CN105933529A

CN105933529A - Shooting picture display method and device

Info

Publication number: CN105933529A
Application number: CN201610365261.2A
Authority: CN
Inventors: 孙垚
Original assignee: Nubia Technology Co Ltd
Current assignee: Nubia Technology Co Ltd
Priority date: 2016-04-20
Filing date: 2016-05-26
Publication date: 2016-09-07

Abstract

The invention discloses a shooting picture display device. The shooting picture display device comprises a first obtaining module, a shooting characteristic information extracting module, and a first display module, wherein the first obtaining module is used for obtaining picture information captured by a camera in real time after a shooting function of the camera is started; the shooting characteristic information extracting module is used for extracting characteristic information of a shooting object from the picture information according to a preset first image recognition algorithm; the first display module is used for displaying a picture according to the characteristic information and a shooting habit model; and the shooting habit model is obtained through machine learning and training. According to the method and the device disclosed by the invention, the purpose of automatically displaying the shooting picture suitable for a shooting habit of the user in shooting is realized.

Description

The display packing of shooting picture and device

Technical field

The present invention relates to technical field of mobile terminals, particularly relate to display packing and the device of shooting picture.

Background technology

Along with the universal of mobile device and the development of mobile technology, a lot of mobile terminals such as mobile phone, flat board etc. It is assembled with photographic head, makes user can take pictures or image.But when user takes pictures or images Time, it is typically only capable to treat shooting picture and carries out auto-focusing and show, and the picture of shooting picture cannot be treated Other acquisition parameters such as face size, aspect ratio are automatically adjusted and show so that user adjusts in shooting Generally require adjustment multiple acquisition parameters time whole and could show the shooting picture meeting user's request, shot Journey is relatively complicated, affects Consumer's Experience.

Summary of the invention

Present invention is primarily targeted at display packing and the device that a kind of shooting picture is provided, it is intended to realize Automatically the purpose meeting the shooting picture that user shoots custom is shown when shooting.

For achieving the above object, the present invention provides the display device of a kind of shooting picture, described device to include:

First acquisition module, after starting at photographic head shoot function, obtains described photographic head and catches in real time The image information obtained；

Shooting characteristic information extracting module, is used for according to the first preset image recognition algorithm from described picture Information is extracted the characteristic information of reference object；

First display module, for according to described characteristic information and shooting custom models show picture, described Shooting custom model is obtained by machine learning training.

Alternatively, described first display module includes:

Matching judgment unit, for being mated with described shooting custom model by described characteristic information, sentences Whether disconnected described characteristic information meets the first shooting custom, and described first shooting custom is described shooting custom Shooting custom corresponding with described characteristic information in model；

Display unit, for when described characteristic information meets described first shooting custom, takes the photograph described in display Image information as head captured in real time；

Adjust trigger element, be used for when described characteristic information does not meets described first shooting custom, according to Described first shooting custom adjusts the acquisition parameters of described photographic head, based on the described acquisition parameters after adjusting Trigger described first acquisition module and obtain the image information of described photographic head captured in real time.

Alternatively, described device also includes:

Second display module, if manually adjusting instruction for receiving, then manually adjusts instruction described in basis Adjust the acquisition parameters of described photographic head, the image information that after display adjustment, described photographic head obtains.

Alternatively, described device also includes:

Second acquisition module, for obtaining the photo in preset memory block and/or video file；

Sample characteristics information extraction modules, is used for according to the second preset image recognition algorithm from described photo And/or video file extracts sample characteristics information successively；

Machine learning module, for confirming that described sample characteristics information is the training sample of machine learning, will Described training sample is trained by preset machine learning algorithm, and obtains described shooting custom model.

Alternatively, described device also includes:

3rd acquisition module, after the photo in described memory block and/or video file have renewal, obtains Take photo and/or the video file of renewal；

Update characteristic information extracting module, be used for according to the 3rd preset image recognition algorithm after updating Described photo and/or video file extract successively and updates characteristic information；

Add module, for being added to described training sample by described renewal characteristic information, make described instruction Practice sample to be updated, in order to be trained the shooting after being updated again with described training sample and practise Used model.

The present invention further provides the display packing of a kind of shooting picture, described method includes step:

After photographic head shoot function starts, obtain the image information of described photographic head captured in real time；

From described image information, the feature letter of reference object is extracted according to the first preset image recognition algorithm Breath；

According to described characteristic information and shooting custom models show picture, described shooting custom model is to pass through Machine learning training obtains.

Alternatively, described according to described characteristic information and shooting custom models show picture include:

Described characteristic information is mated with described shooting custom model, it is judged that whether described characteristic information Meeting the first shooting custom, described first shooting custom is to believe with described feature in described shooting custom model The shooting custom that breath is corresponding；

The most then show the image information of described photographic head captured in real time；

If it is not, then adjust the acquisition parameters of described photographic head according to described first shooting custom, based on adjustment After described acquisition parameters perform the step of image information of described acquisition described photographic head captured in real time.

Alternatively, described method also includes:

Manually adjust instruction if receiving, then manually adjust instruction described in basis and adjust the bat of described photographic head Take the photograph parameter, the image information that after display adjustment, described photographic head obtains.

Alternatively, described method also includes:

Obtain the photo in preset memory block and/or video file；

From described photo and/or video file, sample is extracted successively according to the second preset image recognition algorithm Characteristic information；

Confirm that described sample characteristics information is the training sample of machine learning, by described training sample by pre- The machine learning algorithm put is trained, and obtains described shooting custom model.

Alternatively, described method also includes:

After photo in described memory block and/or video file have renewal, obtain the photo updated and/or regard Frequency file；

According to the 3rd preset image recognition algorithm from update after described photo and/or video file successively Extract and update characteristic information；

Described renewal characteristic information is added to described training sample, makes described training sample be updated, To be trained the custom model of the shooting after being updated again with described training sample.

