WO2016184032A1 - 图片搜索方法、装置和存储介质 - Google Patents

图片搜索方法、装置和存储介质 Download PDF

Info

Publication number
WO2016184032A1
WO2016184032A1 PCT/CN2015/092418 CN2015092418W WO2016184032A1 WO 2016184032 A1 WO2016184032 A1 WO 2016184032A1 CN 2015092418 W CN2015092418 W CN 2015092418W WO 2016184032 A1 WO2016184032 A1 WO 2016184032A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
picture
area
user
search target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2015/092418
Other languages
English (en)
French (fr)
Inventor
阎彤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology Beijing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Priority to US15/504,201 priority Critical patent/US20180336243A1/en
Publication of WO2016184032A1 publication Critical patent/WO2016184032A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G06F16/2433—Query languages
    • G06F16/2435—Active constructs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying

Definitions

  • Embodiments of the present invention relate to the field of search engine technologies, and in particular, to a picture search method, apparatus, and storage medium.
  • the image search engine can be divided into a text-based image search engine, a content-based image search engine, and a semantic-based image search engine.
  • the content-based image search technology uses the visual features of the image, such as color, texture, shape, etc., as matching features of the image to perform matching and searching, thereby obtaining search results that the user may need.
  • the existing content-based image search engine generally requires the background of the picture provided by the user to be searched as simple as possible.
  • the search image used by the user does not necessarily meet such requirements. For example, a user needs to search for a building that he or she passes through, and this building is in the middle of multiple buildings, and it is difficult to find a shooting angle of a building that only captures the search. In this way, it is difficult to obtain a simple picture of the building.
  • the application range of image search is small and the popularity is not high.
  • Embodiments of the present invention provide a picture search method, apparatus, and storage medium to easily identify an image corresponding to an object to be searched from a picture for searching.
  • an embodiment of the present invention provides a picture search method, including:
  • a search request is initiated based on the search target based on a search instruction entered by the user.
  • an embodiment of the present invention further provides an image search apparatus, including:
  • Display module for displaying pictures
  • An identification module configured to identify a selected area according to a trajectory smeared by the user on the picture
  • a target determining module configured to determine a search target in the picture according to the selected area
  • a requesting module configured to initiate a search request based on the search target according to a search instruction input by the user.
  • embodiments of the present invention provide one or more storage media containing computer executable instructions for performing a picture search method when executed by a computer processor, the method comprising the following steps :
  • a search request is initiated based on the search target based on a search instruction entered by the user.
  • the image searching method, apparatus and storage medium provided by the embodiment of the present invention identify a selected area according to a trajectory smeared by the user on the picture by displaying a picture, determine a search target in the picture according to the selected area, and input according to the user
  • the search instruction initiates a search request based on the search target, thereby being able to easily recognize an image corresponding to the object to be searched from the picture for searching.
  • FIG. 1 is a flowchart of a picture search method according to a first embodiment of the present invention
  • FIG. 2 is a flowchart of a picture search method according to a second embodiment of the present invention.
  • 3A is a display interface diagram of a picture before a difference display and a label display according to a second embodiment of the present invention.
  • FIG. 3B is a display interface diagram of a picture after the difference display and the label display according to the second embodiment of the present invention.
  • FIG. 4 is a flowchart of identification in a picture search method according to a third embodiment of the present invention.
  • FIG. 5 is a flowchart of target determination in a picture search method according to a fourth embodiment of the present invention.
  • FIG. 6 is a structural diagram of a picture search apparatus according to a fifth embodiment of the present invention.
  • This embodiment provides a technical solution of the picture search method.
  • This embodiment can be performed by a picture search device, which can be integrated in a computing device on the user side, such as a smart mobile terminal, a PC.
  • the image search method includes:
  • the image used to obtain the search target Before initiating an image search from a search target in the image, the image used to obtain the search target should be obtained and displayed.
