WO2016188304A1 - 拍照的方法及装置 - Google Patents

拍照的方法及装置 Download PDF

Info

Publication number
WO2016188304A1
WO2016188304A1 PCT/CN2016/080762 CN2016080762W WO2016188304A1 WO 2016188304 A1 WO2016188304 A1 WO 2016188304A1 CN 2016080762 W CN2016080762 W CN 2016080762W WO 2016188304 A1 WO2016188304 A1 WO 2016188304A1
Authority
WO
WIPO (PCT)
Prior art keywords
state
photographing
smile
recognized
face
Prior art date
Application number
PCT/CN2016/080762
Other languages
English (en)
French (fr)
Inventor
钟宇恒
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2016188304A1 publication Critical patent/WO2016188304A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
    • G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
    • G03B15/00—Special procedures for taking photographs; Apparatus therefor
    • 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
    • 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

Definitions

  • This document relates to, but is not limited to, the field of communications, and in particular, to a method and apparatus for photographing.
  • photo taking is one of the most used applications for people, that is, taking pictures with a mobile phone or taking a selfie is the most people. Can not be separated from entertainment. Whether it is for the purpose of decompression, boring pastime, or teasing children, the main reason is to take the best moment. Often the photos are the same in the state of no mood, it is extremely tasteless and flat, not worth leaving precious memories, and it is not worth leaving images, so most of them are taken, deleted, and no fun. This reduces the experience of people taking pictures through the terminal, and in the limited memory space of the mobile phone, it is necessary to improve the quality.
  • the embodiment of the invention provides a method and a device for photographing, which can capture the best state of the photographed object when the terminal takes a photo.
  • a method for photographing including: recognizing a face state of the photographing object when the photographing object is photographed by a camera, wherein the face state includes a smile face a state and a non-smile state; determining whether to play a voice prompt sound for causing the photographic subject to present a smile state according to the recognized face state; and taking a photo of the photographic subject when the smile state of the photographing object is acquired.
  • determining, according to the recognized face state, whether to play the voice prompt sound for causing the photographic subject to present a smile state includes: when the face state is recognized as a smile state, prohibiting playing the voice prompt tone; When the face state is a non-smile state, the voice prompt tone is played.
  • the method further includes: when identifying a face state of the photographing object, The gender and/or age of the photographed subject is identified.
  • playing the voice prompt tone comprises: playing a voice prompt tone that matches the gender and/or age of the photographing object.
  • the photographing the photographing object comprises: continuously photographing the photographing object at a predetermined time interval until the photographing object is in a non-smile state.
  • an apparatus for photographing including:
  • the first identification module is configured to identify a face state of the camera object when the camera object is photographed by the camera, wherein the face state includes a smile state and a non-smile state; and the playing module is configured to The recognized face state determines whether to play a voice prompt sound for causing the subject to present a smile state;
  • the photographing module is configured to take a photo of the photographing object when the smile state of the photographing object is acquired.
  • the playing module includes:
  • the prohibiting unit is configured to prohibit playing the voice prompt tone when the face state is recognized as a smile state
  • the first playing unit is configured to play the voice prompt tone when the face state is recognized as a non-smile state.
  • the device further includes: a second identification module, configured to identify a gender and/or an age of the photographing object when the face state of the photographing object is recognized.
  • a second identification module configured to identify a gender and/or an age of the photographing object when the face state of the photographing object is recognized.
  • the playing module further includes: a second playing unit, configured to play a voice prompt sound that matches the gender and/or age of the photographing object when the face state is recognized as a non-smile state.
  • a second playing unit configured to play a voice prompt sound that matches the gender and/or age of the photographing object when the face state is recognized as a non-smile state.
  • the photographing module includes: a photographing unit configured to continuously photograph the photographing object at a predetermined time interval until the photographing object is in a non-smile state.
  • the state of the face of the photographing object is recognized, and according to the recognized state of the face, whether to play a voice prompt sound for causing the photographing object to present a smiling state is determined; Therefore, when the smiling state of the photographing object is acquired, the photographing object is photographed, that is, the photographing object is recognized before the photographing object is photographed.
  • the face state determines whether to play a voice prompt sound that prompts the photographing object to present a smile state, and directly take a photograph when the photographing object is in a smiling state, and in the non-smile state, amusively photograph the object through the prompt sound, and then present
  • the smiling face is photographed, so that the best state of the photographed object is captured when the terminal photographs, and the user experience is improved.
  • FIG. 1 is a flow chart of a method of photographing according to an embodiment of the present invention.
  • FIG. 2 is a block diagram showing the structure of an apparatus for photographing according to an embodiment of the present invention.
  • FIG. 3 is a block diagram of an optional structure of a device for photographing according to an embodiment of the present invention.
  • FIG. 4 is a block diagram 2 of an optional structure of a device for photographing according to an embodiment of the present invention.
  • FIG. 5 is a block diagram 3 of an optional structure of a device for photographing according to an embodiment of the present invention.
  • FIG. 6 is a block diagram 4 of an optional structure of a device for photographing according to an embodiment of the invention.
  • FIG. 1 is a flowchart of a method for photographing according to an embodiment of the present invention. As shown in FIG. 1, the flow includes the following steps:
  • Step S102 Identifying a face state of the photographing object when the photographing object is photographed by the camera, wherein the face state includes a smile state and a non-smile state;
  • Step S104 determining, according to the recognized face state, whether to play a voice prompt sound for causing the photographic subject to present a smile state;
  • Step S106 When the smiling state of the photographing object is acquired, the photographing object is photographed.
  • the camera object is adopted by the camera.
  • identifying a face state of the photographing object determining whether to play a voice prompt sound for causing the photographing object to present a smile state according to the recognized face state; thereby, taking a photo when acquiring the smile state of the photographing object
