WO2017181504A1 - 智能调节字幕大小的方法及电视机 - Google Patents

智能调节字幕大小的方法及电视机 Download PDF

Info

Publication number
WO2017181504A1
WO2017181504A1 PCT/CN2016/084934 CN2016084934W WO2017181504A1 WO 2017181504 A1 WO2017181504 A1 WO 2017181504A1 CN 2016084934 W CN2016084934 W CN 2016084934W WO 2017181504 A1 WO2017181504 A1 WO 2017181504A1
Authority
WO
WIPO (PCT)
Prior art keywords
subtitle
viewer
face image
caption
image information
Prior art date
Application number
PCT/CN2016/084934
Other languages
English (en)
French (fr)
Inventor
罗莎莎
Original Assignee
深圳Tcl数字技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳Tcl数字技术有限公司 filed Critical 深圳Tcl数字技术有限公司
Publication of WO2017181504A1 publication Critical patent/WO2017181504A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/488Data services, e.g. news ticker
    • H04N21/4884Data services, e.g. news ticker for displaying subtitles
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/488Data services, e.g. news ticker
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4312Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213Monitoring of end-user related data
    • H04N21/44218Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/485End-user interface for client configuration
    • H04N21/4858End-user interface for client configuration for modifying screen layout parameters, e.g. fonts, size of the windows

