspond to a different label (ID), and the divided information is respectively linked to a label (ID) corresponding to the expression attribute, and a link between each expression attribute and its corresponding classification information may be established. .
  • the user's expression attribute is obtained according to the character avatar picture; and the information matching the user's expression attribute is pushed to the mobile terminal.
  • the information matching the expression attribute of the user can be pushed to the user according to the current expression attribute of the user, and the current mood of the user is matched, which meets the real needs of the user, can improve the user's attention to the push information, and achieve a good push effect.
  • the embodiment provides an image collection device for a mobile terminal, wherein a plug-in capable of calling a camera is installed in a browser software of the mobile terminal.
  • the image collection device in this embodiment includes:
  • the scanning unit 11 is configured to invoke the camera to perform image scanning after receiving the instruction of image acquisition.
  • the instruction for image acquisition received by the scanning unit 11 is from trigger information generated by the user clicking a preset button in the browser.
  • the character avatar recognition unit 12 is configured to determine whether the image scanned by the camera is a character avatar.
  • the photographing unit 13 is configured to call the camera to take a picture when the image is a character avatar.
  • the sending unit 14 is configured to acquire an image captured by the camera, save the character avatar in the form of a picture, and send the image to the server.
  • the image acquisition device in this embodiment does not need to install a special video processing client software to invoke the camera to perform operations such as scanning, photographing, and photographing, and only needs to respond to the user's instruction to collect images through the browser software of the mobile terminal, and invoke the camera.
  • Corresponding operations reduce the number of client software installed on the mobile terminal, reduce the load on the software and hardware of the mobile terminal, and improve the response speed.
  • the camera is called to take a picture, the character avatar is saved in the form of a picture and sent to the server, thereby avoiding frequent calls of the thread and excessive occupation of the memory of the mobile terminal. It also helps to improve the response speed.
  • the image collection method in this embodiment further includes:
  • the updating unit 15 is configured to start the scanning unit 11 to call the camera to perform an image scanning every preset time interval, and then activate the character avatar identifying unit 12.
  • the image collecting device in the embodiment can enable the server to obtain the updated character avatar in time, and then analyze the latest expression attribute of the user according to the present, so as to timely adjust and update the information pushed to the user, and push the server for the server.
  • Data support is provided by information that matches the user's current needs.
  • the embodiment provides an information pushing device, which is used on the server side, as shown in FIG.
  • the receiving unit 21 is configured to receive a picture of a person's avatar.
  • the expression attribute obtaining unit 22 is configured to acquire an expression attribute of the user corresponding to the picture according to the character avatar picture.
  • the information pushing unit 23 is configured to push information matching the expression attribute of the user to the mobile terminal.
  • the expression attribute obtaining unit 22 includes:
  • the user feature point information obtaining sub-unit 221 is configured to acquire a plurality of user feature point information related to the user's expression attribute in the character avatar picture.
  • the comparison sub-unit 222 is configured to compare the user feature point information with the standard feature point information corresponding to each expression attribute in the face database to obtain a matching expression attribute.
  • the comparison sub-unit 222 can use the same number of expression attributes that are the same or similar to the standard feature point information of all the expression attributes and the user feature point information as the expression attribute of the user.
  • the expression attribute determining sub-unit 223 is configured to use the matched expression attribute as the expression attribute of the user corresponding to the picture.
  • the information pushing unit 23 includes:
  • a classification subunit 231 configured to classify information according to an expression attribute