  • the picture may be a picture taken by a user using a camera, or may be used The image downloaded by the user from the network.
  • the user is allowed to delineate a selected area capable of indicating the display range of the search target by a smear operation on the display screen. After the user performs the smear operation through the touched display screen, the selected area is identified according to the smearing trajectory of the user on the picture.
  • an area on the display screen touched by the finger by the user during the smear operation can be detected.
  • the area touched by the user's finger during the smear operation is the area covered by the smear track.
  • the area touched by the finger during the smear operation can be identified as the selected area. In this way, the identification of the selected area is achieved by the identification of the smearing track.
  • a search target is determined in the selected area.
  • the search target may be automatically determined from the selected area according to a specific target recognition algorithm, and the search target may be determined semi-automatically from the selected area according to a further instruction prompt by the user.
  • a search request can be initiated to the image search server based on the determined search target. Specifically, the search request is initiated according to a search instruction input by a user.
  • the search target may be displayed differentially on the touch display screen, and a search control for initiating the search request may be displayed around the search target that is displayed differently, and according to the user Initiate a search request by searching for the operation of the control.
  • the image search method further includes: displaying the search target differently in the picture; establishing a search tag for the search target and displaying the search tag, wherein the search tag is used for a user to input a search instruction.
  • the image search method includes:
  • the search target After determining the search target from the selected area, the search target is displayed differently in the picture.
  • the difference display means that the image area corresponding to the search target is displayed in a display manner different from other image areas.
  • a translucent mask may be formed over the image area corresponding to the search target, and the mask may be displayed.
  • a search tag is created and displayed for the search target, and the search tag is used for a user to input a search instruction.
  • a search tag can be further displayed.
  • the tag is a display control for the user to enter a command to initiate a search request.
  • the search tag can be a button or other display control.
  • 3A and 3B are display interface diagrams of pictures before and after the difference display and the label display, respectively. Referring to FIGS. 3A and 3B, after the search target 31 is determined based on the area 30 covered by the smear track of the user, the search target 31 is displayed differently. And, a search tag 32 for the user to input a search command is displayed around the search target.
  • the search target is displayed differently in the picture, and a search tag is created and displayed for the search target, and the search tag is used.
  • the user inputs a search instruction, which facilitates the user to input a search instruction according to the search target, thereby initiating a search request.
  • identifying the selected area according to the trajectory smeared by the user on the picture comprises: calculating an area covered by the smeared trajectory; if the area of the area is greater than a preset area threshold, determining the selected area; The area of the area is less than or equal to a preset area threshold, and the abnormal information is sent to the user.
  • identifying the selected area according to the trajectory smeared by the user on the picture includes:
  • the area covered by the user's smear track is too small, it may cause difficulty in determining the selected area from the area covered by the smeared track. Therefore, it is necessary to further screen the area covered by the smeared track by calculation of the area. When performing regional screening, it is first necessary to calculate the area of the area covered by the smeared track.
  • An area threshold is set in advance for the area of the area covered by the applied track.
  • the area threshold is a lower threshold. That is to say, only when the area of the area covered by the smeared track is larger than the area threshold, the area covered by the smeared track can be determined as the selected area.
  • the area of the area covered by the smeared track is not greater than the area threshold, that is, the area of the area is less than or equal to the area threshold, the abnormal information needs to be sent to the user.
  • the user by calculating an area covered by the trajectory of the smear, when the area of the area is greater than a preset area threshold, determining the selected area, and when the area of the area is less than or equal to a preset area threshold, The user sends the abnormal information, which effectively prevents the area of the area covered by the smeared track from being too small, and it is difficult to determine the selected area, thereby improving the fault tolerance of the image search method.