Definitions

  • the invention relates to the field of television, and in particular to a method for intelligently adjusting the size of a subtitle and a television set.
  • the TV as a living room display device plays an important role in the living room culture.
  • the living room serves as a relaxing environment, and many users prefer to watch the program on TV casually, including most of them.
  • Myopia users this part of the user needs to open their eyes or squint to see the subtitles on the screen, especially in the case of myopic users without eyes.
  • the user can manually adjust the size of the font displayed on the display screen, and at the same time, it can also enlarge or reduce the size of the screen, and can also solve the above problem by getting up and looking for and wearing the eyes, but the above are all user-independent ( Active mode) to change the size of itself or the font, creating trouble for the user to watch the movie, causing inconvenience to the user.
  • Active mode Active mode
  • the main object of the present invention is to provide a method for intelligently adjusting the size of a subtitle, which aims to solve the technical problem that a user suffering from myopia needs to manually adjust the display font size when watching a movie.
  • the present invention provides a method for intelligently adjusting a subtitle size, and the method for intelligently adjusting a subtitle size includes the following steps:
  • the television acquires the face image information of the viewer, and determines whether to open the caption zoom function according to the face image information;
  • the subtitle area enlarged by the subtitle is superimposed with the current display screen to generate a new display screen and displayed.
  • the step of the television set acquiring the face image information of the viewer and determining whether to enable the caption zooming function according to the face image information comprises:
  • the television captures a face image of the viewer, and recognizes and acquires face image information in the face image of the viewer through a face recognition algorithm;
  • the caption zoom function When it is determined that the viewer needs to enable the caption zooming function, it is determined according to the face image information whether the viewer wears glasses, and if so, the caption zoom function is not turned on, otherwise, the caption zoom function is turned on.
  • the step of determining, according to the face image information, whether the user needs to enable the caption zooming function comprises:
  • the present invention provides a method for intelligently adjusting a subtitle size, and the method for intelligently adjusting a subtitle size includes the following steps:
  • the television acquires the face image information of the viewer, and determines whether to open the caption zoom function according to the face image information;
  • the subtitle area enlarged by the subtitle is superimposed with the current display screen to generate a new display screen and displayed.
  • the step of enlarging the subtitle in the subtitle area to generate the subtitle area after the subtitle is enlarged comprises:
  • the first image and the second image are superimposed to generate a subtitle region after the subtitle is enlarged.
  • the step of recognizing and acquiring the caption region in the current display screen includes:
  • the step of the television set acquiring the face image information of the viewer and determining whether to enable the caption zooming function according to the face image information comprises:
  • the television captures a face image of the viewer, and recognizes and acquires face image information in the face image of the viewer through a face recognition algorithm;
  • the caption zoom function When it is determined that the viewer needs to enable the caption zooming function, it is determined according to the face image information whether the viewer wears glasses, and if so, the caption zoom function is not turned on, otherwise, the caption zoom function is turned on.
  • the step of determining, according to the face image information, whether the user needs to enable the caption zooming function comprises:
  • the present invention also provides a television set, the television set comprising:
  • the obtaining determining module is configured to acquire the face image information of the viewer, and determine whether to enable the caption zooming function according to the face image information;
  • a subtitle area identification module configured to identify and acquire a subtitle area in the current display screen when the subtitle enlargement function is turned on;
  • a subtitle area enlargement module configured to enlarge a subtitle in the subtitle area, and generate a subtitle area after the subtitle is enlarged
  • the display screen generating module is configured to superimpose the subtitle area enlarged by the subtitle and the current display screen to generate a new display screen and display the same.
  • a method for intelligently adjusting the size of a subtitle and a television set obtains a face image information of a viewing user and determines the face image information, and when it is determined that the caption zoom function needs to be turned on, Identifying and acquiring the subtitle area in the current display screen, and superimposing the subtitle area to superimpose the current display screen to generate and display the superimposed display screen, thereby realizing automatic detection of the status of the viewing user, and when determining that the viewing user needs
  • the subtitle zoom function is enabled, the subtitle portion in the display screen is enlarged, so that the viewing user can clearly see the subtitle content in the display screen, thereby avoiding the manual user setting the enlarged font.
  • FIG. 1 is a schematic flow chart of a first embodiment of a method for intelligently adjusting a subtitle size according to the present invention
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for intelligently adjusting a subtitle size according to the present invention
  • FIG. 3 is a schematic flow chart of a specific implementation step of a specific embodiment of the present invention.
  • FIG. 4 is a schematic flow chart of a third embodiment of a method for intelligently adjusting a subtitle size according to the present invention.
  • FIG. 5 is a schematic diagram of a region in which a subtitle content in a television display interface is often located
  • FIG. 6 is a schematic flow chart of a fourth embodiment of a method for intelligently adjusting a subtitle size according to the present invention.
  • FIG. 7 is a schematic flow chart of a specific implementation step of another embodiment of the present invention.
  • FIG. 8 is a schematic flow chart of a specific implementation step of another specific embodiment of the present invention.
  • FIG. 9 is a schematic diagram of functional modules of a first embodiment of a television set according to the present invention.
  • FIG. 10 is a schematic diagram of functional modules of a second embodiment of a television set according to the present invention.
  • the main solution of the embodiment of the present invention is: the television acquires the face image information of the viewer, and determines whether to open the caption zoom function according to the face image information; when the caption zoom function is enabled, the current display screen is recognized and acquired. Subtitle area; enlarge the subtitle in the subtitle area to generate a subtitle area after the subtitle is enlarged; superimpose the subtitle area enlarged by the subtitle with the current display screen to generate a new display screen and display.
  • the invention provides a solution for the television to automatically turn on the subtitle zooming function according to the current state of the user during the viewing, thereby reducing the manual operation process when the user is watching.
  • the method for intelligently adjusting a subtitle size includes:
  • step S100 the television acquires the face image information of the viewer, and determines whether to open the caption zoom function according to the face image information.
  • the television acquires the face image information in the viewer's face image, and determines whether to turn on the caption enlargement function according to the face image information.
  • the distance between the viewer and the television according to the size of the face image information in the captured image in the captured viewer image can be preferentially prioritized. Judging, if the distance between the viewer and the television is less than the clear viewing distance, it can be considered that the viewer does not need to turn on the subtitle zooming function, and the caption zooming function is not turned on, and the clear viewing distance can be tested according to the size of the television.
  • the caption zoom function is determined, and one method is: acquiring whether the viewer presets It is necessary to wear a glasses viewing mark. If the mark is that the viewer needs to wear the glasses to watch the movie, the caption zoom function is turned on. If not, the caption zoom function is not turned on, and another method is: acquiring the face image preset by the viewer. Information, by identifying the face image information preset by the viewer, determining whether the viewer wears the glasses in the face image information preset by the viewer, and if so, turning on the caption zoom function; otherwise, the caption is not turned on. Zoom in function.
  • Step S200 When the subtitle enlargement function is turned on, the subtitle area in the current display screen is identified and acquired.
  • the current display screen is identified, and the subtitle area in the current display screen is obtained, where the subtitle area is the display area of the subtitle in the current display screen, and the identification may be recognized to ensure the accuracy of the subtitle area identification.
  • the subtitle area is marked, and it is confirmed by the viewer whether the subtitle area is recognized accurately.
  • Step S300 the subtitles in the subtitle area are enlarged, and the subtitle area after the subtitles are enlarged is generated.
  • Enlarging the subtitle in the subtitle area according to the subtitle area, and generating a subtitle area after subtitle enlargement, the method of enlarging the subtitle in the subtitle area comprises: enlarging an area of the subtitle area and enclosing the subtitle area Subtitles use larger fonts.
  • step S400 the subtitle area enlarged by the subtitle is superimposed with the current display screen to generate a new display screen and displayed.
  • a preferred embodiment includes: superimposing the subtitle area of the subtitle to be superimposed In the current display screen, the superimposed area is an area in which the original subtitle area is in the current display screen.
  • the specific implementation manner of this embodiment includes:
  • the subtitle area of the current picture is identified and detected through the current picture; secondly, according to the area of the current subtitle area, a different enlargement ratio is selected to enlarge the subtitle area, and the enlarged subtitle area is generated.
  • the subtitle area enlarged by the subtitle is superimposed on the current display screen, and the screen on which the enlarged subtitle area is superimposed is displayed.
  • the caption zoom function when the viewer face image information is captured and recognized, and the caption zoom function needs to be turned on according to the face image information, the caption region in the current display screen is identified and acquired, and the caption region in the caption region is The subtitle is enlarged, and the enlarged subtitle area is superimposed with the current display screen to generate a display screen of the subtitle enlarged display, so that the television can automatically judge the current viewing environment of the viewer, and determine that the viewer needs to be turned on.
  • the subtitle zoom function is enabled, the subtitle zoom function is turned on, and the size of the subtitle in the subtitle area in the display screen is enlarged, so that the viewer can clearly see the subtitle when watching the movie.
  • a second embodiment of the method for intelligently adjusting the size of a subtitle according to the present invention is based on the embodiment shown in FIG. 1, and the step S300 is to enlarge the subtitle in the subtitle area to generate an enlarged subtitle.
  • the subtitle area includes:
  • Step S301 Perform subtitle recognition on the subtitle area by using a preset subtitle recognition algorithm to obtain a range of subtitle parts and subtitle information in the subtitle area.
  • Performing subtitle recognition on the subtitle area by using a preset subtitle recognition algorithm acquiring a range of subtitle parts in the subtitle area, and subtitle information, where the subtitle information includes: subtitle content and font size.
  • Step S302 filling a range of the subtitle part in the subtitle area according to a preset filling algorithm to generate a first image.
  • Generating a first image by filling a range of the subtitle portion in the subtitle region by a preset padding algorithm, where the padding algorithm may specifically obtain a pixel pair of the subtitle portion in the subtitle region
  • the range is filled to generate a first image, and further, to ensure a filling effect, the generated first image is further processed by a blurring process.
  • Step S303 the subtitles in the subtitle information are enlarged according to the subtitle information to generate a second image.
  • the zoomed magnification ratio may be preset by a viewer or a television manufacturer, and further, the zoomed magnification ratio is further
  • the length of the current subtitle, the subtitle area size, and the subtitle size can be dynamically adjusted. It can be understood that if the text portion in the subtitle area is directly enlarged, the enlarged subtitle blurring problem may occur, and thus, the present invention
  • the preferred embodiment can output the enlarged font size according to the subtitle content in the subtitle information by using the preset font, so that the enlarged subtitle is still clear when displayed.
  • Step S304 superimposing the first image and the second image to generate a subtitle region after the subtitle is enlarged.
  • subtitle recognition is performed on the current subtitle area, and the subtitle area and the non-subtitle are separated, and the current image picture described above is divided into non-subtitle area images and subtitles by deducting the recognized subtitle information.
