CN110119684A

CN110119684A - Image-recognizing method and electronic equipment

Info

Publication number: CN110119684A
Application number: CN201910289400.1A
Authority: CN
Inventors: 王骅
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2019-04-11
Filing date: 2019-04-11
Publication date: 2019-08-13
Also published as: WO2020207328A1

Abstract

The embodiment of the present application provides a kind of image-recognizing method and electronic equipment, wherein this method comprises: electronic equipment calls the first camera to acquire the first image data；First camera includes first sensor, first sensor includes the first image-sensitive cell array, the quantity of image-sensitive unit is less than or equal to 40000 in first image-sensitive cell array, and the color depth of the image data of first sensor output is the first color depth, and the first color depth is less than 8.Implement the embodiment of the present application, the safety of user information can be improved.

Description

Image-recognizing method and electronic equipment

Technical field

This application involves electronic technology field more particularly to a kind of image-recognizing methods and electronic equipment.

Background technique

With the continuous development of the electronic equipments such as mobile phone, plate, smart television, these electronic equipments make in people's lives With more and more common.Currently, settable conventional camera collection image data on electronic equipment, to carry out environment measuring, people Face detection, recognition of face etc..

However, the camera continually opened on electronic equipment for a long time or excessively can obtain user image, behavior, life The privacy informations such as the personal characteristics abundant such as environment living, behavior, environment can be to user information if these information are leaked Safety and privacy cause damages.

Summary of the invention

This application discloses a kind of image-recognizing method and electronic equipments, and the safety of user information can be improved.

In a first aspect, the embodiment of the present application provides a kind of image-recognizing method, which comprises electronic equipment calls First camera acquires the first image data；First camera includes first sensor, and the first sensor includes the One image-sensitive cell array, the quantity of image-sensitive unit is less than or equal to 40000 in the first image-sensitive cell array, and described first passes The color depth of the image data of sensor output is the first color depth, and first color depth is less than 8.

In above-mentioned image-recognizing method, compared with existing camera, the first camera has low color depth and bat Image is taken the photograph with low resolution, carries less information.To reduce the image information quilt abundant of the first camera shooting It reveals and is endangered caused by the safety to user information and privacy, improve the safety of user information.

Wherein, the resolution ratio of camera shooting image is by image-sensitive list in the first image-sensitive cell array in above-mentioned first camera The quantity of member determines.Optionally, image-sensitive cell array is that multiple image-sensitive units arrange the array to be formed, such as according to rectangular uniform Arrangement, laterally upper and longitudinal image-sensitive element number is respectively 128 and 96 to image-sensitive cell array, i.e. image-sensitive cell array is 128 × 96 array, then the resolution ratio of the first camera shooting image is 128 × 96.

Optionally, image-sensitive cell array can be arranged in circular array, then the number of the diametrically image-sensitive unit of the circular array Amount is less than or equal to 200, such as diametrically the quantity of image-sensitive unit is 128.

Optionally, the color depth of the image data of first sensor output is 4, and each pixel can in first sensor 16 grades of certain color in white or three primary colours red, green, blue are described.

In some embodiments of the present application, first camera is always in the electronic device works.Often The first camera opened is with low color depth and shooting image has low resolution, carries less information, improves user's letter The safety of breath.

In some embodiments of the present application, the electronic equipment call the first camera acquire the first image data it Afterwards, the method also includes: the electronic equipments carries out image recognition to the first image data, and according to recognition result and Current state executes relevant operation.

In some embodiments of the present application, first color depth is 4, the image-sensitive cell array it is laterally upper and The maximum quantity of the image-sensitive unit is respectively on 128 and 96 or the lateral upper and longitudinal direction of the image-sensitive cell array on longitudinal direction The maximum quantity of the image-sensitive unit is respectively 144 and 96.

In some embodiments of the present application, the recognition result is to detect facial image, and current state is described Electronic equipment is in the lock state；The electronic equipment executes relevant operation, comprising: the electronic equipment calls second camera Carry out face unlock.Wherein: the second camera includes second sensor, and the second sensor includes the second image-sensitive unit The quantity of array, image-sensitive unit described in the second image-sensitive cell array is greater than picture described in the first image-sensitive cell array The color depth of the quantity of quick unit, the image data of the second sensor output is the second color depth, second color Color depth is greater than first color depth.Second camera can be the camera 200 in example shown in Fig. 1.

In above-mentioned method, by the normally opened acquisition image data of the first camera, and compared with second camera, the first camera shooting Head is with low color depth and shooting image has low resolution, carries less information.It is clapped to reduce normally opened camera The image taken the photograph information abundant is leaked harm caused by safety and privacy to user information, improves the peace of user information Quan Xing.Recognition of face is carried out using second camera to unlock electronic equipment, and second camera has high color depth and shooting Image has high-resolution, and the accuracy of recognition of face can be promoted while guaranteeing user information safety.

In some embodiments of the present application, the recognition result is to detect facial image, and the current state is The electronic equipment is in bright screen state；The electronic equipment executes relevant operation, comprising: by the display screen of the electronic equipment It is set as being always on state.In the above method, the first normally opened camera can real-time detection facial image, detect facial image then Setting display screen is always on, to be offering convenience property of user.And compared with second camera, which has Low color depth and shooting image have low resolution, carry less information.To reduce the figure of the first camera shooting As information abundant is leaked harm caused by safety to user information and privacy, the safety of user information is improved.

In some embodiments of the present application, the recognition result is the facial image for detecting the first user, described to work as Preceding state is that the electronic equipment is in the lock state；The electronic equipment executes relevant operation, comprising: the electronic equipment It calls second camera to carry out recognition of face, identifies and successfully then show the corresponding user's desktop of first user.Above-mentioned use First camera and second camera cooperation are realized in the scheme of electronic equipment unlock, perceive people using the first normally opened camera Face image simultaneously identifies user, so as to promote the ability of electronic equipment facial image identification, also can guarantee and is set using same electronics The isolation of standby user-to-user information improves the convenience that user unlocks electronic equipment.In addition, being executed using the first camera After recognition of face success, recalls with high color depth and there is shooting image high-resolution second camera to execute again Recognition of face just unlocks electronic equipment after identifying successfully, the reliability and safety of face unlock can be improved.

Wherein, compared with the first camera, second camera sensor output image data have high color depth and Shooting image has high-resolution, just opens when called and acquires image data.It is right when electronic equipment is in the lock state The permission of user's operation electronic equipment is defined.After unlocking electronic equipment, user can grasp electronic equipment Make.

Optionally, recognition result is to detect images of gestures, and the current state is that the electronic equipment is in call State；The electronic equipment executes relevant operation, comprising: the electronic equipment turns off or on microphone.Wherein, electronic equipment In preserve images of gestures and mute microphone (MIC) corresponding relationship, or preserve images of gestures and open microphone corresponding relationship.

Illustratively, palm is preserved in electronic equipment is deployed into this images of gestures of holding with a firm grip pass corresponding with mute microphone (MIC) System, and preserve palm grip to this images of gestures of expansion and open microphone corresponding relationship.

In some embodiments of the present application, the current state is that the electronic equipment shows application interface；The knowledge Other result is to detect between the upper direction of facial image and the upper direction of the application interface that angular deviation is greater than or equal to the One threshold value；The electronic equipment executes relevant operation, comprising: the electronic equipment adjusts the upper direction of the application interface, will Angular deviation is adjusted to be less than or equal to described the between the upper direction of the application interface and the upper direction of the facial image One threshold value.In the above method, the first normally opened camera can the upper direction of real-time detection facial image and the top of application interface Angle between carries out horizontal/vertical screen switching according to the angle, to be offering convenience property of user.And with second camera phase Than the first normally opened camera is with low color depth and shooting image has low resolution, carries less information.To The image information abundant for reducing the shooting of the first camera is leaked the safety to user information and danger caused by privacy Evil, improves the safety of user information.

Illustratively, first threshold is 45 degree.

In some embodiments of the present application, the recognition result is to detect interior operator seat environment, described current State is that the electronic equipment is in running order；The electronic equipment executes relevant operation, comprising: the electronic equipment is opened Driving mode, the electronic equipment can broadcast incoming information and message under the driving mode, and be able to respond user speech Execute relevant operation.In the above method, the first normally opened camera can the environment that is presently in of real-time detection, be according to the environment Operator seat environment changing is driving mode, to be offering convenience property of user.And compared with second camera, this normally opened first Camera is with low color depth and shooting image has low resolution, carries less information.To reduce the first camera shooting The image information abundant of head shooting is leaked harm caused by safety and privacy to user information, improves user information Safety.

In some embodiments of the present application, the area of the first image-sensitive cell array and the second image-sensitive unit battle array In the identical situation of the area of column, the density of image-sensitive unit is less than the second image-sensitive unit in the first image-sensitive cell array The density of image-sensitive unit on array；

It is described in the density of the image-sensitive unit and the second image-sensitive cell array in the first image-sensitive cell array In the identical situation of the density of image-sensitive unit, the area of the first image-sensitive cell array is less than the second image-sensitive cell array Area.