  • determining the search target in the picture according to the selected area includes: acquiring at least one selected by the selected area in the picture a pixel; a body including the pixel is identified in the picture as the search target.
  • determining a search target in the picture according to the selected area includes:
  • the selected area is determined on the picture by the smear operation, an image of an object not belonging to the search target may still be included in the selected area.
  • the user may further select at least one pixel belonging to the search target in the selected area. .
  • the subject including the pixel or the pixels is identified from the picture, and the identified subject is used as a search target.
  • the at least one pixel is selected in the picture by acquiring the selected area, and the body including the pixel is identified in the picture as the search target, thereby making the identification of the search target easier.
  • the image search device includes a display module 61, an identification module 62, a target determination module 63, and a request module 66.
  • the display module 61 is configured to display a picture.
  • the identification module 62 is configured to identify the selected area according to the trajectory smeared by the user on the picture.
  • the target determining module 63 is configured to determine a search target in the picture according to the selected area.
  • the requesting module 66 is configured to initiate a search request based on the search target according to a search instruction input by a user.
  • the image search device further includes: a difference display module 64 and a label display module 65.
  • the difference display module 64 is configured to separately display the search target in the picture after determining a search target in the picture according to the selected area.
  • the tag display module 65 is configured to create and display a search tag for the search target, the search tag being used for a user to input a search instruction.
  • the identification module 62 includes:
  • the calculation sub-module is used to calculate the area of the area covered by the smeared track.
  • the area determining submodule is configured to determine the selected area if the area of the area is greater than a preset area threshold.
  • the abnormal submodule is configured to send abnormal information to the user if the area of the area is less than or equal to a preset area threshold.
  • the target determining module 63 includes:
  • the pixel point determining sub-module is configured to acquire at least one pixel selected by the selected area in the picture.
  • the body identification sub-module is configured to identify a body including the pixel point in the picture as the search target.
  • the image search device may perform the image search method provided by any embodiment of the present invention, and has a function module and a beneficial effect corresponding to the execution method.
  • modules or steps of the present invention described above can be implemented by a general-purpose computing device, which can be centralized on a single computing device or distributed over a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computer device, so that they may be stored in the storage device by the computing device, or they may be separately fabricated into individual integrated circuit modules, or multiple modules thereof Or the steps are made into a single integrated circuit module.
  • the invention is not limited to any specific combination of hardware and software.
  • a search request is initiated based on the search target based on a search instruction entered by the user.
  • the foregoing storage medium may further include: after determining the search target in the picture according to the selected area, when the method is performed,
  • a search tag is created and displayed for the search target, the search tag being used for a user to enter a search command.
  • the foregoing storage medium when performing the method, identifies the selected area according to the trajectory smeared by the user on the picture, and may specifically include:
  • the abnormal information is sent to the user.
  • the foregoing storage medium when performing the method, determining a search target in the picture according to the selected area, and specifically includes:
  • a body including the pixel point is identified in the picture as the search target.
  • portions of the technical solution of the present invention that contribute substantially or to the prior art may be embodied in the form of a software product that may be stored in a computer readable storage medium, such as a magnetic disk.
  • a computer readable storage medium such as a magnetic disk.
  • the modules and sub-modules included in the image search device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be implemented;
  • the specific names of the functional units are also for convenience of distinguishing from each other and are not intended to limit the scope of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种图片搜索方法、装置和存储介质。所述图片搜索方法包括：显示图片（S11）；根据用户在所述图片上涂抹的轨迹识别选中区域（S12）；根据所述选中区域在所述图片中确定搜索目标（S13）；根据用户输入的搜索指令，基于所述搜索目标发起搜索请求（S14）。所述图片搜索方法和装置能够从用于搜索的图片中容易的识别出需要搜索的物体对应的图像。

