CN106446873A - Face detection method and device - Google Patents

Face detection method and device Download PDF

Info

Publication number
CN106446873A
CN106446873A CN201610972629.1A CN201610972629A CN106446873A CN 106446873 A CN106446873 A CN 106446873A CN 201610972629 A CN201610972629 A CN 201610972629A CN 106446873 A CN106446873 A CN 106446873A
Authority
CN
China
Prior art keywords
image sensor
exposure
human body
visible light
infrared image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610972629.1A
Other languages
Chinese (zh)
Other versions
CN106446873B (en
Inventor
卢宏刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Megvii Technology Co Ltd
Beijing Aperture Science and Technology Ltd
Original Assignee
Beijing Megvii Technology Co Ltd
Beijing Aperture Science and Technology Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Megvii Technology Co Ltd, Beijing Aperture Science and Technology Ltd filed Critical Beijing Megvii Technology Co Ltd
Priority to CN201610972629.1A priority Critical patent/CN106446873B/en
Publication of CN106446873A publication Critical patent/CN106446873A/en
Application granted granted Critical
Publication of CN106446873B publication Critical patent/CN106446873B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a face detection method and a device. The face detection method comprises an infrared image of a target object acquired by an infrared image sensor; a coordinate region of the human body contour of the target object is extracted from the infrared image; based on the coordinate region, a visible light image sensor is controlled to finish a local exposure of the human body contour, so the exposure of at least a part of the area of the human body contour including the facial area is larger than the exposure of the other areas in the image acquisition range; the local exposure and a collection of a locally exposed visible light image of the target object are finished at the same time; the face detection is applied to the visible light image. According to the face detection method, problems such as slowdowns in performance of the face detection and missing detections in the dark environment are solved effectively. The device has similar advantages.