  • Zone image two parts
  • the pixel value of the non-subtitle area of the second image is retained, and the pixel value in the subtitle area is set to zero;
  • the setting of the non-subtitle area of the second image is zero, and the pixel value in the subtitle area is retained.
  • the subtitle area image is enlarged to a certain extent to obtain a third image
  • the enlargement ratio it may be fixed in advance, or may be dynamically adjusted according to the length and size of the current subtitle;
  • the obtained second image and the third image are superimposed to obtain a subtitle region after the subtitle is enlarged, and the subtitle region after the subtitle is enlarged only enlarges the subtitle without changing the non-subtitle content.
  • the subtitle part in the subtitle area is recognized by the subtitle recognition algorithm, and the subtitle information is obtained, and the subtitle part in the subtitle area is obtained.
  • the subtitle area display is unclear or there are problems such as empty pixels and ghosting.
  • a third embodiment of the method for intelligently adjusting the size of a subtitle according to the present invention based on the embodiment shown in FIG. 1 above, the step S200, when the subtitle enlargement function is turned on, identifies and acquires the current display image.
  • the subtitle area includes:
  • Step S201 Identify, according to the preset location information, whether an area corresponding to the preset location information in the current display picture is a subtitle area, and if yes, acquire a subtitle area in the current picture, otherwise, use a preset algorithm to view the current display picture.
  • the subtitle area is identified to obtain a subtitle area in the current display screen.
  • the subtitle area in the video is basically fixed, as shown in FIG. 5, so in order to reduce the calculation amount in the subtitle area recognition and improve the subtitle area recognition efficiency, the current display screen can be identified according to the preset position information. Whether the area corresponding to the preset position information is a subtitle area, and if yes, acquiring the subtitle area in the current picture; otherwise, the subtitle area in the current display picture is identified by a preset algorithm, and the subtitle area in the current display picture is obtained. It can be understood that the preset location information can be added by the viewer or preset by the TV manufacturer.
  • the horizontal subtitle area is used as the primary subtitle area
  • the right vertical subtitle area is used as the secondary subtitle area.
  • the specific implementation steps include:
  • the area corresponding to the preset subtitle area position information is first identified. Recognizing that the area corresponding to the preset subtitle area position information is the subtitle area, the current subtitle area is acquired, and after identifying the area corresponding to the position information of all the preset subtitle areas, the entire area of the current display screen is identified to obtain the subtitle area, so that the subtitle area is obtained.
  • the recognition operation amount is reduced in the process of subtitle area recognition, and the subtitle area recognition efficiency is improved.
  • a fourth embodiment of the method for intelligently adjusting the size of a subtitle according to the present invention based on the embodiment shown in FIG. 1, the step S100, the television acquires the face image information of the viewer, and according to the Describe the face image information to determine whether to enable the caption zooming function includes:
  • Step S101 the television captures a face image of the viewer, and recognizes and acquires face image information in the face image of the viewer through a face recognition algorithm.
  • the television captures a viewer's face image through the mounted camera, and recognizes face image information in the viewer's face image by a face recognition algorithm, and simultaneously acquires the face image information.
  • Step S102 determining, according to the face image information, whether the viewer needs to enable the caption zooming function.
  • the viewer's user information may further include whether the viewer has the permission information to enable the caption zoom function, if the viewer does not have the caption enabled The zoom function does not enable the caption zoom function. Further, the viewer's user information may further include whether the viewer is allowed to enable the caption zoom function. If not, the caption zoom function is not enabled.
  • Step S103 when it is determined that the viewer needs to enable the caption zooming function, determine whether the viewer wears glasses according to the face image information, and if so, does not turn on the caption zoom function; otherwise, the caption zoom function is turned on.
  • step S102 and step S103 a specific implementation step is shown in FIG. 7, and includes:
  • the caption zoom function needs to be turned on. Otherwise, the caption zoom function does not need to be turned on.
  • the user's face image is captured.
  • the current user has already registered in the system, and directly enters step 2. Otherwise, the current user is registered, that is, when the user first uses the function, the user is prompted to collect the current user's face image.
  • the data is used as registration data. For example, when the user A registers, the user's face feature is retained and the registration information of the glasses is determined by the face feature. (When the first registration is performed, whether the current user A has glasses or not The user may prompt the user to actively input whether to bring glasses as registration information input. After the user registers, the face feature information and whether the information with glasses is stored in the system for subsequent comparison and determination as to whether to enable the automatic font enlargement function. condition;
  • the subtitle area of the current picture is automatically identified and detected through the current picture; secondly, according to the size and length of the current font area, different magnification ratios and display modes are selected;
  • the caption enlargement function is turned on, so that the judgment of whether the caption enlargement function needs to be turned on is more accurate, and the size of the font in the video screen can be automatically adjusted without changing the image content, and the font can be effectively enlarged without losing the screen content.
  • the television set includes:
  • the obtaining judgment module 100 is configured to acquire the face image information of the viewer, and determine whether to open the caption zooming function according to the face image information.
  • the television acquires the face image information in the viewer's face image, and determines whether to turn on the caption enlargement function according to the face image information.
  • the distance between the viewer and the television according to the size of the face image information in the captured image in the captured viewer image can be preferentially prioritized. Judging, if the distance between the viewer and the television is less than the clear viewing distance, it can be considered that the viewer does not need to turn on the subtitle zooming function, and the caption zooming function is not turned on, and the clear viewing distance can be tested according to the size of the television.
  • the caption zoom function is determined, and one method is: acquiring whether the viewer presets It is necessary to wear a glasses viewing mark. If the mark is that the viewer needs to wear the glasses to watch the movie, the caption zoom function is turned on. If not, the caption zoom function is not turned on, and another method is: acquiring the face image preset by the viewer. Information, by identifying the face image information preset by the viewer, determining whether the viewer wears the glasses in the face image information preset by the viewer, and if so, turning on the caption zoom function; otherwise, the caption is not turned on. Zoom in function.
  • the subtitle area identifying module 200 is configured to identify and acquire a subtitle area in the current display screen when the subtitle enlarging function is turned on.
  • the current display screen is identified, and the subtitle area in the current display screen is obtained, where the subtitle area is the display area of the subtitle in the current display screen, and the identification may be recognized to ensure the accuracy of the subtitle area identification.
  • the subtitle area is marked, and it is confirmed by the viewer whether the subtitle area is recognized accurately.
  • the subtitle area enlargement module 300 is configured to enlarge the subtitles in the subtitle area, and generate a subtitle area after the subtitles are enlarged.
  • Enlarging the subtitle in the subtitle area according to the subtitle area, and generating a subtitle area after subtitle enlargement, the method of enlarging the subtitle in the subtitle area comprises: enlarging an area of the subtitle area and enclosing the subtitle area Subtitles use larger fonts.
  • the display screen generating module 400 is configured to superimpose the subtitle area enlarged by the subtitle and the current display screen to generate a new display screen and display the same.
  • a preferred embodiment includes: superimposing the subtitle area of the subtitle to be superimposed In the current display screen, the superimposed area is an area in which the original subtitle area is in the current display screen.
  • the specific implementation manner of this embodiment includes:
  • the subtitle area of the current picture is identified and detected through the current picture; secondly, according to the area of the current subtitle area, a different enlargement ratio is selected to enlarge the subtitle area, and the enlarged subtitle area is generated.
  • the subtitle area enlarged by the subtitle is superimposed on the current display screen, and the screen on which the enlarged subtitle area is superimposed is displayed.
  • the caption zoom function when the viewer face image information is captured and recognized, and the caption zoom function needs to be turned on according to the face image information, the caption region in the current display screen is identified and acquired, and the caption region in the caption region is The subtitle is enlarged, and the enlarged subtitle area is superimposed with the current display screen to generate a display screen of the subtitle enlarged display, so that the television can automatically judge the current viewing environment of the viewer, and determine that the viewer needs to be turned on.
  • the subtitle zoom function is enabled, the subtitle zoom function is turned on, and the size of the subtitle in the subtitle area in the display screen is enlarged, so that the viewer can clearly see the subtitle when watching the movie.
  • the caption area amplifying module 300 includes:
  • the subtitle area analyzing unit 301 is configured to perform subtitle recognition on the subtitle area by using a preset subtitle identification algorithm to obtain a range of subtitle parts and subtitle information in the subtitle area.
  • Performing subtitle recognition on the subtitle area by using a preset subtitle recognition algorithm acquiring a range of subtitle parts in the subtitle area, and subtitle information, where the subtitle information includes: subtitle content and font size.
  • the first image generating unit 302 is configured to fill a range of the caption portion in the caption region according to a preset padding algorithm to generate a first image.
  • Generating a first image by filling a range of the subtitle portion in the subtitle region by a preset padding algorithm, where the padding algorithm may specifically obtain a pixel pair of the subtitle portion in the subtitle region
  • the range is filled to generate a first image, and further, to ensure a filling effect, the generated first image is further processed by a blurring process.
  • the second image generating unit 303 is configured to enlarge the subtitles in the subtitle information according to the subtitle information to generate a second image.
  • the zoomed magnification ratio may be preset by a viewer or a television manufacturer, and further, the zoomed magnification ratio is further
  • the length of the current subtitle, the subtitle area size, and the subtitle size can be dynamically adjusted. It can be understood that if the text portion in the subtitle area is directly enlarged, the enlarged subtitle blurring problem may occur, and thus, the present invention
  • the preferred embodiment can output the enlarged font size according to the subtitle content in the subtitle information by using the preset font, so that the enlarged subtitle is still clear when displayed.
  • the subtitle area generating unit 304 is configured to superimpose the first image and the second image to generate a subtitle area after the subtitle is enlarged.
  • subtitle recognition is performed on the current subtitle area, and the subtitle area and the non-subtitle are separated, and the current image picture described above is divided into non-subtitle areas by deducting the recognized subtitle information.
  • Image and subtitle area image
  • the pixel value of the non-subtitle area of the second image is retained, and the pixel value in the subtitle area is set to zero;
  • the setting of the non-subtitle area of the second image is zero, and the pixel value in the subtitle area is retained.
  • the subtitle area image is enlarged to a certain extent to obtain a third image
  • the enlargement ratio it may be fixed in advance, or may be dynamically adjusted according to the length and size of the current subtitle;
  • the obtained second image and the third image are superimposed to obtain a subtitle region after the subtitle is enlarged, and the subtitle region after the subtitle is enlarged only enlarges the subtitle without changing the non-subtitle content.
  • the subtitle part in the subtitle area is recognized by the subtitle recognition algorithm, and the subtitle information is obtained, and the subtitle part in the subtitle area is obtained.
  • the subtitle area display is unclear or there are problems such as empty pixels and ghosting.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Controls And Circuits For Display Device (AREA)
  • Studio Circuits (AREA)