Description

图片搜索方法、装置和存储介质
本专利申请要求于2015年05月21日提交的，申请号为201510262908.4，申请人为百度在线网络技术(北京)有限公司，发明名称为“图片搜索方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本发明实施例涉及搜索引擎技术领域，尤其涉及一种图片搜索方法、装置和存储介质。
背景技术
在互联网技术大行其道的今天，搜索引擎已经是我们普通人生活中必不可少的工具。随着文本搜索引擎技术的日臻成熟，图片搜索技术开始出现。相比于经过多年研究和实践，已经比较成熟的文本搜索，图片搜索无论在理论研究还是在工程实现上，都比较落后。就现有的图片搜索引擎的实现技术来说，可以将图片搜索引擎区分为基于文本的图片搜索引擎、基于内容的图片搜索引擎和基于语义的图片搜索引擎。
基于内容的图片搜索技术将图片的视觉特征，比如颜色、纹理、形状等，作为图片的表示特征，进行匹配和查找，从而获得用户可能需要的搜索结果。现有的基于内容的图片搜索引擎为了能够从图片中更为容易的识别出用户需要搜索的物体，一般都要求用户提供的用于搜索的图片的背景尽量简单。而实际上，用户使用的搜索图片并不一定满足这样的要求。比如，用户需要搜索自己途经的一幢大楼，而这幢大楼处于多个大楼中间，很难找到只拍摄到要搜索的大楼的拍摄角度。这样，获取到这幢大楼的背景简单的图片就有一定的难度。因为上述原因，就造成图片搜索的适用范围很小，受欢迎程度不高。
发明内容
本发明实施例提供了一种图片搜索方法、装置和存储介质，以从用于搜索的图片中容易的识别出需要搜索的物体对应的图像。
第一方面，本发明实施例提供了一种图片搜索方法，包括：
显示图片；
根据用户在所述图片上涂抹的轨迹识别选中区域；
根据所述选中区域在所述图片中确定搜索目标；
根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
第二方面，本发明实施例还提供了一种图片搜索装置，包括：
显示模块，用于显示图片；
识别模块，用于根据用户在所述图片上涂抹的轨迹识别选中区域；
目标确定模块，用于根据所述选中区域在所述图片中确定搜索目标；
请求模块，用于根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
第三方面，本发明实施例提供了一个或多个包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种图片搜索方法，该方法包括以下步骤：
显示图片；
根据用户在所述图片上涂抹的轨迹识别选中区域；
根据所述选中区域在所述图片中确定搜索目标；
根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
本发明实施例提供的图片搜索方法、装置和存储介质通过显示图片，根据用户在所述图片上涂抹的轨迹识别选中区域，根据所述选中区域在所述图片中确定搜索目标，以及根据用户输入的搜索指令，基于所述搜索目标发起搜索请求，从而能够从用于搜索的图片中容易的识别出需要搜索的物体对应的图像。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所 需使用的附图作简单地介绍，当然，以下描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以对这些附图进行修改和替换。
图1是本发明第一实施例提供的图片搜索方法的流程图；
图2是本发明第二实施例提供的图片搜索方法的流程图；
图3A是本发明第二实施例提供的区别显示和标签显示之前的图片的显示界面图；
图3B是本发明第二实施例提供的区别显示和标签显示之后的图片的显示界面图；
图4是本发明第三实施例提供的图片搜索方法中识别的流程图；
图5是本发明第四实施例提供的图片搜索方法中目标确定的流程图；
图6是本发明第五实施例提供的图片搜索装置的结构图。
具体实施方式
下面将结合附图对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明的一部分实施例，而不是全部的实施例，是为了阐述本发明的原理，而不是要将本发明限制于这些具体的实施例。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。
第一实施例
本实施例提供了图片搜索方法的一种技术方案。本实施例可以由图片搜索装置来执行，该装置可以被集成在用户侧的计算设备中，例如智能移动终端，PC机中。
具体的，参见图1，所述图片搜索方法包括：
S11，显示图片。
在利用从图片中的搜索目标发起图片搜索之前，应该获取并显示用来获取搜索目标的图片。所述图片可以是用户利用摄像头拍摄到的图片，也可以是用 户从网络上下载得到的图片。
S12，根据用户在所述图片上涂抹的轨迹识别选中区域。
为了能更为容易的从所述图片中识别搜索目标，允许用户通过在显示屏幕上的涂抹操作来划定一个能够指示所述搜索目标的显示范围的选中区域。用户通过触控的显示屏幕执行涂抹操作之后，根据用户在所述图片上的涂抹轨迹识别所述选中区域。
具体的，可以检测用户在执行涂抹操作过程中手指触摸到的显示屏幕上的区域。所述涂抹操作过程中用户手指触摸到的区域即是涂抹轨迹覆盖的区域。然后，可以将涂抹操作过程中手指触摸到的区域识别为选中区域。这样，就通过对涂抹轨迹的识别实现了对选中区域的识别。
