CN110210457A - Method for detecting human face, device, equipment and computer readable storage medium - Google Patents
Method for detecting human face, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110210457A CN110210457A CN201910530857.7A CN201910530857A CN110210457A CN 110210457 A CN110210457 A CN 110210457A CN 201910530857 A CN201910530857 A CN 201910530857A CN 110210457 A CN110210457 A CN 110210457A
- Authority
- CN
- China
- Prior art keywords
- face
- frame
- region
- human face
- obtains
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of method for detecting human face, device, equipment and computer readable storage mediums, which comprises obtains the human face region of image by full convolutional neural networks according to the image received；Selective search is carried out to human face region, obtains deep layer face frame feature；Binary conversion treatment is carried out to deep layer face frame feature, the face candidate region of face making profile is oriented from all human face regions；According to face candidate region, by the image pyramid model constructed in advance, several various sizes of face candidate frames are obtained；Face datection is obtained as a result, can effectively avoid the missing inspection of small face by the above method, the position of face frame is calculated in such a way that cascade neural network is successively fine, improves the accuracy of Face datection by joining grade neural network according to face candidate frame.
Description
Technical field
The present invention relates to Computer Image Processing fields more particularly to a kind of face method, apparatus, equipment and computer can
Read storage medium.
Background technique
With the development of computer technology especially mode identification technology, Face datection is appeared in as a technique direction
The visual field of people.Human face detection tech can be used as the basic work of more application items in image procossing and video analysis field
Make, such as recognition of face, facial image retrieval and driver fatigue state detection etc..But when there are rulers in a sub-picture
When very little inconsistent size face, since the face frame of traditional further feature in original image mapping face confines position, there are deviations, lead
Cause the situation for small Face datection inaccuracy occur.
Summary of the invention
It can in view of the above-mentioned problems, the purpose of the present invention is to provide a kind of method for detecting human face, device, equipment and computers
Storage medium is read, an existing deviation when original image mapping face is confined can be effectively reduced, the missing inspection of small face is avoided, improve
The accuracy of Face datection.
In a first aspect, the embodiment of the invention provides a kind of method for detecting human face, comprising the following steps:
The human face region of described image is obtained by full convolutional neural networks according to the image received；
Selective search is carried out to the human face region, obtains deep layer face frame feature；
Binary conversion treatment is carried out to the deep layer face frame feature, face making profile is oriented from all human face regions
Face candidate region；
According to the face candidate region, by the image pyramid model constructed in advance, several different sizes are obtained
Face candidate frame；
Face datection result is obtained by joining grade neural network according to the face candidate frame.
Preferably, the image that the basis receives obtains the face area of described image by full convolutional neural networks
Domain specifically includes:
The image received is input to the full convolutional neural networks, obtains several temperature figures；
Up-sampling and deconvolution processing are carried out to the temperature figure, obtain fused temperature figure；
According to fused temperature figure, human face region is extracted.
Preferably, described that binary conversion treatment is carried out to the deep layer face frame feature, it is oriented from all human face regions
Frame selects the face candidate region of complete facial contour, specifically includes:
Binary conversion treatment is carried out to the deep layer face frame feature；
Face judgement is carried out to the deep layer face frame feature after binary conversion treatment according to preset threshold value, is rejected non-face
Face candidate region obtains the face candidate region that frame selects complete facial contour.
Preferably, described that Face datection is obtained as a result, specific by joining grade neural network according to the face candidate frame
Include:
All face candidate frames are zoomed into the first pre-set dimension, and pass through the first layer convolution of the grade neural network
Neural network carries out frame recurrence to the face candidate frame of the first pre-set dimension, obtains the first frame regression result；
All face candidate frames are zoomed into the second pre-set dimension, and pass through the second layer convolution of the grade neural network
Neural network carries out frame recurrence to the face candidate frame of the second pre-set dimension and the first frame regression result, obtains second
Frame regression result；
All face candidate frames are zoomed into third pre-set dimension, and pass through the third layer convolution of the grade neural network
The face candidate frame of third pre-set dimension, the first frame regression result and second frame are returned in neural network and tied
Fruit carries out frame recurrence, obtains third frame regression result；
According to the first frame regression result, the second frame regression result and third frame regression result, people is obtained
Face testing result.