  • the object is photographed, that is, before the photographing object is photographed, the face state of the photographing object is recognized, and according to the state of the face, whether or not the voice prompt sound that causes the photographing object to present the smiling state is played, and the photographing object is in a smiling state.
  • the object When taking a picture directly, in the non-smile state, the object is amused by the prompt sound, and then the smile is presented to take a picture, thereby realizing the best state of capturing the picture object when the terminal takes a picture, thereby improving the user experience.
  • the manner of determining, according to the recognized face state, whether to play the voice prompt tone for presenting the photographic subject in a smiling state, in the step S104 of the present embodiment may include:
  • Step S104-1 when it is recognized that the face state is a smile state, the voice prompt tone is prohibited from being played;
  • step S104-2 when the face state is recognized as the non-smile state, the voice prompt tone is played.
  • the voice prompt tone involved in the embodiment may be a joke text, a funny video, a graphic interchange format (gif, Graphics Interchange Format) format animation, which is suitable for photographing people's ages by using a mature web search engine. Amusement automatically catches photos with the highest happiness value or keeps this small video.
  • a graphic interchange format gif, Graphics Interchange Format
  • the method in this embodiment further includes:
  • Step S11 identifying the gender and/or age of the photographing object when recognizing the face state of the photographing object;
  • Step S12 When the face state is recognized as a non-smile state, a voice prompt sound matching the gender and/or age of the photographed object is played.
  • the voice prompt sounds mentioned above may be classified according to the gender and/or age of the photographed object, and the terminal may automatically play the corresponding voice prompt sound, or the user may manually adjust the voice prompt sound.
  • playing the voice prompt sound matching the gender and/or age of the photographed object can be realized by presetting the correspondence between the gender and/or the age and the voice prompt sound in the terminal, when the gender of the photographed object is recognized. After the age and/or age, if the face state is recognized as a non-smile state, the voice prompt sound corresponding to the gender and/or age of the photographing object is searched for in the corresponding relationship and played.
  • the manner in which the photographing object is photographed in step S106 of the embodiment may be implemented by: performing continuous shooting on the photographing object at predetermined time intervals until photographing.
  • the object is in a non-smile state.
  • the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium (such as ROM/RAM, disk). And an optical disk, comprising a plurality of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in each of the embodiments of the present invention.
  • a terminal device which may be a mobile phone, a computer, a server, or a network device, etc.
  • the above method can be implemented by a terminal.
  • a device for photographing is provided, which is used to implement the above-mentioned embodiments and optional embodiments, and has not been described again.
  • the term “module” may implement a combination of software and/or hardware of a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • the device includes: a first identifying module 22 configured to face a photographing object when photographing a photographing object through a camera Identifying, wherein the face state includes a smile state and a non-smile state; the play module 24 is coupled to the first recognition module 22, and is configured to determine whether to play the smiley state according to the recognized face state.
  • the voice prompting sound; the photographing module 26 is coupled to the first identifying module 22, and is configured to take a photo of the photographing object when the smiling state of the photographing object is acquired.
  • FIG. 3 is a block diagram of an optional structure of a device for photographing according to an embodiment of the present invention.
  • the playback module 24 includes a prohibition unit 32 coupled to the first identification module 22 and configured to recognize a human face.
  • the first playing unit 34 is coupled to the first recognition module 22, and is configured to play the voice prompt tone when the face state is recognized as the non-smile state.
  • FIG. 4 is a block diagram of an optional structure of a device for photographing according to an embodiment of the present invention.
  • the device further includes: a second identification module 42 coupled to the first identification module 22 and the playback module 24, and configured to be configured as When the face state of the photographed subject is recognized, the gender and/or age of the photographed subject is recognized.
  • FIG. 5 is a block diagram 3 of an optional structure of a device for photographing according to an embodiment of the present invention.
  • the play module 24 further includes: a second playing unit 52 coupled to the first identifying module 22 and the second identifying module 42.
  • the connection is set to play a voice prompt sound that matches the gender and/or age of the photographed subject when the face state is recognized as a non-smile state.
  • the second playing unit 52 is a lower playing unit of the first playing unit 34.
  • FIG. 6 is a block diagram of an optional structure of a device for photographing according to an embodiment of the present invention.
  • the photographing module 26 includes: a photographing unit 62 configured to continuously photograph a photographing object at predetermined time intervals until the photographing object is Non-smiley state.
  • each of the foregoing modules may be implemented by software or hardware.
  • the foregoing may be implemented by, but not limited to, the foregoing modules are all located in the same processor; or, the modules are located in multiple In the processor.
  • the optional embodiment provides a photographing method in which the smiley face or the laughter detection module of the camera is started to automatically take a picture after being captured, thereby improving the shooting success rate and the filming rate, reducing the memory burden, and reducing the manual deletion of the difference film.
  • the redundant process, and the entire shooting process is full of fun, to bring a happy feeling to the photographer and the photographer, to achieve a better camera mood or photo moment.
  • the optional embodiment relates to a camera of the terminal, which has a built-in smile or laugh detection module (defined by a happy value); in the process of taking a photo, the above-mentioned smile or laugh detection function is activated, and the human-computer interaction such as voice dialogue is flexibly utilized.
  • a mature web search engine to search for joke texts or funny videos suitable for the age of the photographer, to automatically capture the photos with the highest happiness value, or to shoot continuously, or to keep a small video for a period of time before and after the highest happiness value.