S13，根据所述选中区域在所述图片中确定搜索目标。
在识别所述选中区域之后，在所述选中区域中确定搜索目标。具体的，可以根据具体的目标识别算法自动的从所述选中区域中确定搜索目标，还可以根据用户进一步的指令提示，半自动的从所述选中区域中确定搜索目标。
S14，根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
一旦确定了搜索目标，即可根据确定的搜索目标向图片搜索服务器发起搜索请求。具体的，根据用户输入的搜索指令来发起所述搜索请求。
进一步的，可以在确定搜索目标之后，在触控的显示屏幕上对所述搜索目标进行区别显示，并在区别显示的搜索目标周围显示用于发起搜索请求的搜索控件，并依据用户对所述搜索控件的操作而发起搜索请求。
本实施例通过显示图片，根据用户在所述图片上涂抹的轨迹识别选中区域，根据所述选中区域在所述图片中确定搜索目标，以及根据用户输入的搜索指令，基于所述搜索目标发起搜索请求，能够从用于搜索的图片中容易的识别出需要搜索的物体对应的图像。
第二实施例
本实施例以本发明的上述实施例为基础，进一步的提供了图片搜索方法的一种技术方案。在该技术方案中，在根据所述选中区域在所述图片中确定搜索 目标之后，所述图片搜索方法还包括：在所述图片中区别显示所述搜索目标；为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
具体的，参见图2，所述图片搜索方法包括：
S21，显示图片。
S22，根据用户在所述图片上涂抹的轨迹识别选中区域。
S23，根据所述选中区域在所述图片中确定搜索目标。
S24，在所述图片中区别显示所述搜索目标。
从所述选中区域中确定搜索目标之后，在所述图片中对所述搜索目标进行区别显示。所述区别显示，就是将所述搜索目标对应的图像区域采用与其他图像区域不同的显示方式进行显示。优选的，可以在所述搜索目标对应的图像区域上方形成半透明的遮罩，并显示该遮罩。
S25，为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
除了对所述搜索目标进行区别显示，还可以进一步地显示一个搜索标签。所述标签是用来供用户输入命令以发起搜索请求的显示控件。具体的，所述搜索标签可以是一个按钮，或者其他显示控件。
图3A及图3B分别是区别显示和标签显示之前及之后的图片的显示界面图。参见图3A及图3B，在根据用户的涂抹轨迹覆盖的区域30确定所述搜索目标31之后，对所述搜索目标31进行区别显示。并且，在所述搜索目标的周围显示用于供用户输入搜索指令的搜索标签32。
S26，根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
本实施例通过在根据所述选中区域在所述图片中确定搜索目标之后，在所述图片中区别显示所述搜索目标，以及为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令，方便了用户根据所述搜索目标输入搜索指令，进而发起搜索请求。
第三实施例
本实施例以本发明的上述实施例为基础，进一步的提供了所述图片搜索方法中识别操作的一种技术方案。在该技术方案中，根据用户在所述图片上涂抹的轨迹识别选中区域包括：计算涂抹的轨迹覆盖的区域面积；若所述区域面积大于预先设定的面积阈值，则确定为选中区域；若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
具体的，参见图4，根据用户在所述图片上涂抹的轨迹识别选中区域包括：
S41，计算涂抹的轨迹覆盖的区域面积。
如果用户的涂抹轨迹覆盖的区域面积过小，会造成从涂抹的轨迹覆盖的区域中确定选中区域的困难。因此，需要通过区域面积的计算对涂抹的轨迹覆盖的区域进行进一步的筛选。在进行区域筛选时，首先需要对涂抹的轨迹覆盖的区域的区域面积进行计算。
S42，若所述区域面积大于预先设定的面积阈值，则确定为选中区域。
对于涂抹的轨迹覆盖的区域的区域面积，预先设定有面积阈值。所述面积阈值是一个下限阈值。也就是说，只有涂抹的轨迹覆盖的区域的区域面积大于该面积阈值的时候，所涂抹的轨迹覆盖的区域才能被确定为选中区域。
S43，若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
如果涂抹的轨迹覆盖的区域的区域面积并不大于所述面积阈值，也就是区域面积小于或者等于所述面积阈值，则需要向用户发送异常信息。
本实施例通过计算涂抹的轨迹覆盖的区域面积，当所述区域面积大于预先设定的面积阈值时，确定为选中区域，以及当所述区域面积小于或等于预先设定的面积阈值时，向用户发送异常信息，有效防止了涂抹的轨迹覆盖的区域的区域面积过小而难以确定选中区域的情况，提高了图片搜索方法的容错性。
第四实施例
本实施例以本发明的上述实施例为基础，进一步的提供了所述图片搜索方法中目标确定操作的一种技术方案。在该技术方案中，根据所述选中区域在所述图片中确定搜索目标包括：获取所述选中区域在所述图片内选择的至少一个 像素点；在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
具体的，参见图5，根据所述选中区域在所述图片中确定搜索目标包括：
S51，获取所述选中区域在所述图片内选择至少一个像素点。