  • a link sub-unit 232 configured to establish a link between each expression attribute and its corresponding classification information
  • the pushing subunit 233 is configured to push the category information corresponding to the user's expression attribute link to the mobile terminal.
  • the information pushing device in this embodiment obtains the expression attribute of the user according to the picture of the person's avatar after receiving the picture of the person's avatar; and pushes information matching the expression attribute of the user to the mobile terminal.
  • the information matching the expression attribute of the user can be pushed to the user according to the current expression attribute of the user, and the current mood of the user is matched, which meets the real needs of the user, can improve the user's attention to the push information, and achieve a good push effect.
  • This embodiment provides a mobile phone, including the image collecting device in Embodiment 3. No need to install special video processing client software to call the camera for scanning, taking photos, taking pictures, etc.
  • the mobile terminal's browser software is used to respond to the user's instructions for acquiring images, and the camera is called to perform corresponding operations, thereby reducing the number of client software installed on the mobile terminal, reducing the load on the mobile terminal's software and hardware, and improving the response. speed.
  • the image scanned by the camera is a character avatar
  • the camera is called to take a picture
  • the character avatar is saved in the form of a picture and sent to the server, thereby avoiding frequent calls of the thread and excessive occupation of the memory of the mobile terminal. It also helps to improve the response speed.
  • the present invention further discloses an image capture device for a mobile terminal, wherein: one or more processors 200; a memory 100; one or more programs, the one or more programs being stored in the memory 100, When executed by the one or more processors 200, the following operations are performed: a plug-in capable of invoking camera work is installed in the browser software of the mobile terminal; the image collection method includes the following steps: S11. When received After the image acquisition instruction, the camera is called to perform image scanning; S12. determining whether the image scanned by the camera is a character avatar; S13. if the image is a character avatar, calling the camera to take a picture of the image; S14. acquiring the camera shooting The image is saved in the form of a picture and sent to the server. Specifically, as shown in FIG. 8, a processor 200 may be included, and as shown in FIG. 9, two processors 200 may be included.
  • the present invention also discloses an information pushing apparatus for a server side, including: one or more processors 400; a memory 300; one or more programs, and the one or more programs are stored in the memory 300
  • the one or more processors 400 are executed, the following operations are performed: S21. receiving a character avatar picture; S22. acquiring an expression attribute of the user corresponding to the picture according to the character avatar picture; S23. Matching the user's expression attributes
  • the information is pushed to the mobile terminal.
  • a processor 400 may be included, and as shown in FIG. 12, two processors 400 may be included.
  • the information pushing device wherein the step of acquiring the expression attribute of the user corresponding to the picture according to the character avatar picture comprises: S221. acquiring multiple related to the user's expression attribute in the character avatar picture User feature point information; S222. Comparing the user feature point information with standard feature point information corresponding to each expression attribute in the face database to obtain a matching expression attribute; S223. Using the matched expression attribute as The expression attribute of the user corresponding to the picture.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the device is implemented in a flow chart A function specified in a block or blocks of a process or multiple processes and/or block diagrams.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Information Transfer Between Computers (AREA)
  • Telephone Function (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种图像采集方法、装置及手机，图像采集方法用于移动终端，且移动终端的浏览器软件中安装有能够调用摄像头工作的插件；当接收到图像采集的指令后，调用摄像头进行图像扫描，并判断摄像头扫描的图像是否为人物头像，若图像为人物头像，调用摄像头对该图像进行拍照，之后获取摄像头拍摄的图像，将人物头像以图片形式进行保存并发送至服务器端。无需安装专门的视频处理客户端软件来调用摄像头进行相应操作，减少了安装于移动终端的客户端软件的数量，降低了移动终端软、硬件的负荷，提高了响应速度。并且当判断摄像头扫描的图像是人物头像后才会调用摄像头对图像进行拍照，避免了线程的频繁调用以及对移动终端内存过多的占用。