In some embodiments of the present application, the first sensor includes the first analog to digital conversion circuit, first mould The detection accuracy that lateral circuit is simulated in number conversion circuit is related to first color depth；The second camera includes second Sensor, the second sensor include the second analog to digital conversion circuit, the color of the image data of the second sensor output Depth is the second color depth, and detection accuracy and second color that lateral circuit is simulated in second analog to digital conversion circuit are deep Degree is related；The detection accuracy that lateral circuit is simulated in first analog to digital conversion circuit is less than mould in second analog to digital conversion circuit The detection accuracy of quasi- lateral circuit, first color depth are less than second color depth.

Illustratively, the level detection precision for simulating lateral circuit can be reduced to 1/16 from 1/256, to reduce camera The color depth of the image data of 100 sensors output.

In some embodiments of the present application, the recognition result is to detect human body image, and the current state is The electronic equipment is stored with the first instruction, and the first instruction instruction detects that the human body image is then sent to terminal and alarms Message；The electronic equipment executes relevant operation, comprising: the electronic equipment sends the warning message to the terminal.

In some embodiments of the present application, the recognition result is to detect to fall down posture, and the current state is The electronic equipment is stored with the second instruction, and the second instruction instruction detects that the posture of falling down then sends alarm to terminal Message；The electronic equipment executes relevant operation, comprising: the electronic equipment sends the warning message to the terminal.

In the above method, under household safety-protection scene the first normally opened camera can real-time detection human body image, detect Human body image is then alarmed according to setting, or detects that falling down posture then alarms according to setting, to be offering convenience property of user. Compared with existing camera, the first normally opened camera is with low color depth and shooting image has low resolution, takes With less information.So that the image information abundant for reducing the shooting of the first camera is leaked the safety to user information It is endangered with caused by privacy, improves the safety of user information.

Second aspect, this application provides a kind of electronic equipment, comprising: one or more processors, memory and first Camera, in which: first camera includes first sensor, and the first sensor includes the first image-sensitive cell array, The quantity of image-sensitive unit is less than or equal to 40000 in the first image-sensitive cell array, the image of the first sensor output The color depth of data is the first color depth, and first color depth is less than 8；The memory is for storing computer Program code, the computer program code include computer instruction, when one or more of processors execute the calculating When machine instructs, so that the electronic equipment executes image described in first aspect or any possible embodiment of first aspect Recognition methods.

The third aspect, this application provides a kind of computer storage mediums, including computer instruction, when the computer refers to When order is run on an electronic device, so that the electronic equipment executes such as first aspect or any possible reality of first aspect The method that the mode of applying provides.

Fourth aspect, the embodiment of the present application provide a kind of computer program product, when computer program product is in computer When upper operation, so that computer executes the method provided such as first aspect or any possible embodiment of first aspect.

It is to be appreciated that electronic equipment described in the second aspect of above-mentioned offer, computer described in the third aspect store Computer program product described in medium or fourth aspect is used to execute first aspect or any possibility of first aspect Embodiment provided by method.Therefore, attainable beneficial effect can refer to the beneficial effect in corresponding method, this Place repeats no more.

Detailed description of the invention

The attached drawing that the embodiment of the present application is used is introduced below.

Fig. 1 is the structural schematic diagram of camera in a kind of electronic equipment provided by the embodiments of the present application；

Fig. 2 is the structural schematic diagram of a kind of electronic equipment 10 provided by the embodiments of the present application；

Fig. 3 is a kind of hardware module 400 of camera 100 provided by the embodiments of the present application and the structure of software module 500 Schematic diagram；

Fig. 4 is a kind of schematic diagram of horizontal/vertical screen switching provided by the embodiments of the present application；

Fig. 5 is the image schematic diagram that a kind of camera 100 provided by the embodiments of the present application is shot；

Fig. 6 is another hardware module 600 of intelligent video camera head provided by the embodiments of the present application and the knot of software module 700 Structure schematic diagram；

Fig. 7 is a kind of structural schematic diagram of intelligent video camera head provided by the embodiments of the present application；

Fig. 8 is a kind of flow diagram of image-recognizing method provided by the embodiments of the present application.

Specific embodiment

The embodiment of the present application is described below with reference to the attached drawing in the embodiment of the present application.The implementation of the embodiment of the present application The term that mode part uses is only used for explaining the specific embodiment of the application, and is not intended to limit the application.

Be described below the invention relates to application scenarios.Camera, microphone, the whole world are configured in electronic equipment Positioning system (global positioning system, GPS) chip, various kinds of sensors (such as magnetic field sensor, gravity pass Sensor, gyro sensor etc.) etc. devices, for perceiving external environment, the movement of user etc..According to the outside perceived The movement of environment and user, electronic equipment provide a user personalized, situated business experience.Wherein, camera can Obtain the movement of environment, user that abundant, accurate information makes outside electronic equipment perception.

For the movement of environment, user outside perception, the camera on electronic equipment can be under electronic equipment open state It is normally opened.Wherein, camera is normally opened refers to, is switched under working condition in electronic equipment, and camera is just constantly in without called Working condition, can acquire image data, and electronic equipment can carry out image recognition according to the image data of acquisition.The embodiment of the present application In, electronic equipment display screen under open state can be breath screen state and be also possible to bright screen state.Specifically, electronic equipment is opened After machine in the case where ceasing screen state, electronic equipment still is able to receive message (such as instant application message), is also able to carry out positioning, step counting Etc. functions, camera normally opened in electronic equipment is also at working condition to acquire image data at this time, and electronic equipment can basis The image data of acquisition carries out image recognition, so that environment, the movement of user etc. outside electronic equipment perception.Electronic equipment is opened After machine under bright screen state, normally opened camera it is similar be also at working condition to acquire image data.

The example that personalized, situated business experience is provided a user using normally opened camera is given below.

Example one: the front camera of electronic equipment is normally opened, and when detecting face, i.e., output analysis result makes electronics The display screen of equipment is always on, and keeps display screen to be always on when user watches electronic equipment display screen to realize.

Example two: front camera is normally opened, and when detecting face, the bat of facial image is detected according to front camera It takes the photograph walking direction user's transverse screen and uses electronic equipment using still vertical screen.When judging result is that user's transverse screen uses electronic equipment Carry out transverse screen display, judging result is user's vertical screen using carrying out vertical screen display when electronic equipment.

Example three: the normally opened detection image data of camera, electronic equipment determine current institute according to the image data detected The environment at place is interior operator seat environment, then adjusting electronic equipment is driving mode.Under driving mode, electronic equipment can show and lead The page that navigates executes navigation feature, and the phonetic order that may also respond to user executes dial feature or AF playing function.Example Property, electronic equipment can broadcast incoming call or short message under driving mode automatically, do not need user and go to operate manually.In addition also There is phonetic function, button, which says speech electronic equipment, on user's click electronic equipment can be performed, such as " playing music ", " give So-and-so makes a phone call."

Example four: for the display screen of electronic equipment in the case where ceasing screen state, front camera is normally opened.It is detected in front camera When face image data, electronic equipment carries out recognition of face according to collected face image data, solves after recognition of face success Lock electronic equipment.After electronic equipment unlock, electronic equipment can show that desktop, desktop include application icon.Application icon can be rung Application, such as " camera ", " music " and " video " etc. is called to apply using the operation at family.

It should be understood that the above-mentioned application scenarios citing to normally opened camera is only used for explaining the embodiment of the present application, no Restriction should be constituted, normally opened camera can be also used for other scenes, and the embodiment of the present application is not construed as limiting this.

The embodiment of the present application provides a kind of camera, which can be applicable on electronic equipment.Electronic equipment is being switched on Under state, the camera is normally opened.Electronic equipment can be implemented as any one following equipment comprising camera: mobile phone, plate Computer (pad), palm PC (personal digital assistant, PDA), laptop, surpasses portable game machine Grade mobile personal computer (ultramobile personal computer, UMPC), handheld computer, net book, vehicle-mounted matchmaker Body playback equipment, wearable electronic, virtual reality (virtual reality, VR) terminal device, augmented reality The Numeral Display Products such as (augmented reality, AR) terminal device.

Referring to Fig. 1, Fig. 1 is the structural schematic diagram of camera in a kind of electronic equipment provided by the embodiments of the present application.Such as It may include camera 100, camera 200 and display screen 300 on electronic equipment 10 shown in Fig. 1.Wherein, camera 100 has low Color depth and shooting image have low resolution.The camera 100 is normally opened under 10 open state of electronic equipment.Camera 100 for perceiving the movement of external environment, user.Camera 200 can be used for acquiring face image data and carry out recognition of face, And then realize the unlock of electronic equipment 10, identity sign test, using unlock etc..Compared with camera 100,200 sensor of camera is defeated Image data out has higher resolution ratio with the image of higher color depth and shooting.

Illustratively, the resolution ratio that camera 100 shoots image is 200 × 200, that is, the every side pixel value of the image shot is 200.The resolution ratio that camera 200 shoots image is 2560 × 1920, that is, the pixel value in the picture traverse direction shot is 2560, The pixel value of short transverse is 1920.The color depth of the image data of 100 sensor of camera output is 4, each pixel The image data of 16 a certain grades (2 4 powers) in exportable white or three primary colours (red, green, blue).Camera 200 passes The color depth of the image data of sensor output is 8, each pixel is exportable white or three primary colours (red, green, blue) in it is a certain 256 grades (2 8 powers) image data.

In above-mentioned electronic equipment 10, the movement of external environment, user is perceived using normally opened camera 100, so as to The ability for promoting electronic equipment perception environment improves the convenience that user uses electronic equipment.It is normally opened compared with camera 200 Camera 100 with low color depth and shooting image have low resolution, letter abundant on the image of shooting can be reduced Breath is leaked harm caused by safety and privacy to user information, improves the safety of user information.