Preferably, described to be returned according to the first frame regression result, the second frame regression result and third frame
As a result, obtaining Face datection as a result, specifically including:
The first frame regression result, the second frame regression result and third frame regression result are weighted and averaged
Processing, obtains the Face datection result.
Preferably, first pre-set dimension is 12 × 12, and the first layer convolutional neural networks are 12 dimension convolutional Neurals
Network；Second pre-set dimension is 24 × 24, and the second layer convolutional neural networks are 24 dimension convolutional neural networks；Described
Two pre-set dimensions are 48 × 48, and the third layer convolutional neural networks are 48 dimension convolutional neural networks.
Second aspect, the embodiment of the invention provides a kind of human face detection devices, comprising:
Human face region obtains module, for obtaining described image by full convolutional neural networks according to the image received
Human face region；
Face search module obtains deep layer face frame feature for carrying out selective search to the human face region；
Binary processing module, for carrying out binary conversion treatment to the deep layer face frame feature, from all human face regions
In orient the face candidate region of face making profile；
Face candidate frame obtains module, for passing through the image pyramid constructed in advance according to the face candidate region
Model obtains several various sizes of face candidate frames；
Face prediction module, for obtaining Face datection knot by joining grade neural network according to the face candidate frame
Fruit.
Preferably, the human face region acquisition module includes:
Temperature figure generation unit obtains several for the image received to be input to the full convolutional neural networks
Temperature figure；
Temperature figure integrated unit obtains fused heat for carrying out up-sampling and deconvolution processing to the temperature figure
Degree figure；
Human face region extraction unit, for extracting human face region according to fused temperature figure.
The third aspect, the embodiment of the invention provides a kind of human-face detection equipments, including processor, memory and storage
In the memory and it is configured as the computer program executed by the processor, the processor executes the computer
The method for detecting human face as described in any one of first aspect is realized when program.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Medium includes the computer program of storage, wherein controls the computer-readable storage medium in computer program operation
Equipment executes the method for detecting human face as described in any one of first aspect where matter.
Above embodiments have the following beneficial effects:
Position sensing region detection is carried out to the image received by full convolutional neural networks, quickly marks the people of image
Face region；Selective search is carried out to the human face region, obtains deep layer face frame feature；To the deep layer face frame feature into
Row binary conversion treatment orients the face candidate region of face making profile from all human face regions, a large amount of inhuman to reject
Face frame or the human face region for being unsatisfactory for condition, improve the speed of COMPUTER DETECTION face；According to the face candidate region,
By the image pyramid models constructed in advance, several various sizes of face candidate frames are obtained, the missing inspection of small face is avoided,
Effectively solve the problems, such as that small face exists and leads to small Face datection inaccuracy；According to the face candidate frame, pass through connection grade mind
Through network, Face datection is obtained as a result, calculating the position of face frame in such a way that cascade neural network is successively fine, improves people
The accuracy of face detection.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, attached drawing needed in embodiment will be made below
Simply introduce, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram for the method for detecting human face that first embodiment of the invention provides；
Fig. 2 is the structural schematic diagram for the human face detection device that second embodiment of the invention provides；
Fig. 3 is the structural schematic diagram for the human-face detection equipment that third embodiment of the invention provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Please refer to Fig. 1, first embodiment of the invention provides a kind of method for detecting human face, can by human-face detection equipment Lai
It executes, and the following steps are included:
S11: the human face region of described image is obtained by full convolutional neural networks according to the image received.
In embodiments of the present invention, the human-face detection equipment can for computer, mobile phone, tablet computer, laptop or
Person's server etc. calculates equipment, and the method for detecting human face can be used as that one of functional module is integrated to be set with the Face datection
It is standby upper, it is executed by the human-face detection equipment.
Full convolutional neural networks (FCN, Fully Convolutional Networks for Semantic
Segmentation), output and input is all an image, but exporting is a temperature figure (corresponding object
Probability, temperature figure is exactly the probability of corresponding face in embodiments of the present invention), and input layer is not by the limit for inputting size
System, and can be realized scene mark end to end, it does not need to be mapped, so that the space of input picture retains well
Come.