The display packing of the shooting picture that the present invention proposes and device, after photographic head shoot function starts, Obtain the image information of described photographic head captured in real time；According to the first preset image recognition algorithm from described Image information extracts the characteristic information of reference object；Show according to described characteristic information and shooting custom model Show that picture, described shooting custom model are obtained by machine learning training.Real by obtaining photographic head Time capture image information, and from this image information, extract the characteristic information of reference object, further according to this Characteristic information shows, with shooting custom model, the image information that photographic head gets in real time so that in shooting The image information that photographic head is obtained by Shi Wuxu carries out various manual regulation, just can automatically according to shooting practise The image information that used display photographic head gets.

Accompanying drawing explanation

Fig. 1 is the hardware architecture diagram of the mobile terminal realizing each embodiment of the present invention；

Fig. 2 is the wireless communication system schematic diagram of mobile terminal as shown in Figure 1；

Fig. 3 is the module diagram of the display device first embodiment of shooting picture of the present invention；

Fig. 4 is the module diagram of the first display module in embodiment illustrated in fig. 3 of the present invention；

Fig. 5 is the exemplary plot shown of finding a view before the adjustment of photographic head acquisition parameters in embodiment illustrated in fig. 4 of the present invention；

Fig. 6 is the exemplary plot shown of finding a view after the adjustment of photographic head acquisition parameters in embodiment illustrated in fig. 4 of the present invention；

Fig. 7 is the module diagram added in embodiment illustrated in fig. 3；

Fig. 8 is the module diagram added in embodiment illustrated in fig. 7；

Fig. 9 is the module diagram added in embodiment illustrated in fig. 8；

Figure 10 is the schematic flow sheet of the display packing first embodiment of shooting picture of the present invention；

Figure 11 is according to described characteristic information and shooting custom models show picture in embodiment illustrated in fig. 10 Refinement step schematic flow sheet.

The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, do referring to the drawings further Explanation.

Detailed description of the invention

Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not used to limit Determine the present invention.

The mobile terminal realizing each embodiment of the present invention is described referring now to accompanying drawing.In follow-up description In, use the suffix being used for representing such as " module ", " parts " or " unit " of element only for having It is beneficial to the explanation of the present invention, itself does not has specific meaning.Therefore, " module " can mix with " parts " Close ground to use.

Mobile terminal can be implemented in a variety of manners.Such as, the terminal described in the present invention can include (individual digital helps for such as mobile phone, smart phone, notebook computer, digit broadcasting receiver, PDA Reason), PAD (panel computer), PMP (portable media player), the mobile end of guider etc. The fixed terminal of end and such as numeral TV, desk computer etc..Hereinafter it is assumed that terminal is mobile whole End.However, it will be understood by those skilled in the art that, in addition to being used in particular for the element of mobile purpose, Structure according to the embodiment of the present invention can also apply to the terminal of fixed type.

Fig. 1 is the hardware configuration signal realizing each one optional mobile terminal of embodiment of the present invention.

Mobile terminal 100 can include wireless communication unit 110, A/V (audio/video) input block 120, User input unit 130, sensing unit 140, output unit 150, memorizer 160, interface unit 170, Controller 180 and power subsystem 190 etc..Fig. 1 shows the mobile terminal with various assembly, but should It is understood by, it is not required that implement all assemblies illustrated.Can alternatively implement more or less of group Part.Will be discussed in more detail below the element of mobile terminal.

Wireless communication unit 110 generally includes one or more assembly, and it allows mobile terminal 100 with wireless Radio communication between communication system or network.Such as, wireless communication unit can include mobile communication At least one in module 111 and wireless Internet module 112.

Mobile communication module 111 send radio signals to base station (such as, access point, node B etc.), In exterior terminal and server at least one and/or receive from it radio signal.Such radio Signal can include voice call signal, video calling signal or according to text and/or Multimedia Message The various types of data sent and/or receive.

Wireless Internet module 112 supports the Wi-Fi (Wireless Internet Access) of mobile terminal.This module can internal or Externally it is couple to terminal.Wi-Fi (Wireless Internet Access) technology involved by this module can include WLAN (nothing Line LAN) (Wi-Fi), Wibro (WiMAX), Wimax (worldwide interoperability for microwave access), HSDPA (at a high speed Downlink packets accesses) etc..

A/V input block 120 is used for receiving audio or video signal.A/V input block 120 can include phase Machine 121 and mike 122, camera 121 in Video Capture pattern or image capture mode by image capturing Static images or the view data of video that device obtains process.Picture frame after process can show On display unit 151.Picture frame after camera 121 processes can be stored in memorizer 160, and (or other deposits Storage media) in or be transmitted via wireless communication unit 110, can provide according to the structure of mobile terminal Two or more cameras 121.Mike 122 can be in telephone calling model, logging mode, speech recognition Pattern etc. operational mode receives sound (voice data) via mike, and can be by such sound It is processed as voice data.Audio frequency (voice) data after process can be changed in the case of telephone calling model For can be sent to the form output of mobile communication base station via mobile communication module 111.Mike 122 is permissible Implement various types of noise elimination (or suppression) algorithm and receiving and transmission audio signal to eliminate (or suppression) During produce noise or interference.

It is mobile to control that user input unit 130 can generate key input data according to the order of user's input The various operations of terminal.User input unit 130 allows user to input various types of information, and permissible Including keyboard, metal dome, touch pad (such as, detection due to touched and cause resistance, pressure, electricity The sensitive component of change held etc.), roller, rocking bar etc..Especially, when touch pad as a layer When being superimposed upon on display unit 151, touch screen can be formed.