Description

图像采集、信息推送方法、装置及手机
交叉引用
本申请要求在2015年12月15日提交中国专利局、申请号为201510931791.4、发明名称为“图像采集、信息推送方法、装置及手机”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
本发明涉及通讯技术领域，具体涉及一种图像采集、信息推送方法、装置及手机。
背景技术
信息推送是近年来的一个热门领域，如涉及电子商务、社交网站等的APP，会根据浏览记录向用户推送一些用户有可能会感兴趣的信息，能够在一定程度上减少信息超载给用户带来的麻烦。
但信息推送本身就会给用户带来打扰，降低用户的体验度，对于一些非刚需的APP，如果打扰次数过多，用户有可能会直接删除APP。但如果不向用户推送信息，APP本身的活跃度又上不去。因此如何向用户推送与其当前需求相匹配的信息以提升用户的体验度是亟待解决的问题。
另，当移动终端的用户需要调用摄像头进行拍照、摄像、扫描等操作时，只能通过装在移动终端上的调用摄像头的客户端软件来进行，但多个客户端软件的启用也加大了移动终端软、硬件的负荷，降低了处理速度。
发明内容
因此，本发明要解决的一个技术问题在于克服现有技术中在调用摄像头进行工作时会导致移动终端软硬件的负荷大、处理速度降低的缺陷，从而提供一种不会增加移动终端软硬件负荷的图像采集方法、装置及手机。
本发明要解决的另一个技术问题在于克服现有技术中推送的信息难以与用户的真实需求相匹配，体验度差的缺陷，从而提供一种与用户真实需求相匹配的信息推送方法、装置及手机。
为此，本发明提供了如下技术方案：
本发明提供了一种图像采集方法，用于移动终端，所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；
所述图像采集方法包括如下步骤：
S11.当接收到图像采集的指令后，调用摄像头进行图像扫描；
S12.判断摄像头扫描的图像是否为人物头像；
S13.若所述图像为人物头像，调用摄像头对该图像进行拍照；
S14.获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。
本发明所述的图像采集方法，所述图像采集的指令来自用户点击浏览器中的预设按钮所产生的触发信息。
本发明所述的图像采集方法，步骤S14之后还包括：
S15.每隔预设时间间隔调用摄像头进行一次图像扫描，之后返回步骤S12。
本发明还提供了一种信息推送方法，用于服务器端，包括如下步骤：
S21.接收人物头像图片；
S22.根据所述人物头像图片获取与所述图片对应的用户的表情属性；
S23.将与所述用户的表情属性相匹配的信息推送至移动终端。
本发明所述的信息推送方法，所述根据所述人物头像图片获取与所述图片对应的用户的表情属性的步骤包括：
S221.获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；
S222.将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；
S223.将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
本发明所述的信息推送方法，将与所述用户的表情属性相匹配的信息推送至移动终端的步骤包括：
S231.根据表情属性对信息进行分类；
S232.建立各个表情属性与其对应的分类信息间的链接；
S233.将用户的表情属性链接对应的分类信息推送至移动终端。
本发明还提供了一种图像采集装置，用于移动终端，所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；
所述图像采集装置包括：
扫描单元，用于在接收到图像采集的指令后，调用摄像头进行图像扫描；
人物头像识别单元，用于判断摄像头扫描的图像是否为人物头像；
拍照单元，用于在所述图像为人物头像时，调用摄像头对该图像进行拍照；
发送单元，用于获取所述摄像头拍摄的图像，将所述人物头像以图片 形式进行保存并发送至服务器端。
本发明还提供了一种信息推送装置，用于服务器端，包括；
接收单元，用于接收人物头像图片；
表情属性获取单元，用于根据所述人物头像图片获取与所述图片对应的用户的表情属性；
信息推送单元，用于将与所述用户的表情属性相匹配的信息推送至移动终端。
本发明所述的信息推送装置，所述表情属性获取单元包括：
用户特征点信息获取子单元，用于获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；
比对子单元，用于将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；
表情属性确定子单元，用于将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
本发明还提供了一种手机，包括上述图像采集装置。
本发明技术方案，具有如下优点：
本发明提供了一种图像采集方法及装置，用于移动终端，且移动终端的浏览器软件中安装有能够调用摄像头工作的插件；当接收到图像采集的指令后，调用摄像头进行图像扫描，并判断摄像头扫描的图像是否为人物头像，若图像为人物头像，调用摄像头对该图像进行拍照，之后获取摄像头拍摄的图像，将人物头像以图片形式进行保存并发送至服务器端。无需安装专门的视频处理客户端软件来调用摄像头进行扫描、拍照、摄像等操作，只需通过移动终端的浏览器软件来响应用户的采集图像的指令，调用 摄像头进行相应操作，减少了安装于移动终端的客户端软件的数量，降低了移动终端软、硬件的负荷，提高了响应速度。并且当判断摄像头扫描的图像是人物头像后才会调用摄像头对图像进行拍照，将人物头像以图片形式进行保存并发送至服务器端，避免了线程的频繁调用以及对移动终端内存过多占用的情况，也有利于提高响应速度。