In embodiments of the present invention, the image received is input to full convolutional neural networks, according to the temperature figure of output,
The human face region in image is marked, initial prospect frame is formed, realizes the quick mark of human face region, solves conventional face's identification
The problem of original image mapping face confines the deviation of position.
S12: selective search is carried out to the human face region, obtains deep layer face frame feature.
S13: binary conversion treatment is carried out to the deep layer face frame feature, orients face making from all human face regions
The face candidate region of profile.
In embodiments of the present invention, by carrying out selective search (selective search) to the human face region,
I.e. face candidate region is traversed inside specific region, the very limited deep layer face frame feature of generation quantity, right later
Deep layer face frame feature carries out image binaryzation processing, quickly judges face by the feature that human face region is mapped to deep layer,
It rejects a large amount of non-face frames or is unsatisfactory for the face frame of condition, obtain the face candidate region for highlighting facial contour, greatly mention
The speed of COMPUTER DETECTION face is risen.
S14: according to the face candidate region, by the image pyramid model constructed in advance, several differences are obtained
The face candidate frame of size.
In embodiments of the present invention, the face candidate frame that different scale is generated using image pyramid, avoids small face
Missing inspection.
S15: Face datection result is obtained by joining grade neural network according to the face candidate frame.
Cascade neural network is a kind of feature extraction from shallow to deep " emperorship ", can be crossed by different big in interception original image
Small region carries out feature extraction, and the detection of face frame is realized finally by the characteristic spectrum of generation, passes through comprehensive different stage
Neural network the probability of face frame is determined, the positioning of the final detection for realizing object and face frame.
In embodiments of the present invention, the face candidate frame that each is remained is rolled up using cascade neural network
Product successively refines the positioning of face frame, improves the accuracy of Face datection by the way of from thick to thin.
In an alternative embodiment, S11: according to the image received, by full convolutional neural networks, described in acquisition
The human face region of image, specifically includes:
The image received is input to the full convolutional neural networks, obtains several temperature figures；
Up-sampling and deconvolution processing are carried out to the temperature figure, obtain fused temperature figure；
According to fused temperature figure, human face region is extracted.
It should be noted that the color of temperature figure and category associations to be dealt with, if the classification in picture is more similar,
The color of position where so is closer to red, and the spatial information of input picture will be retained well.Heat
Degree schemes the probability of corresponding face, therefore, passes through up-sampling and deconvolution to the temperature figure of full convolutional neural networks deep layer output
Mode realizes larger sized temperature figure, and the temperature figure of deep layer is merged with the temperature figure of shallow-layer, by repeatedly this
Operation obtains the temperature figure of size consistent with original image, so that the space of temperature figure is preferably expanded, it is as a result more fine；
Such as 4 × 4 original image by up-sampling (i.e. intermediate insert space (7 × 7)), then image is become larger using deconvolution (3 × 3)
(becoming 5 × 5 from 4 × 4), realizes the expansion of image, as a result more fine.
In an alternative embodiment, S13: binary conversion treatment is carried out to the deep layer face frame feature, from owner
The face candidate region that frame selects complete facial contour is oriented in face region, is specifically included:
Binary conversion treatment is carried out to the deep layer face frame feature；
Face judgement is carried out to the deep layer face frame feature after binary conversion treatment according to preset threshold value, is rejected non-face
Face candidate region obtains the face candidate region that frame selects complete facial contour.
In embodiments of the present invention by obtain human face region deep layer face frame characteristic value (, and this pass through image two
Value processing, the quantity of frame can be greatly reduced, the frame for not highlighting facial contour is weeded out by image binaryzation.