Sensing unit 140 detects the current state of mobile terminal 100, (such as, mobile terminal 100 open or Closed mode), the position of mobile terminal 100, user is for the contact (that is, touch input) of mobile terminal 100 Presence or absence, the orientation of mobile terminal 100, the acceleration or deceleration of mobile terminal 100 move and direction etc., And generate the order or signal being used for controlling the operation of mobile terminal 100.Such as, when mobile terminal 100 When being embodied as sliding-type mobile phone, it is to engage on or off that sensing unit 140 can sense this sliding-type number Close.It addition, sensing unit 140 can detect whether power subsystem 190 provides electric power or interface unit 170 Whether couple with external device (ED).

Interface unit 170 is used as at least one external device (ED) and is connected, with mobile terminal 100, the interface that can pass through. Such as, external device (ED) can include wired or wireless head-band earphone port, external power source (or battery charging Device) port, wired or wireless FPDP, memory card port, there is the device of identification module for connecting Port, audio frequency input/output (I/O) port, video i/o port, ear port etc..Identification module can Be storage for verifying that user uses the various information of mobile terminal 100 and can include that user identifies Module (UIM), client identification module (SIM), Universal Subscriber identification module (USIM) etc..It addition, tool The device (hereinafter referred to as " identifying device ") having identification module can be to take the form of smart card, therefore, identifies Device can be connected with mobile terminal 100 via port or other attachment means.Interface unit 170 can be used In receiving from the input (such as, data message, electric power etc.) of external device (ED) and the input that will receive One or more elements of being transferred in mobile terminal 100 or may be used at mobile terminal and outside dress Data are transmitted between putting.

It addition, when mobile terminal 100 is connected with external base, interface unit 170 can serve as allowing to lead to Cross it provide the path of mobile terminal 100 by electric power from base or can serve as allowing to input from base Various command signals be transferred to the path of mobile terminal by it.Various command signals from base input Or electric power may serve as identifying whether mobile terminal is accurately fitted within the signal on base.Output is single Unit 150 be configured to vision, audio frequency and/or tactile manner provide output signal (such as, audio signal, Video signal, alarm signal, vibration signal etc.).Output unit 150 can include display unit 151, Dio Output Modules 152, alarm unit 153 etc..

Display unit 151 may be displayed on the information processed in mobile terminal 100.Such as, mobile terminal is worked as 100 when being in telephone calling model, display unit 151 can show and call or other communicate (such as, civilian This information receiving and transmitting, multimedia file download etc.) relevant user interface (UI) or graphic user interface (GUI). When mobile terminal 100 is in video calling pattern or image capture mode, display unit 151 can show Show the image of capture and/or the image of reception, UI or GUI etc. of video or image and correlation function is shown Deng.

Meanwhile, when display unit 151 and touch pad the most superposed on one another to form touch screen time, aobvious Show that unit 151 can serve as input equipment and output device.Display unit 151 can include liquid crystal display (LCD), thin film transistor (TFT) LCD (TFT-LCD), Organic Light Emitting Diode (OLED) display, flexibility show Show at least one in device, three-dimensional (3D) display etc..Some in these display may be constructed such that Transparence is to allow user to watch from outside, and this is properly termed as transparent display, typical transparent display Can for example, TOLED (transparent organic light emitting diode) display etc..According to the specific enforcement wanted Mode, mobile terminal 100 can include two or more display units (or other display device), such as, Mobile terminal can include outernal display unit (not shown) and inner display unit (not shown).Touch screen can For detecting touch input pressure and touch input position and touch input area.

Dio Output Modules 152 can be in call signal at mobile terminal and receive pattern, call mode, note Time under the isotypes such as record pattern, speech recognition mode, broadcast reception mode, wireless communication unit 110 is connect Receive or in memorizer 160 storage voice data transducing audio signal and be output as sound.And, Dio Output Modules 152 can provide the audio frequency output (example relevant to the specific function of mobile terminal 100 execution As, call signal receives sound, message sink sound etc.).Dio Output Modules 152 can include raising one's voice Device, buzzer etc..

Alarm unit 153 can provide output to notify event to mobile terminal 100.Typically Event can include calling reception, message sink, key signals input, touch input etc..Except audio frequency Or outside video frequency output, alarm unit 153 can provide in a different manner and export the generation with notification event. Such as, alarm unit 153 can with vibration form provide output, when receive calling, message or some When other enters communication (incoming communication), alarm unit 153 can provide sense of touch to export (i.e., Vibration) to notify to user.By providing such sense of touch to export, even if at the mobile phone of user When being in the pocket of user, user also is able to identify the generation of various event.Alarm unit 153 also may be used To provide the output of the generation of notification event via display unit 151 or dio Output Modules 152.

Memorizer 160 can store the process performed by controller 180 and the software program controlling operation etc., Or can temporarily store data (such as, telephone directory, message, the static state that oneself maybe will export through output Image, video etc.).And, memorizer 160 can store and export about when touch is applied to touch screen The vibration of various modes and the data of audio signal.

Memorizer 160 can include the storage medium of at least one type, described storage medium include flash memory, Hard disk, multimedia card, card-type memorizer (such as, SD or DX memorizer etc.), random access storage device (RAM), static random-access memory (SRAM), read only memory (ROM), electrically erasable Read only memory (EEPROM), programmable read only memory (PROM), magnetic storage, disk, light Dish etc..And, mobile terminal 100 can be connected the storage function performing memorizer 160 with by network Network storage device cooperation.

Controller 180 generally controls the overall operation of mobile terminal.Such as, controller 180 performs and voice Control that call, data communication, video calling etc. are relevant and process.It addition, controller 180 can wrap Including the multi-media module 181 for reproducing (or playback) multi-medium data, multi-media module 181 can construct In controller 180, or it is so structured that separate with controller 180.Controller 180 can perform pattern to be known Other places are managed, so that the handwriting input performed on the touchscreen or picture drafting input are identified as character or figure Picture.

Power subsystem 190 receives external power or internal power under the control of controller 180 and provides behaviour Make the suitable electric power needed for each element and assembly.