Abstract

公开了一种智能调节字幕大小的方法,电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。还公开了一种电视机,能自动调节视频画面中的字体的大小而不改变图像内容的效果,在用户观看电影的时,能有效的放大字体而不损失画面内容,使得用户无须佩戴眼镜或者手动改变字幕大小,即可以清楚的看到显示画面中的字幕内容,有效的提高了用户体验。

Description

智能调节字幕大小的方法及电视机
技术领域
本发明涉及电视领域,尤其涉及智能调节字幕大小的方法及电视机。
背景技术
在视频播放系统中,电视机作为一个客厅的显示器件,在客厅文化中扮演者重要角色,然而客厅作为一个放松的环境,许多用户喜欢随性随意通过电视观看节目,其中这部分包含了大部分的近视用户,这部分用户需要瞪大眼睛或者半眯着眼睛才能看清楚屏幕上的字幕,特别是在近视者用户不带眼睛的情况下表现的尤为突出。
在现有技术中,用户可以通过手动调节显示屏显示字体的大小,同时也会带来画面的放大或者缩小,也可以通过起身寻找并佩戴眼睛的方式解决上述问题,但上述都属于用户自主(主动模式)去改变自身或者字体的大小,给用户观影制造了麻烦,为用户使用带来了不便。
发明内容
本发明的主要目的在于提供一种智能调节字幕大小的方法,旨在解决患有近视的用户在观影时需要手动调节显示屏显示字体大小的技术问题。
为实现上述目的,本发明提供一种智能调节字幕大小的方法,所述智能调节字幕大小的方法包括以下步骤:
电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域;
通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息;根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像;根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像;将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域;
将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
优选地,所述电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能的步骤包括:
电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
优选地,所述根据所述人脸图像信息判断所述用户是否需要开启字幕放大功能的步骤包括:
根据所述人脸图像信息获取所述观看者的用户信息;
判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
为实现上述目的,本发明提供一种智能调节字幕大小的方法,所述智能调节字幕大小的方法包括以下步骤:
电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;
放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;
将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
优选地,所述放大所述字幕区域中的字幕,生成字幕放大后的字幕区域的步骤包括:
通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息;
根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像;
根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像;
将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域。
优选地,所述当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域的步骤包括:
根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域。
优选地,所述电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能的步骤包括:
电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
优选地,所述根据所述人脸图像信息判断所述用户是否需要开启字幕放大功能的步骤包括:
根据所述人脸图像信息获取所述观看者的用户信息;
判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
此外,为实现上述目的,本发明还提供一种电视机,所述电视机包括:
获取判断模块,用于获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
字幕区域识别模块,用于当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;
字幕区域放大模块,用于放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;
显示画面生成模块,用于将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
本发明实施例提出的一种智能调节字幕大小的方法及电视机,通过获取观影用户的人脸图像信息,并对所述人脸图像信息进行判断,当判断到需要开启字幕放大功能时,识别并获取当前显示画面中的字幕区域,将字幕区域进行放大后与当前显示画面叠加,生成并显示叠加后的显示画面,实现了自动检测观影用户状态,当判断到所述观影用户需要字幕放大功能时,放大显示画面中的字幕部分,使观影用户可以清楚的看到显示画面中的字幕内容,避免了观影用户手动设置放大字体。
附图说明
图1为本发明智能调节字幕大小的方法的第一实施例的流程示意图;
图2为本发明智能调节字幕大小的方法的第二实施例的流程示意图;
图3为本发明一种具体实施方式具体实施步骤流程示意图;
图4为本发明智能调节字幕大小的方法的第三实施例的流程示意图;
图5为一种电视机显示界面中字幕内容常在区域示意图;
图6为本发明智能调节字幕大小的方法的第四实施例的流程示意图;
图7为本发明又一种具体实施方式具体实施步骤流程示意图;
图8为本发明另一种具体实施方式具体实施步骤流程示意图;
图9为本发明电视机第一实施例的功能模块示意图;
图10为本发明电视机第二实施例的功能模块示意图。
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
本发明实施例的主要解决方案是:电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
由于现有技术需要用户手动设置开启字体放大功能,对用户观影过程造成了不便。
本发明提供一种解决方案,使用户在观影时,电视机可根据用户当前状态自动开启字幕放大功能,减少了用户观影时的手动操作过程。
参照图1,本发明智能调节字幕大小的方法的第一实施例,所述智能调节字幕大小的方法包括:
步骤S100,电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能。
用户观影时,电视机获取所述观看者脸部图像中的人脸图像信息,根据所述人脸图像信息判断是否开启字幕放大功能。
可以理解的,所述根据人脸图像信息判断是否开启字幕放大功能,可以优先根据拍摄到的观看者图像中人脸图像信息在所述拍摄画面中的大小对观看者与电视机之间的距离进行判断,若观看者与电视机之间的距离小于清楚观看距离,则可以认为观看者不需要开启字幕放大功能,则不开启字幕放大功能,所述清楚观看距离可根据电视机尺寸进行试验得出;
进一步的,当所述观看者与电视机之间的距离大于清楚观看距离时,则根据所述观看者的人脸图像信息判断观看者是否佩戴有眼镜,若观看者已佩戴眼镜,则不开启字幕放大功能;
进一步的,当根据所述观看者的人脸图像信息判断到所述观看者未佩戴眼镜时,则对观看者是否需要开启字幕放大功能进行判断,一种方法为:获取观看者预设的是否需要佩戴眼镜观影标记,若所述标记为观看者需要佩戴眼镜观影,则开启字幕放大功能,若否,则不开启字幕放大功能,另一方法为:获取观看者预设的人脸图像信息,通过对观看者预设的人脸图像信息进行识别,判断观看者预设的人脸图像信息中,所述观看者是否佩戴有眼镜,若是,则开启字幕放大功能,否则,不开启字幕放大功能。
步骤S200,当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域。