In an alternative embodiment, face S15: is obtained by joining grade neural network according to the face candidate frame
Testing result specifically includes:
All face candidate frames are zoomed into the first pre-set dimension, and pass through the first layer convolution of the grade neural network
Neural network carries out frame recurrence to the face candidate frame of the first pre-set dimension, obtains the first frame regression result；
All face candidate frames are zoomed into the second pre-set dimension, and pass through the second layer convolution of the grade neural network
Neural network carries out frame recurrence to the face candidate frame of the second pre-set dimension and the first frame regression result, obtains second
Frame regression result；
All face candidate frames are zoomed into third pre-set dimension, and pass through the third layer convolution of the grade neural network
The face candidate frame of third pre-set dimension, the first frame regression result and second frame are returned in neural network and tied
Fruit carries out frame recurrence, obtains third frame regression result；
According to the first frame regression result, the second frame regression result and third frame regression result, people is obtained
Face testing result.
In an alternative embodiment, it is described according to the first frame regression result, the second frame regression result with
And third frame regression result, Face datection is obtained as a result, specifically including:
The first frame regression result, the second frame regression result and third frame regression result are weighted and averaged
Processing, obtains the Face datection result.
In an alternative embodiment, first pre-set dimension is 12 × 12, the first layer convolutional neural networks
For 12 dimension convolutional neural networks；Second pre-set dimension is 24 × 24, and the second layer convolutional neural networks are 24 dimension convolution
Neural network；Second pre-set dimension is 48 × 48, and the third layer convolutional neural networks are 48 dimension convolutional neural networks.
In embodiments of the present invention, by the face candidate frame, resize and puts first into 12 × 12 respectively one by one
In 12- convolutional neural networks, the main function of the network is exactly to obtain to carry out identification to face candidate frame and to face candidate
Frame carries out frame recurrence.The major way that frame returns is to delete a large amount of candidate window using the method for non-maxima suppression,
Realize the adjustment of candidate frame.By the face candidate frame, resize and puts first 24- convolution mind into 24 × 24 respectively one by one
Through in network, the main function of the network is exactly to obtain to carry out identification to the face candidate frame and to the face candidate frame
Carry out frame recurrence.The frame that the frame regression result of 24- convolutional neural networks will merge 12- convolutional neural networks returns knot
Fruit realizes the adjustment by slightly confining position to the face of essence.By the face candidate frame, resize is put to 48 × 48, and respectively one by one
Into in first 48- convolutional neural networks, the main function of the network be exactly obtain to the face candidate frame identified with
And frame recurrence is carried out to the face candidate frame.The frame regression result of 48- convolutional neural networks will merge 12- convolutional Neural
The frame regression result of network, 24 convolutional neural networks realizes the adjustment by slightly confining position to the face of essence.In the detection of face
Identification level: the frame regression result of 48- convolutional neural networks, 12- convolutional neural networks, 24 convolutional neural networks is added
Weight average realizes the prediction of face frame, obtains Face datection result.
Compared with the existing technology, the beneficial effect of the embodiment of the present invention is:
1, the embodiment of the present invention has the advantages that preferable Target Segmentation using full convolutional neural networks, in full convolutional Neural
The inspection of position sensing region is fast implemented in network by the way of the further feature deconvolution up-sampling of fusion FCN and shallow-layer feature
Quick, the accurate mark for surveying and realizing human face region solves the problems, such as that tradition confines the deviation of position in original image mapping face, improves
Face confines the precision of position.
2, by carrying out selective search to the human face region, the very limited deep layer face frame of generation quantity is special
Sign carries out image binaryzation processing to deep layer face frame feature later, quick by the feature that human face region is mapped to deep layer
Judge face, reject a large amount of non-face frames or be unsatisfactory for the face frame of condition, obtains the face candidate area for highlighting facial contour
Domain, the significant increase speed of COMPUTER DETECTION face.
3, the face candidate frame that different scale is generated using image pyramid, is avoided the missing inspection of small face, solves small face
There is a problem of and leads to small Face datection inaccuracy.
4, the face candidate frame remained using cascade neural network to each carries out convolution, using from thick to thin
Mode successively refines the positioning of face frame, improves the accuracy of Face datection.