  • randomly search and preview the pictures, videos or laughter recordings of the album to increase the happiness or presence of the photographer to take photos or continuous shooting or small video.
  • Step S702 turning on and detecting.
  • the camera function is turned on, that is, the smiley face or the laughter detection module is turned on, as long as the smileless face is recognized or the happiness value is low for a period of time, the background automatically enters the human-computer interaction module.
  • Step S704 when it is detected that the subject has no smile, the human-computer interaction module is activated.
  • Step S706 when capturing a smile or a laugh of the photographer, taking a quick photo
  • it can also be continuous shooting, or small video.
  • the hardware and software involved in the present embodiment are described in detail in the specific application scenarios.
  • the hardware involved in the optional embodiment includes: a camera, a built-in smile or laughter detection module, and voice. Module; software: web search engine, etc.
  • start the camera in the process of taking pictures, start smile or (or) laugh detection function, judge the happy value situation, use voice dialogue, joke display, smiley laugh capture and other human-computer interaction, using mature web search engine (including text And video and other formats), search for joke text, funny video, gif format animation suitable for the age of the photographer (appropriate reference to gender), amused to automatically catch the photos with the highest happiness value or keep this small video. Or randomly search and preview the pictures or videos collected by this machine, or laugh the sound of the recording section to increase the happiness or presence of the photographer to take pictures.
  • the method of this embodiment includes:
  • Step S802 the photographing function is turned on, at which time smile or laugh detection (which can be performed by using emotion recognition) is turned on, as long as no smile is recognized or the emotion value is low (corresponding to the non-smile state in the above embodiment), for example, the happiness value is recorded.
  • the initial value is HAPPY (TN+0), and the background automatically enters the human-computer interaction module.
  • the photo person takes a group of photos and is worthy of happiness according to the happiness, the person's state has not been laughing, it is cool, record the current smile value and enter the human-computer interaction module of S804.
  • step S804 the voice assistant will pronounce the prompt (corresponding to the voice prompt tone in the above embodiment), and at the same time, the small icon "Click me to try” is popped up, and when the photographer selects, the process proceeds to step S806.
  • the prompt tone can be: the master, give yourself a smile? Beautiful and beautiful; it should be noted that different tips can be given according to gender and age.
  • step S806 the content that has been retrieved according to the reference age or gender is randomly displayed in the background, and is displayed. At the same time, the photographer's smile or laughter is constantly captured in the background. Once captured, the process proceeds to step S808.
  • the search network search and local search web search
  • the main search content is: text joke, or voice, or video, or funny picture combination.
  • Content retrieved locally is a picture or photo, video, or recording that has been marked as a favorite in this machine.
  • the network search includes: text: search for the current popular short jokes; video: search and play funny video or gif animation; funny photo collection: search for funny photo collection; small sub-recording: celebrity small paragraph;
  • local search includes: the machine is marked as already collected pictures; already recorded video (can be prioritized according to the number of times of play, etc.); recording section (can be based on the number of plays, this recording laughs, etc.);
  • the content retrieved above may be played in the order of the photographer's demand or randomly, or may be played in turn according to the retrieved content. If the first text joke does not achieve the effect, the initial value of the happy value of the photographer is Happy ( Tn+0) is compared with the current value HAPPY(Tn+1):
  • the initial value and the current value involved in this embodiment are collectively referred to as a happy value, that is, the highest happiness value is obtained.
  • step S808 the best recorded picture or picture stream is selected before and after the happy value.
  • step S806 the emotion of the photographer will gradually change, the camera keeps recording, and the highest value of the happiness value is taken, that is, the existing value is continuously recorded, and the smile value of the next moment is compared, and the best time picture is retained or Picture stream (reaching the continuous shooting effect).
  • the laughter of the photographer is captured (the laughter entrance can be obtained by means of a receiver, etc.)
  • the same process is processed to record the best value. That is, when the face recognizes that the happiness value is the highest or the laughter is captured, the process proceeds to step S810.
  • Step S810 presenting the photographing object in the snapping laugh, presenting the photographing object in the continuous shooting change, and presenting the photographing object in the recording happy.
  • the promotion point of each happiness value can be recorded as a point of continuous shooting.
  • the voice prompts in each case are given in the form of voice, and the voice intonation is suitable for different judgment scenes, pop-up faces, cute faces, and naughty faces.
  • Embodiments of the present invention also provide a storage medium.
  • the above The storage medium can be configured to store program code for performing the following steps:
  • Step S1 Identifying a face state of the photographing object when the photographing object is photographed by the camera, wherein the face state includes a smile state and a non-smile state;
  • Step S2 determining, according to the recognized face state, whether to play a voice prompt sound for causing the photographic subject to present a smile state;
  • Step S3 When the smiling state of the photographing object is acquired, the photographing object is photographed.
  • each of the above-described modules or steps of the present invention can be implemented by a general-purpose computing device, which can be centralized on a single computing device or distributed across multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from The steps shown or described are performed sequentially, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated into a single integrated circuit module. Thus, the invention is not limited to any specific combination of hardware and software.
  • Embodiments of the present invention also provide a computer readable storage medium storing computer executable instructions for performing any of the methods described above.
  • each module/unit in the foregoing embodiment may be implemented in the form of hardware, for example, by implementing an integrated circuit to implement its corresponding function, or may be implemented in the form of a software function module, for example, by executing a memory and a memory in a processor. Programs/instructions to implement their respective functions.
  • the invention is not limited to any specific form of combination of hardware and software.
  • the above technical solution captures the best state of the photographed object when the terminal takes a picture, thereby improving the user experience.