Be described below the invention relates to concept.

(1) resolution ratio

For same focal length camera, the details that the image of the more camera output of pixel includes is more, figure As more clear.Image resolution ratio is represented by the pixel quantity on each direction.Such as resolution ratio 640 × 480, indicate camera shooting The pixel quantity in the picture traverse direction of head shooting is 640, and the pixel quantity of short transverse is 480, can be by 307200 pixels The camera of (about 300,000 pixels) shoots to obtain.For another example the image that a resolution ratio is 1600 × 1200, it can be by pixel number Amount shoots to obtain for 1920000 camera.

In the embodiment of the present application, camera shoots the resolution ratio of image by image-sensitive unit in image-sensitive cell array in camera Quantity determine.The description as described in image-sensitive cell array can refer to example introduction described by Fig. 3.Illustratively, if camera Image-sensitive cell array be 128 × 96 array, then camera shooting image resolution ratio be 128 × 96.

(2) color depth

Color depth is also known as color digit, with binary position (bit) for unit, indicates the quantity of record tone.Color The bigger image of depth, have bigger Color Range, image more can more subtly restore true scene each color highlights and The details of dark portion.For example, the image that color depth is 24, can theoretically indicate that 16777216 (2 24 powers) plant color.

Image data with a certain color depth is the figure of another color depth exported using the sensor of camera As data are calculated by demosaicing algorithms, the color depth of the image data of camera sensing device output determines the color of image Color depth.The image data of general camera sensing device output is at least 8 color depths, i.e., white or three primary colours (it is red, It is green, blue) in a certain color be divided into (2 8 powers) 256 different grades.Therefore, the image of camera sensing device output The color depth of data is bigger, and the color depth of the image of shooting is bigger, and image more can truly restore color, and image is taken Band is mostly by the information of bat object.

Fig. 2 is the structural schematic diagram of a kind of electronic equipment 10 provided by the embodiments of the present application.

Electronic equipment 10 may include processor 110, external memory interface 120, internal storage 121, general serial Bus (universal serial bus, USB) interface 130, charge management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio-frequency module 170, loudspeaker 170A, receiver 170B, microphone 170C, earphone interface 170D, sensor module 180, key 190, motor 191, indicator 192, camera 193, display screen 194 and Subscriber Identity Module (subscriber identification module, SIM) card interface 195 Deng.Wherein sensor module 180 may include pressure sensor 180A, gyro sensor 180B, baroceptor 180C, magnetic Sensor 180D, acceleration transducer 180E, range sensor 180F, close to optical sensor 180G, fingerprint sensor 180H, temperature Spend sensor 180J, touch sensor 180K, ambient light sensor 180L, bone conduction sensor 180M etc..

It is understood that the structure of signal of the embodiment of the present invention does not constitute the specific restriction to electronic equipment 10.? In other embodiments of the application, electronic equipment 10 may include than illustrating more or fewer components, or the certain portions of combination Part perhaps splits certain components or different component layouts.The component of diagram can be with hardware, software or software and hardware Combination realize.

Processor 110 may include one or more processing units, such as: processor 110 may include application processor (application processor, AP), modem processor, graphics processor (graphics processing Unit, GPU), image-signal processor (image signal processor, ISP), controller, memory, coding and decoding video Device, digital signal processor (digital signal processor, DSP), baseband processor and/or Processing with Neural Network Device (neural-network processing unit, NPU) etc..Wherein, different processing units can be independent device, Also it can integrate in one or more processors.

Wherein, controller can be nerve center and the command centre of electronic equipment 10.Controller can be grasped according to instruction Make code and clock signal, generates operating control signal, the control completing instruction fetch and executing instruction.

Memory can also be set in processor 110, for storing instruction and data.

In some embodiments, processor 110 may include one or more interfaces.Interface may include integrated circuit (inter-integrated circuit, I2C) interface, integrated circuit built-in audio (inter-integrated circuit Sound, I2S) interface, pulse code modulation (pulse code modulation, PCM) interface, universal asynchronous receiving-transmitting transmitter (universal asynchronous receiver/transmitter, UART) interface, mobile industry processor interface (mobile industry processor interface, MIPI), universal input export (general-purpose Input/output, GPIO) interface, Subscriber Identity Module (subscriber identity module, SIM) interface, and/or Universal serial bus (universal serial bus, USB) interface etc..

It is understood that the interface connection relationship of each intermodule of signal of the embodiment of the present invention, only schematically illustrates, The structure qualification to electronic equipment 10 is not constituted.In other embodiments of the application, electronic equipment 10 can also use upper State the combination of interface connection type or multiple interfaces connection type different in embodiment.

Charge management module 140 is used to receive charging input from charger.Wherein, charger can be wireless charger, It is also possible to wired charger.

Power management module 141 is for connecting battery 142, charge management module 140 and processor 110.Power management mould Block 141 receives the input of battery 142 and/or charge management module 140, is processor 110, internal storage 121, external storage Device, display screen 194, the power supply such as camera 193 and wireless communication module 160.

The wireless communication function of electronic equipment 10 can pass through antenna 1, antenna 2, mobile communication module 150, wireless communication Module 160, modem processor and baseband processor etc. are realized.

Antenna 1 and antenna 2 electromagnetic wave signal for transmitting and receiving.

Mobile communication module 150, which can provide, applies wirelessly communicating on electronic equipment 10 including 2G/3G/4G/5G etc. Solution.Mobile communication module 150 may include at least one filter, switch, power amplifier, low-noise amplifier (low noise amplifier, LNA) etc..

Modem processor may include modulator and demodulator.Wherein, modulator is used for low frequency base to be sent Band signal is modulated into high frequency signal.Demodulator is used to received electromagnetic wave signal being demodulated into low frequency baseband signal.Then solution Adjust device that the low frequency baseband signal that demodulation obtains is sent to baseband processor.Low frequency baseband signal is through baseband processor Afterwards, it is delivered to application processor.

In some embodiments, the antenna 1 of electronic equipment 10 and mobile communication module 150 couple, antenna 2 and wireless communication Module 160 couples, and allowing electronic equipment 10, technology is communicated with network and other equipment by wireless communication.

Electronic equipment 10 realizes display function by GPU, display screen 194 and application processor etc..GPU is at image The microprocessor of reason connects display screen 194 and application processor.GPU is calculated for executing mathematics and geometry, is used for figure wash with watercolours Dye.Processor 110 may include one or more GPU, execute program instructions to generate or change display information.

Display screen 194 is for showing image, video etc..In some embodiments, electronic equipment 10 may include 1 or N A display screen 194, N are the positive integer greater than 1.

Electronic equipment 10 can be by ISP, camera 193, Video Codec, GPU, display screen 194 and at It manages device etc. and realizes shooting function.

ISP is used to handle the data of the feedback of camera 193.For example, opening shutter when taking pictures, light is passed by camera lens It is delivered on camera photosensitive element, optical signal is converted to electric signal, and camera photosensitive element passes to the electric signal at ISP Reason, is converted into macroscopic image.ISP can also be to the noise of image, brightness, colour of skin progress algorithm optimization.ISP can be with Exposure to photographed scene, the parameter optimizations such as colour temperature.In some embodiments, ISP can be set in camera 193.

Camera 193 is for capturing still image or video.Object generates optical imagery by camera lens and projects photosensitive member Part.The photosensitive element is sensor 630 described in image-sensitive cell array or Fig. 6 in sensor 420 described in Fig. 3 In image-sensitive cell array.Photosensitive element can be charge-coupled device (charge coupled device, CCD) or complementation Metal-oxide semiconductor (MOS) (complementary metal-oxide-semiconductor, CMOS) phototransistor.It is photosensitive Optical signal is converted into electric signal by element, and electric signal is passed to ISP later and is converted into data image signal.ISP is by digitized map As signal is output to DSP working process.Data image signal is converted into the RGB of standard, the picture signal of the formats such as YUV by DSP. In some embodiments, electronic equipment 10 may include 1 or N number of camera 193, and N is the positive integer greater than 1.N number of camera 193 may include camera 100 and camera 200 shown in figure 1.

Wherein, sensor 630 described in the sensor 420 and Fig. 6 in camera 100 described in Fig. 3, is not included in In sensor module 180, sensor 630 described in sensor 420 and Fig. 6 described in Fig. 3 is the component part of camera. Image-sensitive cell array in sensor 630 described in image-sensitive cell array and Fig. 6 in sensor 420 described in Fig. 3 is Photosensitive element in aforementioned camera 193.Image-sensitive unit battle array in image-sensitive cell array and sensor 630 in sensor 420 Column e.g. charge coupled device ccd imaging sensor or cmos image sensor.

Digital signal processor, in addition to can handle data image signal, can also handle it for handling digital signal His digital signal.For example, digital signal processor is used to carry out in Fu frequency point energy when electronic equipment 10 is when frequency point selects Leaf transformation etc..

Video Codec is used for compression of digital video or decompression.Electronic equipment 10 can support one or more views Frequency codec.In this way, electronic equipment 10 can play or record the video of a variety of coded formats, and such as: dynamic image expert Group (moving picture experts group, MPEG) 1, MPEG2, mpeg 3, MPEG4 etc..