当开启字幕放大功能时,对当前显示画面进行识别,获取当前显示画面中的字幕区域,所述字幕区域为当前显示画面中字幕的显示区域,为保证字幕区域识别的准确度,可将识别的字幕区域进行标记,由观看者确认字幕区域是否识别准确。
步骤S300,放大所述字幕区域中的字幕,生成字幕放大后的字幕区域。
根据所述字幕区域放大所述字幕区域中的字幕,并生成经过字幕放大后的字幕区域,所述放大所述字幕区域中的字幕的方法包括:对字幕区域的面积进行放大和将字幕区域里的字幕使用更大的字体。
步骤S400,将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
将所述字幕放大后的字幕区域与当前显示画面进行叠加,生成新的显示画面,并显示叠加后的显示画面,一种较佳的实施方式包括:将所述字幕放大后的字幕区域叠加到当前显示画面中,叠加区域为原字幕区域在所述当前显示画面中的区域。
具体实施时,本实施例具体实施方式包括:
1、拍摄用户脸部图像,通过对拍摄的用户脸部图像进行人脸识别,并判断当前用户是否带有眼镜;
2、基于观看者与电视机之间的距离及当前用户是否带有眼镜的检测结果,自适应地应用字体是否放大功能;
3、在应用字体是否放大功能中,首先要通过当前画面,识别并检测到当前画面的字幕区域;其次根据对当前字幕区域的面积,选择不同的放大比例对字幕区域进行放大,生成放大后的字幕区域;
4、将所述字幕放大后的字幕区域叠加到当前显示画面中,显示叠加有放大后的字幕区域的画面。
在本实施例中,通过拍摄并识别获取观看者人脸图像信息,根据人脸图像信息判断到需要开启字幕放大功能时,识别并获取当前显示画面中的字幕区域,对所述字幕区域中的字幕进行放大,并将放大后的字幕区域与当前显示画面叠加,生成字幕放大后的显示画面并显示,使得电视机可以自动对观看者当前观影环境进行判断,并且在判断到观看者需要开启字幕放大功能时开启字幕放大功能,放大显示画面中的字幕区域中字幕的大小,使观看者观影时可以清晰的看到字幕。
进一步的,参照图2,本发明智能调节字幕大小的方法的第二实施例,基于上述图1所示的实施例,所述步骤S300,放大所述字幕区域中的字幕,生成字幕放大后的字幕区域包括:
步骤S301,通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息。
通过预设字幕识别算法对所述字幕区域进行字幕识别,获取所述字幕区域中字幕部分的范围,及字幕信息,所述字幕信息包括:字幕内容及字体大小。
步骤S302,根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像。
通过预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像,所述填充算法具体可以通过获取所述字幕区域中所述字幕部分的范围周边的像素对所述字幕部分的范围进行填充生成第一图像,进一步的,为了保证填充效果,通过模糊处理对所述生成的第一图像进行进一步处理。
步骤S303,根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像。
根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像,其中,所述放大的放大比例可由观看者或电视机生产厂商预设,进一步的,所述放大的放大比例还可以通过当前字幕的长度、字幕区域大小及字幕大小进行动态调整,可以理解的,若直接对字幕区域中文本部分进行放大,则可能出现放大后的字幕模糊等问题,因此,本发明的一种较佳实施方式可以根据字幕信息中的字幕内容采用预设字体使用放大后的字号进行输出,进而使得显示时放大后的字幕依然清晰。
步骤S304,将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域。
将所述第一图像与第二图像叠加,即将所述第二图像叠加到所述第一图像中,生成字幕放大后的字幕区域,所述字幕区域中仅对字幕部分进行放大,非字幕部分未进行放大。
具体实施时,本实施例的具体实施步骤如图3所示,包括:
1、在当前显示画面即第一图像中,自动检测当前画面的字幕区域,并判断当前区域是否存在字幕信息;
2、在字幕区域内,对当前字幕区域进行字幕识别,并将字幕区域和非字幕分割开来,依靠扣出识别出来的字幕信息,将上述所述的当前图像画面分成非字幕区图像和字幕区图像两部分,
对于非字幕区图像,具有如下特点,保留第二图像的非字幕区域的像素值,对于字幕区域内的像素值则设置为零;
对于字幕区图像,具有如下特点,对于第二图像的非字幕区域的设置为零,对于字幕区域内的像素值则保留。
3、对于非字幕区图像,对图像中进行孔洞填充操作,即该图像中字幕区域位置像素上(以上因字幕区域设置位零的位置)依靠周边像素进行内容填充,完成孔洞填充操作,得到第三图像;
对于字幕区域图像,对字幕区域图像进行一定程度的放大,得到第三图像;
其中,对于放大比例,可以预先固定,也可以根据当前字幕的长度以及大小进行动态调整;
4、将得到的第二图像与第三图像进行叠加,得到字幕放大后的字幕区域,该字幕放大后的字幕区域仅仅对字幕进行放大而不改变非字幕内容。
在本实施例中,基于上一实施例所述的优点,本实施例在对字幕区域进行放大时,通过字幕识别算法,识别字幕区域中的字幕部分并获得字幕信息,对字幕区域中字幕部分采用周边像素进行填充生成第一图像,对字幕部分内容进行放大,生成第二图像,叠加第一图像和第二图像生成字幕放大后的字幕区域,提高了叠加后的字幕区域质量,避免显示时字幕区域显示不清楚或出现空像素、重影等问题。
进一步的,参照图4,本发明智能调节字幕大小的方法的第三实施例,基于上述图1所示的实施例,所述步骤S200,当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域包括:
步骤S201,根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域。
由于播放大部分视频时,视频中的字幕区域基本固定,如图5所示,因此为减少字幕区域识别时的运算量,提高字幕区域识别效率,可根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域,可以理解的,所述预设位置信息可由观看者添加或电视机生产厂商预置。
进一步的,具体实施时,如图5所示,将横向字幕区域作为主要字幕区域,而右侧竖向字幕区域作为次要字幕区域,具体实施步骤包括:
根据主要字幕区域位置信息识别当前显示换面中所述主要字幕区域位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,若否,则根据次要字幕区域位置信息识别当前显示换面中所述次要字幕区域位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,若否,则通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域。
在本实施例中,基于上一实施例所述的优点,本实施例中,通过预设字幕区域位置信息,在对字幕区域进行识别时,首先识别预设字幕区域位置信息对应的区域,若识别到预设字幕区域位置信息对应的区域为字幕区域则获取当前字幕区域,对所有预设字幕区域位置信息对应的区域识别完后,在对当前显示画面整个区域进行识别从而获得字幕区域,使得在字幕区域识别的过程中减少了识别运算量,同时提高了字幕区域识别效率。
进一步的,参照图6,本发明智能调节字幕大小的方法的第四实施例,基于上述图1所示的实施例,所述步骤S100,电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能包括:
步骤S101,电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息。
电视机通过搭载的摄像头拍摄观看者脸部图像,并通过人脸识别算法识别所述观看者的脸部图像中的人脸图像信息,同时获取所述人脸图像信息。
步骤S102,根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能。
根据所述人脸图像信息获取所述观看者的用户信息;判断所述用户信息中所述观看者预设的人脸图像信息是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能,可以理解的,所述观看者的用户信息中还可以包括观看者是否具有开启字幕放大功能的权限信息,若观看者不具有开启字幕放大功能,则不开启字幕放大功能,进一步的,所述观看者的用户信息中还可以包括观看者是否允许开启字幕放大功能,若不允许,则不开启字幕放大功能。
步骤S103,当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
本实施例中,针对步骤S102和步骤S103,一种具体实施步骤如图7所示,包括:
1、对拍摄的当前用户脸部图像进行人脸识别,将检测到的用户人脸,与系统中的前期入库(系统中的注册过的人脸数据库)的真实人脸的照片做人脸识别,判断当前获取的图像信息中,是否存在当前用户的人脸;