Abstract

一种拍照的方法，包括：在通过摄像头对拍照对象进行拍照时，对拍照对象的人脸状态进行识别，其中，人脸状态包括笑脸状态和非笑脸状态（S102）；根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音（S104）；在获取到拍照对象的笑脸状态时，对拍照对象进行拍照（S106）。还公开了拍照方法相应的装置。

Description

拍照的方法及装置 技术领域
本文涉及但不限于通信领域，具体而言，涉及一种拍照的方法及装置。
背景技术
随着科技的发展，终端的功能也越来越多，人们可以通过终端购物、出行、拍照等等，其中，拍照是人们使用终端最多的一个应用，即用手机拍照或自拍成了大多数人离不开娱乐方式。无论是出于解压、无聊消遣，还是逗小孩子玩的目的，主要还是想拍出心情最佳的瞬间。往往在没有心情状态下的照片都是一样，显得极其无味和平淡，不值得留下珍贵回忆，也不值得留下影像，所以大多都是拍了删，删了拍，没有乐趣。这样降低了人们通过终端拍照的体验效果，而且在有限的手机内存空间里，提高质量是很需要的。
针对相关技术中通过终端拍照难以捕捉到拍照对象最佳状态的问题，目前尚未存在有效的解决方案。
发明内容
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。
本发明实施例提供了一种拍照的方法及装置，能够在终端拍照时捕捉到拍照对象最佳状态。
根据本发明实施例的一个方面，提供了一种拍照的方法，包括：在通过摄像头对拍照对象进行拍照时，对所述拍照对象的人脸状态进行识别，其中，所述人脸状态包括笑脸状态和非笑脸状态；根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；在获取到所述拍照对象的笑脸状态时，对所述拍照对象进行拍照。
可选地，根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音包括：在识别到人脸状态为笑脸状态时，禁止播放所述语音提示音；在识别到人脸状态为非笑脸状态时，播放所述语音提示音。
可选地，所述方法还包括：在对所述拍照对象的人脸状态进行识别时， 识别所述拍照对象的性别和/或年龄。
可选地，播放所述语音提示音包括：播放与所述拍照对象的性别和/或年龄匹配的语音提示音。
可选地，对所述拍照对象进行拍照包括：对所述拍照对象以预定时间间隔进行连拍直到所述拍照对象为非笑脸状态。
根据本发明实施例的另一个方面，提供了一种拍照的装置，包括：
第一识别模块，设置为在通过摄像头对拍照对象进行拍照时，对所述拍照对象的人脸状态进行识别，其中，所述人脸状态包括笑脸状态和非笑脸状态；播放模块，用于根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；
拍照模块，设置为在获取到所述拍照对象的笑脸状态时，对所述拍照对象进行拍照。
可选地，所述播放模块包括：
禁止单元，设置为在识别到人脸状态为笑脸状态时，禁止播放所述语音提示音；
第一播放单元，设置为在识别到人脸状态为非笑脸状态时，播放所述语音提示音。
可选地，所述装置还包括：第二识别模块，设置为在对所述拍照对象的人脸状态进行识别时，识别所述拍照对象的性别和/或年龄。
可选地，所述播放模块还包括：第二播放单元，设置为在识别到人脸状态为非笑脸状态时，播放与所述拍照对象的性别和/或年龄匹配的语音提示音。
可选地，所述拍照模块包括：拍照单元，设置为对所述拍照对象以预定时间间隔进行连拍直到所述拍照对象为非笑脸状态。
通过本发明实施例，采用在通过摄像头对拍照对象进行拍照时，对拍照对象的人脸状态进行识别，根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；从而在获取到拍照对象的笑脸状态时，对拍照对象进行拍照，也就是说，在对拍照对象进行拍照前，会识别拍照对象 的人脸状态，并根据人脸状态确定是否播放促使拍照对象呈现笑脸状态的语音提示音，在拍照对象是笑脸状态时直接拍照，而在非笑脸状态时，通过提示音逗乐拍照对象，进而呈现笑脸以拍照，从而在终端拍照时捕捉到了拍照对象最佳状态，提高了用户体验。
在阅读并理解了附图和详细描述后，可以明白其他方面。
附图概述
图1是根据本发明实施例的拍照的方法的流程图；
图2是根据本发明实施例的拍照的装置结构框图；
图3是根据本发明实施例的拍照的装置可选结构框图一；
图4是根据本发明实施例的拍照的装置可选结构框图二；
图5是根据本发明实施例的拍照的装置可选结构框图三；
图6是根据本发明实施例的拍照的装置可选结构框图四。
本发明的实施方式
下文中将参考附图并结合实施例来详细说明本发明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
在本实施例中提供了一种拍照的方法，图1是根据本发明实施例的拍照的方法的流程图，如图1所示，该流程包括如下步骤：
步骤S102：在通过摄像头对拍照对象进行拍照时，对拍照对象的人脸状态进行识别，其中，人脸状态包括笑脸状态和非笑脸状态；
步骤S104：根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；
步骤S106：在获取到拍照对象的笑脸状态时，对拍照对象进行拍照。
通过本实施例的步骤S102至步骤S106，采用在通过摄像头对拍照对象 进行拍照时，对拍照对象的人脸状态进行识别，根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；从而在获取到拍照对象的笑脸状态时，对拍照对象进行拍照，也就是说，在对拍照对象进行拍照前，会识别拍照对象的人脸状态，并根据人脸状态确定是否播放促使拍照对象呈现笑脸状态的语音提示音，在拍照对象是笑脸状态时直接拍照，而在非笑脸状态时，通过提示音逗乐拍照对象，进而呈现笑脸以拍照，从而实现了在终端拍照时捕捉到了拍照对象的最佳状态，提高了用户体验。
在本实施例的可选实施方式中，对于本本实施例步骤S104中涉及到的根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音的方式，可以包括：