本发明所述图像采集方法及装置，每隔预设时间间隔就会调用摄像头进行一次图像扫描，在判断摄像头扫描的图像为人物头像后，调用摄像头对图像进行拍照，将新获取的人物头像以图片形式进行保存并发送至服务器端。能够使服务器端及时获取到更新后的人物头像进而能够据此分析出用户最新的表情属性，以对推送给用户的信息及时进行调整和更新，为服务器端推送出与用户需求相匹配的信息提供了数据支持。
本发明还提供了一种信息推送方法及装置，接收人物头像图片后，根据人物头像图片获取与图片对应的用户的表情属性；将与用户的表情属性相匹配的信息推送至移动终端。能够根据用户当前的表情属性向用户推送与其表情属性相匹配的信息，与用户当前的情绪相匹配，符合用户的真实需求，能够提升用户对推送信息的关注度，达到一个好的推送效果。
本发明又公开了一种图像采集装置，用于移动终端，其中：一个或者多个处理器；存储器；一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时，进行如下操作：所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；所述图像采集方法包括如下步骤：S11.当接收到图像采集的指令后，调用摄像头进行图像扫描；S12.判断摄像头扫描的图像是否为人物头像；S13.若所述图像为人物头像，调用摄像头对该图像进行拍照；S14.获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。
本发明还公开了一种信息推送装置，用于服务器端，其中，包括；一个或者多个处理器；存储器；一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时，进行如下操作：S21.接收人物头像图片；S22.根据所述人物头像图片获取与所述图片对应的用户的表情属性；S23.将与所述用户的表情属性相匹配的信息推送至移动终端。
所述的信息推送装置，其中，所述根据所述人物头像图片获取与所述图片对应的用户的表情属性的步骤包括：S221.获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；S222.将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；S223.将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
附图说明
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式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，下面描述中的附图是本发明的一些实施方式，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为本发明实施例1图像采集方法中预设按钮的一个具体实例的示意图；
图2为本发明实施例1中图像采集方法的一个具体实例的流程图；
图3为本发明实施例2中信息推送方法的一个具体实例的流程图；
图4为本发明实施例2信息推送方法中根据人物头像图片获取用户的表情属性的一个具体实例的流程图；
图5为本发明实施例2信息推送方法中将与用户的表情属性相匹配的信息推送至移动终端的一个具体实例的流程图；
图6为本发明实施例3中图像采集装置的一个具体实例的流程图；
图7为本发明实施例4中信息推送装置的一个具体实例的流程图；
图8为本发明实施例6的具有一个处理器的图像采集装置的结构示意图；
图9为本发明实施例6的具有二个处理器的图像采集装置的结构示意图；
图10为本发明实施例7的具有一个处理器的信息推送装置的结构示意图；
图11为本发明实施例7的具有二个处理器的信息推送装置的结构示意图；
附图标记：
a-菜单项按钮，11-扫描单元；12-人物头像识别单元；13-拍照单元；14-发送单元；15-更新单元；21-接收单元；22-表情属性获取单元；23-信息推送单元；221-用户特征点信息获取子单元；222-比对子单元；223-表情属性确定子单元；231-分类子单元；232-链接子单元；233-推送子单元。
具体实施方式
下面将结合附图对本发明的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做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。
在本发明的描述中，需要说明的是，术语“中心”、“上”、“下”、“左”、“右”、“竖直”、“水平”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。此外，术语“第一”、“第二”、“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性。
在本发明的描述中，需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，还可以是两个元件内部的连通，可以是无线连接，也可以是有线连接。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。
此外，下面所描述的本发明不同实施方式中所涉及的技术特征只要彼此之间未构成冲突就可以相互结合。
实施例1
本实施例提供了一种图像采集方法，用于移动终端，该移动终端的浏览器软件中安装有能够调用摄像头进行工作的插件。具体地，移动终端包括但不限于手机、个人数字助理(PDA)、掌上电脑或者平板电脑等。移动终端可以安装支持htm15的浏览器软件，并在该浏览器软件中安装扫描插件、拍照插件等能够调用摄像头进行扫描、拍照等操作的插件。安装上述插件后，可以在浏览器上设置能够触发上述插件的菜单项按钮作为触发上述插件的接口。用户在点开浏览器浏览的同时，就会在浏览界面看到能够触发上述操作的菜单项按钮。除了可以用文字对上述菜单项按钮进行标识外，为了更加形象生动，也可以设计小图像来对菜单项按钮进行标识，如图1所示，可以用一个小相机来对能够触发扫描插件的菜单项按钮a进行标识。用户通过浏览器浏览信息时，点击浏览器显示的上述菜单项按钮，就可以调用摄像头工作了，非常便捷。