Various embodiment described herein can be to use such as computer software, hardware or its any group The computer-readable medium closed is implemented.Implementing for hardware, embodiment described herein can pass through Use application-specific IC (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, control Device, microcontroller, microprocessor, it is designed to perform in the electronic unit of function described herein extremely Few one is implemented, and in some cases, such embodiment can be implemented in controller 180.Right Implementing in software, the embodiment of such as process or function can perform at least one function or behaviour with permission The single software module made is implemented.Software code can be by writing with any suitable programming language Software application (or program) is implemented, and software code can be stored in memorizer 160 and by controlling Device 180 performs.

So far, oneself is through describing mobile terminal according to its function.Below, for the sake of brevity, will describe Various types of mobile terminals of such as folded form, board-type, oscillating-type, slide type mobile terminal etc. In slide type mobile terminal as example.Therefore, the present invention can be applied to any kind of mobile whole End, and it is not limited to slide type mobile terminal.

As shown in Figure 1 mobile terminal 100 may be constructed such that and utilizes via frame or packet transmission data The most wired and wireless communication system and satellite-based communication system operate.

The communication system being wherein operable to according to the mobile terminal of the present invention is described referring now to Fig. 2.

Such communication system can use different air interfaces and/or physical layer.Such as, by communication system The air interface that system uses includes such as frequency division multiple access (FDMA), time division multiple acess (TDMA), CDMA (CDMA) move lead to UMTS (UMTS) (especially, Long Term Evolution (LTE)), the whole world Communication system (GSM) etc..As non-limiting example, explained below relates to cdma communication system, but It is that such teaching is equally applicable to other type of system.

With reference to Fig. 2, cdma wireless communication system can include multiple mobile terminal 100, multiple base station (BS) 270, base station controller (BSC) 275 and mobile switching centre (MSC) 280.MSC280 is configured to Interface is formed with Public Switched Telephony Network (PSTN) 290.MSC280 is also structured to and can be via returning Journey circuit is couple to the BSC275 of base station 270 and forms interface.If the interface that back haul link can be known according to Ganji In any one construct, described interface includes such as E1/T1, ATM, IP, PPP, frame relay, HDSL, ADSL or xDSL.It will be appreciated that system as shown in Figure 2 can include multiple BSC2750.

Each BS270 can service one or more subregion (or region), by multidirectional antenna or sensing certain party To antenna cover each subregion radially away from BS270.Or, each subregion can be by for dividing Two or more antennas that collection receives cover.Each BS270 may be constructed such that support multiple frequencies distribution, And the distribution of each frequency has specific frequency spectrum (such as, 1.25MHz, 5MHz etc.).

Intersecting that subregion and frequency are distributed can be referred to as CDMA Channel.BS270 can also be referred to as base station Transceiver subsystem (BTS) or other equivalent terms.In this case, term " base station " can be used In broadly representing single BSC275 and at least one BS270.Base station can also be referred to as " cellular station ". Or, each subregion of specific BS270 can be referred to as multiple cellular station.

As shown in Figure 2, broadcast singal is sent in system the shifting operated by broadcsting transmitter (BT) 295 Dynamic terminal 100.Broadcast reception module 111 is arranged on mobile terminal 100 and sentences reception as shown in Figure 1 The broadcast singal sent by BT295.In fig. 2 it is shown that several global positioning systems (GPS) satellite 300. Satellite 300 helps to position at least one in multiple mobile terminals 100.

In fig. 2, depict multiple satellite 300, it is understood that be, it is possible to use any number of defend Star obtains useful location information.GPS module 115 is generally configured to and satellite 300 as shown in Figure 1 Coordinate the location information wanted with acquisition.Substitute GPS tracking technique or outside GPS tracking technique, can To use other technology of the position that can follow the tracks of mobile terminal.It addition, at least one gps satellite 300 can Optionally or additionally to process satellite dmb transmission.

As a typical operation of wireless communication system, BS270 receives from various mobile terminals 100 Reverse link signal.Mobile terminal 100 generally participates in call, information receiving and transmitting communicates with other type of.Special The each reverse link signal determining base station 270 reception is processed in specific BS270.The data obtained It is forwarded to the BSC275 being correlated with.BSC provides call resource distribution and the soft handover included between BS270 The mobile management function of the coordination of process.The data received also are routed to MSC280 by BSC275, its Extra route service for forming interface with PSTN290 is provided.Similarly, PSTN290 with MSC280 forms interface, MSC Yu BSC275 forms interface, and BSC275 correspondingly controls BS270 Forward link signals to be sent to mobile terminal 100.

Based on above-mentioned mobile terminal hardware configuration and communication system, the display of shooting picture of the present invention is proposed Each embodiment of device.

With reference to Fig. 3, it is proposed that the first embodiment of the display device of shooting picture of the present invention, in this embodiment, The display device of shooting picture includes:

First acquisition module 10, after starting at photographic head shoot function, obtains described photographic head real-time The image information of capture；

Shooting characteristic information extracting module 20, is used for according to the first preset image recognition algorithm from described picture Surface information extracts the characteristic information of reference object；

First display module 30, for according to described characteristic information and shooting custom models show picture, institute State shooting custom model to be obtained by machine learning training.

The display device of the shooting picture that the present invention provides is mainly used in the terminal unit of band photographic head and carries out The image information that photographic head gets is shown when taking a picture or shoot the video.Shooting picture refers to by shooting Head is found a view the picture got.

The mode of above-mentioned startup photographic head shoot function has a lot, generally at the terminal unit with photographic head Upper meeting arranges physical button or application program launching button makes terminal unit startup photographic head shoot function make Photographic head enters shooting state, and under shooting state, the photographic head of terminal unit can be opened, and works as photographic head Scape can be obtained in real time after unlatching.

After photographic head shoot function starts, the first acquisition module 10 obtains the picture of photographic head captured in real time Information.I.e. under photographic head open mode, photographic head can continuous collecting image information.