步骤S104-1，在识别到人脸状态为笑脸状态时，禁止播放语音提示音；
步骤S104-2，在识别到人脸状态为非笑脸状态时，播放语音提示音。
需要说明的是，本实施例中涉及到的语音提示音可以是利用成熟的网络搜索引擎搜索到适合拍照人年龄段的笑话文本、搞笑视频、图像交换格式(gif，Graphics Interchange Format)格式动画、逗乐自动抓怕快乐值最高时的照片或保留这段小录像。
而在本实施例的另一个可选实施方式中，本实施例的方法还包括：
步骤S11：在对拍照对象的人脸状态进行识别时，识别拍照对象的性别和/或年龄；
步骤S12：而在识别到人脸状态为非笑脸状态时，播放与拍照对象的性别和/或年龄匹配的语音提示音。
也就是说，对于上述涉及到的语音提示音可以根据拍照对象的性别和/或年龄进行分类，终端可以自动播放相应的语音提示音，也可以是用户手动调整语音提示音。
上述方法中，播放与拍照对象的性别和/或年龄匹配的语音提示音可以通过在终端中预先设置性别和/或年龄、语音提示音之间的对应关系来实现，当识别出拍照对象的性别和/或年龄后，如果识别到人脸状态为非笑脸状态，则在对应关系中查找拍照对象的性别和/或年龄对应的语音提示音，并播放。
而在本实施例的另一个可选实施方式中，对于本实施例步骤S106中涉及到对拍照对象进行拍照的方式，可以通过如下方式来实现：对拍照对象以预定时间间隔进行连拍直到拍照对象为非笑脸状态。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明每一个实施例所述的方法。
上述方法可以通过终端实现。
在本实施例中还提供了一种拍照的装置，该装置用于实现上述实施例及可选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图2是根据本发明实施例的拍照的装置结构框图，如图2所示，该装置包括：第一识别模块22，设置为在通过摄像头对拍照对象进行拍照时，对拍照对象的人脸状态进行识别，其中，人脸状态包括笑脸状态和非笑脸状态；播放模块24，与第一识别模块22耦合连接，设置为根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；拍照模块26，与第一识别模块22耦合连接，设置为在获取到拍照对象的笑脸状态时，对拍照对象进行拍照。
图3是根据本发明实施例的拍照的装置可选结构框图一，如图3所示，该播放模块24包括：禁止单元32，与第一识别模块22耦合连接，设置为在识别到人脸状态为笑脸状态时，禁止播放语音提示音；第一播放单元34，与第一识别模块22耦合连接，设置为在识别到人脸状态为非笑脸状态时，播放语音提示音。
图4是根据本发明实施例的拍照的装置可选结构框图二，如图4所示，该装置还包括：第二识别模块42，与第一识别模块22和播放模块24耦合连接，设置为在对拍照对象的人脸状态进行识别时，识别拍照对象的性别和/或年龄。
图5是根据本发明实施例的拍照的装置可选结构框图三，如图5所示，该播放模块24还包括：第二播放单元52，与第一识别模块22和第二识别模块42耦合连接，设置为在识别到人脸状态为非笑脸状态时，播放与拍照对象的性别和/或年龄匹配的语音提示音。
需要说明的是，该第二播放单元52是第一播放单元34更下位的播放单元。
图6是根据本发明实施例的拍照的装置可选结构框图四，如图6所示，该拍照模块26包括：拍照单元62，设置为对拍照对象以预定时间间隔进行连拍直到拍照对象为非笑脸状态。
需要说明的是，上述每一个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述模块分别位于多个处理器中。
下面结合本发明的可选实施例对本发明进行举例说明；
本可选实施例提供了一种拍照方法，在该方法中启动相机的笑脸或笑声检测模块捕捉后自动拍照，提高了拍摄成功率和出片率，降低内存负担，并减少人工删除差片的冗余流程，且整个拍摄过程乐趣十足，给拍摄者和被拍摄者带来快乐感，达到更好的拍照心情或拍照瞬间。
本可选实施例涉及到了终端的摄像头，内置笑脸或笑声检测模块(后面以快乐值定义)；在拍照的过程中，启动上述笑脸或笑声检测功能，并灵活运用语音对话等人机交互，利用成熟的网络搜索引擎搜索到适合拍照人年龄段的笑话文本或者搞笑视频，以逗乐自动抓怕快乐值最高时的照片，或连拍，或保留快乐值最高时前后一段时间的小录像。或者随机搜索并预览本机收藏的图片、视频或笑声朗朗的录音段子，来增加拍照人的幸福感或存在感进行拍照或连拍或小录像。
本可选实施例的拍照方法的的方法包括：
步骤S702，开启和检测。
其中，开启拍照功能，即开启笑脸或笑声检测模块，只要在一段时间内识别到无笑脸或者快乐值低，后台自动进入人机交互模块。
步骤S704，当检测到被拍摄者无笑脸时，启动人机交互模块。
其中，根据拍照人(即上述拍照对象)不同的状态或场景给予不同的语音提示，根据拍照人的年龄，性格等特点给出适合的检索内容：搞笑文本、搞笑视频或gif、搞笑录音小段子，或者展示收藏过的本地视频或图片或录音。可按拍照人的需求进行人机交互选择，达到任意展示或者轮番展示。
步骤S706，当捕捉到拍照人的笑脸或者笑声时，快速拍照；
其中，也可以是连拍，或小录像。
下面结合本可选实施例涉及到的硬件和软件，在具体应用场景中对本可选实施例进行详细说明；本可选实施例涉及到的硬件包括：摄像头、内置笑脸或笑声检测模块、语音模块；软件：网络搜索引擎等。
启动摄像头，在拍照的过程中，启动笑脸或(or)笑声检测功能，判断快乐值情况，运用语音对话、笑话展示、笑脸笑声捕捉等人机交互，利用成熟的网络搜索引擎(含文本和视频等格式)，搜索到适合拍照人年龄段(适当参考性别)的笑话文本、搞笑视频、gif格式动画，逗乐自动抓怕快乐值最高时的照片或保留这段小录像。或者随机搜索并预览本机收藏的图片or视频，or笑声朗朗的录音段子，来增加拍照人的幸福感或存在感进行拍照。该具体实施例的方法包括：
步骤S802，开启拍照功能，此时笑脸或笑声检测(可以利用情绪识别)开启，只要识别到无笑脸或者情绪值低(对应于上述实施例中的非笑脸状态)，例如，记录快乐值的初值HAPPY(TN+0)，后台自动进入人机交互模块。