Referring to Fig. 2, second embodiment of the invention provides a kind of human face detection device, comprising:
Human face region obtains module 1, for obtaining the figure by full convolutional neural networks according to the image received
The human face region of picture；
Face search module 2 obtains deep layer face frame feature for carrying out selective search to the human face region；
Binary processing module 3, for carrying out binary conversion treatment to the deep layer face frame feature, from all human face regions
In orient the face candidate region of face making profile；
Face candidate frame obtains module 4, for passing through the image pyramid constructed in advance according to the face candidate region
Model obtains several various sizes of face candidate frames；
Face prediction module 5, for obtaining Face datection knot by joining grade neural network according to the face candidate frame
Fruit.
In an alternative embodiment, the human face region acquisition module 1 includes:
Temperature figure generation unit obtains several for the image received to be input to the full convolutional neural networks
Temperature figure；
Temperature figure integrated unit obtains fused heat for carrying out up-sampling and deconvolution processing to the temperature figure
Degree figure；
Human face region extraction unit, for extracting human face region according to fused temperature figure.
In an alternative embodiment, the binary processing module 3 includes:
Binary conversion treatment unit, for carrying out binary conversion treatment to the deep layer face frame feature；
Face judging unit, for carrying out face to the deep layer face frame feature after binary conversion treatment according to preset threshold value
Non-face face candidate region is rejected in judgement, obtains the face candidate region that frame selects complete facial contour.
In an alternative embodiment, the face prediction module 5 includes:
First frame returns unit, for all face candidate frames to be zoomed to the first pre-set dimension, and by described
The first layer convolutional neural networks of grade neural network carry out frame recurrence to the face candidate frame of the first pre-set dimension, obtain first
Frame regression result；
Second frame returns unit, for all face candidate frames to be zoomed to the second pre-set dimension, and by described
The second layer convolutional neural networks of grade neural network return knot to the face candidate frame of the second pre-set dimension and first frame
Fruit carries out frame recurrence, obtains the second frame regression result；
Third frame returns unit, for all face candidate frames to be zoomed to third pre-set dimension, and by described
Knot is returned to the face candidate frame of third pre-set dimension, first frame in the third layer convolutional neural networks of grade neural network
Fruit and the second frame regression result carry out frame recurrence, obtain third frame regression result；
Face datection unit, for according to the first frame regression result, the second frame regression result and third side
Frame regression result obtains Face datection result.
In an alternative embodiment, the Face datection unit includes:
Weighted average processing subelement, for the first frame regression result, the second frame regression result and third
Frame regression result is weighted and averaged processing, obtains the Face datection result.
In an alternative embodiment, first pre-set dimension is 12 × 12, the first layer convolutional neural networks
For 12 dimension convolutional neural networks；Second pre-set dimension is 24 × 24, and the second layer convolutional neural networks are 24 dimension convolution
Neural network；Second pre-set dimension is 48 × 48, and the third layer convolutional neural networks are 48 dimension convolutional neural networks.
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
It is the schematic diagram for the human-face detection equipment that third embodiment of the invention provides referring to Fig. 3.As shown in figure 3, the face
Detection device includes: at least one processor 11, such as CPU, at least one network interface 14 or other users interface 13 are deposited
Reservoir 15, at least one communication bus 12, communication bus 12 is for realizing the connection communication between these components.Wherein, user
Interface 13 optionally may include USB interface and other standards interface, wireline interface.Network interface 14 optionally may include
Wi-Fi interface and other wireless interfaces.Memory 15 may include high speed RAM memory, it is also possible to further include non-unstable
Memory (non-volatilememory), a for example, at least magnetic disk storage.Memory 15 optionally may include to
Few one is located remotely from the storage device of aforementioned processor 11.
In some embodiments, memory 15 stores following element, executable modules or data structures, or
Their subset or their superset:
Operating system 151 includes various system programs, for realizing various basic businesses and hardware based of processing
Business；
Program 152.
Specifically, processor 11 executes people described in above-described embodiment for calling the program 152 stored in memory 15
Face detecting method, such as step S11 shown in FIG. 1.Alternatively, being realized when the processor execution computer program above-mentioned each
The function of each module/unit in Installation practice, such as human face region obtain module.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the human-face detection equipment.