Description

Method for detecting human face and device
Technical field
The present invention relates to image identification technical field, more particularly, to one kind can improve half-light environment human face detection performance Method for detecting human face and device.
Background technology
With expanding economy, advancing by leaps and bounds of the quickening of city-building speed, and the Internet, lead to population in city close Collection, recurrent population increases, and has caused the traffic in urban construction, social security, key area is taken precautions against, the network crime becomes increasingly conspicuous Deng city management problem, therefore video monitoring system is increasingly widely applied, and how to make collection image comprise high-quality Facial image become research emphasis.
In current image acquisition, subject matter is the dark images gathering under dark environment and obscures, unfavorable In human face detection and recognition.At present in dark environment, in order to improve picture quality, with the raising Face datection of equipment Can, mainly it is realized by the following method：One, adjust the digital gain of AE (automatic exposure), the mould of ISP (image-signal processor) Intend gain, BLC, the image quality parameter such as parameter and brightness, contrast such as wide dynamic, to improve picture quality, but this During the defect of kind of method, light also is difficult to detect face when too dark；Two, adopt additional light compensating lamp on the basis of method one Mode carries out light filling, the defect of this method be light compensating lamp be not directed at face and face with background image similar brightness when easily leak Inspection.
Accordingly, it is desirable to provide a kind of method for detecting human face and device, to solve issue noted above at least in part.
Content of the invention
Introduce a series of concept of reduced forms in Summary, this will specific embodiment partly in enter one Step describes in detail.The Summary of the present invention is not meant to the pass attempting to limit technical scheme required for protection Key feature and essential features, more do not mean that the protection domain attempting to determine technical scheme required for protection.
In order to solve the above problems at least in part, the invention provides a kind of method for detecting human face, including：By infrared Imageing sensor obtains the infrared image of destination object；The human body contour outline of described destination object is extracted from described infrared image Coordinates regional；Visible light image sensor is controlled to carry out partial exposure to described human body contour outline based on described coordinates regional, so that The light exposure at least a portion region of inclusion facial zone obtaining described human body contour outline is than other areas in image-capture field The light exposure in domain is big；The visible images of the described destination object through partial exposure for collection while described partial exposure；Right Described visible images carry out Face datection.
Exemplarily, the coordinates regional bag of the described human body contour outline extracting described destination object from described infrared image Include：Coordinate figure in described infrared image for the heat radiation point that acquisition infrared image sensor senses；By described infrared image Described in heat radiation point the corresponding pixel value of coordinate be labeled as 1 and pixel value is 1 region as in described infrared image Human body contour outline；Extract the coordinates regional of described facial contour.
Exemplarily, described based on described coordinates regional control visible light image sensor office is carried out to described human body contour outline Portion's exposure includes：Based on coordinate transform amount, described coordinates regional is transformed to the coordinates regional of described visible light image sensor； Coordinates regional according to described visible light image sensor controls described visible light image sensor to carry out partial exposure.
Exemplarily, methods described also includes the infrared image based on goal-selling and visible images acquisition coordinate transform Amount, the wherein said step obtaining coordinate transform amount includes：In described visible light image sensor and infrared image sensor A blank sheet of paper is placed in angular field of view, and four stains of four corner mark in blank sheet of paper；By described visible light image sensor Obtain a secondary image including described blank sheet of paper with infrared image sensor respectively；In described visible light image sensor and infrared figure Find out described stain and its coordinate as in the image of the described blank sheet of paper of inclusion of sensor acquisition；By stain described in two width images Coordinate obtain described coordinate transform amount, wherein, the back side of each described stain apply thermal source.
Exemplarily, described based on described coordinates regional control visible light image sensor office is carried out to described human body contour outline Portion's exposure includes：The photosensitive region of described visible light image sensor is divided into multiple blocks；Arrange different for each block Exposure weighted value, wherein said human body contour outline inclusion facial zone the block corresponding at least a portion region weight Value is higher than the exposure weighted value of other blocks；Weighted value according to each block controls described visible light image sensor to be exposed Light simultaneously gathers the visible images of exposed described destination object.
According to another aspect of the present invention, additionally provide a kind of human face detection device, it includes：Infrared image obtains mould Block, described infrared image acquisition module is used for obtaining the infrared image of destination object；Profile extraction module, described contours extract mould Block is used for extracting the coordinates regional of the human body contour outline of described destination object from described infrared image；Partial exposure module, described Partial exposure module is used for controlling visible light image sensor described human body contour outline to be carried out locally expose based on described coordinates regional Light is so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline is than in image-capture field The light exposure in other regions is big；Visible images acquisition module, described visible images acquisition module is used for exposing in described local The visible images of the described destination object through partial exposure for collection while light；Face detection module, described Face datection mould Block is used for carrying out Face datection to described visible images.
Exemplarily, described profile extraction module includes：Coordinate acquisition submodule, described coordinate acquisition submodule is used for obtaining Take coordinate figure in described infrared image for the heat radiation point that infrared image sensor senses；Element marking submodule, described Element marking submodule is used for for the corresponding pixel value of coordinate of heat radiation point described in described infrared image being labeled as 1 and by picture The region for 1 for the element value is as the human body contour outline in described infrared image；Coordinate extracting sub-module, described coordinate extracting sub-module is used In the coordinates regional extracting described facial contour.
Exemplarily, described partial exposure module includes：Region division submodule, described region division submodule is used for will The photosensitive region of described visible light image sensor is divided into multiple blocks；Weight arranges submodule, and described weight arranges submodule Block is used for as each block different exposure weighted values of setting, at least one of the inclusion facial zone of wherein said human body contour outline The weighted value of the block corresponding to subregion is higher than the exposure weighted value of other blocks；Spectrum assignment submodule, described exposure control The weighted value that system module is used for according to each block controls described visible light image sensor to be exposed.
Exemplarily, described partial exposure module also includes coordinate transform submodule, for based on coordinate transform amount by institute State the coordinates regional that coordinates regional is transformed to described visible light image sensor.
Exemplarily, described profile extraction module, described partial exposure module and described face detection module are by same Processor is realized.
Human face detection device according to the present invention according to the method for detecting human face of the present invention and device, by sensing human body Heat radiation simultaneously forms infrared image, then extracts the coordinates regional of human body contour outline from infrared image, and human body contour outline is changed For the coordinates regional of human body contour outline in visible light image sensor, and visible light image sensor is controlled to carry out office to human body contour outline Portion exposes, thus strengthening at least the one of the inclusion facial zone of human body contour outline described in the image that visible light image sensor gathers The brightness of subregion, so when the image that visible light image sensor is gathered carries out human face detection and recognition, accuracy To be substantially improved with performance, efficiently solve the problems, such as dark environment human face detection hydraulic performance decline and easy missing inspection.
Brief description
The drawings below of the embodiment of the present invention is used for understanding the present invention in this as the part of the present invention.Shown in accompanying drawing Embodiments of the invention and its description, for explaining the principle of the present invention.In the accompanying drawings,
Fig. 1 is for realizing the method for detecting human face of device according to embodiments of the present invention and device exemplary electronic device Schematic block diagram；
Fig. 2 is the indicative flowchart of the method for detecting human face according to the embodiment of the present invention；
Fig. 3 is the indicative flowchart according to contour extraction method in the method for detecting human face of the embodiment of the present invention；
Fig. 4 is the indicative flowchart according to local exposure method in the method for detecting human face of the embodiment of the present invention；
Fig. 5 is the schematic block diagram of the human face detection device according to the embodiment of the present invention；
Fig. 6 is the schematic block diagram of the profile extraction module according to the embodiment of the present invention；
Fig. 7 is the schematic block diagram of the partial exposure module according to the embodiment of the present invention；
Fig. 8 is the schematic block diagram of the image detecting apparatus according to the embodiment of the present invention.
Specific embodiment
In the following description, a large amount of concrete details are given to provide more thorough understanding of the invention.So And, it will be apparent to one skilled in the art that the embodiment of the present invention can one or more of these details And be carried out.In other examples, in order to avoid obscuring with the embodiment of the present invention, for more well known in the art Technical characteristic is not described.
It should be appreciated that the present invention can be implemented in different forms, and should not be construed as being limited to propose here Embodiment.On the contrary, it is open thoroughly and complete to provide these embodiments will make, and will fully convey the scope of the invention to Those skilled in the art.In the accompanying drawings, in order to clear, the size of part, element etc. and relative size may be exaggerated.Ad initio Represent identical element to whole same reference numerals.
So that the object, technical solutions and advantages of the present invention become apparent from, describe root below with reference to accompanying drawings in detail Example embodiment according to the present invention.Obviously, described embodiment is only a part of embodiment of the present invention, rather than this Bright whole embodiments are not it should be appreciated that the present invention is limited by example embodiment described herein.Described in the present invention The embodiment of the present invention, the obtained all other embodiment in the case of not paying creative work of those skilled in the art All should fall under the scope of the present invention.
First, the example for realizing method for detecting human face according to embodiments of the present invention and device to be described with reference to Fig. 1 Electronic equipment 100.
As shown in figure 1, electronic equipment 100 includes one or more processors 102, one or more storage device 104, defeated Enter/output device 106, communication interface 108 and one or more image-signal processor (ISP) 110, visible images sensing Device 114 and infrared image sensor 116, these assemblies pass through bus system 112 and/or the bindiny mechanism of other forms (does not show Go out) interconnection.It should be noted that the assembly of electronic equipment 100 shown in Fig. 1 and structure are illustrative, and not restrictive, root According to needs, described electronic equipment can also have other assemblies and structure it is also possible to not include aforesaid members, for example may be used To include communication interface 108 it is also possible to not packet communication interface 108.
Described processor 102 typically represent any types or form can processing data or explain and execute instruction place Reason unit.In general, processor can be CPU (CPU) or have data-handling capacity and/or instruction hold The processing unit of the other forms of row ability, and the other assemblies in described electronic equipment 100 can be controlled to execute expectation Function.In a particular embodiment, processor 102 can receive the instruction from software application or module.These instructions are permissible Lead to the function of one or more example embodiment that processor 102 completes to be described herein and/or illustrate.
Described storage device 104 can include one or more computer programs, and described computer program can To include various forms of computer-readable recording mediums, such as volatile memory and/or nonvolatile memory.Described easy The property lost memorizer for example can include random access memory (RAM) and/or cache memory (cache) etc..Described non- Volatile memory for example can include read only memory (ROM), hard disk, flash memory etc..In described computer-readable recording medium On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired function.In described meter Various application programs and various data can also be stored in calculation machine readable storage medium storing program for executing, such as described application program using and/or Various data producing etc..
Described input/output device 106 can be the device for input instruction with to the various information of outside output for the user, For example input equipment can include one or more of keyboard, mouse, mike and touch screen etc..Output device can include One or more of display, speaker etc..
Communication interface 108 widely represent any types or form can promote exemplary electronic device 100 and one or The adapter of the communication between multiple optional equipments or communication equipment.For example, communication interface 108 can promote electronic equipment 100 Communication with front end or accessory electronic device and back-end server or high in the clouds.The example of communication interface 108 includes but is not limited to Wired network interface (such as NIC), radio network interface (such as wireless network interface card), modem and appoint What his suitable interface.In one embodiment, communication interface 108 by with the direct-connected offer of the network of such as the Internet to remote Journey server/remote front-end equipment direct-connected.In a particular embodiment, communication interface 108 by with dedicated network, such as video The direct-connected offer of the networks such as monitoring network, Skynet system network is direct-connected to remote server/remote front-end equipment.Communication interface 108 can also provide this connection by any other suitable connection indirectly.
Image-signal processor (ISP) 110 is used for controlling visible light image sensor 114 and infrared image sensor 116 Carry out image acquisition, and adjust the digital gain of AE (automatic exposure), analog gain, BLC, the wide parameter such as dynamic and bright The image quality parameters such as degree, contrast and other specification, with adjusting image quality, and are based on visible light image sensor 114 Generate corresponding visible light exposure image and infrared image with the output signal of infrared image sensor 116, and by such as total The connection unit of linear system system 112 transmits and carries out subsequent treatment to processor 102.Meanwhile, image-signal processor (ISP) 110 The order from processor 102 or instruction can be accepted, with to visible light image sensor 114 and infrared image sensor 116 It is adjusted controlling.Image-signal processor (ISP) 110 can as needed and visible light image sensor 114 and infrared The quantity setting of imageing sensor 116 is one or more, and image-signal processor (ISP) 110 can be with processor 102 etc. Integrated, it is embodied as SOC(system on a chip) (SOC) it is also possible to set up setting, and carried out even by the connection unit of such as bus system 112 Connect.