其中，如果当拍照人拍过一组照片后，根据快乐值得出，此人状态一直不笑，很酷，记录当前笑脸值并进入S804的人机交互模块。
步骤S804，语音小助手会发音提示(对应于上述实施例中的语音提示音)，同时弹出小图标“点我试试”，当拍照人选择，进入步骤S806。
其中，该提示音可以是：主人，给自己一个笑脸吧？美美哒；需要说明的是，可以根据不同性别、年龄来给出不同提示。
整个过程中，为不打扰拍照人情绪，可以不中断逗笑过程，不停的去对比前一秒或前几秒的快乐值，取最优的值，作为最终图片。也可以连拍不同状态的照片，由拍照人自己选择留哪一组或一张照片。
步骤S806，随机弹出后台已经根据参考年龄or性别检索出的内容，给予展示。同时，在后台不断捕捉拍照人的笑脸或笑声。一旦捕捉到就进入步骤S808。
其中，检索分网络检索和本地检索；网络检索，主要检索的内容为：文本笑话，或语音，或视频、或搞笑图片组合。本地检索的内容是本机中已经标记为收藏的图片或照片、视频或录音。根据网络和本地检索内容分别做以下说明：
1，网络检索包括：文本：搜索到当前比较热门的小段子笑话；视频：搜索到并播放搞笑视频or gif动画；搞笑图片集：搜索到搞笑图片集；小段子录音：名人小段子；
2，本地检索包括：本机标记为已经收藏的图片；已经录制的视频(可以根据播放次数排优先级等)；录音段子(可以根据播放次数，本录音笑点评分等)；
上述检索的内容可以按拍照人需求次序或者随机轮流播放，也可以根据所检索到的某一类内容轮流播放，如第一个文本笑话达不到效果，即将拍照人快乐值的初值Happy(Tn+0)和现在的值HAPPY(Tn+1)进行比较:
当Happy(Tn+1)>HAPPY(Tn+0)时，保存当前照片；
当Happy(Tn+1)<＝HAPPY(Tn+0)时，继续下一展示(且此时的N值自动加1)；继续记录快乐值，继续对比本次记录的快乐值和上一次记录的快乐值，保留分值较高(可以更具拍照人自己选择模式，进行覆盖或者保留)。
在没有明显提升或者比初始值还低时，语音提示再来一组视频，直到当前快乐值比初始值高，进入步骤S808。需要说明的是，在本实施例中涉及到的初始值和现在的值统一称为快乐值，即取快乐值最高的。
此外，在终端的搜索一栏中可以增加定位一个拍照人的籍贯或生长地点，可以有更多的当地文化内容搜索，如脱口秀之类的。如四川的李白清—适合大多数四川重庆人，老少皆宜。如上海的周立波脱口秀之类的。
对于小孩可以有小动画以供选择，设计出小孩哭闹的时候，逗逗小朋友，留下前后哭和笑的照片，值得做一组对比照保存展现。
步骤S808，快乐值前后对比选取最佳记录图片或图片流。
其中，在步骤S806的展示过程中，拍照人的情绪会逐渐变化，摄像头不断记录，拍下快乐值最高画面，即不断记录现有值，和下一时刻笑脸值对比，保留最佳时刻图片或图片流(达到连拍效果)。当捕捉到拍照人笑声时(可以用受话器感应等方式获取笑声入口)，同样流程处理，记录下最佳值的。即当人脸识别到快乐值最高或捕捉到笑声，就进入步骤S810。
步骤S810，呈现抓拍笑中的拍照对象，呈现连拍变化中的拍照对象，呈现录制快乐中的拍照对象。
其中，每一个快乐值的提升点都可以作为连拍的一个点记录。为了不打扰欣赏的雅兴，可以选择后台一直抓拍，或录制笑声的瞬间片段视频，然后等结束后，提示：例如，主人，真替你高兴，(弹出高兴的鬼脸)来看看你的魅力容颜吧，精彩一瞬间等提示。
需要说明的是，对于上述涉及到的语音小助手，是以语音形式给予每一种情况下的语音提示，语音语调适合不同判断场景、弹出鬼脸、萌脸，调皮脸。
后台搜索：可以根据拍照人的网络情况选择搜索的范围、内容大小等。也可以根据拍照人网络情况选择，例如wifi情况下，网络优先。拍照人同意情况下，网络优先等。
笑脸检测功能：这里可以和快乐值(happy值)高低直接关联，当微笑、大笑、为快乐值高，不笑时定义为快乐值很一般，不笑且有沮丧表情为快乐值低，哭泣为快乐值负数等。实现中快乐值可以取-1到1区间，Happy＝[-1，1]。
本发明的实施例还提供了一种存储介质。可选地，在本实施例中，上述 存储介质可以被设置为存储用于执行以下步骤的程序代码：
步骤S1：在通过摄像头对拍照对象进行拍照时，对拍照对象的人脸状态进行识别，其中，人脸状态包括笑脸状态和非笑脸状态；
步骤S2：根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；
步骤S3：在获取到拍照对象的笑脸状态时，对拍照对象进行拍照。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本发明的每一个模块或每一个步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算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，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，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结合。
本发明实施例还提出了一种计算机可读存储介质，存储有计算机可执行指令，计算机可执行指令用于执行上述描述的任意一个方法。
本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序来指令相关硬件(例如处理器)完成，所述程序可以存储于计算机可读存储介质中，如只读存储器、磁盘或光盘等。可选地，上述实施例的全部或部分步骤也可以使用一个或多个集成电路来实现。相应地，上述实施例中的各模块/单元可以采用硬件的形式实现，例如通过集成电路来实现其相应功能，也可以采用软件功能模块的形式实现，例如通过处理器执行存储与存储器中的 程序/指令来实现其相应功能。本发明不限于任何特定形式的硬件和软件的结合。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。
工业实用性
上述技术方案在终端拍照时捕捉到了拍照对象最佳状态，提高了用户体验。