The human-face detection equipment can be the calculating such as desktop PC, notebook, palm PC and cloud server
Equipment.The human-face detection equipment may include, but be not limited only to, processor, memory.It will be understood by those skilled in the art that
The schematic diagram is only the example of human-face detection equipment, does not constitute the restriction to human-face detection equipment, may include than figure
Show more or fewer components, perhaps combines certain components or different components.
Alleged processor 11 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor 11 is the control centre of the human-face detection equipment, utilizes various interfaces and connection entire face inspection
The various pieces of measurement equipment.
The memory 15 can be used for storing the computer program and/or module, the processor 11 by operation or
Computer program and/or the module stored in the memory is executed, and calls the data being stored in memory, is realized
The various functions of the human-face detection equipment.The memory 15 can mainly include storing program area and storage data area, wherein
Storing program area can application program needed for storage program area, at least one function (for example sound-playing function, image play
Function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio data, phone directory etc.) according to mobile phone
Deng.It can also include nonvolatile memory in addition, memory 15 may include high-speed random access memory, such as hard disk,
Memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD)
Card, flash card (Flash Card), at least one disk memory, flush memory device or other volatile solid-state parts.
Wherein, if module/unit that the human-face detection equipment integrates is realized in the form of SFU software functional unit and makees
It is independent product when selling or using, can store in a computer readable storage medium.Based on this understanding,
The present invention realizes all or part of the process in above-described embodiment method, can also be instructed by computer program relevant hard
Part is completed, and the computer program can be stored in a computer readable storage medium, the computer program is processed
When device executes, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program generation
Code, the computer program code can be source code form, object identification code form, executable file or certain intermediate forms
Deng.The computer-readable medium may include: any entity or device, record that can carry the computer program code
Medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), with
Machine access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..
It should be noted that the content that the computer-readable medium includes can be according to legislation and patent practice in jurisdiction
It is required that carrying out increase and decrease appropriate, such as in certain jurisdictions, do not wrapped according to legislation and patent practice, computer-readable medium
Include electric carrier signal and telecommunication signal.
Fourth embodiment of the invention provides a kind of computer readable storage medium, the computer readable storage medium packet
Include the computer program of storage, wherein where controlling the computer readable storage medium in computer program operation
Equipment executes the method for detecting human face as described in any one of first embodiment.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of method for detecting human face, which comprises the following steps:
The human face region of described image is obtained by full convolutional neural networks according to the image received；
Selective search is carried out to the human face region, obtains deep layer face frame feature；
Binary conversion treatment is carried out to the deep layer face frame feature, the people of face making profile is oriented from all human face regions
Face candidate region；
According to the face candidate region, by the image pyramid model constructed in advance, several various sizes of people are obtained
Face candidate frame；
Face datection result is obtained by joining grade neural network according to the face candidate frame.
2. method for detecting human face as described in claim 1, which is characterized in that the image that the basis receives, by rolling up entirely
Product neural network, obtains the human face region of described image, specifically includes:
The image received is input to the full convolutional neural networks, obtains several temperature figures；
Up-sampling and deconvolution processing are carried out to the temperature figure, obtain fused temperature figure；
According to fused temperature figure, human face region is extracted.
3. method for detecting human face as described in claim 1, which is characterized in that described to carry out two to the deep layer face frame feature
Value processing, the face candidate region that frame selects complete facial contour is oriented from all human face regions, is specifically included:
Binary conversion treatment is carried out to the deep layer face frame feature；
Face judgement is carried out to the deep layer face frame feature after binary conversion treatment according to preset threshold value, rejects non-face face
Candidate region obtains the face candidate region that frame selects complete facial contour.
4. method for detecting human face as described in claim 1, which is characterized in that it is described according to the face candidate frame, pass through connection
Grade neural network obtains Face datection as a result, specifically including:
All face candidate frames are zoomed into the first pre-set dimension, and pass through the first layer convolutional Neural of the grade neural network
Network carries out frame recurrence to the face candidate frame of the first pre-set dimension, obtains the first frame regression result；
All face candidate frames are zoomed into the second pre-set dimension, and pass through the second layer convolutional Neural of the grade neural network
Network carries out frame recurrence to the face candidate frame of the second pre-set dimension and the first frame regression result, obtains the second frame
Regression result；
All face candidate frames are zoomed into third pre-set dimension, and pass through the third layer convolutional Neural of the grade neural network
In network to the face candidate frame of third pre-set dimension, the first frame regression result and the second frame regression result into
Row frame returns, and obtains third frame regression result；
According to the first frame regression result, the second frame regression result and third frame regression result, face inspection is obtained
Survey result.