如图2所示，图像采集方法包括如下步骤：
S11.当接收到图像采集的指令后，调用摄像头进行图像扫描。优选地，图像采集的指令来自用户点击浏览器中的预设按钮所产生的触发信息。一般情况下将能够触发扫描插件的菜单项按钮作为预设按钮，接收到点击该预设按钮所产生的触发信息，就可以调用摄像头进行图像扫描了。具体地，如果移动终端包括多个摄像头，可以优先调用预先设置好的摄像头或者根据用户的选择调用相应的摄像头。比如手机，有的包括前置摄像头和后置摄像头，一般优先调用前置摄像头进行图像扫描，这样在用户使用浏览器进行网页浏览的过程中点击浏览器显示的预设按钮就能调用前置摄像头对用户的面部进行图像扫描了，不会中断用户的浏览过程，体验度更高。
S12.判断摄像头扫描的图像是否为人物头像。具体地，在图像扫描的过程中，通过移动终端本地所保存的Facial Recognition(面部识别)算法，就可以确定暂时缓存于移动终端本地的摄像头扫描的图像是否为人物头像了。
S13.若图像为人物头像，调用摄像头对该图像进行拍照。具体地，在确定图像为人物头像后，就可以通过内部线程自动调用摄像头对该图像进行拍照了，无需用户进行额外的操作。
S14.获取摄像头拍摄的图像，将人物头像以图片形式进行保存并发送至服务器端。
本实施例中的图像采集方法，无需安装专门的视频处理客户端软件来调用摄像头进行扫描、拍照、摄像等操作，只需通过移动终端的浏览器软件来响应用户的采集图像的指令，调用摄像头进行相应操作，减少了安装于移动终端的客户端软件的数量，降低了移动终端软、硬件的负荷，提高了响应速度。并且当判断摄像头扫描的图像是人物头像后才会调用摄像头对图像进行拍照，将人物头像以图片形式进行保存并发送至服务器端，避 免了线程的频繁调用以及对移动终端内存过多占用的情况，也有利于提高响应速度。
优选地，S15.每隔预设时间间隔调用摄像头进行一次图像扫描，之后返回步骤S12。
具体地，从第一次发送人物头像图片至服务器时起算，每隔预设时间间隔，比如每隔30s，就会调用摄像头进行一次图像扫描，在判断摄像头扫描的图像为人物头像后，调用摄像头对图像进行拍照，将新获取的人物头像以图片形式进行保存并发送至服务器端。能够使服务器端及时获取到更新后的人物头像进而能够据此分析出用户最新的表情属性，以对推送给用户的信息及时进行调整和更新，为服务器端推送出与用户当前需求相匹配的信息提供了数据支持。
实施例2
本实施例提供了一种信息推送方法，用于服务器端，服务器端可以为云服务器，运算速度快，能够及时响应用户的需求。如图3所示，本实施例中的信息推送方法包括如下步骤：
S21.接收人物头像图片。
S22.根据人物头像图片获取与该图片对应的用户的表情属性。具体地，用户的表情属性可以分为高兴、愤怒、悲伤、平静、惊奇这五类，能够反映用户当前的情绪。
优选地，如图4所示，步骤S22包括：
S221.获取人物头像图片中与用户的表情属性相关的多个用户特征点信息。具体地，服务器端在接收到移动终端发送的人物头像图片后，可以通过face++的脸部识别算法获取人物头像图片中与用户的表情属性相关的多个用户特征点信息，例如眉毛、眼睛、鼻子和嘴等脸部相应部位的特征 点信息，通过上述用户特征点信息，就能够对用户当前的面部表情进行全面的表述，为后期分析获取准确的用户表情属性奠定了基础。
S222.将用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性。
S223.将匹配的表情属性作为与该图片对应的用户的表情属性。
优选地，可以将所有表情属性中标准特征点信息与用户特征点信息相同或相近的数目最多的表情属性作为匹配的表情属性。具体地，通过将用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，就能获取到每个表情属性中的标准特征点信息与用户特征点信息相同或相近的数目，数目越多，则说明用户的表情属性与人脸数据库中的该表情属性越贴近，比如悲伤这个表情属性中的标准特征点信息与用户特征点信息相同或相近的数目最多，则可以判断用户的表情属性为悲伤。通过将所有表情属性中标准特征点信息与用户特征点信息相同或相近的数目最多的表情属性确定为匹配的表情属性，并将匹配的表情属性作为与该图片对应的用户的表情属性，能够对用户的表情属性进行准确划分。
S23.将与用户的表情属性相匹配的信息推送至移动终端。具体地，比如经判断用户的表情属性为悲伤，可以给用户推送一些能够缓解其悲伤情绪的信息，尽可能与用户当前的需求相匹配。
优选地，如图5所示，步骤S23包括：
S231.根据表情属性对信息进行分类。具体地，比如表情属性分为高兴、愤怒、悲伤、平静、惊奇这五类时，按照这五类表情属性对信息进行划分，也即划分为表情属性为高兴时适合推送的信息、为愤怒时适合推送的信息、为悲伤时适合推送的信息、为平静时适合推送的信息、为惊奇时适合推送的信息等等，当然也可以根据实际的推送效果对信息的划分进行适应性调整以更符合用户的需求。
S232.建立各个表情属性与其对应的分类信息间的链接。具体地，各个表情属性可以对应不同的标签(ID)，将划分后的信息分别链接到其表情属性对应的标签(ID)中，就可以建立起各个表情属性与其对应的分类信息间的链接了。
S233.将用户的表情属性链接对应的分类信息推送至移动终端。能够向用户推送与其需求相匹配的信息。