Visible light image sensor 114 can gather or shoot the desired visible light exposure of user image (such as photo, Video etc.), and captured image is stored in described storage device 104 so that other assemblies use.Visible images One example of sensor 114 is RGB sensor, or RGBW sensor or black and white sensor (can only gather black white image) etc. Deng, it forms colour or black white image/video by sensing visible ray, thus referred to here as visible light image sensor.Accordingly Visible light image sensor collection terminal image/video be referred to as visible images/video or visible light exposure image/video.
Infrared image sensor 116 is used for gathering infrared image, and it is based on heat radiation and is imaged, and therefore no matter ambient light is strong Weak, all can gather infrared image.
Exemplarily, the exemplary electronic device for realizing method for detecting human face according to embodiments of the present invention and device can To be implemented as the image acquisition of such as smart mobile phone, panel computer, the image acquisition end of gate control system, preventing road monitoring system The rear end control process end of end, the image acquisition end of safety-protection system and various monitoring, safety-security area etc. or server end or cloud End etc..
Fig. 2 is the indicative flowchart of the method for detecting human face according to the embodiment of the present invention.Below in conjunction with Fig. 2 to basis The method for detecting human face of the embodiment of the present invention is described.
As shown in Fig. 2 method for detecting human face includes disclosed in the embodiment of the present invention：
First, in step s 201, the infrared image of destination object is obtained by infrared image sensor.
Infrared image is the image being formed based on heat radiation infrared sensitive, and compared with visible ray, infrared imaging is not subject to ring The strong and weak impact of environmental light, therefore can with half-light also can or clearly infrared image.
In embodiments of the present invention, infrared image sensor can be controlled to obtain destination object by image-signal processor Infrared image, the infrared ray that the radiation of angular field of view interior-heat is formed is sensed by infrared image sensor, and infrared ray is believed Number it is converted into the signal of telecommunication, after image-signal processor is processed, form destination object infrared image.
From described infrared image, in step S202, extract the coordinates regional of the human body contour outline of described destination object.
The infrared image of the destination object obtaining in step S201 is processed, therefrom extract the coordinate of human body contour outline Region, and extract the coordinates regional of described facial contour from the coordinates regional of this human body contour outline, as the coordinate of human body contour outline How region extracts, and is subsequently described in detail.
In step S203, visible light image sensor is controlled to carry out office to described human body contour outline based on described coordinates regional Portion exposes, so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline compares image-capture field The light exposure in other interior regions is big.
Due to when ambient light is weaker it is seen that the image of optical image sensor collection due to excessively secretly obscuring, face and the back of the body Scape similar brightness etc. reason makes the increase of Face datection difficulty, Face datection efficiency and hydraulic performance decline, in order to improve under half-light Face datection performance, in the present invention based on the human body contour outline being extracted coordinates regional control visible light image sensor carry out Partial exposure, so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline is than image acquisition model The light exposure in other regions in enclosing is big.I.e. in visible light image sensor with corresponding to the coordinates regional of described human body contour outline Region carries out partial exposure so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline compares image The light exposure in other regions in acquisition range is big, so that the image of visible light image sensor collection includes facial zone Other regional luminances height are compared at least a portion region, thus beneficial to follow-up Face datection.
Exemplarily, in one example of the present invention, step S203 further includes：
Step 2030：Based on coordinate transform amount, described coordinates regional is transformed to the coordinate of described visible light image sensor Region.
Position misaligned, therefore infrared image sensing due to visible light image sensor and infrared image sensor The coordinate of human body contour outline and position the coordinate equal to human body contour outline in visible light image sensor/image in device/infrared image And position, therefore in this step coordinate transform is carried out to the coordinates regional of the human body contour outline in infrared image, thus obtain can See the coordinates regional of human body contour outline in optical image sensor/image.So-called coordinate transform i.e. human body contour outline in infrared image Coordinate on superposition coordinate transform amount thus obtaining the coordinates regional of human body contour outline in visible light image sensor/image.
Described coordinate transform amount can be only the converted quantity in a direction up conversion amount or multiple directions.? In the embodiment of the present invention, described coordinate transform amount can infrared image based on goal-selling and visible images obtaining.
Exemplarily, in the present invention one example, described coordinate transform amount can be obtained by following step：
First, place a blank sheet of paper in the angular field of view of described visible light image sensor and infrared image sensor, And four stains of four corner mark in blank sheet of paper, and apply thermal source so that infrared figure can be formed in the behind of each stain Picture.In the present invention one example it is preferable that infrared image sensor and visible light image sensor select identical resolution with And horizontal and vertical visual angle, and it is horizontally disposed with circuit boards and close proximity to reduce the error of coordinate transform.
Then, a described blank sheet of paper of secondary inclusion is obtained respectively by described visible light image sensor and infrared blit image sensor Image.In the present invention one example, visible light image sensor and infrared image sensing can be controlled by picture signal device Device gathers image, with obtain respectively one secondary include described blank sheet of paper infrared image and visible images.
Then, in the image of the described blank sheet of paper of inclusion that described visible light image sensor and infrared blit image sensor obtain Find out described stain and its coordinate.Stain and its coordinate can be obtained by the coordinate system of algorithm and image.When acquisition two After width image stain and its coordinate, described coordinate transform amount can be obtained by the coordinate of stain described in two width images.For example, The coordinate one of vertical direction in the present invention one example it is seen that in the coordinate system of optical image sensor and infrared image sensor Cause, and the coordinate of horizontal direction has difference, therefore by comparing horizontal coordinate difference or the pixel of corresponding stain in two width images Value difference dPix can obtain the coordinate transform amount of horizontal direction.Exemplarily, the coordinate of such as horizontal direction (being expressed as X-direction) Transformation for mula is X (visible light image sensor)=X (infrared image sensor)+dPix.It is understood that dPix be based on can The relative position seeing optical image sensor and infrared blit image sensor can be on the occasion of can also negative value.
Yes may be appreciated, the set-up mode of above-mentioned visible light image sensor and infrared blit image sensor and coordinate The acquisition methods of converted quantity are only examples, and those skilled in the art can be obtained by additive method based on similar principles Described coordinate transform amount, and described coordinate transform amount can be only in a direction up conversion amount or multiple directions Converted quantity.
Step 2031：Coordinates regional according to described visible light image sensor controls described visible light image sensor to enter Row partial exposure.
It should be noted that the coordinates regional of human body contour outline refers to when visible in so-called visible light image sensor It is seen that the region of human body can be sensed in optical image sensor during optical image sensor collection image, namely visible light collection Human body region in image.
In an embodiment of the present invention, visible light image sensor can be controlled to described by image-signal processor Region corresponding to the coordinates regional of human body contour outline carries out partial exposure, that is, pass through to adjust the corresponding ginseng of image-signal processor Count so that human body contour outline region includes the exposure at least a portion region of facial zone in visible light image sensor Amount is bigger than other regions, and the image that so can strengthen visible light image sensor collection includes at least of facial zone Subregional brightness.In a kind of partial exposure mode of example, by adjust image-signal processor relevant parameter so that The light exposure of the facial zone in human body contour outline region in visible light image sensor is bigger than other regions, so can increase The brightness of the facial zone of destination object in the visible images of strong collection, consequently facilitating follow-up Face datection operation.Another In a kind of partial exposure mode of example, by adjusting the relevant parameter of image-signal processor so that visible images sense In device, the light exposure of human body contour outline region is bigger than other regions, so can strengthen target pair in the visible images of collection As the brightness of region (inclusion facial zone), thus also allowing for follow-up Face datection operation.
Exemplarily, in embodiments of the present invention, visible light image sensor can be adjusted by image-signal processor The weighted value of zones of different to carry out partial exposure to described human body contour outline region, even if people in visible light image sensor Body profile region includes the exposure power more than other regions for the exposure weighted value at least a portion region of facial zone Weight values are realizing described partial exposure.
In step S204, the visible ray of the described destination object through partial exposure for collection while described partial exposure Image.
In embodiments of the present invention, visible light image sensor can be controlled to obtain local by image-signal processor to expose Light image, is gathered the optical signal of partial exposure, and converts optical signal into the signal of telecommunication by visible light image sensor, passes through Image-signal processor forms partial exposure image after processing.
In step S205, Face datection is carried out to described visible images.
Then carry out Face datection after obtaining the partial exposure image of visible light image sensor, pass from visible images Facial image is extracted in the partial exposure image of sensor.Wherein, after carrying out Face datection, can enter for the face detecting The various feasible subsequent operation such as row feature extraction, attributive analysiss, recognition of face, here is omitted.
The image of described visible light image sensor collection can also be able to be video for picture.When visible images sensing When the image of device collection is video, then each frame picture being directed to this video of composition carries out Face datection and extraction.In this step In whether comprise face it may be determined that going out in visible light image sensor acquired image, and visible images pass Face is oriented in visible light image sensor acquired image in the case of comprising face in sensor acquired image Region.
Exemplary property, for example, can be gathered in visible light image sensor using the good human-face detector of training in advance Image in locating human face region.For example, it is possible to advance with the Face datection such as Ha Er (Haar) algorithm, Adaboost algorithm with Recognizer trains human-face detector on the basis of a large amount of pictures, and for the single-frame imagess of input, this training in advance is good Human-face detector can quickly locate out human face region.Additionally, the multiframe figure for visible light image sensor continuous acquisition Picture, after orienting human face region in first two field picture, can be based on human face region in the previous frame image of current frame image Position to follow the trail of the position of human face region in current frame image in real time.
After detecting facial image in the image gathering in visible light image sensor and provide corresponding coordinate, then may be used By coordinate, facial image is plucked out (being commonly called as scratching figure), to obtain facial image.
Exemplarily, described people can be detected from the image of described visible light image sensor collection in step S205 The coordinate data of face image position；According to the coordinate data of described destination object, adopt from described visible light image sensor Take, in the image of collection, the image only including described face.As an example, when the coordinate determining facial image position After data, can be marked at these coordinates, for example, be labeled as 1, and the position mark outside these coordinates is 0, thus really Determine region, profile and pixel of facial image etc., then can use existing figure cutting techniques (for example, Graph Cut algorithm) The region being labeled as 1 is taken out, thus only being comprised the image of face.
Further, in embodiments of the present invention, the facial image that can also detect from step S205/extract is further Extract the characteristic information of face.
So-called characteristic information, refer to can be used for face or the letter being distinguished face to be identified and other faces Breath., so-called characteristic information exemplarily can include such as face overall information, such as shape of face, face taking facial image as a example Layout etc., can also include local feature information, such as nevuss, freckle, scar etc., can also include face characteristic information, for example Left ear information (size, shape etc.), auris dextra information (size, shape etc.), left eyebrow information (such as shape, position, length and width etc.), Right eyebrow information (such as shape, position, length and width etc.), and left eye information (such as shape, position, length and width etc.), right eye information (such as shape, position, length and width etc.) etc..
Exemplarily, in one embodiment, Sobel operator extraction characteristics algorithm or Gabor characteristic algorithm etc. can be passed through The characteristic information of facial image is extracted in the facial image that feature extraction algorithm extracts from step 205.In another embodiment, Can be using the good crucial spot locator of training in advance come locating human face's key point in human face region (such as eyes, canthus, eye Eyeball center, eyebrow, nose, nose, face, the corners of the mouth and face mask etc.).For example, it is possible to advance with cascade homing method exist Crucial spot locator is trained in a large number on the basis of the face picture of artificial mark.Alternatively, it would however also be possible to employ traditional face Crucial independent positioning method, it is based on parametric shape model, according to the appearance features near key point, learns a parameter mould Type, iteratively optimizes the position of key point, finally obtains crucial point coordinates when using, after obtaining crucial point coordinates, permissible One step is carried out based on this coordinate and obtains key point (such as eyes, canthus, eye center, eyebrow, nose, nose, face, the corners of the mouth With face mask etc.) other information, such as size, shape etc. information.