NPU is neural network (neural-network, NN) computation processor, by using for reference biological neural network structure, Such as transfer mode between human brain neuron is used for reference, it, can also continuous self study to input information fast processing.Pass through NPU The application such as intelligent cognition of electronic equipment 10 may be implemented, such as: image recognition, recognition of face, speech recognition, text understanding Deng.Such as realize that Face datection example, recognition of face example, gestures detection example and environment measuring are shown in the embodiment of the present application Example.

External memory interface 120 can be used for connecting external memory card, such as Micro SD card, realize that extension electronics is set Standby 10 storage capacity.External memory card is communicated by external memory interface 120 with processor 110, realizes that data store function Energy.Such as by music, the files such as video are stored in external memory card.

Internal storage 121 can be used for storing computer executable program code, and the executable program code includes Instruction.Processor 110 is stored in the instruction of internal storage 121 by operation, thereby executing the various functions of electronic equipment 10 Using and data processing.Internal storage 121 may include storing program area and storage data area.In addition, internal storage 121 may include high-speed random access memory, can also include nonvolatile memory.

Electronic equipment 10 can be by audio-frequency module 170, loudspeaker 170A, receiver 170B, microphone 170C, and earphone connects Mouth 170D and application processor etc. realize audio-frequency function.Such as music, recording etc..

Audio-frequency module 170 is used to for digitized audio message to be converted into analog audio signal output, is also used for analogue audio frequency Input is converted to digital audio and video signals.Audio-frequency module 170 can be also used for audio-frequency signal coding and decoding.

Loudspeaker 170A, also referred to as " loudspeaker ", for audio electrical signal to be converted to voice signal.Electronic equipment 10 can lead to It crosses loudspeaker 170A and listens to music, or listen to hand-free call.

Receiver 170B, also referred to as " earpiece ", for audio electrical signal to be converted into voice signal.When electronic equipment 10 is answered It, can be by the way that receiver 170B be answered voice close to human ear when phone or voice messaging.

Microphone 170C, also referred to as " microphone ", " microphone ", for voice signal to be converted to electric signal.

Earphone interface 170D is for connecting wired earphone.

Pressure signal can be converted into electric signal for experiencing pressure signal by pressure sensor 180A.In some implementations In example, pressure sensor 180A be can be set in display screen 194.

Gyro sensor 180B is determined for the athletic posture of electronic equipment 10.It in some embodiments, can be with Determine that electronic equipment 10 surrounds the angular speed of three axis (that is, x, y and z-axis) by gyro sensor 180B.

Baroceptor 180C is for measuring air pressure.In some embodiments, electronic equipment 10 passes through baroceptor The atmospheric pressure value that 180C is measured calculates height above sea level, auxiliary positioning and navigation.

Magnetic Sensor 180D includes Hall sensor.Electronic equipment 10 can use Magnetic Sensor 180D flip cover leather sheath Folding.

Acceleration transducer 180E can detect the size of (the generally three axis) acceleration in all directions of electronic equipment 10. It can detect that size and the direction of gravity when electronic equipment 10 is static.

Range sensor 180F, for measuring distance.

It may include such as light emitting diode (LED) and photodetector, such as photodiode close to optical sensor 180G.

Ambient light sensor 180L is for perceiving environmental light brightness.

Fingerprint sensor 180H is for acquiring fingerprint.The fingerprint characteristic that electronic equipment 10 can use acquisition realizes fingerprint solution Lock accesses application lock, and fingerprint is taken pictures, fingerprint incoming call answering etc..

Temperature sensor 180J is for detecting temperature.In some embodiments, electronic equipment 10 utilizes temperature sensor The temperature of 180J detection, executes Temperature Treatment strategy.

Touch sensor 180K, also referred to as " touch panel ".Touch sensor 180K can be set in display screen 194, by touching It touches sensor 180K and display screen 194 forms touch screen, also referred to as " touch screen ".

The available vibration signal of bone conduction sensor 180M.In some embodiments, bone conduction sensor 180M can be with Obtain the vibration signal of human body part vibration bone block.

Key 190 includes power button, volume key etc..Key 190 can be mechanical key.It is also possible to touch-key. Electronic equipment 10 can receive key-press input, generate key signals related with the user setting of electronic equipment 10 and function control Input.

Motor 191 can produce vibration prompt.

Indicator 192 can be indicator light, can serve to indicate that charged state, electric quantity change can be used for instruction and disappear Breath, missed call, notice etc..

SIM card interface 195 is for connecting SIM card.

The structure of hardware module and software module that a kind of camera 100 provided by the embodiments of the present application is described below is shown Example.Camera 100 is the normally opened camera 100 described by Fig. 1 in example, on the electronic equipments such as mobile phone that can be applicable to 10.Please It is a kind of hardware module 400 of camera 100 provided by the embodiments of the present application and the structure of software module 500 refering to Fig. 3, Fig. 3 Schematic diagram.As shown in figure 3, the hardware module 400 of camera 100 includes lens group 410, sensor 420 and image signal process Unit 430.Wherein:

Lens group 410 may include one or more lens, for the light refraction to entrance, on sensor 420 at Picture.

Optical signal from lens group is converted to telecommunications for realizing the conversion of optical signal to electric signal by sensor 420 Number it is transferred to image signal processing unit 430.

Specifically, sensor 420 may include image-sensitive cell array and analog-to-digital conversion (analog to digital, A/D) electricity Road.Wherein, image-sensitive cell array includes multiple image-sensitive units, and image-sensitive cell array is made to receive from the formed figure of lens group light Picture, each image-sensitive unit by thereon the electric signal that is converted at image.The electric signal is the signal of analog form.Image-sensitive unit Quantity determine the pixel of camera 100, that is, determine that camera 100 shoots the resolution ratio of image.Analog to digital conversion circuit is used for will The electric signal of each pixel unit output analog form is converted to digital signal.The design of analog to digital conversion circuit determines that camera passes The color depth of the image data of sensor output.Illustratively, image-sensitive cell array is that multiple image-sensitive units arrange the battle array to be formed Column, such as arranged according to rectangular uniform, laterally upper and longitudinal image-sensitive element number is respectively 128 Hes to image-sensitive cell array 96, then it is 128 × 96 that camera 100, which shoots the resolution ratio of image,.For another example image-sensitive cell array can be arranged in circular array, Then the quantity of the diametrically image-sensitive unit of the circular array is less than or equal to 200, such as diametrically the quantity of image-sensitive unit is 128。

Wherein, figure of the camera 100 in the embodiment of the present application compared with camera 200 with low color depth and shooting As having low resolution.Illustratively, it is 128 × 96 that camera 100, which shoots the resolution ratio of image, camera sensing device output The color depth of image data is 4, and each pixel can describe 16 of certain color in white or three primary colours (red, green, blue) Grade.In the embodiment of the present application, compared with camera 200, sensor 420 makes the image data of output have low color depth And the image of shooting has low resolution.In addition, the resolution ratio that camera 100 shoots image can also be that x × y, x and y are Positive integer less than or equal to 200.Color depth is less than 8.

In the embodiment of the present application, the color depth that camera 100 has refers to, the sensor output in camera 100 The color depth of image data.Illustratively, the color depth that camera 100 has is 4, i.e. sensing in camera 100 The color depth of the image data of device output is 4.

In the embodiment of the present application, camera 100 is the first camera, and the sensor 420 in Fig. 3 is first sensor, is passed Sensor 420 includes the first image-sensitive cell array, the maximum quantity of the upper and longitudinal upper image-sensitive unit of the first image-sensitive cell array transverse direction Less than or equal to 200, the color depth of the image data of first sensor output is the first color depth, and the first color depth is small In 8.In addition, camera 200 is second camera, second camera includes second sensor, and second sensor includes second Image-sensitive cell array, the quantity of image-sensitive unit is greater than image-sensitive unit in the first image-sensitive cell array in the second image-sensitive cell array Quantity, the color depth of the image data of second sensor output are the second color depth, and the second color depth is greater than the first color Color depth.

The mode of the camera 100 of two kinds of acquisition low resolution is described below.Implementation one: in existing high-resolution Camera sensor (such as sensor that camera 200 includes in example shown in Fig. 1) on the basis of reduce image-sensitive unit The area of array, and keep the density of existing image-sensitive unit constant, to reduce the quantity of image-sensitive unit to reduce camera Pixel, to realize the camera 100 of low resolution.Implementation two: in the sensor of existing high-resolution camera Keep the area of image-sensitive cell array constant on the basis of (such as sensor that camera 200 includes in example shown in Fig. 1), and Increase the spacing between image-sensitive unit, to reduce the quantity of image-sensitive unit to realize the low camera 100 of resolution ratio.

The color depth that the image data of 100 sensor of camera output can be reduced by simplifying A/D circuit.Specifically, It can reduce and simulate the level detection precision of lateral circuit in A/D circuit to obtain the lower camera 100 of color depth.It is exemplary , the level detection precision for simulating lateral circuit can be reduced to 1/16 from 1/256, to reduce the output of 100 sensor of camera The color depth of image data.In the embodiment of the present application, it is 4 that color depth can be obtained by way of above-mentioned simplified A/D circuit The camera 100 of position.