After the image information getting photographic head captured in real time, shoot characteristic information extracting module 20 basis The first preset image recognition algorithm extracts the characteristic information of the reference object in the first image information, and first Image information is the picture that photographic head gets in real time.Above-mentioned reference object can be that photographic head gets Personage in image information or building, it is also possible to be personage and the reference object such as scenery, specifically chosen which A little reference objects carry out feature extraction and can be set the most in advance.Features described above information refers to take the photograph The information of the representative reference object feature that the image information got as head includes, such as number of person, The characteristic informations such as personage's size, building size, specifically needing to obtain which characteristic information can be according to need Select.Above-mentioned first image recognition algorithm is the shooting characteristic information in discriminatory analysis image The algorithm used.Conventional image recognition algorithm has a lot, can select as required.In reality Now, it is first determined which characteristic information in the first image information will be obtained, then select suitably figure As recognizer identifies the characteristic information in the first image information.

Above-mentioned preset shooting custom model comprises and represents user and shoot the characteristic information of finding a view of custom, such as Personage's size in the picture when user shoots, the coordinate position etc. of personage's X-axis in the picture.This shooting Custom model is that the training by machine learning obtains.

Machine learning (Machine Learning, ML) is a subject of artificial intelligence field, machine learning Purpose be to make computer simulation or realize the learning behavior of the mankind, to obtain new knowledge or skills, weight The existing knowledge structure of new organization.Machine learning can be divided into supervised learning and unsupervised learning two kinds.

Generally before carrying out machine learning, need to obtain substantial amounts of data and set up training set, in training set Data be referred to as sample data, then training set is trained by the algorithm of machine learning, output is passed through The parameter that training optimizes, obtains comprising the model of parameters optimization.Concrete, training is through sample number According to the parameter come in Optimized model, the result making model obtain more meets target requirement.Training set is passed through The algorithm of machine learning carries out the process that the process of computing is exactly training.Common machine learning algorithm has shellfish This algorithm of leaf, artificial neural network algorithm, clustering algorithm, Integrated Algorithm etc..

It is understood that for some terminal unit, can arrange and use not according to different users Same shooting custom model, specifically obtains the mark of user, selects corresponding shooting according to ID Custom model.

After extracting shooting characteristic information from image information, the first display module 30 is according to shooting characteristic information It is accustomed to models show picture, so that at terminal demonstration interface, user sees that photographic head will with preset shooting The picture of shooting, generates or time video starts the instruction recorded when now receiving photo, can be according to current Image information generates photo or recorded video.

With reference to Fig. 4, the first embodiment of display device based on shooting picture proposes shooting picture of the present invention The district of the first embodiment of the display device of the second embodiment of display device, the present embodiment and shooting picture It is not whether meet shooting when display according to shooting characteristic information and be accustomed in model and shooting feature letter The shooting custom that breath is corresponding shows the picture that photographic head gets, and in the present embodiment, above-mentioned first shows Show that module 30 includes:

Matching judgment unit 31, for described characteristic information is mated with described shooting custom model, Judging whether described characteristic information meets the first shooting custom, described first shooting custom is that described shooting is practised Shooting custom corresponding with described characteristic information in used model；

Display unit 32, for when described shooting characteristic information meets described first shooting custom, showing The image information of described photographic head captured in real time；

Adjust trigger element 33, be used for when described shooting characteristic information does not meets described first shooting custom, The acquisition parameters of described photographic head is adjusted, based on the described shooting after adjusting according to described first shooting custom Parameter triggers described first acquisition module and obtains the image information of described photographic head captured in real time.

Carrying out mating with custom model by characteristic information in embodiments of the present invention is to judge currently to obtain To the first image information in shooting feature whether meet user shooting custom, matching judgment unit 31 Whether judging characteristic information meets the first shooting custom, and above-mentioned first shooting custom is in shooting custom model The shooting custom corresponding with characteristic information, wherein the first shooting custom is embodied by characteristic information, i.e. By embodying the characteristic information of user habit and the characteristic information phase of picture of currently finding a view can be represented when realizing Join.Simultaneously, it can be determined that the most very meet, it is also possible to meet in the range of certain error, Specifically can set as required.

When characteristic information meets the first shooting custom, display photographic head implements the image information of capture, tool Body is that the image information got in real time by photographic head shows the display interface in terminal, makes the user can root Carry out taking pictures or recorded video according to current image information.

When shooting characteristic information and not meeting the first shooting custom, then adjust shooting according to the first shooting custom The acquisition parameters of head, and trigger the first acquisition module again obtain shooting based on the acquisition parameters after adjusting The image information of head captured in real time.

Such as, when receiving the instruction starting photographic head, the view data that photographic head returns is DataArray, DataArray is carried out image recognition analysis by the first preset image recognition algorithm, it is assumed that get figure Image height degree is height, and width is width, and mark array is done for { { P in multiple personage orientation_up1、P_bottom1、P_left1、 P_right1}…{P_upi、P_bottomi、P_lefti、P_righti, wherein, P_upiFor the coordinate of i-th people's peak, P_bottomi For the coordinate bottom i-th people, P_leftiFor coordinate, P on the left of i-th people_rightiFor position, the i-th people rightmost side The coordinate put.Then the height of i-th people is (P_upi-P_bottomi), it is fat or thin is (P_righti-P_lefti).Again According to preset shooting custom model, obtain user and tend to make when shooting the position of 1/n that personage accounts for picture Put.The picture the most now adjusted in the acquisition parameters of camera zooms in or out, and then reacquires picture Face, until by the highest or most crucial personage's height adjustment to height/n.

Here, again obtain the image information of photographic head acquisition after once adjusting and extract shooting The reason that characteristic information carries out mating is may not have to be adjusted in place completely, therefore after adjusting for the first time Can repeatedly finely tune until the image information got best suits the shooting custom of user.Meanwhile, also The number of times of adjustment can be the most directly set, such as, arrange and only adjust once or only adjust twice, again Or repeatedly adjust within 4 times, no longer it is adjusted when more than 4 times.