Should be appreciated that the present invention is not limited by the facial image extracting method specifically adopting and characteristics information extraction method, no By be existing facial image extracting method and characteristics information extraction method or in the future the facial image extracting method of exploitation and Feature extracting method, can be applied to Face datection according to embodiments of the present invention and become in method, and also should include at this In the protection domain of invention.
Exemplarily, the method for detecting human face according to the present embodiment can be deployed at man face image acquiring end, for example, Security protection application, can be deployed in the image acquisition end of gate control system；In financial application field, personal terminal can be deployed in Place, smart phone, panel computer, personal computer etc..
Alternatively, method for detecting human face according to embodiments of the present invention can also be deployed in server end (or cloud with being distributed End) and personal terminal at.For example, in financial application field, image acquisition can be carried out in personal terminal, form partial exposure figure Picture, carries out Face datection extraction and identification etc. in server end (or high in the clouds).
According to the method for detecting human face of the present embodiment, by sensing the heat radiation of human body and forming infrared image, Ran Houcong Extract the coordinates regional of human body contour outline in infrared image, and visible light image sensor is controlled to human body wheel based on this coordinates regional Exterior feature carries out partial exposure, so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline compares image The light exposure in other regions in acquisition range is big, thus the image strengthening visible light image sensor collection includes facial area The brightness at least a portion region in domain, so when the image that visible light image sensor is gathered carries out human face detection and recognition When, accuracy and performance will be substantially improved, and efficiently solve dark environment human face detection hydraulic performance decline and easy leak The problem of inspection.
Fig. 3 is the indicative flowchart according to contour extraction method in the method for detecting human face of the embodiment of the present invention.Below In conjunction with Fig. 3, contour extraction method according to embodiments of the present invention is described.
As shown in figure 3, contour extraction method includes disclosed in the embodiment of the present invention：
First, in step S301, obtain the coordinate figure in infrared in figure for the heat radiation point.
Infrared image is formed by induction heat infrared radiation line, therefore when there is human body, can be by sensing human body Heat radiation infrared ray formed infrared image.The coordinate therefore passing through to obtain heat radiation point in infrared image can obtain human body wheel Wide.In embodiments of the present invention, can judge that position in the coordinate system of infrared image for the heat radiation point is obtained by algorithm Take the coordinate of heat radiation point in infrared image.
In step s 302, corresponding for above-mentioned coordinate pixel value is labeled as 1.Will infrared image all heat radiations point Pixel value corresponding to coordinate is labeled as 1, and the region that pixel value is 1 is as the human body contour outline in described infrared image.And And exemplarily, can also further use existing figure cutting techniques (for example, Graph Cut algorithm) to be 1 by pixel value Region takes out, thus only comprised human body contour outline infrared image.
Exemplarily, in one example, by the pixel value labelling corresponding to the coordinate of all for infrared image heat radiation points During for 1, the pixel value in other regions is labeled as 0.Or, in another embodiment, can be in advance by the pixel of all pixels Value is defaulted as 0, after obtaining heat radiation point in the coordinate figure of infrared in figure, then the coordinate institute by all for infrared image heat radiation points Corresponding pixel value is labeled as 1, so equally can obtain human body contour outline from infrared image.
In step S303, extract the coordinates regional of described facial contour.
According to the human body contour outline obtaining in step S302, extract facial contour using with aforementioned similar method.
Exemplarily, contour extraction method according to embodiments of the present invention can have visible light image sensor, red Realize in the unit of outer imageing sensor and processor or system.
Contour extraction method according to embodiments of the present invention can be deployed at man face image acquiring end, for example, in security protection Application, can be deployed in the image acquisition end of gate control system；In financial application field, can be deployed at personal terminal, Smart phone, panel computer, personal computer etc..
According to the contour extraction method of the present embodiment, by sensing the heat radiation of human body and forming infrared image, Ran Houcong The coordinates regional of extraction human body contour outline in infrared image, and extract the coordinates regional of facial contour, so just can be based on described Coordinates regional controls visible light image sensor to carry out partial exposure to human body contour outline region, thus strengthening visible images The image of sensor acquisition includes the brightness at least a portion region of facial zone.
Fig. 4 is the indicative flowchart according to local exposure method in the method for detecting human face of the embodiment of the present invention.Below In conjunction with Fig. 4, local exposure method according to embodiments of the present invention is described.
As shown in figure 4, local exposure method according to embodiments of the present invention includes：
In step 401, described visible light image sensor is divided into multiple blocks.
In an embodiment of the present invention, can will be seen that optical image sensor is divided into m*n by image-signal processor Block.This m*n block can be preset by image-signal processor it is also possible to obtain the coordinates regional of human body contour outline Afterwards, divided based on the coordinates regional of human body contour outline.
In step 402, for the exposure weighted value that the setting of each block is different, the inclusion face of wherein said human body contour outline The weighted value of the block corresponding at least a portion region in region is higher than the exposure weighted value of other blocks.I.e. to described visible In m*n block of optical image sensor, corresponding at least a portion region of inclusion facial zone of described human body contour outline The higher exposure weighted value of block setting, and the exposure weighted value relatively low to the setting of other blocks.Assume described visible images Sensor is divided into tetra- blocks of 2*2, is expressed as A, B, C, D, and at least the one of the inclusion facial zone of human body contour outline Block corresponding to subregion is B, then when arranging the exposure weighted value of tetra- blocks of A, B, C, D, can be by the exposure of B block It is higher that light weighted value is arranged, and the setting of the exposure weighted value in A, C and D region is relatively low, such as in the present invention one example, permissible The exposure weighted value of B block is set to 70%, the exposure weighted value of A, C and D block is set to 10%.Show the present invention is another In example, the exposure weighted value of B block can be set to 1, the exposure weighted value of A, C and D block is set to 0, that is, only to B block It is exposed, and A, C and D block is not exposed.
In step 403, the weighted value according to each block controls described visible light image sensor to carry out partial exposure, And gather the visible images of exposed described destination object.
In an embodiment of the present invention, after setting up the exposure weighted value of visible light image sensor each block, then base Exposure weighted value in set each block controls visible light image sensor to carry out partial exposure, so that visible images pass In sensor, the light exposure of the block corresponding at least a portion region of inclusion facial zone of human body contour outline is bigger than other blocks, Thus the image strengthening visible light image sensor collection includes the brightness at least a portion region of facial zone.
In the present invention one example, only the coordinates regional of human body contour outline is exposed when carrying out partial exposure, and right Other regions are then not all right to expose so that only human region brightness is higher in the image of collection, and other regions are then dark, beneficial to face inspection Survey and identify.
Exemplarily, the local exposure method according to the present embodiment can have equipment, the dress of memorizer and processor Put or system in realize.Local exposure method according to embodiments of the present invention can be deployed at man face image acquiring end, example Image acquisition end of gate control system as the shooting generator terminal of preventing road monitoring system, Companies House etc. etc., or in financial field Can be deployed at personal terminal.
According to the local exposure method of the present embodiment, by making the inclusion face of human body contour outline in visible light image sensor The light exposure of the block corresponding at least a portion region in region is bigger than other blocks, thus strengthening visible light image sensor The image of collection includes the brightness at least a portion region of facial zone, beneficial to human face detection and recognition.
It is understood that described above be only local exposure method an example, the partial exposure side of the present invention Method not limited to this, such as, except including said one or several step, can also include other steps, for example in one example, In addition to the coordinates regional based on human body contour outline for the setting arranges the exposure weighted value of each block of visible light image sensor, also may be used To arrange the digital gain in each region, analog gain, BLC, the wide image such as parameter and brightness, contrast such as dynamic Mass parameter, includes the quality at least a portion region of facial zone and this region and other regions to improve image Difference.
Fig. 5 is the schematic block diagram of the human face detection device according to the embodiment of the present invention.With reference to Fig. 5 to basis The human face detection device of the embodiment of the present invention is described.
As shown in figure 5, human face detection device 500 according to embodiments of the present invention includes infrared image module 510, profile carries Delivery block 520, partial exposure control module 530 and face detection module 540.
Infrared image module 510 is used for gathering the infrared image of destination object by infrared image sensor.Infrared image Module 510 can processor 102 in electronic equipment as shown in Figure 1 or image-signal processor 110 Running storage device 104 The programmed instruction of middle storage is realizing, and can execute in target object information generation method according to embodiments of the present invention Step S201.In the present invention one example, the processor 102 in infrared image module 510 electronic equipment as shown in Figure 1 runs In storage device 104 programmed instruction of storage to obtain by image-signal processor 110 or infrared image sensor 116 infrared Image.
Profile extraction module 520 is used for the coordinates regional that described infrared image extracts human body contour outline, and is based on this human body wheel Wide coordinates regional extracts the coordinates regional of facial contour.That is, extract from the infrared image that infrared image module 510 obtains The coordinates regional of human body contour outline therein, and therefrom extract the coordinates regional of facial contour.Profile extraction module 520 can be by scheming In processor 102 Running storage device 104 in electronic equipment shown in 1, the programmed instruction of storage to be realizing, and can hold Step S202 in row method for detecting human face according to embodiments of the present invention, and step S301 in contour extraction method～ S303.
Partial exposure control module 530 is based on described coordinates regional and controls visible light image sensor to described human body contour outline Carry out partial exposure so that the light exposure at least a portion region of inclusion facial zone of described human body contour outline is adopted than image The light exposure in other regions in the range of collection is big, thus strengthen including face by the image that visible light image sensor gathers The brightness at least a portion region in region.Partial exposure control module 530 can process in electronic equipment as shown in Figure 1 In device 102 and/or picture signal device 110 Running storage device 104, the programmed instruction of storage to be realizing, and can execute basis Step S203 in the method for detecting human face of the embodiment of the present invention, and the S401～S403 in local exposure method.
Visible images acquisition module 530 is used for controlling described visible light sensing in described partial exposure control module 530 The visible images of the described destination object through partial exposure for collection while device partial exposure.Visible images acquisition module 530 can deposit in processor 102 in electronic equipment as shown in Figure 1 and/or picture signal device 110 Running storage device 104 The programmed instruction of storage is realizing, and can execute step S204 in method for detecting human face according to embodiments of the present invention.
Face detection module 550 carries out face inspection based on described visible light image sensor partial exposure acquired image Survey.From the image of visible light image sensor collection, detect and extract face, Face datection and extracting method is for example aforementioned retouches State, will not be described here.Face detection module 550 can run storage dress by the processor 102 in electronic equipment as shown in Figure 1 Put the programmed instruction storing in 104 to realize, and the step in method for detecting human face according to embodiments of the present invention can be executed Rapid S205.
Exemplarily, as shown in fig. 6, in an embodiment of the present invention, profile extraction module 520 includes coordinate and obtains submodule Block 5210, element marking submodule 5220 and coordinate transform submodule 5230.
The heat radiation point that coordinate acquisition submodule 5210 senses for infrared image sensor is in described infrared image Coordinate figure.Coordinate acquisition submodule 5210 can processor 102 Running storage device in electronic equipment as shown in Figure 1 In 104, the programmed instruction of storage to be realizing, and can execute the step in contour extraction method according to embodiments of the present invention S301.
Element marking submodule 5220 is used for the corresponding pixel value of coordinate of heat radiation point described in described infrared image It is marked, to obtain human body contour outline.Exemplarily, element marking submodule 5220 is by heat radiation described in described infrared image Point the corresponding pixel value of coordinate be labeled as 1 and pixel value is 1 region as the human body contour outline in described infrared image.Picture Plain labelling submodule 5220 can in processor 102 Running storage device 104 in electronic equipment as shown in Figure 1 storage journey Sequence instructs to be realized, and can execute step S302 in contour extraction method according to embodiments of the present invention.
Coordinate extracting sub-module 5230 is used for extracting the coordinates regional of described facial contour.Coordinate extracting sub-module 5230 can To be realized with the programmed instruction of storage in processor 102 Running storage device 104 in electronic equipment as shown in Figure 1, and Step S303 in contour extraction method according to embodiments of the present invention can be executed.
Further, in an embodiment of the present invention, local includes control module 530 and includes coordinate transform submodule 5310th, region division submodule 5320, weight setting submodule 5330 and spectrum assignment submodule 5340.
Coordinate transform submodule 5310 is used for, based on coordinate transform amount, described coordinates regional is transformed to described visible ray figure Coordinates regional as sensor.For example, coordinate transform submodule 5310 is used for the coordinates regional of the human body contour outline in infrared image Enter line translation, to obtain the coordinates regional of the human body contour outline in visible light image sensor.Coordinate transform submodule 5310 is permissible The journey of storage in processor 102 in electronic equipment as shown in Figure 1 or image-signal processor 110 Running storage device 104 Sequence instructs to be realized, and can execute step S303 in contour extraction method according to embodiments of the present invention.