5. method for detecting human face as claimed in claim 4, which is characterized in that it is described according to the first frame regression result,
Second frame regression result and third frame regression result, obtain Face datection as a result, specifically including:
Place is weighted and averaged to the first frame regression result, the second frame regression result and third frame regression result
Reason, obtains the Face datection result.
6. method for detecting human face as claimed in claim 4, which is characterized in that first pre-set dimension is 12 × 12, described
First layer convolutional neural networks are 12 dimension convolutional neural networks；Second pre-set dimension is 24 × 24, the second layer convolution
Neural network is 24 dimension convolutional neural networks；Second pre-set dimension is 48 × 48, and the third layer convolutional neural networks are
48 dimension convolutional neural networks.
7. a kind of human face detection device characterized by comprising
Human face region obtains module, for obtaining the people of described image by full convolutional neural networks according to the image received
Face region；
Face search module obtains deep layer face frame feature for carrying out selective search to the human face region；
Binary processing module, it is fixed from all human face regions for carrying out binary conversion treatment to the deep layer face frame feature
Position goes out the face candidate region of face making profile；
Face candidate frame obtains module, for according to the face candidate region, by the image pyramid model constructed in advance,
Obtain several various sizes of face candidate frames；
Face prediction module, for obtaining Face datection result by joining grade neural network according to the face candidate frame.
8. human face detection device as claimed in claim 7, which is characterized in that the human face region obtains module and includes:
Temperature figure generation unit obtains several temperatures for the image received to be input to the full convolutional neural networks
Figure；
Temperature figure integrated unit obtains fused temperature figure for carrying out up-sampling and deconvolution processing to the temperature figure；
Human face region extraction unit, for extracting human face region according to fused temperature figure.
9. a kind of human-face detection equipment, which is characterized in that including processor, memory and storage in the memory and by
It is configured to the computer program executed by the processor, is realized when the processor executes the computer program as right is wanted
Method for detecting human face described in asking any one of 1 to 6.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 6 described in method for detecting human face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530857.7A CN110210457A (en) | 2019-06-18 | 2019-06-18 | Method for detecting human face, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530857.7A CN110210457A (en) | 2019-06-18 | 2019-06-18 | Method for detecting human face, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110210457A true CN110210457A (en) | 2019-09-06 |
Family
ID=67793465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910530857.7A Pending CN110210457A (en) | 2019-06-18 | 2019-06-18 | Method for detecting human face, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210457A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781770A (en) * | 2019-10-08 | 2020-02-11 | 高新兴科技集团股份有限公司 | Living body detection method, device and equipment based on face recognition |
| CN111079643A (en) * | 2019-12-13 | 2020-04-28 | 三一重工股份有限公司 | Face detection method and device based on neural network and electronic equipment |
| CN111382687A (en) * | 2020-03-05 | 2020-07-07 | 平安科技（深圳）有限公司 | Face detection method and system |
| CN111950342A (en) * | 2020-06-22 | 2020-11-17 | 广州杰赛科技股份有限公司 | Face detection method, device and storage medium |
| CN112686851A (en) * | 2020-12-25 | 2021-04-20 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
| CN113239631A (en) * | 2021-06-07 | 2021-08-10 | 昆明理工大学 | Modeling method and system for improving complex dynamic scene segmentation |
| WO2021218899A1 (en) * | 2020-04-30 | 2021-11-04 | 京东方科技集团股份有限公司 | Method for training facial recognition model, and method and apparatus for facial recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912990A (en) * | 2016-04-05 | 2016-08-31 | 深圳先进技术研究院 | Face detection method and face detection device |