2、存在当前用户的人脸,且带有眼镜;
3、通过是否带有眼睛模块的计算分析,对当前人脸进行是否带有眼镜的识别分析,并给出识别结果;
4、若识别结果是当前用户未带有眼镜,则需要开启字幕放大功能,否则,不需要开启字幕放大功能。
本实施例具体实施时,具体实施步骤如图8所示,包括:
1、拍摄用户脸部图像,当前用户已经在系统中注册,直接进入步骤2,反之,则对当前用户进行注册,即当用户第一次使用该功能时,提示用户采集当前用户的人脸图像数据作为注册数据,如当用户A注册后,保留用户A的人脸特征以及依靠该人脸特征判断出是否带有眼镜的注册信息,(第一次注册时,当前用户A是否带有眼镜也可由用户提示用户主动输入是否带眼镜作为注册信息输入),该用户注册后,人脸特征信息以及是否带有眼镜的信息存储在系统中,以便后续进行对比和作为是否开启字体自动放大功能的判别条件;
2、通过对拍摄的用户脸部图像进行人脸识别,并判断当前用户是否带有眼镜;
3、基于当前用户是否带有眼镜的检测结果,自适应地应用字体是否放大功能;
4、在应用字体是否放大功能中,首先要通过当前画面,自动识别并检测到当前画面的字幕区域;其次根据对当前字体区域的大小及长度,选择不同的放大比例及显示方式;
5、将放大后的字幕区域与图像进行叠加,显示放大后的界面。
在本实施例中,基于上一实施例所述的优点,通过对观看者保存的图像与当前观影时观看者图像进行对比,判断到观看者平时佩戴眼镜,但此次观影时未佩戴眼镜时,开启字幕放大功能,使得对是否需要开启字幕放大功能的判断更为准确,且能够自动调节视频画面中的字体的大小而不改变图像内容,并能有效的放大字体而不损失画面内容。
参照图9,本发明电视机的第一实施例,所述电视机包括:
获取判断模块100,用于获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能。
用户观影时,电视机获取所述观看者脸部图像中的人脸图像信息,根据所述人脸图像信息判断是否开启字幕放大功能。
可以理解的,所述根据人脸图像信息判断是否开启字幕放大功能,可以优先根据拍摄到的观看者图像中人脸图像信息在所述拍摄画面中的大小对观看者与电视机之间的距离进行判断,若观看者与电视机之间的距离小于清楚观看距离,则可以认为观看者不需要开启字幕放大功能,则不开启字幕放大功能,所述清楚观看距离可根据电视机尺寸进行试验得出;
进一步的,当所述观看者与电视机之间的距离大于清楚观看距离时,则根据所述观看者的人脸图像信息判断观看者是否佩戴有眼镜,若观看者已佩戴眼镜,则不开启字幕放大功能;
进一步的,当根据所述观看者的人脸图像信息判断到所述观看者未佩戴眼镜时,则对观看者是否需要开启字幕放大功能进行判断,一种方法为:获取观看者预设的是否需要佩戴眼镜观影标记,若所述标记为观看者需要佩戴眼镜观影,则开启字幕放大功能,若否,则不开启字幕放大功能,另一方法为:获取观看者预设的人脸图像信息,通过对观看者预设的人脸图像信息进行识别,判断观看者预设的人脸图像信息中,所述观看者是否佩戴有眼镜,若是,则开启字幕放大功能,否则,不开启字幕放大功能。
字幕区域识别模块200,用于当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域。
当开启字幕放大功能时,对当前显示画面进行识别,获取当前显示画面中的字幕区域,所述字幕区域为当前显示画面中字幕的显示区域,为保证字幕区域识别的准确度,可将识别的字幕区域进行标记,由观看者确认字幕区域是否识别准确。
字幕区域放大模块300,用于放大所述字幕区域中的字幕,生成字幕放大后的字幕区域。
根据所述字幕区域放大所述字幕区域中的字幕,并生成经过字幕放大后的字幕区域,所述放大所述字幕区域中的字幕的方法包括:对字幕区域的面积进行放大和将字幕区域里的字幕使用更大的字体。
显示画面生成模块400,用于将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
将所述字幕放大后的字幕区域与当前显示画面进行叠加,生成新的显示画面,并显示叠加后的显示画面,一种较佳的实施方式包括:将所述字幕放大后的字幕区域叠加到当前显示画面中,叠加区域为原字幕区域在所述当前显示画面中的区域。
具体实施时,本实施例具体实施方式包括:
1、拍摄用户脸部图像,通过对拍摄的用户脸部图像进行人脸识别,并判断当前用户是否带有眼镜;
2、基于观看者与电视机之间的距离及当前用户是否带有眼镜的检测结果,自适应地应用字体是否放大功能;
3、在应用字体是否放大功能中,首先要通过当前画面,识别并检测到当前画面的字幕区域;其次根据对当前字幕区域的面积,选择不同的放大比例对字幕区域进行放大,生成放大后的字幕区域;
4、将所述字幕放大后的字幕区域叠加到当前显示画面中,显示叠加有放大后的字幕区域的画面。
在本实施例中,通过拍摄并识别获取观看者人脸图像信息,根据人脸图像信息判断到需要开启字幕放大功能时,识别并获取当前显示画面中的字幕区域,对所述字幕区域中的字幕进行放大,并将放大后的字幕区域与当前显示画面叠加,生成字幕放大后的显示画面并显示,使得电视机可以自动对观看者当前观影环境进行判断,并且在判断到观看者需要开启字幕放大功能时开启字幕放大功能,放大显示画面中的字幕区域中字幕的大小,使观看者观影时可以清晰的看到字幕。
进一步的,参照图10,本发明电视机的第二实施例,基于上述图9所示的实施例,所述字幕区域放大模块300包括:
字幕区域分析单元301,用于通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息。
通过预设字幕识别算法对所述字幕区域进行字幕识别,获取所述字幕区域中字幕部分的范围,及字幕信息,所述字幕信息包括:字幕内容及字体大小。
第一图像生成单元302,用于根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像。
通过预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像,所述填充算法具体可以通过获取所述字幕区域中所述字幕部分的范围周边的像素对所述字幕部分的范围进行填充生成第一图像,进一步的,为了保证填充效果,通过模糊处理对所述生成的第一图像进行进一步处理。
第二图像生成单元303,用于根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像。
根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像,其中,所述放大的放大比例可由观看者或电视机生产厂商预设,进一步的,所述放大的放大比例还可以通过当前字幕的长度、字幕区域大小及字幕大小进行动态调整,可以理解的,若直接对字幕区域中文本部分进行放大,则可能出现放大后的字幕模糊等问题,因此,本发明的一种较佳实施方式可以根据字幕信息中的字幕内容采用预设字体使用放大后的字号进行输出,进而使得显示时放大后的字幕依然清晰。
字幕区域生成单元304,用于将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域。
将所述第一图像与第二图像叠加,即将所述第二图像叠加到所述第一图像中,生成字幕放大后的字幕区域,所述字幕区域中仅对字幕部分进行放大,对非字幕部分未进行放大。
具体实施时,本实施例的具体实施步骤如图3所示,包括:
1、在当前显示画面即第一图像中,自动检测当前画面的字幕区域,并判断当前区域是否存在字幕信息;
2、在字幕区域内,对当前字幕区域进行字幕识别,并将字幕区域和非字幕分割开来,依靠扣出识别出来的字幕信息,将上述所述的当前图像画面分成非字幕区 图像和字幕区图像两部分,
对于非字幕区图像,具有如下特点,保留第二图像的非字幕区域的像素值,对于字幕区域内的像素值则设置为零;
对于字幕区图像,具有如下特点,对于第二图像的非字幕区域的设置为零,对于字幕区域内的像素值则保留。
3、对于非字幕区图像,对图像中进行孔洞填充操作,即该图像中字幕区域位置像素上(以上因字幕区域设置位零的位置)依靠周边像素进行内容填充,完成孔洞填充操作,得到第三图像;
对于字幕区域图像,对字幕区域图像进行一定程度的放大,得到第三图像;
其中,对于放大比例,可以预先固定,也可以根据当前字幕的长度以及大小进行动态调整;
4、将得到的第二图像与第三图像进行叠加,得到字幕放大后的字幕区域,该字幕放大后的字幕区域仅仅对字幕进行放大而不改变非字幕内容。
在本实施例中,基于上一实施例所述的优点,本实施例在对字幕区域进行放大时,通过字幕识别算法,识别字幕区域中的字幕部分并获得字幕信息,对字幕区域中字幕部分采用周边像素进行填充生成第一图像,对字幕部分内容进行放大,生成第二图像,叠加第一图像和第二图像生成字幕放大后的字幕区域,提高了叠加后的字幕区域质量,避免显示时字幕区域显示不清楚或出现空像素、重影等问题。