可以理解的是，虽然通过涂抹操作在所述图片上确定了选中区域，但是，所述选中区域内仍然可能包括不属于所述搜索目标的物体的图像。为了进一步的从所述选中区域内容易的识别出所述搜索目标，在所述图片上确定所述选中区域之后，用户还可以在所述选中区域内选择属于所述搜索目标的至少一个像素点。
S52，在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
获取所述至少一个像素点之后，从所述图片中识别包含这个或者这些像素点的主体，并将识别得到的主体作为搜索目标。
本实施例通过获取所述选中区域在所述图片内选择至少一个像素点，在所述图片中识别包括所述像素点的主体，作为所述搜索目标，从而使得对搜索目标的识别更为容易。
第五实施例
本实施例提供了图片搜索装置的一种技术方案。在该技术方案中，所述图片搜索装置包括：显示模块61、识别模块62、目标确定模块63以及请求模块66。
所述显示模块61用于显示图片。
所述识别模块62用于根据用户在所述图片上涂抹的轨迹识别选中区域。
所述目标确定模块63用于根据所述选中区域在所述图片中确定搜索目标。
所述请求模块66用于根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
进一步的，所述图片搜索装置还包括：区别显示模块64以及标签显示模块65。
所述区别显示模块64用于在根据所述选中区域在所述图片中确定搜索目标之后，在所述图片中区别显示所述搜索目标。
所述标签显示模块65用于为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
进一步的，所述识别模块62包括：
所述计算子模块用于计算涂抹的轨迹覆盖的区域面积。
所述区域确定子模块用于若所述区域面积大于预先设定的面积阈值，则确定为选中区域。
所述异常子模块用于若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
进一步的，所述目标确定模块63包括：
所述像素点确定子模块用于获取所述选中区域在所述图片内选择的至少一个像素点。
所述主体识别子模块用于在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
上述图片搜索装置可执行本发明任意实施例所提供的图片搜索方法，具备执行方法相应的功能模块和有益效果。
本领域普通技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个计算装置上，或者分布在多个计算装置所组成的网络上，可选地，他们可以用计算机装置可执行的程序代码来实现，从而可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件的结合。
第六实施例
一个或多个包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种图片搜索方法，其特征在于，所述方法包括以下步骤：
显示图片；
根据用户在所述图片上涂抹的轨迹识别选中区域；
根据所述选中区域在所述图片中确定搜索目标；
根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
上述存储介质在执行所述方法时，在根据所述选中区域在所述图片中确定搜索目标之后，还可包括：
在所述图片中区别显示所述搜索目标；
为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
上述存储介质在执行所述方法时，根据用户在所述图片上涂抹的轨迹识别选中区域，还具体可以包括：
计算涂抹的轨迹覆盖的区域面积；
若所述区域面积大于预先设定的面积阈值，则确定为选中区域；
若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
上述存储介质在执行所述方法时，根据所述选中区域在所述图片中确定搜索目标，还具体可以包括：
获取所述选中区域在所述图片内选择的至少一个像素点；
在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到，本发明可借助软件及必需的通过硬件来实现，当然也可以通过硬件实现，但很多情况下前者是更佳的实施方式，基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如磁盘、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述的方法。
值得注意的是，上述图片搜索装置的实施例中，所包括的各个模块和子模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的具体名称也只是为了便于相互区分，并不用于限定本发明的保护范围。
本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间的相同或相似的部分互相参见即可。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何本技术领域的技术人员在本发明披露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围以所述权利要求的保护范围为准。