Image processing unit 430 is used to receive the image data of digital form from sensor 420, realizes image coding.Tool Body, image processing unit 430 carries out demosaicing processing, auto-exposure control (automatic to the image data received Exposure control, AEC), automatic growth control (automatic gain control, AGC), automatic white balance The processing such as (automatic white balance, AWB), colour correction.In the embodiment of the present application, demosaicing processing will be every The image data of several other image-sensitive units of 4 image data combination peripheries output of a image-sensitive unit output, calculates 8 rgb image datas out.I.e. 8 color depths for correspondence image.The exportable image data of image processing unit 430 is given Software module 500.Image processing unit 430 ISP in electronic equipment can be realized as shown in Figure 2.

As shown in figure 3, software module 500, receives the image data from image processing unit 430, the inspection of Lai Shixian face Survey, recognition of face, gestures detection and environment measuring etc..Wherein, Face datection is used to determine the picture number that hardware module 400 detects According to whether being face image data.Use belonging to the recognition of face face image data that hardware module 400 detects for identification Family.Whether the image data that gestures detection is used to determine that hardware module 400 detects is images of gestures data.Environment measuring is used for root The image data detected according to hardware module 400 determines the environment being presently in.Software module 500 is carrying out Face datection, face Output analysis is as a result, electronic equipment 10 executes relevant operation based on the analysis results after identification, gestures detection and environment measuring.Below The operation executed after analysis result is exported to Face datection, recognition of face, gestures detection and environment measuring respectively to illustrate.

1. Face datection example

Illustratively, electronic equipment 10 acquires image data by camera 100, and by the feature of the image data of acquisition It is matched with the face characteristic prestored, successful match, which then exports analysis result instruction, face.When electronic equipment 10 is by taking the photograph When having detected face as first 100, electronic equipment 10 keeps display screen to be always on state.If current electronic device 10 is in bright screen State, electronic equipment can detect whether current display screen is arranged to be always on state.If detecting that current display screen is not set It is set to the state of being always on, then electronic equipment 10 can be arranged display screen according to the analysis result and be always on.Display screen is arranged to be always on shape After state, even if not receiving operation (such as touch operation), the state that display screen is still persistently lit, until electronic equipment Display screen is closed the state of being always on.Electronic equipment 10 can carry out people to the image data that camera 100 acquires with certain frequency Face detection, when analysis result instruction " not being facial image " either indicates " being ceiling image " or indicates other images, What electronic equipment 10 can close display screen is always on state.After display screen is closed the state of being always on, (such as 1 minute) is continued for some time After not receiving operation (such as touch operation), display is held one's breath until being reawaked, such as detects clicking for power button Operation, then display screen, which is reawaked, lights to be shown.When analyzing result instruction " facial image ", if electronic equipment 10 detect that current display screen has been arranged to be always on state, then terminate.Optionally, electronic equipment 10 can reach pre- in bright screen If when the time, having detected whether face, if having detected face, do not stop shielding, i.e., does not execute the operation of breath screen；If people is not detected Face then ceases screen.

In the above method, compared with camera 200, normally opened camera 100 can real-time detection facial image, detect people Face image is then arranged display screen and is always on, to be offering convenience property of user.And compared with camera 200, the normally opened camera 100 with low color depth and shooting image has low resolution, carries less information.To reduce the bat of camera 100 The image taken the photograph information abundant is leaked harm caused by safety and privacy to user information, improves the peace of user information Quan Xing.

In addition, when the progress Face datection of electronic equipment 10, which obtains analysis result instruction, face, if Current electronic is set Standby 10 are in the lock state, and electronic equipment 10 can also be called with high color depth and shooting image has high-resolution camera shooting First 200 acquisition face image data carries out recognition of face.Face knowledge is carried out according to the face image data that camera 200 acquires Not, it identifies and successfully then unlocks electronic equipment 10, show user's desktop.It may include application icon on user's desktop.

There is camera 200 high color depth to refer to, compared with camera 100, what the sensor in camera 200 exported The color depth of image data is higher.Illustratively, the color depth that camera 200 has is 8, i.e., in camera 200 The color depth of the image data of sensor output is 8.Camera 200, which shoots image, has high-resolution, refers to and images First 100 compare, and in the sensor of camera 200, the quantity of image-sensitive cell array is more, and illustratively, pixel quantity is 1920000。

It is above-mentioned to be realized in the scheme of the unlock of electronic equipment 10 using normally opened camera 100 and the cooperation of camera 200, it will image First 100 normally opened acquisition image data, and compared with camera 200, camera 100 has low color depth and the image of shooting tool Have low resolution, carry less information, thus the image information abundant for reducing the shooting of normally opened camera be leaked to It is endangered caused by the safety and privacy of family information, improves the safety of user information.In addition, being carried out using camera 200 To unlock electronic equipment, camera 200 has high-resolution with the image of high color depth and shooting, can protect for recognition of face The accuracy of recognition of face is promoted while demonstrate,proving user information safety.

In some embodiments of the present application, when calling camera 100 to detect face, camera 100 can detect people The upper direction of face image.Electronic equipment can watch the direction of electronic equipment according to the upper walking direction user of the facial image.Such as Fruit electronic equipment shows application interface, such as instant messaging application interface or e-book reading application interface.It is answered when detecting It is more than certain threshold value (such as each 45 degree of left and right), electronic equipment with the upper direction at interface and the upper deviation of directivity of user's facial image Application interface display direction can be adjusted according to the upper direction of user's facial image, to ensure the upper direction of user's facial image and answer It is maintained within threshold value with direction in interface display.

Illustratively, referring to Fig. 4, Fig. 4 is a kind of schematic diagram of horizontal/vertical screen switching provided by the embodiments of the present application.Such as figure Shown in (a) in 4, the display area 300 of electronic equipment 10 shows application interface 1400, and the upper direction of application interface 1400 is flat Row is in the long side of electronic equipment 10.Electronic equipment 10 acquires facial image 1500 using camera 100, and detects the facial image Whether angle between 1500 upper direction and the upper direction of application interface 1400 is more than first threshold, such as 45 degree.In Fig. 4 (a) shown in, when the angle between the upper direction of the facial image 1500 and the upper direction of application interface 1400 be no more than this When one threshold value, such as angle is 0 degree, the still vertical screen display application interface 1400 of electronic equipment 10.

As shown in (b) in Fig. 4, when user changes the gripping view direction of electronic equipment, electronic equipment 10 is utilized and is taken the photograph As the acquisition facial image 1500 of head 100, the upper direction of facial image 1500 is detected, the short side of electronic equipment 10 is parallel to.Electronics Equipment 10 detects that the angle between the upper direction of the facial image 1500 and the upper direction of application interface 1400 is 90 degree, is more than 45 degree of the first threshold.Then as shown in (c) in Fig. 4, electronic equipment 10 can be according to the upper direction tune of user's facial image 1500 Whole 1400 display direction of application interface, to ensure the upper direction of user's facial image 1500 and the upper direction guarantor of application interface 1400 It holds within the threshold value.It should be understood that above-mentioned be only used for the citing that first threshold is 45 degree to explain the embodiment of the present application, no Restriction should be constituted, which can also be greater or lesser angle.

In the method for above-mentioned automatic carry out horizontal/vertical screen switching, normally opened camera 100 can real-time detection facial image Angle between 1500 upper direction and the upper direction of application interface 1400 carries out horizontal/vertical screen switching according to the angle, to be Offering convenience property of user.And compared with camera 200, which has low color depth and shooting image tool There is low resolution, carries less information.It is leaked to reduce the image information abundant of the shooting of camera 100 to user It is endangered caused by the safety and privacy of information, improves the safety of user information.

2. recognition of face example

Electronic equipment 10 can the corresponding face characteristic of prestored user A and B and A and the corresponding face characteristic of B.For every For a user, the corresponding user's desktop of electronic equipment 10 (such as mobile phone).If electronic equipment 10 is exported by recognition of face Result instruction " facial image of A " is analyzed, electronic equipment 10 is in the lock state, and electronic equipment 10 shows that A is corresponding after unlock User's desktop.In some embodiments of the present application, electronic equipment 10 executes following steps to unlock and show user's desktop.

Step 101, electronic equipment 10 carry out recognition of face, output analysis result to the image data that camera 100 acquires It indicates " facial image of A ".

Specifically, the feature for the image data that electronic equipment 10 acquires camera 100 respectively with the face characteristic of A and B Face characteristic matched, camera 100 acquire image data feature and A face characteristic successful match, then export Analyze result instruction " facial image of A ".The feature for the image data that camera 100 acquires and the face characteristic successful match of B, Then export analysis result instruction " facial image of B ".

Wherein, user A can be the first user, and user B can be second user.

Step 102, when electronic equipment 10 carry out face recognition result instruction " facial image of A " when, electronic equipment 10 adjust With high color depth and shooting image there is high-resolution camera 200 to acquire face image data.

Wherein, camera 100 is normally opened, 200 sensor of camera output image data have high color depth and Shooting image has high-resolution, just opens when called and acquires image data.When electronic equipment 10 carries out recognition of face When as a result indicating " facial image of A ", if electronic equipment 10 recalls high color depth and shooting image tool in lock state There is high-resolution camera 200 to execute face unlock.Wherein, when electronic equipment 10 is in the lock state, to user's operation electricity The permission of sub- equipment is defined.After unlocking electronic equipment 10, user can operate electronic equipment 10.It releases After lock state, electronic equipment can respond the operation of user to call types of applications, such as " camera ", " music " and " video " Equal APP.