Claims (18)

  1. 一种智能调节字幕大小的方法,其特征在于,所述智能调节字幕大小的方法包括以下步骤:
    电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
    根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域;
    通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息;根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像;根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像;将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域;
    将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
  2. 权利要求1所述的智能调节字幕大小的方法,其特征在于,所述电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能的步骤包括:
    电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  3. 权利要求2所述的智能调节字幕大小的方法,其特征在于,所述根据所述人脸图像信息判断所述用户是否需要开启字幕放大功能的步骤包括:
    根据所述人脸图像信息获取所述观看者的用户信息;
    判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
  4. 种智能调节字幕大小的方法,其特征在于,所述智能调节字幕大小的方法包括以下步骤:
    电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
    当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;
    放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;
    将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
  5. 权利要求4所述的智能调节字幕大小的方法,其特征在于,所述放大所述字幕区域中的字幕,生成字幕放大后的字幕区域的步骤包括:
    通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息;
    根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像;
    根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像;
    将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域。
  6. 权利要求4所述的智能调节字幕大小的方法,其特征在于,所述电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能的步骤包括:
    电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  7. 权利要求5所述的智能调节字幕大小的方法,其特征在于,所述电视机获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能的步骤包括:
    电视机拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  8. 权利要求6所述的智能调节字幕大小的方法,其特征在于,所述根据所述人脸图像信息判断所述用户是否需要开启字幕放大功能的步骤包括:
    根据所述人脸图像信息获取所述观看者的用户信息;
    判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
  9. 权利要求7所述的智能调节字幕大小的方法,其特征在于,所述根据所述人脸图像信息判断所述用户是否需要开启字幕放大功能的步骤包括:
    根据所述人脸图像信息获取所述观看者的用户信息;
    判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
  10. 种电视机,其特征在于,所述电视机包括:
    获取判断模块,用于获取观看者的人脸图像信息,并根据所述人脸图像信息判断是否开启字幕放大功能;
    字幕区域识别模块,用于当开启字幕放大功能时,识别并获取当前显示画面中的字幕区域;
    字幕区域放大模块,用于放大所述字幕区域中的字幕,生成字幕放大后的字幕区域;
    显示画面生成模块,用于将所述字幕放大后的字幕区域与当前显示画面进行叠加后生成新的显示画面并显示。
  11. 权利要求10所述的电视机,其特征在于,所述字幕区域放大模块包括:
    字幕区域分析单元,用于通过预设字幕识别算法对所述字幕区域进行字幕识别,获得所述字幕区域中字幕部分的范围及字幕信息;
    第一图像生成单元,用于根据预设填充算法填充所述字幕区域中所述字幕部分的范围,生成第一图像;
    第二图像生成单元,用于根据所述字幕信息对所述字幕信息中的字幕进行放大,生成第二图像;
    字幕区域生成单元,用于将所述第一图像与第二图像叠加,生成字幕放大后的字幕区域。
  12. 权利要求11所述的电视机,其特征在于,所述字幕区域识别模块包括:
    预设位置优先识别单元,用于根据预设位置信息识别当前显示画面中所述预设位置信息对应的区域是否为字幕区域,若是,则获取当前画面中的字幕区域,否则,通过预设算法对当前显示画面中的字幕区域进行识别,获取当前显示画面中的字幕区域。
  13. 权利要求10所述的电视机,其特征在于,所述获取判断模块包括:
    人脸图像信息获取单元,用于拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    用户功能判断单元,用于根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    功能开启判断单元,用于当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  14. 权利要求11所述的电视机,其特征在于,所述获取判断模块包括:
    人脸图像信息获取单元,用于拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    用户功能判断单元,用于根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    功能开启判断单元,用于当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  15. 权利要求12所述的电视机,其特征在于,所述获取判断模块包括:
    人脸图像信息获取单元,用于拍摄观看者的脸部图像,并通过人脸识别算法识别并获取所述观看者的脸部图像中的人脸图像信息;
    用户功能判断单元,用于根据所述人脸图像信息判断所述观看者是否需要开启字幕放大功能;
    功能开启判断单元,用于当判断到所述观看者需要开启字幕放大功能时,根据所述人脸图像信息判断所述观看者是否佩戴有眼镜,若是,则不开启字幕放大功能,否则,开启字幕放大功能。
  16. 权利要求13所述的电视机,其特征在于,所述用户功能判断单元包括:
    用户信息获取单元,用于根据所述人脸图像信息获取所述观看者的用户信息;
    开启判断单元,用于判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
  17. 权利要求14所述的电视机,其特征在于,所述用户功能判断单元包括:
    用户信息获取单元,用于根据所述人脸图像信息获取所述观看者的用户信息;
    开启判断单元,用于判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
  18. 权利要求15所述的电视机,其特征在于,所述用户功能判断单元包括:
    用户信息获取单元,用于根据所述人脸图像信息获取所述观看者的用户信息;
    开启判断单元,用于判断所述用户信息中所述观看者是否带有眼镜,若是,则判断所述观看者需要开启字幕放大功能,否则,判断所述观看者不需要开启字幕放大功能。
PCT/CN2016/084934 2016-04-18 2016-06-06 智能调节字幕大小的方法及电视机 WO2017181504A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610243428.8 2016-04-18
CN201610243428.8A CN105872845A (zh) 2016-04-18 2016-04-18 智能调节字幕大小的方法及电视机