Such as, when the characteristic information of reference object and sample characteristics information being compared, it is right to obtain shooting In the characteristic information of elephant, the height of building is the 2/3 of picture, if now picture shows display circle in terminal Face then as it is shown in figure 5, and when shooting that in custom model, the user that comprises shoots depth of building be picture 5/6, the most now adjust the acquisition parameters of photographic head, when making photographic head find a view, the height of personage is picture 5/6, it is then based on the acquisition parameters after adjusting and again obtains the image information that photographic head obtains in real time, from this In image information extract shooting characteristic information, then will now shoot characteristic information with shooting be accustomed to model carry out Coupling, obtains height is picture the 5/6 of now personage, then the picture that can directly be got by photographic head Information shows in terminal, and display effect as shown in Figure 6, can be believed according to the picture that now photographic head obtains Breath carries out taking a picture or recorded video.

It is also possible to preserve the acquisition parameters after adjusting after the adjustment, open shooting when again receiving Head instruction time, can directly obtain image information according to the acquisition parameters preserved, the most now obtain Image information be the shooting image information that gets of custom according to user so that user when shooting without Need the most repeatedly to adjust, it is possible to directly shoot.

In embodiments of the present invention by the characteristic information of reference object is mated with shooting custom model And judge whether the characteristic information of reference object meets the first shooting custom, when these segmentation symbols match, directly display and take the photograph As head implements the image information of capture, when not meeting, adjust the shooting ginseng of photographic head according to the first custom Number, based on the acquisition parameters after adjusting, again obtains the image information of photographic head captured in real time, now draws Surface information is the image information that photographic head captures according to the acquisition parameters after adjusting, and obtains picture the most again If information meets the shooting custom of user, it is directly displayed at the display interface of terminal.By obtaining photographic head The image information photographed the picture being adjusted so that shooting shows according to shooting custom model accord with all the time The shooting custom closed.

With reference to Fig. 7, the first embodiment of display device based on shooting picture proposes shooting picture of the present invention The district of the first embodiment of the display device of the 3rd embodiment of display device, the present embodiment and shooting picture It is not in the present embodiment when receiving other and adjusting order, life can be adjusted according to other received Order is adjusted, and in the present embodiment, the display device of the shooting picture that the present invention proposes also includes:

Second display module 40, if manually adjusting instruction for receiving, then manually adjusts finger described in basis Order adjusts the acquisition parameters of described photographic head, the image information that after display adjustment, described photographic head obtains.

It is the most above-mentioned that to manually adjust instruction be the acquisition parameters to photographic head that triggers of user The instruction being adjusted.When receive manually adjust instruction after the second display module 40 according to manually adjusting finger The image information that photographic head is got by order in real time is adjusted, and the method for adjustment is according to manually adjusting finger Order adjusts the acquisition parameters of photographic head, and the acquisition parameters after then adjusting according to photographic head obtains and shows picture Surface information.

It is understandable that can also arrange other adjusts instruction and priority, makes in the bat adjusting photographic head Preferential acquisition parameters is selected to be adjusted according to the priority adjusting instruction when taking the photograph parameter.

In embodiments of the present invention when again obtaining after image information being adjusted according to shooting custom model Get when manually adjusting instruction, adjust, according to manually adjusting instruction, the image information that photographic head obtains in real time, The image information that photographic head is obtained meets the shooting custom of user all the time.

With reference to Fig. 8, the 4th embodiment of the display device of shooting picture of the present invention is proposed based on above-described embodiment, The present embodiment is with the difference of display device above-described embodiment of shooting picture, and the present embodiment passes through machine The method learnt sets up shooting custom model, in the present embodiment, showing of the shooting picture that the present invention proposes Showing device also includes:

Second acquisition module 50, for obtaining the photo in preset memory block and/or video file；

Sample characteristics information extraction modules 60, is used for according to the second preset image recognition algorithm from described photograph Sheet and/or video file extract sample characteristics information successively；

Machine learning module 70, for confirming that described sample characteristics information is the training sample of machine learning, Described training sample is trained by preset machine learning algorithm, and obtains described shooting custom mould Type.

Module in embodiments of the present invention is for creating shooting custom model according to the mode of machine learning.

Second acquisition module 50 obtains the photo in preset memory block and/or regards in embodiments of the present invention Frequency file, preset memory block can select as required, such as, can be that user terminal preserves Photo and/or the memory block of video, it is also possible to be photo and/or the video etc. of the preservation of network storage address.

Above-mentioned second image recognition algorithm is for discriminatory analysis photo and/or video file thus to extract successively Sample characteristics information in photo and/or video file, above-mentioned second image recognition algorithm can be as required Select, can consistent with the first image recognition algorithm can also be inconsistent, specifically can be as required Select.Can also be according to photo and/or the dissimilar selection of video file when selecting image algorithm Different image recognition algorithms is identified.Above-mentioned sample characteristics information is carried out according to the purpose of machine learning Selecting, will choose which characteristic information and carry out which characteristic information machine learning just selects, sample characteristics is believed The feature of breath can include the feature shooting characteristic information but be not limited to shoot the feature of characteristic information.Such as Sample characteristics information can include personage's number, the personage position in picture, the relation of personage and scenery, The information such as the number of building area, animal etc. and the position in picture, ratio.

After sample characteristics information extraction modules 60 extracts sample characteristics information, machine learning module 70 confirms Sample characteristics information is the training sample of machine learning, by training sample by preset machine learning algorithm It is trained, represents user shoot the model of custom exporting after training, confirm that this model is Shooting custom model.Suitable machine learning algorithm can be selected as required to be trained.

Such as, by gathering great amount of samples, number of person, building quantity, people in sample information is extracted Thing and the scale information of building, by individual as personage in the shooting custom model that machine learning obtains Number is 1, and when building quantity is 1, personage is 1:2 with the size of building.When reality During shooting, or get photographic head captured in real time to middle personage's number be 1, building quantity is 1 Time individual, the parameter adjustment setting that size is 1:2 to personage Yu building that photographic head is found a view.