Claims (9)

  1. 一种图片搜索方法，其特征在于，包括：
    显示图片；
    根据用户在所述图片上涂抹的轨迹识别选中区域；
    根据所述选中区域在所述图片中确定搜索目标；
    根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
  2. 根据权利要求1所述的方法，其特征在于，在根据所述选中区域在所述图片中确定搜索目标之后，还包括：
    在所述图片中区别显示所述搜索目标；
    为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
  3. 根据权利要求1或2所述的方法，其特征在于，根据用户在所述图片上涂抹的轨迹识别选中区域包括：
    计算涂抹的轨迹覆盖的区域面积；
    若所述区域面积大于预先设定的面积阈值，则确定为选中区域；
    若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
  4. 根据权利要求1或2所述的方法，根据所述选中区域在所述图片中确定搜索目标包括：
    获取所述选中区域在所述图片内选择的至少一个像素点；
    在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
  5. 一种图片搜索装置，其特征在于，包括：
    显示模块，用于显示图片；
    识别模块，用于根据用户在所述图片上涂抹的轨迹识别选中区域；
    目标确定模块，用于根据所述选中区域在所述图片中确定搜索目标；
    请求模块，用于根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
  6. 根据权利要求5所述的装置，其特征在于，还包括：
    区别显示模块，用于在根据所述选中区域在所述图片中确定搜索目标之后，在所述图片中区别显示所述搜索目标；
    标签显示模块，用于为所述搜索目标建立搜索标签并进行显示，所述搜索标签用于供用户输入搜索指令。
  7. 根据权利要求5或6所述的装置，其特征在于，所述识别模块包括：
    计算子模块，用于计算涂抹的轨迹覆盖的区域面积；
    区域确定子模块，用于若所述区域面积大于预先设定的面积阈值，则确定为选中区域；
    异常子模块，用于若所述区域面积小于或等于预先设定的面积阈值，向用户发送异常信息。
  8. 根据权利要求5或6所述的装置，其特征在于，所述目标确定模块包括：
    像素点确定子模块，用于获取所述选中区域在所述图片内选择的至少一个像素点；
    主体识别子模块，用于在所述图片中识别包括所述像素点的主体，作为所述搜索目标。
  9. 一个或多个包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种图片搜索方法，其特征在于，所述方法包括以下步骤：
    显示图片；
    根据用户在所述图片上涂抹的轨迹识别选中区域；
    根据所述选中区域在所述图片中确定搜索目标；
    根据用户输入的搜索指令，基于所述搜索目标发起搜索请求。
PCT/CN2015/092418 2015-05-21 2015-10-21 图片搜索方法、装置和存储介质 Ceased WO2016184032A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/504,201 US20180336243A1 (en) 2015-05-21 2015-10-21 Image Search Method, Apparatus and Storage Medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510262908.4A CN104866194B (zh) 2015-05-21 2015-05-21 图片搜索方法及装置
CN201510262908.4 2015-05-21

Publications (1)

Publication Number Publication Date
WO2016184032A1 true WO2016184032A1 (zh) 2016-11-24

Family

ID=53912061

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/092418 Ceased WO2016184032A1 (zh) 2015-05-21 2015-10-21 图片搜索方法、装置和存储介质

Country Status (3)

Country Link
US (1) US20180336243A1 (zh)
CN (1) CN104866194B (zh)
WO (1) WO2016184032A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104866194B (zh) * 2015-05-21 2018-07-13 百度在线网络技术（北京）有限公司 图片搜索方法及装置
CN106649741A (zh) * 2016-12-26 2017-05-10 努比亚技术有限公司 图片搜索方法、装置和系统
CN107133620A (zh) * 2017-06-06 2017-09-05 广东小天才科技有限公司 一种搜索目标的确定方法及装置
CN111081094A (zh) * 2019-08-02 2020-04-28 广东小天才科技有限公司 一种听写内容的选取方法及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102929552A (zh) * 2012-10-25 2013-02-13 东莞宇龙通信科技有限公司 终端和信息搜索方法
CN102968268A (zh) * 2012-10-23 2013-03-13 深圳市中兴移动通信有限公司 一种裁剪图片的方法与装置
CN103020184A (zh) * 2012-11-29 2013-04-03 北京百度网讯科技有限公司 使用拍摄图像获取搜索结果的方法和系统
CN104866194A (zh) * 2015-05-21 2015-08-26 百度在线网络技术（北京）有限公司 图片搜索方法及装置