本实施例中的信息推送方法，接收人物头像图片后，根据人物头像图片获取用户的表情属性；将与用户的表情属性相匹配的信息推送至移动终端。能够根据用户当前的表情属性向用户推送与其表情属性相匹配的信息，与用户当前的情绪相匹配，符合用户的真实需求，能够提升用户对推送信息的关注度，达到一个好的推送效果。
实施例3
本实施例提供了一种图像采集装置，用于移动终端，其中移动终端的浏览器软件中安装有能够调用摄像头工作的插件。
如图6所示，本实施例中的图像采集装置包括：
扫描单元11，用于在接收到图像采集的指令后，调用摄像头进行图像扫描。优选地，扫描单元11接收的图像采集的指令来自用户点击浏览器中的预设按钮所产生的触发信息。
人物头像识别单元12，用于判断摄像头扫描的图像是否为人物头像。
拍照单元13，用于在图像为人物头像时，调用摄像头对该图像进行拍照。
发送单元14，用于获取摄像头拍摄的图像，将人物头像以图片形式进行保存并发送至服务器端。
本实施例中的图像采集装置，无需安装专门的视频处理客户端软件来调用摄像头进行扫描、拍照、摄像等操作，只需通过移动终端的浏览器软件来响应用户的采集图像的指令，调用摄像头进行相应操作，减少了安装于移动终端的客户端软件的数量，降低了移动终端软、硬件的负荷，提高了响应速度。并且当判断摄像头扫描的图像是人物头像后才会调用摄像头对图像进行拍照，将人物头像以图片形式进行保存并发送至服务器端，避免了线程的频繁调用以及对移动终端内存过多占用的情况，也有利于提高响应速度。
优选地，本实施例中的图像采集方法，还包括：
更新单元15，用于每隔预设时间间隔启动扫描单元11调用摄像头进行一次图像扫描，之后启动人物头像识别单元12。
本实施例中的图像采集装置，能够使服务器端及时获取到更新后的人物头像进而能够据此分析出用户最新的表情属性，以对推送给用户的信息及时进行调整和更新，为服务器端推送出与用户当前需求相匹配的信息提供了数据支持。
实施例4
本实施例提供了一种信息推送装置，用于服务器端，如图7所示，包括；
接收单元21，用于接收人物头像图片。
表情属性获取单元22，用于根据人物头像图片获取与该图片对应的用户的表情属性。
信息推送单元23，用于将与用户的表情属性相匹配的信息推送至移动终端。
优选地，表情属性获取单元22包括：
用户特征点信息获取子单元221，用于获取人物头像图片中与用户的表情属性相关的多个用户特征点信息。
比对子单元222，用于将用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性。优选地，比对子单元222可以将所有表情属性中标准特征点信息与用户特征点信息相同或相近的数目最多的表情属性作为用户的表情属性。
表情属性确定子单元223，用于将匹配的表情属性作为与该图片对应的用户的表情属性。
优选地，信息推送单元23包括：
分类子单元231，用于根据表情属性对信息进行分类；
链接子单元232，用于建立各个表情属性与其对应的分类信息间的链接；
推送子单元233，用于将用户的表情属性链接对应的分类信息推送至移动终端。
本实施例中的信息推送装置，接收人物头像图片后，根据人物头像图片获取用户的表情属性；将与用户的表情属性相匹配的信息推送至移动终端。能够根据用户当前的表情属性向用户推送与其表情属性相匹配的信息，与用户当前的情绪相匹配，符合用户的真实需求，能够提升用户对推送信息的关注度，达到一个好的推送效果。
实施例5
本实施例提供了一种手机，包括实施例3中的图像采集装置。无需安装专门的视频处理客户端软件来调用摄像头进行扫描、拍照、摄像等操作， 只需通过移动终端的浏览器软件来响应用户的采集图像的指令，调用摄像头进行相应操作，减少了安装于移动终端的客户端软件的数量，降低了移动终端软、硬件的负荷，提高了响应速度。并且当判断摄像头扫描的图像是人物头像后才会调用摄像头对图像进行拍照，将人物头像以图片形式进行保存并发送至服务器端，避免了线程的频繁调用以及对移动终端内存过多占用的情况，也有利于提高响应速度。
实施例6
本发明又公开了一种图像采集装置，用于移动终端，其中：一个或者多个处理器200；存储器100；一个或者多个程序，所述一个或者多个程序存储在所述存储器100中，当被所述一个或者多个处理器200执行时，进行如下操作：所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；所述图像采集方法包括如下步骤：S11.当接收到图像采集的指令后，调用摄像头进行图像扫描；S12.判断摄像头扫描的图像是否为人物头像；S13.若所述图像为人物头像，调用摄像头对该图像进行拍照；S14.获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。具体为如图8所示可以包括一个处理器200，如图9所示可以包括二个处理器200。
实施例7
本发明还公开了一种信息推送装置，用于服务器端，其中，包括；一个或者多个处理器400；存储器300；一个或者多个程序，所述一个或者多个程序存储在所述存储器300中，当被所述一个或者多个处理器400执行时，进行如下操作：S21.接收人物头像图片；S22.根据所述人物头像图片获取与所述图片对应的用户的表情属性；S23.将与所述用户的表情属性相匹配 的信息推送至移动终端。具体为如图11所示可以包括一个处理器400，如图12所示可以包括二个处理器400。
所述的信息推送装置，其中，所述根据所述人物头像图片获取与所述图片对应的用户的表情属性的步骤包括：S221.获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；S222.将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；S223.将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个 流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。