Publications (1)

Publication Number Publication Date
WO2017181504A1 true WO2017181504A1 (zh) 2017-10-26

Family

ID=56632942

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/084934 WO2017181504A1 (zh) 2016-04-18 2016-06-06 智能调节字幕大小的方法及电视机

Country Status (2)

Country Link
CN (1) CN105872845A (zh)
WO (1) WO2017181504A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110248255A (zh) * 2019-06-13 2019-09-17 深圳市金锐显数码科技有限公司 一种字幕显示方法、字幕显示装置及终端

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109756788B (zh) * 2017-11-03 2022-08-23 腾讯科技(深圳)有限公司 视频字幕自动调整方法及装置、终端及可读存储介质
CN109141249B (zh) * 2018-08-07 2021-11-09 深圳Tcl数字技术有限公司 距离测量方法及计算机可读存储介质
CN109379631B (zh) * 2018-12-13 2020-11-24 广州艾美网络科技有限公司 一种通过移动终端编辑视频字幕的方法
CN109933266A (zh) * 2018-12-27 2019-06-25 维沃移动通信有限公司 一种显示方法及终端设备
CN111026316A (zh) * 2019-11-25 2020-04-17 维沃移动通信有限公司 一种图像显示方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7345684B2 (en) * 1998-06-25 2008-03-18 Intel Corporation Perceptually based display
CN101437121A (zh) * 2008-12-19 2009-05-20 中兴通讯股份有限公司 一种实现手机电视字幕动态缩放的移动终端及方法
US20090292988A1 (en) * 2008-05-20 2009-11-26 Hon Hai Precision Industry Co., Ltd. System and method for adjusting font size of information displayed in an electronic device
CN101866643A (zh) * 2009-01-27 2010-10-20 索尼爱立信移动通信日本株式会社 显示设备、显示控制方法和显示控制程序
CN103312863A (zh) * 2012-03-08 2013-09-18 中兴通讯股份有限公司 移动终端视频的呈现方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101630525A (zh) * 2009-07-07 2010-01-20 广州番禺巨大汽车音响设备有限公司 一种可动态调整字幕大小的便携式dvd系统及方法
CN102892039A (zh) * 2012-06-29 2013-01-23 广东九联科技股份有限公司 一种基于机顶盒的字幕放大方法
CN103903591A (zh) * 2012-12-25 2014-07-02 扬智科技股份有限公司 画面调整方法与装置以及显示装置
CN103648042A (zh) * 2013-11-27 2014-03-19 乐视致新电子科技(天津)有限公司 一种字符输出控制方法和装置
CN103731745A (zh) * 2013-11-27 2014-04-16 乐视致新电子科技(天津)有限公司 一种字符输出控制方法和装置
CN105094299B (zh) * 2014-05-14 2018-06-01 三星电子(中国)研发中心 控制电子装置的方法和设备
CN104125496A (zh) * 2014-07-07 2014-10-29 京东方科技集团股份有限公司 一种带有字幕信息的视频显示方法及显示装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7345684B2 (en) * 1998-06-25 2008-03-18 Intel Corporation Perceptually based display
US20090292988A1 (en) * 2008-05-20 2009-11-26 Hon Hai Precision Industry Co., Ltd. System and method for adjusting font size of information displayed in an electronic device
CN101437121A (zh) * 2008-12-19 2009-05-20 中兴通讯股份有限公司 一种实现手机电视字幕动态缩放的移动终端及方法
CN101866643A (zh) * 2009-01-27 2010-10-20 索尼爱立信移动通信日本株式会社 显示设备、显示控制方法和显示控制程序
CN103312863A (zh) * 2012-03-08 2013-09-18 中兴通讯股份有限公司 移动终端视频的呈现方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110248255A (zh) * 2019-06-13 2019-09-17 深圳市金锐显数码科技有限公司 一种字幕显示方法、字幕显示装置及终端

Also Published As

Publication number Publication date
CN105872845A (zh) 2016-08-17

Similar Documents

Publication Publication Date Title
WO2017181504A1 (zh) 智能调节字幕大小的方法及电视机
WO2018166224A1 (zh) 全景视频的目标追踪显示方法、装置及存储介质
WO2015142016A1 (ko) 컨텐츠의 재생 제어 방법 및 이를 수행하기 위한 컨텐츠 재생 장치
WO2017090837A1 (en) Digital photographing apparatus and method of operating the same
WO2017164716A1 (en) Method and device for processing multimedia information
WO2017107388A1 (zh) Hdmi版本切换方法及显示设备
WO2014042445A1 (en) Display apparatus and method for controlling display apparatus thereof
WO2019114269A1 (zh) 一种节目续播方法、电视设备及计算机可读存储介质
WO2020010671A1 (zh) 显示方法、装置以及电视机、存储介质
WO2019051683A1 (zh) 补光拍照方法、移动终端及计算机可读存储介质
WO2017215116A1 (zh) 智能电视的拍照方法及系统
WO2013166796A1 (zh) 自动识别3d视频播放模式的方法和装置
WO2017113614A1 (zh) 视频播放过程中插播广告的方法及装置
WO2018227869A1 (zh) 显示屏画面调整方法、显示终端及可读存储介质
WO2021261830A1 (en) Video quality assessment method and apparatus
WO2017181508A1 (zh) 多媒体会议控制方法及服务器
WO2016093510A1 (en) Display apparatus and display method
WO2019041851A1 (zh) 家电售后咨询方法、电子设备和计算机可读存储介质
WO2018032680A1 (zh) 音视频播放方法及系统
WO2018233221A1 (zh) 多窗口声音输出方法、电视机以及计算机可读存储介质
WO2017088437A1 (zh) 智能电视控制终端摄像头切换方法及装置
WO2018032679A1 (zh) 电视定时开关机的设置方法和装置
WO2018023925A1 (zh) 拍摄方法及系统
WO2018094812A1 (zh) 调节液晶显示装置屏幕背光亮度的方法及装置
WO2018018680A1 (zh) 应用提示信息显示方法及装置

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16899091

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16899091

Country of ref document: EP

Kind code of ref document: A1

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26.03.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16899091

Country of ref document: EP

Kind code of ref document: A1