Further, in the present invention one example, the infrared image also based on goal-selling for the coordinate transform submodule 5310 Obtain coordinate transform amount with visible images.Coordinate transform amount can execute coordinate as above with coordinate transform submodule 5310 The step of converted quantity acquisition methods obtains.
Region division submodule 5320 is used for it will be seen that optical image sensor is divided into multiple blocks.Region division submodule 5310 can be in advance it will be seen that optical image sensor be divided into m*n block it is also possible to obtain in coordinate transform submodule 5310 After the coordinates regional of human body contour outline in visible light image sensor, will be seen that light image passes based on the coordinates regional of this human body contour outline Sensor is divided into m*n block.Region division submodule 5320 can the picture signal in electronic equipment as shown in Figure 1 be processed In device 110 Running storage device 104, the programmed instruction of storage to be realizing, and can execute local according to embodiments of the present invention Step S401 in exposure method.
Weight arranges submodule 5330 and is used for the every of the visible light image sensor for region division submodule 5320 division The different exposure weighted value of individual block setting, so that at least a portion region institute of the inclusion facial zone of described human body contour outline is right The exposure weighted value of the block answered is higher, and the exposure region thresholding of other blocks is relatively low.Weight setting submodule 5330 can be by The journey of storage in processor 102 in electronic equipment shown in Fig. 1 and/or image-signal processor 110 Running storage device 104 Sequence instructs to be realized, and can execute step S402 in local exposure method according to embodiments of the present invention.
Spectrum assignment submodule 5340 arranges, based on weight, each block that submodule 5330 is visible light image sensor The exposure weighted value of setting controls visible light image sensor to carry out partial exposure, so that human body wheel in visible light image sensor The light exposure of wide region is big, and the light exposure in other regions is little, thus strengthening in the image that visible light image sensor gathers Including the brightness at least a portion region of facial zone, and the contrast in this region and other regions, to improve Face datection Performance and efficiency.Spectrum assignment submodule 5340 can the image-signal processor 110 in electronic equipment as shown in Figure 1 run In storage device 104, the programmed instruction of storage to be realizing, and can execute local exposure method according to embodiments of the present invention In step S403.
According to the human face detection device of the present invention, by sensing the heat radiation of human body and forming infrared image, then from red Extract the coordinates regional of human body contour outline in outer image, and human body contour outline is converted to human body contour outline in visible light image sensor Coordinates regional, and control visible light image sensor to carry out partial exposure to the coordinates regional of human body contour outline, thus strengthening visible Optical image sensor collection image in inclusion facial zone at least a portion region brightness, and this region and its The contrast in his region, so when the image that visible light image sensor is gathered carries out human face detection and recognition, accuracy and Performance will be substantially improved, and efficiently solve the problems, such as dark environment human face detection hydraulic performance decline and easy missing inspection.
Fig. 8 is the schematic block diagram of the image detecting apparatus according to the embodiment of the present invention.With reference to Fig. 8 to basis The image detecting apparatus system of the embodiment of the present invention is described.
As shown in figure 8, image detecting apparatus 800 according to embodiments of the present invention include infrared image sensor 810, visible Optical image sensor 820, storage device 830 and processor 840.
Described infrared image sensor 810 is used for gathering the infrared image of destination object.Visible light image sensor 820 is used Visible light exposure image in collection destination object.Visible light image sensor 820 can be RGB sensor or black White sensor.Infrared image sensor 810 and visible light image sensor 820 can gather picture and can also gather video.When So, infrared image sensor 810, visible light image sensor 820 gathered data process can electronic equipment as shown in Figure 1 In processor 102 or image-signal processor 110 Running storage device 104 in storage programmed instruction realizing, to obtain Picture or video data.
Further, in embodiments of the present invention, infrared image sensor 810 and visible light image sensor 820 are preferred Ground is identical in directions such as resolution, horizontal view angle, verticals angle of view.
Described storage device 830 stores for realizing the corresponding steps in method for detecting human face according to embodiments of the present invention Program code.
Described processor 840 is used for running the program code of storage in described storage device 830, to execute according to the present invention The corresponding steps of the method for detecting human face of embodiment, and for realizing in human face detection device according to embodiments of the present invention Infrared image module 510, profile extraction module 520, partial exposure control module 530, visible images acquisition module 540 and people Face detection module 550；And the coordinate acquisition submodule 5210 in profile extraction module 520, element marking submodule 5220 and Coordinate transform submodule 5310 in coordinate extracting sub-module 5230, and local inclusion control module 530, region division submodule 5320th, weight setting submodule 5330 and spectrum assignment submodule 5340.
In one embodiment, following steps are executed when described program code is run by described processor 840：
Obtain the infrared image of destination object by infrared image sensor；
The coordinates regional of the human body contour outline of described destination object is extracted from described infrared image；
Visible light image sensor is controlled to carry out partial exposure to described human body contour outline based on described coordinates regional, so that The light exposure at least a portion region of inclusion facial zone of described human body contour outline is than other regions in image-capture field Light exposure big；
The visible images of the described destination object through partial exposure for collection while described partial exposure；
Face datection is carried out to described visible images.
In one embodiment, processor 840 can be implemented as central processing unit (CPU) and image-signal processor (ISP), wherein, central processing unit (CPU) obtains infrared image by infrared image sensor 810, is then stored by execution Corresponding program code in device 830, extracts human body contour outline from infrared image, and is translated into visible light image sensor Human body contour outline region in 820, is then based on the difference that this human body contour outline region is in visible light image sensor The different exposure weighted value of region setting, then sends the exposure weighted value of this zones of different to image-signal processor (ISP), image-signal processor passes through to execute the corresponding exposure weight based on zones of different for the program code in storage device 830 Value controls visible light image sensor 820 to be exposed, so that human region in the image of visible light image sensor 820 collection Brightness and human region relative to other regions to relatively higher, subsequent central processing unit (CPU) is by based on visible ray figure Image as sensor 820 collection carries out Face datection by executing corresponding program code in storage device 830.
Exemplarily, image detecting apparatus 800 according to embodiments of the present invention can be implemented with infrared image sensing Device, visible light image sensor, the unit of memorizer, communication interface/unit and processor or system.
Image detecting apparatus 800 according to embodiments of the present invention can be deployed in Face datection identifying system, for example, Security protection application, can be deployed in gate control system or preventing road monitoring system；In financial application field, can be with bank, exchange Etc. identity authorization system in.
Additionally, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage Instruction, when described program instruction is run by computer or processor for execute the embodiment of the present invention method for detecting human face, Contour extraction method, the corresponding steps of local exposure method, and for realizing Face datection dress according to embodiments of the present invention Put, the corresponding module/submodule of profile extraction module, partial exposure control module.Described storage medium for example can include intelligence Can the storage card of phone, the memory unit of panel computer, the hard disk of personal computer, read only memory (ROM), erasable compile Journey read only memory (EPROM), portable compact disc read only memory (CD-ROM), USB storage or above-mentioned storage medium Combination in any.Described computer-readable recording medium can be any group of one or more computer-readable recording mediums Close, such as one computer-readable recording medium comprises the computer-readable program code generating for target object information, Another computer-readable recording medium comprises the computer-readable program code for target object information identification.
In one embodiment, described computer program instructions can be realized when being run by computer according to the present invention in fact Apply each functional module in the method for detecting human face device of example, and/or people according to embodiments of the present invention can be executed Face detecting method.
In one embodiment, described computer program instructions execute following steps when being run by computer：By red Outer imageing sensor obtains the infrared image of destination object；The human body contour outline of described destination object is extracted from described infrared image Coordinates regional；Visible light image sensor is controlled to carry out partial exposure to described human body contour outline based on described coordinates regional, with The light exposure at least a portion region of inclusion facial zone making described human body contour outline is than other in image-capture field The light exposure in region is big；The visible images of the described destination object through partial exposure for collection while described partial exposure； Face datection is carried out to described visible images.
Each module in human face detection device according to embodiments of the present invention can be by people according to embodiments of the present invention The processor of the electronic equipment of face detection runs the computer program instructions storing in memory to realize, or can be in root According to the computer instruction storing in the computer-readable recording medium of the computer program of the embodiment of the present invention by computer Realize during operation.
Method for detecting human face according to embodiments of the present invention and device, image detecting apparatus and storage medium, by infrared Image zooming-out human body contour outline, and control visible light image sensor to carry out partial exposure to human body contour outline region, enhance Visible light image sensor collection image in described human body contour outline inclusion facial zone at least a portion region bright Degree, and the contrast in this region and other regions, so when the image that visible light image sensor is gathered carries out Face datection With during identification, accuracy and performance will be substantially improved, efficiently solve dark environment human face detection hydraulic performance decline and The easily problem of missing inspection.
Although here by reference to Description of Drawings example embodiment it should be understood that above-mentioned example embodiment is merely exemplary , and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein And modification, it is made without departing from the scope of the present invention and spirit.All such changes and modifications are intended to be included in claims Within required the scope of the present invention.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually To be executed with hardware or software mode, the application-specific depending on technical scheme and design constraint.Professional and technical personnel Each specific application can be used different methods to realize described function, but this realization is it is not considered that exceed The scope of the present invention.
It should be understood that disclosed equipment and method in several embodiments provided herein, can be passed through it Its mode is realized.For example, apparatus embodiments described above are only schematically, for example, the division of described unit, and only It is only a kind of division of logic function, actual can have other dividing mode when realizing, and for example multiple units or assembly can be tied Close or be desirably integrated into another equipment, or some features can be ignored, or do not execute.
In description mentioned herein, illustrate a large amount of details.It is to be appreciated, however, that the enforcement of the present invention Example can be put into practice in the case of not having these details.In some instances, known method, structure are not been shown in detail And technology, so as not to obscure the understanding of this description.
Similarly it will be appreciated that in order to simplify the present invention and help understand one or more of each inventive aspect, In description to the exemplary embodiment of the present invention, each feature of the present invention be sometimes grouped together into single embodiment, figure, Or in descriptions thereof.However, not should by this present invention method be construed to reflect following intention：I.e. claimed Application claims than the feature being expressly recited in each claim more features.More precisely, as accordingly As claims are reflected, its inventive point is can be with all features of embodiment single disclosed in certain Feature is solving corresponding technical problem.Therefore, it then follows claims of specific embodiment are thus expressly incorporated in this tool Body embodiment, wherein each claim itself is as the separate embodiments of the present invention.
It will be understood to those skilled in the art that in addition to mutually exclusive between feature, any combinations pair can be adopted All features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed any method Or all processes of equipment or unit are combined.Unless expressly stated otherwise, (including adjoint right will for this specification Ask, make a summary and accompanying drawing) disclosed in each feature can be replaced by the alternative features providing identical, equivalent or similar purpose.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments In included some features rather than further feature, but the combination of the feature of different embodiment means to be in the present invention's Within the scope of and form different embodiments.For example, in detail in the claims, embodiment required for protection one of arbitrarily Can in any combination mode using.
The all parts embodiment of the present invention can be realized with hardware, or to run on one or more processor Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that can use in practice Microprocessor or digital signal processor (DSP) are realizing some moulds in article analytical equipment according to embodiments of the present invention The some or all functions of block.The present invention is also implemented as a part for executing method as described herein or complete The program of device (for example, computer program and computer program) in portion.Such program realizing the present invention can store On a computer-readable medium, or can have the form of one or more signal.Such signal can be from the Internet Download on website and obtain, or provide on carrier signal, or provided with any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference markss between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such Element.The present invention can come real by means of the hardware including some different elements and by means of properly programmed computer Existing.If in the unit claim listing equipment for drying, several in these devices can be by same hardware branch To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame Claim.
The above, the only specific embodiment of the present invention or the explanation to specific embodiment, the protection of the present invention Scope is not limited thereto, any those familiar with the art the invention discloses technical scope in, can be easily Expect change or replacement, all should be included within the scope of the present invention.Protection scope of the present invention should be with claim Protection domain is defined.