The sample characteristics information of said extracted can be all as training set, it is also possible to choose a portion As training set, another part is as test set.

In embodiments of the present invention by obtaining the photo in preset memory block and/or video file, and from The photo got and/or video file extract sample characteristics information successively, the sample characteristics letter that will extract Cease the training sample as machine learning, training sample is trained, obtain shooting custom model, make When must shoot again by photographic head, the shooting that can be extracted by the image information that capture from photographic head is special Reference breath mates with shooting custom model, thus the acquisition parameters adjustment photographic head adjusting photographic head is caught The picture that the image information obtained makes photographic head photograph meets user and shoots custom, and use to photo and/ Or video file carries out the mode of machine learning and sets up the foundation more adduction making model of shooting custom model Reason is with accurate.

With reference to Fig. 9, the 4th embodiment of display device based on shooting picture proposes shooting picture of the present invention The district of the 4th embodiment of the display device of the 5th embodiment of display device, the present embodiment and shooting picture Not being, training set is constantly updated by the present embodiment so that shooting custom model can constantly be revised, at this In embodiment, the display device of the shooting picture that the present invention proposes also includes:

3rd acquisition module 80, after the photo in described memory block and/or video file have renewal, Obtain the photo and/or video file updated；

Update characteristic information extracting module 90, be used for according to the 3rd preset image recognition algorithm after updating Described photo and/or video file in successively extract update characteristic information；

Add module 100, for described renewal characteristic information is added to described training sample, make described Training sample is updated, in order to be trained the shooting after being updated again with described training sample Custom model.

In embodiments of the present invention after the photo in memory block and/or video file have renewal, the 3rd obtains Module 80 obtains the photo and/or video file updated.When the photo in memory block and/or video file have Update and show that user newly have taken photo or recorded video or have modified former shooting photo and/or video Image information, then update characteristic information extracting module 90 according to the 3rd preset image recognition algorithm from renewal Photo and/or video file extract renewal characteristic information successively.Above-mentioned 3rd image recognition algorithm can be with Second image recognition algorithm unanimously can also be inconsistent, specifically can select as required.

After extracting renewal characteristic information, add module 100 and renewal characteristic information is added to former training sample In Ben, make training sample constantly update, after training sample updates, can continue training sample is carried out Training obtains new shooting custom model, so that shooting custom model is constantly updated, makes to take the photograph every time It is accustomed to as can more meet the shooting of user when head is found a view.

It is understood that again obtain in preset memory block, the photo of renewal and/or the time of video can To be set as required, can with the photo of the renewal in the preset memory block of timing acquisition and/or video, Which kind of can also all obtain after user have taken new photo and/or video, specifically in condition every time Lower obtain the photo and/or video updated and extract renewal characteristic information and add to can be according to need in training set Being set, the training sample in training set is the biggest, the most accurate to the model of training output.

In embodiments of the present invention in the case of the photo preserved in memory block and/or video file have renewal, Obtain the photo and/or video file updated, extract renewal spy successively from the photo updated and/or video file Reference ceases, and adds, by updating characteristic information, the training being used for carrying out machine learning foundation shooting custom model Collection so that the data of the training set of shooting custom model are more, so that shooting custom model is more accurate, Also the purpose that shooting custom model changes therewith can be reached along with the change of the custom of user.

With reference to Figure 10, it is proposed that the first embodiment of the display packing of shooting picture of the present invention, the present embodiment It is method item embodiment corresponding to the display device first embodiment of shooting picture of the present invention, at the present embodiment In, the display packing of shooting picture that the present invention proposes includes step:

Step S10, after photographic head shoot function starts, obtains the picture letter of described photographic head captured in real time Breath；

Step S20, extracts reference object according to the first preset image recognition algorithm from described image information Characteristic information；

Step S30, according to described characteristic information and shooting custom models show picture, described shooting custom mould Type is obtained by machine learning training.

The display packing of the shooting picture that the present invention provides is mainly used in the terminal unit of band photographic head and carries out The image information that photographic head gets is shown when taking a picture or shoot the video.Shooting picture refers to by shooting Head is found a view the picture got.

After photographic head shoot function starts, obtain the image information of photographic head captured in real time.I.e. in shooting Under head open mode, photographic head can continuous collecting image information.

After the image information getting photographic head captured in real time, according to the first preset image recognition algorithm Extracting the characteristic information of reference object in the first image information, the first image information is that photographic head obtains in real time The image information got.Above-mentioned reference object can be the personage in the image information that photographic head gets or Building, it is also possible to being the reference objects such as personage and scenery, which reference object specifically chosen carries out feature Extraction can be set the most in advance.Features described above information refers to the picture letter that photographic head gets The information of the representative reference object feature that breath includes, such as number of person, personage's size, building are big Little characteristic information such as grade, specifically needing to obtain which characteristic information can select as required.Above-mentioned One image recognition algorithm is the algorithm that the shooting characteristic information in discriminatory analysis image is used.Conventional Image recognition algorithm have a lot, can select as required.When realizing, it is first determined obtain Take which characteristic information in the first image information, then select suitable image recognition algorithm to identify Characteristic information in one image information.

After extracting shooting characteristic information from image information, practise according to shooting characteristic information and preset shooting Used models show picture, so that user sees, at terminal demonstration interface, the picture that photographic head will shoot, when Now receive photo generate or video start record instruction time, can according to current picture information generate shine Sheet or recorded video.