| CN106295502A (en) * | 2016-07-25 | 2017-01-04 | 厦门中控生物识别信息技术有限公司 | A kind of method for detecting human face and device |
| US20170147905A1 (en) * | 2015-11-25 | 2017-05-25 | Baidu Usa Llc | Systems and methods for end-to-end object detection |
-
2019
- 2019-06-18 CN CN201910530857.7A patent/CN110210457A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147905A1 (en) * | 2015-11-25 | 2017-05-25 | Baidu Usa Llc | Systems and methods for end-to-end object detection |
| CN105912990A (en) * | 2016-04-05 | 2016-08-31 | 深圳先进技术研究院 | Face detection method and face detection device |
| CN106295502A (en) * | 2016-07-25 | 2017-01-04 | 厦门中控生物识别信息技术有限公司 | A kind of method for detecting human face and device |
Non-Patent Citations (1)
| Title |
|---|
| 刘丽娴 等: "融合全卷积和级联卷积神经网络的人脸检测方法", 《移动通信》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781770A (en) * | 2019-10-08 | 2020-02-11 | 高新兴科技集团股份有限公司 | Living body detection method, device and equipment based on face recognition |
| CN110781770B (en) * | 2019-10-08 | 2022-05-06 | 高新兴科技集团股份有限公司 | Living body detection method, device and equipment based on face recognition |
| CN111079643A (en) * | 2019-12-13 | 2020-04-28 | 三一重工股份有限公司 | Face detection method and device based on neural network and electronic equipment |
| CN111079643B (en) * | 2019-12-13 | 2023-04-07 | 三一重工股份有限公司 | Face detection method and device based on neural network and electronic equipment |
| CN111382687A (en) * | 2020-03-05 | 2020-07-07 | 平安科技（深圳）有限公司 | Face detection method and system |
| WO2021218899A1 (en) * | 2020-04-30 | 2021-11-04 | 京东方科技集团股份有限公司 | Method for training facial recognition model, and method and apparatus for facial recognition |
| CN111950342A (en) * | 2020-06-22 | 2020-11-17 | 广州杰赛科技股份有限公司 | Face detection method, device and storage medium |
| CN112686851A (en) * | 2020-12-25 | 2021-04-20 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
| CN112686851B (en) * | 2020-12-25 | 2022-02-08 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
| CN113239631A (en) * | 2021-06-07 | 2021-08-10 | 昆明理工大学 | Modeling method and system for improving complex dynamic scene segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255352B (en) | Target detection method, device and system | |
| CN110210457A (en) | Method for detecting human face, device, equipment and computer readable storage medium | |
| CN109697416B (en) | Video data processing method and related device | |
| CN109815770B (en) | Two-dimensional code detection method, device and system | |
| CN109815843B (en) | Image processing method and related product | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| CN105989144B (en) | Notification message management method, device and system and terminal equipment | |
| CN109948497A (en) | A kind of object detecting method, device and electronic equipment | |
| CN110363091A (en) | Face identification method, device, equipment and storage medium in the case of side face | |
| CN110163076A (en) | A kind of image processing method and relevant apparatus | |
| CN107291825A (en) | With the search method and system of money commodity in a kind of video | |
| CN110942456B (en) | Tamper image detection method, device, equipment and storage medium | |
| CN113496208B (en) | Video scene classification method and device, storage medium and terminal | |
| CN106407908A (en) | Training model generation method and human face detection method and device | |
| CN113781164B (en) | Virtual fitting model training method, virtual fitting method and related devices | |
| CN115880536A (en) | Data processing method, training method, target object detection method and device | |
| CN107315984B (en) | Pedestrian retrieval method and device | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| CN109787977B (en) | Product information processing method, device and equipment based on short video and storage medium | |
| CN115115825A (en) | Method and device for detecting object in image, computer equipment and storage medium | |
| CN111310531A (en) | Image classification method and device, computer equipment and storage medium | |
| CN108875496A (en) | The generation of pedestrian's portrait and the pedestrian based on portrait identify | |
| CN115223022B (en) | Image processing method, device, storage medium and equipment | |
| CN106874835B (en) | A kind of image processing method and device | |
| CN115731442A (en) | Image processing method, image processing device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190906 |
|
| RJ01 | Rejection of invention patent application after publication |