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0713186B1 (en) * 1994-11-15 2006-07-05 Canon Kabushiki Kaisha Method and apparatus for retrieving images from a database
JP2004240750A (ja) * 2003-02-06 2004-08-26 Canon Inc 画像検索装置
JP5009577B2 (ja) * 2005-09-30 2012-08-22 富士フイルム株式会社 画像検索装置および方法並びにプログラム
US20070288453A1 (en) * 2006-06-12 2007-12-13 D&S Consultants, Inc. System and Method for Searching Multimedia using Exemplar Images
JP4735995B2 (ja) * 2008-12-04 2011-07-27 ソニー株式会社 画像処理装置、画像表示方法および画像表示プログラム
CN102016909A (zh) * 2008-12-19 2011-04-13 松下电器产业株式会社 图像检索装置以及图像检索方法
WO2010073329A1 (ja) * 2008-12-25 2010-07-01 富士通株式会社 コンピュータプログラム、入力装置及び入力方法
US20120092357A1 (en) * 2010-10-14 2012-04-19 Microsoft Corporation Region-Based Image Manipulation
US20130148898A1 (en) * 2011-12-09 2013-06-13 Viewdle Inc. Clustering objects detected in video
JP6071289B2 (ja) * 2012-07-09 2017-02-01 キヤノン株式会社 画像処理装置、画像処理方法、およびプログラム
KR101993241B1 (ko) * 2012-08-06 2019-06-26 삼성전자주식회사 이미지에 대한 부가 정보 태깅 및 검색 방법과 시스템, 기기와 그 기록 매체
US9916081B2 (en) * 2013-02-01 2018-03-13 Intel Corporation Techniques for image-based search using touch controls
JP6403368B2 (ja) * 2013-09-13 2018-10-10 京セラ株式会社 携帯端末、画像検索プログラムおよび画像検索方法
US9230322B2 (en) * 2014-04-04 2016-01-05 Kabushiki Kaisha Toshiba Image processor, treatment system, and image processing method
JP6256206B2 (ja) * 2014-05-30 2018-01-10 ブラザー工業株式会社 画像処理装置、および、コンピュータプログラム
WO2016017987A1 (en) * 2014-07-31 2016-02-04 Samsung Electronics Co., Ltd. Method and device for providing image
KR102402511B1 (ko) * 2015-02-03 2022-05-27 삼성전자주식회사 영상 검색 방법 및 이를 위한 장치

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968268A (zh) * 2012-10-23 2013-03-13 深圳市中兴移动通信有限公司 一种裁剪图片的方法与装置
CN102929552A (zh) * 2012-10-25 2013-02-13 东莞宇龙通信科技有限公司 终端和信息搜索方法
CN103020184A (zh) * 2012-11-29 2013-04-03 北京百度网讯科技有限公司 使用拍摄图像获取搜索结果的方法和系统
CN104866194A (zh) * 2015-05-21 2015-08-26 百度在线网络技术（北京）有限公司 图片搜索方法及装置

Also Published As

Publication number Publication date
US20180336243A1 (en) 2018-11-22
CN104866194A (zh) 2015-08-26
CN104866194B (zh) 2018-07-13

Similar Documents

Publication Publication Date Title
CN111460967B (zh) 一种违法建筑识别方法、装置、设备及存储介质
US10438077B2 (en) Face liveness detection method, terminal, server and storage medium
CN104252410B (zh) 一种对页面中的控件进行测试的方法和设备
US10311115B2 (en) Object search method and apparatus
US20130293467A1 (en) User input processing with eye tracking
CN112381104B (zh) 一种图像识别方法、装置、计算机设备及存储介质
US20130258198A1 (en) Video search system and method
WO2018067475A1 (en) Techniques for incorporating a text-containing image into a digital image
MY195861A (en) Information Processing Method, Electronic Device, and Computer Storage Medium
CN104536729A (zh) 一种实现在浏览器页面中进行截图的方法和装置
CN111124888A (zh) 录制脚本的生成方法和装置及电子装置
US10289932B2 (en) Object recognition state indicators
TWI586160B (zh) 利用行動電話及雲端可視化搜尋引擎之即時物體掃描
CN108876804A (zh) 抠像模型训练和图像抠像方法、装置和系统及存储介质
CN104778195A (zh) 终端和基于触摸操作的搜索方法
WO2016184031A1 (zh) 图片搜索方法、装置和存储介质
Nuzhdin et al. HaGRIDv2: 1M images for static and dynamic hand gesture recognition
JP6858159B2 (ja) 頭部装着装置を使用して関心領域を標識するテレプレゼンスのフレームワーク
US20180336243A1 (en) Image Search Method, Apparatus and Storage Medium
US10631050B2 (en) Determining and correlating visual context on a user device with user behavior using digital content on the user device
CN112104914A (zh) 视频推荐方法及装置
CN107995442A (zh) 视频数据的处理方法、装置及计算设备
CN113158912B (zh) 手势识别方法及装置、存储介质及电子设备
CN110942056A (zh) 服饰关键点定位方法、装置、电子设备及介质
US9697608B1 (en) Approaches for scene-based object tracking

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: 15892410

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15504201

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15892410

Country of ref document: EP

Kind code of ref document: A1