Claims (10)

  1. 一种拍照的方法，包括：
    在通过摄像头对拍照对象进行拍照时，对所述拍照对象的人脸状态进行识别，其中，所述人脸状态包括笑脸状态和非笑脸状态；
    根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；
    在获取到所述拍照对象的笑脸状态时，对所述拍照对象进行拍照。
  2. 根据权利要求1所述的方法，其中，根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音包括：
    在识别到人脸状态为笑脸状态时，禁止播放所述语音提示音；
    在识别到人脸状态为非笑脸状态时，播放所述语音提示音。
  3. 根据权利要求2所述的方法，所述方法还包括：
    在对所述拍照对象的人脸状态进行识别时，识别所述拍照对象的性别和/或年龄。
  4. 根据权利要求3所述的方法，其中，播放所述语音提示音包括：
    播放与所述拍照对象的性别和/或年龄匹配的语音提示音。
  5. 根据权利要求1所述的方法，其中，对所述拍照对象进行拍照包括：
    对所述拍照对象以预定时间间隔进行连拍直到所述拍照对象为非笑脸状态。
  6. 一种拍照的装置，包括：
    第一识别模块，设置为在通过摄像头对拍照对象进行拍照时，对所述拍照对象的人脸状态进行识别，其中，所述人脸状态包括笑脸状态和非笑脸状态；
    播放模块，设置为根据识别到的人脸状态确定是否播放用于使拍摄对象呈现笑脸状态的语音提示音；
    拍照模块，设置为在获取到所述拍照对象的笑脸状态时，对所述拍照对 象进行拍照。
  7. 根据权利要求6所述的装置，其中，所述播放模块包括：
    禁止单元，设置为在识别到人脸状态为笑脸状态时，禁止播放所述语音提示音；
    第一播放单元，设置为在识别到人脸状态为非笑脸状态时，播放所述语音提示音。
  8. 根据权利要求7所述的装置，所述装置还包括：
    第二识别模块，设置为在对所述拍照对象的人脸状态进行识别时，识别所述拍照对象的性别和/或年龄。
  9. 根据权利要求8所述的装置，所述播放模块还包括：
    第二播放单元，设置为在识别到人脸状态为非笑脸状态时，播放与所述拍照对象的性别和/或年龄匹配的语音提示音。
  10. 根据权利要求6所述的装置，其中，所述拍照模块包括：
    拍照单元，设置为对所述拍照对象以预定时间间隔进行连拍直到所述拍照对象为非笑脸状态。
PCT/CN2016/080762 2016-03-04 2016-04-29 拍照的方法及装置 WO2016188304A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610124813.0 2016-03-04
CN201610124813.0A CN107155056A (zh) 2016-03-04 2016-03-04 拍照的方法及装置