Claims (10)

1. a kind of method for detecting human face is it is characterised in that include：
Obtain the infrared image of destination object by infrared image sensor；
The coordinates regional of the human body contour outline of described destination object is extracted from described infrared image；
Visible light image sensor is controlled to carry out partial exposure to described human body contour outline based on described coordinates regional, so that described The light exposure at least a portion region of inclusion facial zone of human body contour outline is than the exposure in other regions in image-capture field Light quantity is big；
The visible images of the described destination object through partial exposure for collection while described partial exposure；
Face datection is carried out to described visible images.
2. method for detecting human face according to claim 1 it is characterised in that described extract from described infrared image described The coordinates regional of the human body contour outline of destination object includes：
Coordinate figure in described infrared image for the heat radiation point that acquisition infrared image sensor senses；
The corresponding pixel value of coordinate of heat radiation point described in described infrared image is labeled as 1 and the region being 1 by pixel value As the human body contour outline in described infrared image；
Extract the coordinates regional of facial contour.
3. method for detecting human face according to claim 2 it is characterised in that described based on described coordinates regional control visible Optical image sensor carries out partial exposure to described human body contour outline and includes：
Based on coordinate transform amount, described coordinates regional is transformed to the coordinates regional of described visible light image sensor；
Coordinates regional according to described visible light image sensor controls described visible light image sensor to carry out partial exposure.
4. method for detecting human face according to claim 3 is it is characterised in that methods described is also included based on goal-selling Infrared image and visible images obtain coordinate transform amount, and the step of wherein said acquisition coordinate transform amount includes：
Place a blank sheet of paper in the angular field of view of described visible light image sensor and infrared image sensor, and in blank sheet of paper Four stains of four corner mark；
The one secondary image including described blank sheet of paper is obtained respectively by described visible light image sensor and infrared image sensor；
The image of the described blank sheet of paper of inclusion that described visible light image sensor and infrared image sensor obtain is found out described Stain and its coordinate；
Described coordinate transform amount is obtained by the coordinate of stain described in two width images,
Wherein, apply thermal source at the back side of each described stain.
5. the method for detecting human face according to any one in claim 1-4 it is characterised in that described based on described seat Mark Region control visible light image sensor carries out partial exposure to described human body contour outline and includes：
The photosensitive region of described visible light image sensor is divided into multiple blocks；
For the different exposure weighted value of each block setting, at least a portion of the inclusion facial zone of wherein said human body contour outline The weighted value of the block corresponding to region is higher than the exposure weighted value of other blocks；
Weighted value according to each block controls described visible light image sensor to be exposed and gather exposed described mesh The visible images of mark object.
6. a kind of human face detection device is it is characterised in that include：
Infrared image acquisition module, described infrared image acquisition module is used for obtaining the infrared image of destination object；
Profile extraction module, described profile extraction module is used for extracting the human body wheel of described destination object from described infrared image Wide coordinates regional；
Partial exposure module, described partial exposure module is used for controlling visible light image sensor to institute based on described coordinates regional State human body contour outline carry out partial exposure so that described human body contour outline inclusion facial zone at least a portion region exposure Amount is bigger than the light exposure in other regions in image-capture field；
Visible images acquisition module, described visible images acquisition module is used for gathering through office while described partial exposure The visible images of the described destination object of portion's exposure；
Face detection module, described face detection module is used for carrying out Face datection to described visible images.
7. human face detection device according to claim 6 is it is characterised in that described profile extraction module includes：
Coordinate acquisition submodule, described coordinate acquisition submodule exists for obtaining the heat radiation point that infrared image sensor senses Coordinate figure in described infrared image；
Element marking submodule, described element marking submodule is used for the coordinate pair of heat radiation point described in described infrared image The pixel value answered be labeled as 1 and pixel value is 1 region as the human body contour outline in described infrared image；
Coordinate extracting sub-module, described coordinate extracting sub-module is used for extracting the coordinates regional of described facial contour.
8. human face detection device according to claim 6 is it is characterised in that described partial exposure module includes：
Region division submodule, described region division submodule is used for dividing the photosensitive region of described visible light image sensor For multiple blocks；
Weight arranges submodule, and described weight arranges submodule and is used for arranging different exposure weighted values for each block, wherein The weighted value of the block corresponding at least a portion region of inclusion facial zone of described human body contour outline is than the exposure of other blocks Light weighted value is high；
Spectrum assignment submodule, the weighted value that described spectrum assignment submodule is used for according to each block controls described visible ray figure As sensor is exposed.
9. human face detection device according to claim 8 is it is characterised in that described partial exposure module also includes coordinate change Change submodule, described coordinate transform submodule is used for, based on coordinate transform amount, described coordinates regional is transformed to described visible ray figure Coordinates regional as sensor.
10. the human face detection device according to any one of claim 6 to 9 it is characterised in that described profile extraction module, Described partial exposure module and described face detection module are realized by same processor.
CN201610972629.1A 2016-11-03 2016-11-03 Face detection method and device Active CN106446873B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610972629.1A CN106446873B (en) 2016-11-03 2016-11-03 Face detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610972629.1A CN106446873B (en) 2016-11-03 2016-11-03 Face detection method and device