Step 103, electronic equipment 10 carry out recognition of face according to the face image data that camera 200 acquires.

If step 104 carries out recognition of face success according to the face image data that camera 200 acquires, electricity is unlocked Sub- equipment 10, the corresponding user's desktop of display A.

In the embodiment of the present application, the process that the face image data acquired according to camera 200 carries out recognition of face can class Than camera 100, which is not described herein again.I.e. when electronic equipment 10 carries out face knowledge by the facial image that camera 200 acquires Do not obtain result instruction " facial image of A ", show according to camera 200 acquire face image data carry out recognition of face at Function.

It is above-mentioned to be realized using normally opened camera 100 and the cooperation of camera 200 in scheme that electronic equipment 10 unlocks, using normal The camera 100 opened perceives facial image and identifies user, can also so as to promote the ability of electronic equipment facial image identification Guarantee the isolation of information between user A and B using same electronic equipment 10, improves the convenience that user unlocks electronic equipment Property.

In addition, recalling after being identified as function using the execution face of camera 100 with high color depth and shooting image tool There is high-resolution camera 200 to execute recognition of face again, electronic equipment is just unlocked after identifying successfully, face unlock can be improved Reliability and safety.

By the normally opened acquisition image data of camera 100, and compared with camera 200, camera 100 has low color depth And shooting image has low resolution, carries less information.To reduce the image letter abundant of normally opened camera shooting Breath is leaked harm caused by safety and privacy to user information, improves the safety of user information.In addition, using taking the photograph As first 200 progress recognition of face to unlock electronic equipment, camera 200 is with high color depth and shooting image has high-resolution Rate can promote the accuracy of recognition of face while guaranteeing user information safety.

In the embodiment of the present application, the image with low color depth and shooting has the camera 100 of low resolution can be with Face is identified, the recognition of face scene not high to safety requirements for user, such as non-pay scene.Specifically such as The scene that corresponding user's desktop is shown according to face recognition result shown in step 102~step 104.Again for example hereinafter, root The scene of old man or the corresponding playlist of child is played according to face recognition result.Camera 100 can identify some diversity factor ratios Obvious face.Such as Fig. 5 shows and distinguishes the examples such as round face, oval face or state's word face in example.

Illustratively, referring to Fig. 5, Fig. 5 is the image signal that a kind of camera 100 provided by the embodiments of the present application is shot Figure.As shown in figure 5, camera 100 acquires since camera 100 with low color depth and shoots image with low resolution Facial image by only can recognize that face 1200 after image recognition, and distinguish round face, oval face or state's word face.It can Choosing, it can also distinguish between out and distinguish biggish five features, such as heavy eyebrows and light eyebrow can be distinguished, oxeye and pigsney etc.. But minutia cannot be distinguished after passing through image recognition in electronic equipment 10, for example whether double-edged eyelid.

Optionally, electronic equipment 10 can not also identify local environment 1300 after passing through image recognition, or only can determine that institute It is indoor or outdoor for locating environment 1300.

Since compared with camera 200, above-mentioned camera 100 has image-sensitive unit on low color depth and camera 100 Array makes the image of shooting have low resolution, carries less information.Have with the image of existing camera shooting rich Rich information is compared, and is shot image using camera 100 and is carried out recognition of face, environment measuring etc., and normally opened be leaked pair is reduced It is endangered caused by the safety and privacy of user information, improves the safety of user information.

Be not limited to the example of above-mentioned recognition of face, when electronic equipment 10 is intelligent sound box, intelligent sound box can for user A and Playlist is respectively set in user B.Such as A is old man, B is child, since camera 100 has low color depth and shooting figure As can only be distinguished after there is low resolution, the facial image that electronic equipment 10 is acquired by camera 100 to carry out image recognition It is old man or child that facial image, which is 1200, out.Electronic equipment 10 is known by the image data acquired to camera 100 Not, when recognition result indicates " facial image of old man ", speaker can play the corresponding playlist of old man, such as opera column Table.Electronic equipment 10 is identified by the image acquired to camera 100, when recognition result indicates " facial image of child " When, speaker can play the corresponding playlist of child, such as nursery rhymes list.

3. gestures detection example

Electronic equipment 10 can store the corresponding feature of gesture, specifically, can store palm is deployed into this gesture pair of holding with a firm grip The feature answered simultaneously stores palm grip to the corresponding feature of this gesture is unfolded.Voice call process is carried out in electronic equipment 10 In, the feature for the image data that camera 100 acquires is deployed into palm to the corresponding feature of this gesture of holding with a firm grip and is matched. Successful match then exports analysis result instruction: palm is deployed into gesture of holding with a firm grip.If detecting that current electronic device 10 is not set It is set to mute, i.e. the microphone of current electronic device is not closed, then it is quiet that electronic equipment 10 can be arranged according to the analysis result Sound.Similar, feature and the palm grip to this gesture pair of expansion of the image data that electronic equipment 10 acquires camera 100 The feature answered is matched.Successful match then exports analysis result instruction: palm grip to expansion gesture.If detected current Electronic equipment 10 is arranged to mute, i.e. the microphone of current electronic device 10 is closed, then can be closed according to the analysis result Electronic equipment 10 is mute, unlatching microphone.

4. environment measuring example

Electronic equipment 10 carries out environment measuring according to the image data that camera 100 acquires.Illustratively, electronic equipment 10 It can the corresponding feature of storage condition template.Environment templates may include interior operator seat environment.Electronic equipment 10 adopts camera 100 The feature of the image data of collection is matched with the feature of interior operator seat environment.Successful match then exports analysis result instruction: Interior operator seat environment.When testing result indicate " interior operator seat environment " when, if detect current electronic device 10 not by It is set as driving mode, then electronic equipment 10 can be set as driving mode according to the analysis result.When testing result instruction is " interior When operator seat environment ", if electronic equipment 10 detects when being currently arranged to driving mode, terminate.

In the embodiment of the present application, different environment measuring scene, to the color of the image data of camera sensing device output Depth is different with the shooting resolution requirement of image.If high to the resolution requirement of camera color depth and shooting image, Such as need to identify some position of indoor ceiling using electronic equipment 10, desktop is placed in electronic equipment 10 to realize When upper camera takes ceiling in this position, electronic equipment 10 prompts weather condition.The figure of 100 sensor of camera output The resolution ratio of color depth and shooting image as data can be higher, and resolution ratio is 200 × 200, and color depth is 4.If The resolution requirement of color depth and shooting image to the image data of camera sensing device output is lower, such as requires nothing more than and take the photograph As head is able to carry out Face datection, display screen is kept to be always on when realizing that user watches electronic equipment display screen.Camera 100 passes Sensor output image data color depth and shooting image resolution ratio can be lower, resolution ratio be 144 × 96 or 128 × 96, color depth is 3.

In a kind of achievable mode, on the one hand, electronic equipment 10 can be detected some obvious, typical by camera 100 Scene, such as indoor environment, outdoor environment and aforementioned interior driving environment etc..On the other hand, with camera shown in Fig. 1 200 compare, which can only detect obvious, typical scene, will not always to accurate, the fine environment of user and The facial detail information of user carries out detection and tracking.To realize can identify some scenes, but will not detect and with The accurate information of track user reduces the leakage of user privacy information.

It should be understood that above-mentioned be only used for explaining to Face datection, recognition of face, gestures detection and the citing of environment measuring The embodiment of the present application should not constitute restriction.Above-mentioned Face datection, recognition of face, gestures detection and environment measuring are that image is known Not.Electronic equipment 10 can also execute other operations according to recognition result, and the embodiment of the present application is not construed as limiting this.

In some embodiments of the present application, it is intelligent video camera head, the intelligence comprising camera that electronic equipment is also implementable Household electrical appliance (refrigerator, desk lamp, air purifier etc.) etc..The scene with intelligent video camera head for family's monitoring is lifted below Example.

Referring to Fig. 6, Fig. 6 is the hardware module 600 and software mould of a kind of intelligent video camera head provided by the embodiments of the present application The structural schematic diagram of block 700.The camera can be applicable to the scene of family's monitoring.As shown in fig. 6, intelligent video camera head includes hardware Module 600 and software module 700.Hardware module 600 includes lens group 610, sensor 620 and image signal processing unit 630.

Wherein, the intelligent video camera head in the embodiment of the present application has low resolution with the image of low color depth and shooting Rate.Illustratively, the resolution ratio of intelligent video camera head shooting image is 144 × 96, and color depth is 4, and each pixel is exportable 16 a certain grades (2 4 powers) in white or three primary colours (red, green, blue).In the embodiment of the present application, sensor 620 makes Intelligent video camera head is with low color depth and shooting image has low resolution.

In the embodiment of the present application, Fig. 3 can refer to about lens group 610, sensor 620 and image signal processing unit 630 The description of lens group 410, sensor 420 and image signal processing unit 430 in shown example, which is not described herein again.

As shown in fig. 6, software module 700, receives the image data from image processing unit 630, the inspection of Lai Jinhang human body Survey, attitude detection etc..Wherein, whether the image data that human testing is used to determine that hardware module 600 acquires is human body picture number According to.The posture of human body in the attitude detection human body image data that hardware module 600 detects for identification, such as fall down, stand up, It the postures such as lies down.Software module 700 carry out human testing, after attitude detection output analysis as a result, intelligent video camera head according to dividing Analysis result executes operation.Human testing, attitude detection are illustrated separately below.