Publications (1)

Publication Number Publication Date
WO2016188304A1 true WO2016188304A1 (zh) 2016-12-01

Family

ID=57393563

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/080762 WO2016188304A1 (zh) 2016-03-04 2016-04-29 拍照的方法及装置

Country Status (2)

Country Link
CN (1) CN107155056A (zh)
WO (1) WO2016188304A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018188007A1 (zh) * 2017-04-13 2018-10-18 华为技术有限公司 自拍的方法、装置和终端设备
CN111610851A (zh) * 2019-02-22 2020-09-01 阿里巴巴集团控股有限公司 互动方法、装置以及用于实现该互动方法的用户终端

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111653282A (zh) * 2020-05-27 2020-09-11 星络智能科技有限公司 一种影像拍摄方法、智能家居控制器及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101335838A (zh) * 2007-06-28 2008-12-31 索尼株式会社 图像拾取设备、图像拾取方法及其程序
JP2011171921A (ja) * 2010-02-17 2011-09-01 Nikon Corp デジタルカメラ
JP2015082728A (ja) * 2013-10-22 2015-04-27 株式会社ニコン 撮像装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4853425B2 (ja) * 2007-08-14 2012-01-11 ソニー株式会社 撮像装置、撮像方法およびプログラム
KR101634247B1 (ko) * 2009-12-04 2016-07-08 삼성전자주식회사 피사체 인식을 알리는 디지털 촬영 장치, 상기 디지털 촬영 장치의 제어 방법
CN103369214A (zh) * 2012-03-30 2013-10-23 华晶科技股份有限公司 图像获取方法与图像获取装置
CN103813076B (zh) * 2012-11-12 2018-03-27 联想(北京)有限公司 信息处理的方法及电子设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101335838A (zh) * 2007-06-28 2008-12-31 索尼株式会社 图像拾取设备、图像拾取方法及其程序
JP2011171921A (ja) * 2010-02-17 2011-09-01 Nikon Corp デジタルカメラ
JP2015082728A (ja) * 2013-10-22 2015-04-27 株式会社ニコン 撮像装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018188007A1 (zh) * 2017-04-13 2018-10-18 华为技术有限公司 自拍的方法、装置和终端设备
CN110268702A (zh) * 2017-04-13 2019-09-20 华为技术有限公司 自拍的方法、装置和终端设备
CN111610851A (zh) * 2019-02-22 2020-09-01 阿里巴巴集团控股有限公司 互动方法、装置以及用于实现该互动方法的用户终端
CN111610851B (zh) * 2019-02-22 2024-04-16 阿里巴巴集团控股有限公司 互动方法、装置以及用于实现该互动方法的用户终端

Also Published As

Publication number Publication date
CN107155056A (zh) 2017-09-12

Similar Documents

Publication Publication Date Title
US9779775B2 (en) Automatic generation of compilation videos from an original video based on metadata associated with the original video
TWI253860B (en) Method for generating a slide show of an image
US20160358629A1 (en) Interactive real-time video editor and recorder
US8548249B2 (en) Information processing apparatus, information processing method, and program
US20160099023A1 (en) Automatic generation of compilation videos
US10541000B1 (en) User input-based video summarization
KR101513847B1 (ko) 화상들을 재생하기 위한 방법 및 장치
US8131024B2 (en) Apparatus and method of image capture for facial recognition
US11062143B2 (en) Systems and methods for generating a video summary
Garwood Sense of Film Narration
US20110184542A1 (en) Method and apparatus for generating a sequence of a plurality of images to be displayed whilst accompanied by audio
US20170213576A1 (en) Live Comics Capturing Camera
WO2016188304A1 (zh) 拍照的方法及装置
WO2014179749A1 (en) Interactive real-time video editor and recorder
CN112422844A (zh) 在视频中添加特效的方法、装置、设备及可读存储介质
Merchant (Re) constructing the tourist experience? Editing experience and mediating memories of learning to dive
JP2010252008A (ja) 撮影装置、表示装置、再生装置、撮影方法、および表示方法
US9928877B2 (en) Method and system for automatic generation of an animated message from one or more images
CN112492400A (zh) 互动方法、装置、设备以及通信方法、拍摄方法
JP5847646B2 (ja) テレビ制御装置、テレビ制御方法及びテレビ制御プログラム
CN107147842B (zh) 一种儿童照相的方法及装置
JP2012169743A (ja) 情報処理装置及び情報処理方法
US11954402B1 (en) Talk story system and apparatus
CN107809597A (zh) 一种记录音乐的拍照方法及系统
EP4309060A1 (fr) Procede d&#39;authentification, dispositif electronique, produit programme d&#39;ordinateur et support correspondants

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: 16799193

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: 16799193

Country of ref document: EP

Kind code of ref document: A1