Claims (13)

  1. 一种图像采集方法，用于移动终端，其特征在于：
    所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；
    所述图像采集方法包括如下步骤：
    S11.当接收到图像采集的指令后，调用摄像头进行图像扫描；
    S12.判断摄像头扫描的图像是否为人物头像；
    S13.若所述图像为人物头像，调用摄像头对该图像进行拍照；
    S14.获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。
  2. 根据权利要求1所述的图像采集方法，其特征在于，所述图像采集的指令来自用户点击浏览器中的预设按钮所产生的触发信息。
  3. 根据权利要求1或2所述的图像采集方法，其特征在于，步骤S14之后还包括：
    S15.每隔预设时间间隔调用摄像头进行一次图像扫描，之后返回步骤S12。
  4. 一种信息推送方法，用于服务器端，其特征在于，包括如下步骤：
    S21.接收人物头像图片；
    S22.根据所述人物头像图片获取与所述图片对应的用户的表情属性；
    S23.将与所述用户的表情属性相匹配的信息推送至移动终端。
  5. 根据权利要求4所述的信息推送方法，其特征在于，所述根据所述人物头像图片获取与所述图片对应的用户的表情属性的步骤包括：
    S221.获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；
    S222.将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；
    S223.将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
  6. 根据权利要求4或5所述的信息推送方法，其特征在于，将与所述用户的表情属性相匹配的信息推送至移动终端的步骤包括：
    S231.根据表情属性对信息进行分类；
    S232.建立各个表情属性与其对应的分类信息间的链接；
    S233.将用户的表情属性链接对应的分类信息推送至移动终端。
  7. 一种图像采集装置，用于移动终端，其特征在于：
    所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；
    所述图像采集装置包括：
    扫描单元(11)，用于在接收到图像采集的指令后，调用摄像头进行图像扫描；
    人物头像识别单元(12)，用于判断摄像头扫描的图像是否为人物头像；
    拍照单元(13)，用于在所述图像为人物头像时，调用摄像头对该图像进行拍照；
    发送单元(14)，用于获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。
  8. 一种信息推送装置，用于服务器端，其特征在于，包括；
    接收单元(21)，用于接收人物头像图片；
    表情属性获取单元(22)，用于根据所述人物头像图片获取与所述图片对应的用户的表情属性；
    信息推送单元(23)，用于将与所述用户的表情属性相匹配的信息推送至移动终端。
  9. 根据权利要求8所述的信息推送装置，其特征在于，所述表情属性获取单元(22)包括：
    用户特征点信息获取子单元(221)，用于获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；
    比对子单元(222)，用于将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；
    表情属性确定子单元(223)，用于将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
  10. 一种手机，其特征在于，包括权利要求7所述的图像采集装置。
  11. 一种图像采集装置，用于移动终端，其特征在于：
    一个或者多个处理器；
    存储器；
    一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时，进行如下操作：
    所述移动终端的浏览器软件中安装有能够调用摄像头工作的插件；
    所述图像采集方法包括如下步骤：
    S11.当接收到图像采集的指令后，调用摄像头进行图像扫描；
    S12.判断摄像头扫描的图像是否为人物头像；
    S13.若所述图像为人物头像，调用摄像头对该图像进行拍照；
    S14.获取所述摄像头拍摄的图像，将所述人物头像以图片形式进行保存并发送至服务器端。
  12. 一种信息推送装置，用于服务器端，其特征在于，包括；
    一个或者多个处理器；
    存储器；
    一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时，进行如下操作：
    S21.接收人物头像图片；
    S22.根据所述人物头像图片获取与所述图片对应的用户的表情属性；
    S23.将与所述用户的表情属性相匹配的信息推送至移动终端。
  13. 根据权利要求12所述的信息推送装置，其特征在于，所述根据所述人物头像图片获取与所述图片对应的用户的表情属性的步骤包括：
    S221.获取所述人物头像图片中与用户的表情属性相关的多个用户特征点信息；
    S222.将所述用户特征点信息与人脸数据库中每个表情属性对应的标准特征点信息进行比对，得到匹配的表情属性；
    S223.将所述匹配的表情属性作为与所述图片对应的用户的表情属性。
PCT/CN2016/088535 2015-12-15 2016-07-05 图像采集、信息推送方法、装置及手机 WO2017101323A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/241,455 US20170171462A1 (en) 2015-12-15 2016-08-19 Image Collection Method, Information Push Method and Electronic Device, and Mobile Phone

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510931791.4 2015-12-15
CN201510931791.4A CN105898137A (zh) 2015-12-15 2015-12-15 图像采集、信息推送方法、装置及手机

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/241,455 Continuation US20170171462A1 (en) 2015-12-15 2016-08-19 Image Collection Method, Information Push Method and Electronic Device, and Mobile Phone

Publications (1)

Publication Number Publication Date
WO2017101323A1 true WO2017101323A1 (zh) 2017-06-22

Family

ID=57002402

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/088535 WO2017101323A1 (zh) 2015-12-15 2016-07-05 图像采集、信息推送方法、装置及手机

Country Status (2)

Country Link
CN (1) CN105898137A (zh)
WO (1) WO2017101323A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109194865A (zh) * 2018-08-06 2019-01-11 光锐恒宇（北京）科技有限公司 图像生成方法、装置、智能终端和计算机可读存储介质
CN113766061A (zh) * 2021-08-31 2021-12-07 北京百度网讯科技有限公司 一种图像获取方法、装置、设备以及存储介质
CN114271737A (zh) * 2022-01-26 2022-04-05 深圳巴诺机器人有限公司 一种迎宾式扫地机的控制方法和装置
CN117499477A (zh) * 2023-11-16 2024-02-02 北京易华录信息技术股份有限公司 一种基于大模型训练的信息推送方法以及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107959791B (zh) * 2017-11-17 2020-02-18 广州高清视信数码科技股份有限公司 视频图像采集处理的方法、装置、计算机设备及存储介质
CN114071242A (zh) * 2021-11-16 2022-02-18 重庆赛迪奇智人工智能科技有限公司 视频播放方法、视频推送方法、装置和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110219042A1 (en) * 2006-10-27 2011-09-08 Samsung Electronics Co., Ltd. Method and apparatus for generating meta data of content
CN102946491A (zh) * 2012-11-23 2013-02-27 广东欧珀移动通信有限公司 一种根据用户心情自动调整壁纸的方法及系统
CN103577516A (zh) * 2013-07-01 2014-02-12 北京百纳威尔科技有限公司 内容显示方法和装置
CN104036557A (zh) * 2013-03-06 2014-09-10 中国科学技术大学苏州研究院 基于b/s架构的分布式人脸识别考勤系统及其考勤方法
CN104917896A (zh) * 2015-06-12 2015-09-16 努比亚技术有限公司 一种推送数据的方法和终端设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5814700B2 (ja) * 2011-08-25 2015-11-17 キヤノン株式会社 画像処理システム及び画像処理方法
JP5866728B2 (ja) * 2011-10-14 2016-02-17 サイバーアイ・エンタテインメント株式会社 画像認識システムを備えた知識情報処理サーバシステム
CN104463123A (zh) * 2014-12-11 2015-03-25 南威软件股份有限公司 一种基于b/s的人脸识别方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110219042A1 (en) * 2006-10-27 2011-09-08 Samsung Electronics Co., Ltd. Method and apparatus for generating meta data of content
CN102946491A (zh) * 2012-11-23 2013-02-27 广东欧珀移动通信有限公司 一种根据用户心情自动调整壁纸的方法及系统
CN104036557A (zh) * 2013-03-06 2014-09-10 中国科学技术大学苏州研究院 基于b/s架构的分布式人脸识别考勤系统及其考勤方法
CN103577516A (zh) * 2013-07-01 2014-02-12 北京百纳威尔科技有限公司 内容显示方法和装置
CN104917896A (zh) * 2015-06-12 2015-09-16 努比亚技术有限公司 一种推送数据的方法和终端设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109194865A (zh) * 2018-08-06 2019-01-11 光锐恒宇（北京）科技有限公司 图像生成方法、装置、智能终端和计算机可读存储介质
CN113766061A (zh) * 2021-08-31 2021-12-07 北京百度网讯科技有限公司 一种图像获取方法、装置、设备以及存储介质
CN114271737A (zh) * 2022-01-26 2022-04-05 深圳巴诺机器人有限公司 一种迎宾式扫地机的控制方法和装置
CN114271737B (zh) * 2022-01-26 2022-11-29 深圳巴诺机器人有限公司 一种迎宾式扫地机的控制方法和装置
CN117499477A (zh) * 2023-11-16 2024-02-02 北京易华录信息技术股份有限公司 一种基于大模型训练的信息推送方法以及系统
CN117499477B (zh) * 2023-11-16 2024-06-07 北京易华录信息技术股份有限公司 一种基于大模型训练的信息推送方法以及系统

Also Published As

Publication number Publication date
CN105898137A (zh) 2016-08-24

Similar Documents

Publication Publication Date Title
WO2017101323A1 (zh) 图像采集、信息推送方法、装置及手机
US11675494B2 (en) Combining first user interface content into second user interface
US11605389B1 (en) User identification using voice characteristics
US20230393666A1 (en) Navigating through augmented reality content
US10013600B2 (en) Digital image processing method and apparatus, and storage medium
WO2021017932A1 (zh) 一种图像显示方法与电子设备
US11354029B2 (en) Content collection method, apparatus and storage medium
US11178086B2 (en) Media item attachment system
US20120054691A1 (en) Methods, apparatuses and computer program products for determining shared friends of individuals
WO2020207413A1 (zh) 一种内容推送方法、装置与设备
CN106095465B (zh) 设置身份图像的方法及装置
CN105183837B (zh) 一种移动终端的缩略图列表视图显示方法及系统
US20120242840A1 (en) Using face recognition to direct communications
WO2015043512A1 (zh) 一种图片管理方法和装置
KR20200042019A (ko) 실시간 추적 보상 이미지 효과
WO2018028253A1 (zh) 一种信息处理方法、装置及存储介质
CN103167258A (zh) 用于选择图像捕获装置上捕获的图像的方法、系统和设备
KR20200024264A (ko) 고속 사용자들을 위한 콘텐츠를 선택하기 위한 시스템들 및 방법들
EP4127971A1 (en) Speech-based selection of augmented reality content for detected objects
US11863508B2 (en) Progressive attachments system
US11140257B1 (en) Setting shared ringtone for calls between users
US20210304754A1 (en) Speech-based selection of augmented reality content
US20170171462A1 (en) Image Collection Method, Information Push Method and Electronic Device, and Mobile Phone
KR100785617B1 (ko) 멀티미디어메시징서비스를 이용한 사진 전송시스템 및 그방법
US11860959B1 (en) Ranking notifications in a social network feed

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: 16874386

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: 16874386

Country of ref document: EP

Kind code of ref document: A1