A. human testing example

Intelligent video camera head matches the feature of the image data of acquisition with the characteristics of human body prestored, and successful match is then defeated Analysis result instruction out: human body image.It is sent out if user setting intelligent video camera head detects human body image to user mobile phone Warning message is sent, then when testing result indicates " human body image ", intelligent video camera head can be according to the analysis result to user mobile phone Send warning message.Wherein, intelligent video camera head can be stored with the first instruction, and the first instruction instruction detects human body image then to end (user mobile phone) is held to send warning message.

B. attitude detection example

Intelligent video camera head matches the feature of the image data of acquisition with the feature of the human body attitude prestored, if with It falls down attitude matching success and then exports analysis result instruction: falling down posture.If user setting intelligent video camera head detects people Body falls down posture and then sends warning message and placement of emergency calls to user mobile phone, then when testing result indicates " falling down posture " When, intelligent video camera head can send warning message or placement of emergency calls to user mobile phone according to the analysis result.Wherein, intelligence Camera can be stored with the second instruction, and the second instruction instruction, which detects to fall down posture and then send to alarm to terminal (user mobile phone), to disappear Breath or placement of emergency calls.

In the above-mentioned example for executing family's monitoring using intelligent video camera head, compared with existing camera, normally opened intelligence Camera has low resolution and low color depth, can reduce information abundant on the image of shooting and be leaked to user information It is endangered caused by safety and privacy, improves the safety of user information.

It should be understood that intelligent video camera head is not limited to execute human testing and posture detection, it can be also used for other detections. It is above-mentioned that intelligent video camera head progress human testing and the citing of posture detection are only used for explaining the embodiment of the present application, limit should not be constituted It is fixed.Intelligent video camera head can also execute other operations according to testing result, and the embodiment of the present application is not construed as limiting this.

Referring to Fig. 7, Fig. 7 is a kind of structural schematic diagram of intelligent video camera head provided by the embodiments of the present application.Such as Fig. 7 institute Show, which includes hardware module 600, one or more processors 800, memory 900, communication interface 1000, Hardware module 600, processor 800, memory 900, communication interface 1000 can be connected by bus or other way, the application Embodiment by bus 1100 for being connected.Hardware module 600 can be the hardware module 600 in example described by Fig. 3.Its In:

Processor 800 can be made of one or more general processor, such as CPU.

Communication interface 1000 can be wireline interface (such as Ethernet interface) or wireless interface (such as cellular network interface Or use wireless lan interfaces), for being communicated with other nodes.In the embodiment of the present application, communication interface 1000 is specific It can be used for being communicated with electronic equipments such as mobile phones.

Memory 900 may include volatile memory (volatile memory), such as RAM；Memory also can wrap It includes nonvolatile memory (non-vlatile memory), such as ROM, flash memory (flash memory), HDD or solid State hard disk SSD；Memory 900 can also include the combination of the memory of mentioned kind.Memory 900 can be used for storing one group of journey Sequence code, in order to which processor 800 calls the program code stored in memory 900 to realize the software in example shown in Fig. 3 Module.

It should be noted that intelligent video camera head shown in Fig. 7 is only a kind of implementation of the embodiment of the present application, actually answer In, intelligent video camera head can also include more or fewer components, here with no restriction.

Optionally, be not limited to above-mentioned intelligent video camera head, above-mentioned low resolution, low color depth camera can also apply In the speaker comprising camera, vehicle-mounted camera or smart home device (such as intelligent refrigerator) comprising camera, the application Embodiment to this with no restriction.Then the structure of above-mentioned speaker, vehicle-mounted camera and smart home device can refer to and show shown in Fig. 7 Example.It further include loudspeaker and for speaker.It further include refrigeration system for intelligent refrigerator.It can also include other More or fewer components, here with no restriction.

In the embodiment of the present application, electronic equipment may include above-mentioned intelligent video camera head, speaker, vehicle-mounted camera or comprising taking the photograph As the smart home device of head.

Referring to Fig. 8, Fig. 8 is a kind of flow diagram of image-recognizing method provided by the embodiments of the present application.Such as Fig. 8 institute Show, which includes S101~S102.

S101, electronic equipment call the first camera to acquire the first image data.

Wherein, the first camera includes first sensor, and first sensor includes the first image-sensitive cell array, the first image-sensitive The quantity of image-sensitive unit is less than or equal to 40000 in cell array, and the color depth of the image data of first sensor output is First color depth, the first color depth is less than 8.Wherein, the first camera can be camera 100 shown in FIG. 1, knot Structure sees example shown in Fig. 3.

Wherein, the first color depth is 4, and the upper and longitudinal image-sensitive unit of the image-sensitive cell array transverse direction is most Big quantity is respectively the maximum quantity of 128 and 96 or the upper and longitudinal image-sensitive unit of image-sensitive cell array transverse direction Respectively 144 and 96.

In some embodiments of the present application, the first camera is always in electronic device works.

S102, electronic equipment carry out image recognition to the first image data, and according to recognition result and current state, hold Row relevant operation.

In above-mentioned image-recognizing method, compared with second camera, the first camera has low color depth and shooting Image has low resolution, carries less information.It is let out to reduce the image information abundant of the first camera shooting Reveal and endangered caused by the safety to user information and privacy, improves the safety of user information.

In some embodiments of the present application, current state is in the lock state for electronic equipment；Electronic equipment executes Relevant operation, comprising: electronic equipment calls second camera to carry out face unlock.About the above process, aforementioned face can refer to The exemplary specific descriptions of detection, which is not described herein again.By the normally opened acquisition image data of the first camera, and and second camera It compares, the first camera is with low color depth and shooting image has low resolution, carries less information.To reduce The image information abundant of normally opened camera shooting is leaked harm caused by safety and privacy to user information, improves The safety of user information.Recognition of face is carried out using second camera to unlock electronic equipment, and second camera has high color Color depth and shooting image have high-resolution, the accurate of recognition of face can be promoted while guaranteeing user information safety Property.

Wherein: second camera includes second sensor, and second sensor includes the second image-sensitive cell array, the second image-sensitive The quantity of image-sensitive unit is greater than the quantity of image-sensitive unit in the first image-sensitive cell array in cell array, second sensor output The color depth of image data is the second color depth, and the second color depth is greater than the first color depth.Second camera can be with It is the camera 200 in example shown in Fig. 1.

In some embodiments of the present application, the area of the area of the first image-sensitive cell array and the second image-sensitive cell array In identical situation, the density of image-sensitive unit is less than image-sensitive unit in the second image-sensitive cell array in the first image-sensitive cell array Density；The density of image-sensitive unit is identical in the density of image-sensitive unit and the second image-sensitive cell array in first image-sensitive cell array In the case of, the area of the area of the first image-sensitive cell array less than the second image-sensitive cell array.

In other embodiments of the application, first sensor includes the first analog to digital conversion circuit, the first analog-to-digital conversion The detection accuracy that lateral circuit is simulated in circuit is related to the first color depth；Second camera includes second sensor, and second passes Sensor includes the second analog to digital conversion circuit, and the color depth of the image data of second sensor output is the second color depth, the The detection accuracy that lateral circuit is simulated in two analog to digital conversion circuits is related to the second color depth；It is simulated in first analog to digital conversion circuit The detection accuracy of lateral circuit is less than the detection accuracy for simulating lateral circuit in the second analog to digital conversion circuit, and the first color depth is less than the Two color depths.Description can be with reference to the description of sensor 420 shown in Fig. 3 as described in first sensor, and which is not described herein again.

In some embodiments of the present application, recognition result is to detect facial image, and current state is electronic equipment In bright screen state；Electronic equipment executes relevant operation, comprising: is set as the display screen of electronic equipment to be always on state.About The above process can refer to the exemplary specific descriptions of aforementioned Face datection, and which is not described herein again.In the above method, normally opened One camera can real-time detection facial image, detect that facial image is then arranged display screen and is always on, to offer convenience for user Property.And compared with second camera, the first normally opened camera is with low color depth and shooting image has low resolution, Carry less information.So that the image information abundant for reducing the shooting of the first camera is leaked the safety to user information Property and privacy caused by endanger, improve the safety of user information.

In some embodiments of the present application, recognition result is the facial image for detecting the first user, current state It is in the lock state for electronic equipment；Electronic equipment executes relevant operation, comprising: electronic equipment calls second camera to carry out people Face identification, identifies and successfully then shows the corresponding user's desktop of the first user.About the above process, it can refer to aforementioned recognition of face and show The specific descriptions of example, which is not described herein again.

It is above-mentioned to be realized in the scheme of electronic equipment unlock using the first camera and second camera cooperation, using normally opened First camera perception facial image simultaneously identifies user, so as to promote the ability of electronic equipment facial image identification, can also protect Card improves the convenience that user unlocks electronic equipment using the isolation of the user-to-user information of same electronic equipment.In addition, sharp It is executed after face is identified as function with the first camera, recalls with high color depth and shooting image has high-resolution the Two cameras execute recognition of face again, and electronic equipment is just unlocked after identifying successfully, and the reliability and peace of face unlock can be improved Quan Xing.

In some embodiments of the present application, current state is that electronic equipment shows application interface；Recognition result is detection To facial image upper direction and application interface upper direction between angular deviation be greater than or equal to first threshold；Electronic equipment is held Row relevant operation, comprising: electronic equipment adjusts the upper direction of application interface, by the upper of the upper direction of application interface and facial image Angular deviation is adjusted to be less than or equal to first threshold between direction.About the above process, aforementioned recognition of face example can refer to Specific descriptions, which is not described herein again.

In the above method, the first normally opened camera can the upper direction of real-time detection facial image and the top of application interface Angle between carries out horizontal/vertical screen switching according to the angle, to be offering convenience property of user.And with second camera phase Than the first normally opened camera is with low color depth and shooting image has low resolution, carries less information.To The image information abundant for reducing the shooting of the first camera is leaked the safety to user information and danger caused by privacy Evil, improves the safety of user information.

In some embodiments of the present application, recognition result is to detect interior operator seat environment, and current state is electricity Sub- equipment is in running order；Electronic equipment executes relevant operation, comprising: electronic equipment opens driving mode, under driving mode Electronic equipment can broadcast incoming information and message, and be able to respond user speech and execute relevant operation.It, can about the above process With reference to the specific descriptions of aforesaid environmental detection example, which is not described herein again.

In the above method, the first normally opened camera can the environment that is presently in of real-time detection, be to drive according to the environment Position environment changing is driving mode, to be offering convenience property of user.And compared with second camera, the first normally opened camera shooting Head is with low color depth and shooting image has low resolution, carries less information.To reduce the bat of the first camera The image taken the photograph information abundant is leaked harm caused by safety and privacy to user information, improves the peace of user information Quan Xing.

In some embodiments of the present application, recognition result is to detect human body image, and current state is electronic equipment It is stored with the first instruction, the first instruction instruction detects that human body image then sends warning message to terminal；Electronic equipment executes phase Close operation, comprising: electronic equipment sends warning message to terminal.About the above process, it is exemplary to can refer to aforementioned human testing It specifically describes, which is not described herein again.

In some embodiments of the present application, recognition result is to detect to fall down posture, and current state is electronic equipment It is stored with the second instruction, the second instruction instruction detects that falling down posture then sends warning message to terminal；Electronic equipment executes phase Close operation, comprising: electronic equipment sends warning message to terminal.About the above process, it is exemplary to can refer to aforementioned attitude detection It specifically describes, which is not described herein again.

The embodiment of the present application also provides a kind of electronic equipment, comprising: one or more processors, memory and the first camera shooting Head, in which: first camera includes first sensor, and the first sensor includes the first image-sensitive cell array, described The quantity of image-sensitive unit is less than or equal to 40000 in first image-sensitive cell array, the image data of the first sensor output Color depth be the first color depth, first color depth is less than 8；The memory is for storing computer program Code, the computer program code include computer instruction, are referred to when one or more of processors execute the computer When enabling, so that the electronic equipment executes image-recognizing method described in Fig. 8.

Wherein, which can be Fig. 1 or electronic equipment illustrated in fig. 2.

The embodiment of the present application also provides a kind of computer readable storage medium, stored in the computer readable storage medium There is instruction, when it runs on a computer or a processor, so that computer or processor execute in any of the above-described a method One or more steps.

The embodiment of the present application also provides a kind of computer program products comprising instruction.When the computer program product exists When being run on computer or processor, so that computer or processor execute one or more steps in any of the above-described a method Suddenly.

In the above-described embodiments, all or part of function can by the combination of software, hardware or software plus hardware come It realizes.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer journey Sequence product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all Or it partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated Computer, computer network or other programmable devices.The computer instruction can store in computer-readable storage medium In matter.The computer readable storage medium can be any usable medium that computer can access or include one or The data storage devices such as multiple usable mediums integrated server, data center.The usable medium can be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium are (for example, solid state hard disk (solid State disk, SSD)) etc..

Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, the process Relevant hardware can be instructed to complete by computer program, which can be stored in computer-readable storage medium, should Program is when being executed, it may include such as the process of above-mentioned each method embodiment.And storage medium above-mentioned includes: ROM or deposits at random Store up the medium of the various program storage codes such as memory body RAM, magnetic or disk.

Claims

1. a kind of image-recognizing method, which is characterized in that the described method includes:

Electronic equipment calls the first camera to acquire the first image data；

First camera include first sensor, the first sensor include the first image-sensitive cell array, described first The quantity of image-sensitive unit is less than or equal to 40000 in image-sensitive cell array, the color of the image data of the first sensor output Color depth is the first color depth, and first color depth is less than 8.

2. the method according to claim 1, wherein first camera is in the electronic device works, It is always on.

3. method according to claim 1 or 2, which is characterized in that the electronic equipment calls the first camera acquisition the After one image data, the method also includes:

The electronic equipment carries out image recognition to the first image data, and according to recognition result and current state, holds Row relevant operation.

4. method according to any one of claims 1 to 3, which is characterized in that first color depth is 4, described Laterally the upper maximum quantity with longitudinal image-sensitive unit is respectively 128 and 96 or the image-sensitive list to image-sensitive cell array Laterally the upper maximum quantity with longitudinal image-sensitive unit is respectively 144 and 96 to element array.

5. according to the method described in claim 3, it is characterized in that, the recognition result be detect facial image, it is described to work as Preceding state is that the electronic equipment is in the lock state；The electronic equipment executes relevant operation, comprising:

The electronic equipment calls second camera to carry out face unlock；

Wherein: the second camera includes second sensor, and the second sensor includes the second image-sensitive cell array, described The quantity of image-sensitive unit described in second image-sensitive cell array is greater than image-sensitive unit described in the first image-sensitive cell array The color depth of quantity, the image data of the second sensor output is the second color depth, and second color depth is big In first color depth.

6. according to the method described in claim 3, it is characterized in that, the recognition result be detect facial image, it is described to work as Preceding state is that the electronic equipment is in bright screen state；The electronic equipment executes relevant operation, comprising:

It is set as the display screen of the electronic equipment to be always on state.

7. according to the method described in claim 3, it is characterized in that, the recognition result is the face figure for detecting the first user Picture, the current state are that the electronic equipment is in the lock state；The electronic equipment executes relevant operation, comprising:

The electronic equipment calls second camera to carry out recognition of face, identifies and successfully then shows the corresponding use of first user Family desktop；

8. according to the method described in claim 3, it is characterized in that, the current state is that the electronic equipment is shown using boundary Face；The recognition result is to detect that angular deviation is greater than between the upper direction of facial image and the upper direction of the application interface Or it is equal to first threshold；The electronic equipment executes relevant operation, comprising:

The electronic equipment adjusts the upper direction of the application interface, by the upper direction of the application interface and the facial image Upper direction between angular deviation be adjusted to be less than or equal to the first threshold.

9. according to the method described in claim 3, it is characterized in that, the recognition result be detect interior operator seat environment, The current state is that the electronic equipment is in running order；The electronic equipment executes relevant operation, comprising:

The electronic equipment opens driving mode, and the electronic equipment can broadcast incoming information and disappear under the driving mode Breath, and be able to respond user speech and execute relevant operation.

10. the method according to claim 5 or 7, which is characterized in that the area of the first image-sensitive cell array and described In the identical situation of area of second image-sensitive cell array, the density of image-sensitive unit is less than institute in the first image-sensitive cell array State the density of image-sensitive unit in the second image-sensitive cell array；

The image-sensitive in the density of the image-sensitive unit and the second image-sensitive cell array in the first image-sensitive cell array In the identical situation of the density of unit, the area of the first image-sensitive cell array is less than the face of the second image-sensitive cell array Product.

11. the method according to any of claims 1 to 10, which is characterized in that the first sensor includes the first mould Conversion circuit is counted, the detection accuracy that lateral circuit is simulated in first analog to digital conversion circuit is related to first color depth；

The electronic equipment includes second camera, and the second camera includes second sensor, the second sensor packet Containing the second analog to digital conversion circuit, the color depth of the image data of the second sensor output is the second color depth, described The detection accuracy that lateral circuit is simulated in second analog to digital conversion circuit is related to second color depth；

The detection accuracy that lateral circuit is simulated in first analog to digital conversion circuit, which is less than in second analog to digital conversion circuit, to be simulated The detection accuracy of lateral circuit, first color depth are less than second color depth.

12. according to the method described in claim 3, it is characterized in that, the recognition result be detect human body image, it is described to work as Preceding state is that the electronic equipment is stored with the first instruction, and the first instruction instruction detects the human body image then to end End sends warning message；The electronic equipment executes relevant operation, comprising:

The electronic equipment sends the warning message to the terminal.

13. described to work as according to the method described in claim 3, it is characterized in that, the recognition result is to detect and fall down posture Preceding state is that the electronic equipment is stored with the second instruction, and the second instruction instruction, which detects, described falls down posture then to end End sends warning message；The electronic equipment executes relevant operation, comprising:

The electronic equipment sends the warning message to the terminal.

14. a kind of electronic equipment, which is characterized in that the electronic equipment includes: one or more processors, memory and first Camera, in which:

First camera include first sensor, the first sensor include the first image-sensitive cell array, described first The quantity of image-sensitive unit is less than or equal to 40000 in image-sensitive cell array, the color of the image data of the first sensor output Color depth is the first color depth, and first color depth is less than 8；

The memory is for storing computer program code, and the computer program code includes computer instruction, when described When one or more processors execute the computer instruction, so that the electronic equipment is executed as appointed in claim 1 to 13 Image-recognizing method described in one.