Publications (2)

Publication Number Publication Date
CN106446873A true CN106446873A (en) 2017-02-22
CN106446873B CN106446873B (en) 2021-01-26

Family

ID=58179721

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610972629.1A Active CN106446873B (en) 2016-11-03 2016-11-03 Face detection method and device

Country Status (1)

Country Link
CN (1) CN106446873B (en)

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106851124A (en) * 2017-03-09 2017-06-13 广东欧珀移动通信有限公司 Image processing method, processing unit and electronic installation based on the depth of field
CN107155063A (en) * 2017-06-19 2017-09-12 深圳市泰衡诺科技有限公司上海分公司 Night scene filming control method, system and equipment
CN107197170A (en) * 2017-07-14 2017-09-22 维沃移动通信有限公司 A kind of exposal control method and mobile terminal
CN107277481A (en) * 2017-07-14 2017-10-20 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN107317971A (en) * 2017-07-27 2017-11-03 广东欧珀移动通信有限公司 Image defogging processing method, device, storage medium and mobile terminal
CN107395965A (en) * 2017-07-14 2017-11-24 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN107483811A (en) * 2017-07-28 2017-12-15 广东欧珀移动通信有限公司 Imaging method and electronic installation
CN107492074A (en) * 2017-07-21 2017-12-19 触景无限科技（北京）有限公司 Image acquisition and processing method, device and terminal device
CN107679481A (en) * 2017-09-27 2018-02-09 广东欧珀移动通信有限公司 Solve lock control method and Related product
CN107734129A (en) * 2017-09-27 2018-02-23 广东欧珀移动通信有限公司 Solve lock control method and Related product
CN108289170A (en) * 2018-01-12 2018-07-17 深圳奥比中光科技有限公司 The camera arrangement and method of metering region can be detected
CN109427264A (en) * 2017-08-30 2019-03-05 深圳市奥拓电子股份有限公司 A kind of light control plate and LED display
CN109492531A (en) * 2018-10-10 2019-03-19 深圳前海达闼云端智能科技有限公司 Face image key point extraction method and device, storage medium and electronic equipment
CN109508588A (en) * 2017-09-15 2019-03-22 杭州海康威视数字技术股份有限公司 Monitoring method, device, system, electronic equipment and computer readable storage medium
CN109614910A (en) * 2018-12-04 2019-04-12 青岛小鸟看看科技有限公司 A kind of face identification method and device
CN110060272A (en) * 2018-01-18 2019-07-26 杭州海康威视数字技术股份有限公司 Determination method, apparatus, electronic equipment and the storage medium of human face region
CN110115025A (en) * 2017-03-09 2019-08-09 Oppo广东移动通信有限公司 Control method, control device and electronic device based on depth
CN110211024A (en) * 2019-03-14 2019-09-06 厦门启尚科技有限公司 A kind of method that image intelligent moves back bottom
CN110572580A (en) * 2019-10-10 2019-12-13 珠海格力电器股份有限公司 photographing method suitable for mobile terminal and mobile terminal
CN110826366A (en) * 2018-08-10 2020-02-21 北京魔门塔科技有限公司 Face image acquisition system for data analysis at night
CN111161351A (en) * 2019-12-18 2020-05-15 万翼科技有限公司 Target component coordinate obtaining method and system
CN111839519A (en) * 2020-05-26 2020-10-30 合肥工业大学 Non-contact respiratory frequency monitoring method and system
CN111984347A (en) * 2019-05-21 2020-11-24 北京小米移动软件有限公司 Interaction processing method, device, equipment and storage medium
CN112200002A (en) * 2020-09-11 2021-01-08 深圳市优必选科技股份有限公司 Body temperature measuring method and device, terminal equipment and storage medium
CN112571613A (en) * 2020-12-04 2021-03-30 淄博昊祥模具科技有限公司 Automatic grouting production line for hand mold manufacturing and hand mold manufacturing method
CN112752031A (en) * 2020-07-31 2021-05-04 腾讯科技（深圳）有限公司 Image acquisition detection method and device, electronic equipment and storage medium
CN112911146A (en) * 2021-01-27 2021-06-04 杭州寰宇微视科技有限公司 Intelligent dimming method based on human face
CN113542616A (en) * 2021-07-09 2021-10-22 深圳英飞拓智能技术有限公司 Brightness adjusting method and device for face snapshot, computer equipment and storage medium
CN113545028A (en) * 2019-09-25 2021-10-22 谷歌有限责任公司 Gain control for face authentication
CN114257712A (en) * 2020-09-25 2022-03-29 华为技术有限公司 Method and device for controlling light supplementing time of camera module
CN115294676A (en) * 2022-07-08 2022-11-04 重庆甲智甲创科技有限公司 Face recognition unlocking method and face recognition unlocking device
EP4055443A4 (en) * 2019-12-13 2023-01-11 Sony Group Corporation Extraction of subject from background
CN115761638A (en) * 2022-11-17 2023-03-07 广州极数科技有限公司 Online real-time intelligent analysis method based on image data and terminal equipment
US12046072B2 (en) 2019-10-10 2024-07-23 Google Llc Camera synchronization and image tagging for face authentication
US12096001B2 (en) 2019-06-25 2024-09-17 Zhejiang Dahua Technology Co., Ltd. Systems and methods for video decoding

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1744672A (en) * 2004-08-31 2006-03-08 佳能株式会社 Image capture apparatus and control method therefor
CN102663349A (en) * 2012-03-22 2012-09-12 北京水晶石数字科技股份有限公司 Intelligent interaction method based on face identification and apparatus thereof
CN102800059A (en) * 2012-07-05 2012-11-28 清华大学 Image visibility enhancing method with assistance of near-infrared image
CN103413395A (en) * 2013-08-15 2013-11-27 北京声迅电子股份有限公司 Intelligent smoke detecting and early warning method and device
CN103702015A (en) * 2013-12-20 2014-04-02 华南理工大学 Exposure control method for human face image acquisition system under near-infrared condition
CN103870814A (en) * 2014-03-18 2014-06-18 上海理工大学 Non-contact real-time eye movement identification method based on intelligent camera
CN105096267A (en) * 2015-07-02 2015-11-25 广东欧珀移动通信有限公司 Method and device for adjusting brightness of eye portion based on shooting identification
CN105407276A (en) * 2015-11-03 2016-03-16 北京旷视科技有限公司 Photographing method and equipment
CN105608415A (en) * 2015-12-14 2016-05-25 联想(北京)有限公司 Information processing method and electronic apparatus
CN105830428A (en) * 2013-12-19 2016-08-03 株式会社理光 Object detection apparatus, moving body device control system and program thereof

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1744672A (en) * 2004-08-31 2006-03-08 佳能株式会社 Image capture apparatus and control method therefor
CN102663349A (en) * 2012-03-22 2012-09-12 北京水晶石数字科技股份有限公司 Intelligent interaction method based on face identification and apparatus thereof
CN102800059A (en) * 2012-07-05 2012-11-28 清华大学 Image visibility enhancing method with assistance of near-infrared image
CN103413395A (en) * 2013-08-15 2013-11-27 北京声迅电子股份有限公司 Intelligent smoke detecting and early warning method and device
CN105830428A (en) * 2013-12-19 2016-08-03 株式会社理光 Object detection apparatus, moving body device control system and program thereof
CN103702015A (en) * 2013-12-20 2014-04-02 华南理工大学 Exposure control method for human face image acquisition system under near-infrared condition
CN103870814A (en) * 2014-03-18 2014-06-18 上海理工大学 Non-contact real-time eye movement identification method based on intelligent camera
CN105096267A (en) * 2015-07-02 2015-11-25 广东欧珀移动通信有限公司 Method and device for adjusting brightness of eye portion based on shooting identification
CN105407276A (en) * 2015-11-03 2016-03-16 北京旷视科技有限公司 Photographing method and equipment
CN105608415A (en) * 2015-12-14 2016-05-25 联想(北京)有限公司 Information processing method and electronic apparatus