With reference to Figure 11, the first embodiment of display packing based on shooting picture of the present invention proposes the present invention The first of the display packing of the second embodiment of the display packing of shooting picture, the present embodiment and shooting picture The difference of embodiment is, the present embodiment is that display device second embodiment of shooting picture of the present invention is corresponding Method item embodiment, in the present embodiment, above-mentioned according to described characteristic information and shooting custom model show Show that the refinement step of picture includes:

Step S31, mates described characteristic information with described shooting custom model, it is judged that described feature Whether information meets the first shooting custom, and described first shooting custom is that described shooting is accustomed in model and institute State the shooting custom that characteristic information is corresponding；If so, step S32 is performed；If it is not, perform step S33；

Step S32, shows the image information of described photographic head captured in real time；

Step S33, adjusts the acquisition parameters of described photographic head, based on adjustment according to described first shooting custom After described acquisition parameters perform the step of image information of described acquisition described photographic head captured in real time.

It is current in order to judge for carrying out mating with shooting custom model by characteristic information in embodiments of the present invention Whether the shooting feature in the first image information got meets the shooting custom of user.Specifically judge Whether characteristic information meets the first shooting custom, and above-mentioned first shooting custom is that shooting is accustomed in model and spy The shooting custom that reference breath is corresponding, wherein the first shooting custom is embodied by characteristic information, i.e. realizes Time can match embodying currently the find a view characteristic information of picture of the characteristic information of user habit and expression. Simultaneously, it can be determined that the most very meet, it is also possible to meet in the range of certain error, specifically Can set as required.

When shooting characteristic information and not meeting the first shooting custom, then adjust shooting according to the first shooting custom The acquisition parameters of head, and the picture of photographic head captured in real time is again obtained based on the acquisition parameters after adjusting Information.

The first embodiment of display packing based on shooting picture of the present invention proposes shooting picture of the present invention The district of the first embodiment of the display packing of the 3rd embodiment of display packing, the present embodiment and shooting picture Not being, the present embodiment is the method item that the 3rd embodiment of the display device of shooting picture of the present invention is corresponding Embodiment, in the present embodiment, the display packing of the shooting picture that the present invention proposes also includes:

It is the most above-mentioned that to manually adjust instruction be the acquisition parameters to photographic head that triggers of user The instruction being adjusted.When receive manually adjust instruction after according to manually adjust instruction real-time to photographic head The image information got is adjusted, and the method for adjustment adjusts photographic head according to manually adjusting instruction Acquisition parameters, the acquisition parameters after then adjusting according to photographic head obtains and shows image information.

Display packing above-described embodiment based on shooting picture of the present invention proposes the aobvious of shooting picture of the present invention Show that the 4th embodiment of method, the present embodiment exist with the difference of display packing above-described embodiment of shooting picture It is that method item corresponding to the 4th embodiment of the display device of shooting picture of the present invention is implemented in, the present embodiment Example, in the present embodiment, the display packing of the shooting picture that the present invention proposes also includes:

Obtain the photo in preset memory block and/or video file；

The step described in embodiments of the present invention is to create shooting custom mould according to the mode of machine learning The process of type.

First the photo in preset memory block and/or video file are obtained, preset Memory block can select as required, can be such as user terminal preserve photo and/or video Memory block, it is also possible to be the photo that preserves of network storage address and/or video etc..

After extracting sample characteristics information, confirmatory sample characteristic information is the training sample of machine learning, will instruction Practice sample to be trained by preset machine learning algorithm, represent user's bat exporting after training Take the photograph the model of custom, confirm that this model is for shooting custom model.Suitable machine can be selected as required Device learning algorithm is trained.

4th embodiment of display packing based on shooting picture of the present invention proposes shooting picture of the present invention The district of the first embodiment of the display packing of the 5th embodiment of display packing, the present embodiment and shooting picture Not being, the present embodiment is the method item that the 5th embodiment of the display device of shooting picture of the present invention is corresponding Embodiment, in an embodiment, the display packing of the shooting picture that the present invention proposes also includes:

In embodiments of the present invention after the photo in memory block and/or video file have renewal, obtain and update Photo and/or video file.When the photo in memory block and/or video file have renewal to show, user newly claps Take the photograph photo or recorded video or have modified former shooting photo and/or the image information of video, the most permissible More new feature is extracted successively from the photo updated and/or video file according to the 3rd preset image recognition algorithm Information.Above-mentioned 3rd image recognition algorithm can consistent with the second image recognition algorithm can also be inconsistent, Specifically can select as required.

After extracting renewal characteristic information, renewal characteristic information is added to former training sample, makes training Sample is constantly updated, and after training sample updates, can continue to be trained training sample to obtain new Shooting custom model, so that shooting custom model is constantly updated, energy when making each photographic head find a view More meet the shooting custom of user.

These are only the preferred embodiments of the present invention, not thereby limit the scope of the claims of the present invention, every Utilize equivalent structure or equivalence flow process conversion that description of the invention and accompanying drawing content made, or directly or Connect and be used in other relevant technical fields, be the most in like manner included in the scope of patent protection of the present invention.

Claims

1. the display device of a shooting picture, it is characterised in that described device includes:

2. device as claimed in claim 1, it is characterised in that described first display module includes:

3. device as claimed in claim 1, it is characterised in that described device also includes:

4. the device as described in any one of claims 1 to 3, it is characterised in that described device also includes:

5. display device as claimed in claim 4, it is characterised in that described device also includes:

6. the display packing of a shooting picture, it is characterised in that said method comprising the steps of:

7. method as claimed in claim 6, it is characterised in that described according to described characteristic information and bat Take the photograph custom models show picture to include:

8. method as claimed in claim 6, it is characterised in that described method also includes:

9. the method as described in any one of claim 6 to 8, it is characterised in that described method also includes:

Obtain the photo in preset memory block and/or video file；

From described photo and/or video file, sample is extracted successively according to the second preset image recognition algorithm Eigen information；

10. method as claimed in claim 9, it is characterised in that described method also includes:

After photo in described memory block and/or video file have renewal, obtain the photo updated and/or Video file；

According to the 3rd preset image recognition algorithm from update after described photo and/or video file depend on Secondary extraction updates characteristic information；