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
谢志华等: "基于局部二元模式的快速红外人脸识别系统", 《红外与激光工程》 *

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110115025B (en) * 2017-03-09 2022-05-20 Oppo广东移动通信有限公司 Depth-based control method, control device and electronic device
CN106851124A (en) * 2017-03-09 2017-06-13 广东欧珀移动通信有限公司 Image processing method, processing unit and electronic installation based on the depth of field
CN106851124B (en) * 2017-03-09 2021-03-02 Oppo广东移动通信有限公司 Image processing method and device based on depth of field and electronic device
US11145086B2 (en) 2017-03-09 2021-10-12 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Electronic device, and method and apparatus for controlling the same
CN110115025A (en) * 2017-03-09 2019-08-09 Oppo广东移动通信有限公司 Control method, control device and electronic device based on depth
CN107155063A (en) * 2017-06-19 2017-09-12 深圳市泰衡诺科技有限公司上海分公司 Night scene filming control method, system and equipment
CN107277481A (en) * 2017-07-14 2017-10-20 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN107395965A (en) * 2017-07-14 2017-11-24 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN107395965B (en) * 2017-07-14 2019-11-29 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN107197170A (en) * 2017-07-14 2017-09-22 维沃移动通信有限公司 A kind of exposal control method and mobile terminal
CN107492074A (en) * 2017-07-21 2017-12-19 触景无限科技（北京）有限公司 Image acquisition and processing method, device and terminal device
CN107317971A (en) * 2017-07-27 2017-11-03 广东欧珀移动通信有限公司 Image defogging processing method, device, storage medium and mobile terminal
CN107483811A (en) * 2017-07-28 2017-12-15 广东欧珀移动通信有限公司 Imaging method and electronic installation
CN109427264A (en) * 2017-08-30 2019-03-05 深圳市奥拓电子股份有限公司 A kind of light control plate and LED display
US11275952B2 (en) 2017-09-15 2022-03-15 Hangzhou Hikvision Digital Technology Co., Ltd. Monitoring method, apparatus and system, electronic device, and computer readable storage medium
CN109508588A (en) * 2017-09-15 2019-03-22 杭州海康威视数字技术股份有限公司 Monitoring method, device, system, electronic equipment and computer readable storage medium
CN107734129A (en) * 2017-09-27 2018-02-23 广东欧珀移动通信有限公司 Solve lock control method and Related product
CN107679481A (en) * 2017-09-27 2018-02-09 广东欧珀移动通信有限公司 Solve lock control method and Related product
CN108289170A (en) * 2018-01-12 2018-07-17 深圳奥比中光科技有限公司 The camera arrangement and method of metering region can be detected
CN108289170B (en) * 2018-01-12 2020-02-14 深圳奥比中光科技有限公司 Photographing apparatus, method and computer readable medium capable of detecting measurement area
CN110060272A (en) * 2018-01-18 2019-07-26 杭州海康威视数字技术股份有限公司 Determination method, apparatus, electronic equipment and the storage medium of human face region
CN110826366A (en) * 2018-08-10 2020-02-21 北京魔门塔科技有限公司 Face image acquisition system for data analysis at night
CN109492531A (en) * 2018-10-10 2019-03-19 深圳前海达闼云端智能科技有限公司 Face image key point extraction method and device, storage medium and electronic equipment
CN109614910A (en) * 2018-12-04 2019-04-12 青岛小鸟看看科技有限公司 A kind of face identification method and device
CN110211024A (en) * 2019-03-14 2019-09-06 厦门启尚科技有限公司 A kind of method that image intelligent moves back bottom
CN111984347B (en) * 2019-05-21 2024-09-17 北京小米移动软件有限公司 Interactive processing method, device, equipment and storage medium
CN111984347A (en) * 2019-05-21 2020-11-24 北京小米移动软件有限公司 Interaction processing method, device, equipment and storage medium
US12096001B2 (en) 2019-06-25 2024-09-17 Zhejiang Dahua Technology Co., Ltd. Systems and methods for video decoding
US11687635B2 (en) 2019-09-25 2023-06-27 Google PLLC Automatic exposure and gain control for face authentication
CN113545028A (en) * 2019-09-25 2021-10-22 谷歌有限责任公司 Gain control for face authentication
CN110572580B (en) * 2019-10-10 2020-11-03 珠海格力电器股份有限公司 Photographing method suitable for mobile terminal and mobile terminal
CN110572580A (en) * 2019-10-10 2019-12-13 珠海格力电器股份有限公司 photographing method suitable for mobile terminal and mobile terminal
US12046072B2 (en) 2019-10-10 2024-07-23 Google Llc Camera synchronization and image tagging for face authentication
EP4055443A4 (en) * 2019-12-13 2023-01-11 Sony Group Corporation Extraction of subject from background
US11765309B2 (en) 2019-12-13 2023-09-19 Sony Group Corporation Video capturing subject using IR light
CN111161351A (en) * 2019-12-18 2020-05-15 万翼科技有限公司 Target component coordinate obtaining method and system
CN111839519B (en) * 2020-05-26 2021-05-18 合肥工业大学 Non-contact respiratory frequency monitoring method and system
CN111839519A (en) * 2020-05-26 2020-10-30 合肥工业大学 Non-contact respiratory frequency monitoring method and system
CN112752031B (en) * 2020-07-31 2024-02-06 腾讯科技（深圳）有限公司 Image acquisition and detection method and device, electronic equipment and storage medium
CN112752031A (en) * 2020-07-31 2021-05-04 腾讯科技（深圳）有限公司 Image acquisition detection method and device, electronic equipment and storage medium
CN112200002A (en) * 2020-09-11 2021-01-08 深圳市优必选科技股份有限公司 Body temperature measuring method and device, terminal equipment and storage medium
CN112200002B (en) * 2020-09-11 2023-12-01 深圳市优必选科技股份有限公司 Body temperature measuring method, device, terminal equipment and storage medium
CN114257712A (en) * 2020-09-25 2022-03-29 华为技术有限公司 Method and device for controlling light supplementing time of camera module
CN112571613B (en) * 2020-12-04 2022-04-26 淄博昊祥模具科技有限公司 Automatic grouting production line for hand mold manufacturing and hand mold manufacturing method
CN112571613A (en) * 2020-12-04 2021-03-30 淄博昊祥模具科技有限公司 Automatic grouting production line for hand mold manufacturing and hand mold manufacturing method
CN112911146A (en) * 2021-01-27 2021-06-04 杭州寰宇微视科技有限公司 Intelligent dimming method based on human face
CN113542616B (en) * 2021-07-09 2022-08-09 深圳英飞拓智能技术有限公司 Brightness adjusting method and device for face snapshot, computer equipment and storage medium
CN113542616A (en) * 2021-07-09 2021-10-22 深圳英飞拓智能技术有限公司 Brightness adjusting method and device for face snapshot, computer equipment and storage medium
CN115294676A (en) * 2022-07-08 2022-11-04 重庆甲智甲创科技有限公司 Face recognition unlocking method and face recognition unlocking device
CN115294676B (en) * 2022-07-08 2024-03-19 重庆甲智甲创科技有限公司 Face recognition unlocking method and face recognition unlocking device
CN115761638A (en) * 2022-11-17 2023-03-07 广州极数科技有限公司 Online real-time intelligent analysis method based on image data and terminal equipment

Also Published As

Publication number Publication date
CN106446873B (en) 2021-01-26

Similar Documents

Publication Publication Date Title
CN106446873A (en) Face detection method and device
CN109583285B (en) Object recognition method
CN109271921B (en) Intelligent identification method and system for multispectral imaging
CN107358146B (en) Method for processing video frequency, device and storage medium
CN106650665A (en) Human face tracing method and device
CN103577801B (en) Quality metrics method and system for biometric authentication
US8761446B1 (en) Object detection with false positive filtering
Steiner et al. Design of an active multispectral SWIR camera system for skin detection and face verification
CN109816745B (en) Human body thermodynamic diagram display method and related products
CN111462128B (en) Pixel-level image segmentation system and method based on multi-mode spectrum image
CN106682620A (en) Human face image acquisition method and device
TW202026948A (en) Methods and devices for biological testing and storage medium thereof
CN106778518A (en) A kind of human face in-vivo detection method and device
CN106203305A (en) Human face in-vivo detection method and device
CN105631439A (en) Human face image collection method and device
CN104794458A (en) Fuzzy video person identifying method
CN103383723A (en) Method and system for spoof detection for biometric authentication
CN105022999A (en) Man code company real-time acquisition system
CN206322194U (en) A kind of anti-fraud face identification system based on 3-D scanning
CN107169458A (en) Data processing method, device and storage medium
EP3161727A2 (en) Photo tagging system and method
CN115170792B (en) Infrared image processing method, device and equipment and storage medium
CN107622497A (en) Image cropping method, apparatus, computer-readable recording medium and computer equipment
CN110210292A (en) A kind of target identification method based on deep learning
CN113222973A (en) Image processing method and device, processor, electronic device and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313

Applicant after: MEGVII INC.

Applicant after: Beijing maigewei Technology Co., Ltd.

Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313

Applicant before: MEGVII INC.

Applicant before: Beijing aperture Science and Technology Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant