CN107220951A - Facial image noise-reduction method, device, storage medium and computer equipment - Google Patents
Facial image noise-reduction method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN107220951A CN107220951A CN201710401502.9A CN201710401502A CN107220951A CN 107220951 A CN107220951 A CN 107220951A CN 201710401502 A CN201710401502 A CN 201710401502A CN 107220951 A CN107220951 A CN 107220951A
- Authority
- CN
- China
- Prior art keywords
- image
- field pictures
- face information
- field
- picture
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000001815 facial effect Effects 0.000 title claims abstract description 32
- 230000009467 reduction Effects 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000009471 action Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20201—Motion blur correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of facial image noise-reduction method, device, storage medium and computer equipment, first, obtain M frames and shoot the image for having face, the M is natural number, and M >=2.Afterwards, the face information that each frame described image is included in identification N two field pictures respectively, and Z two field pictures are picked out from the N two field pictures as the input picture of multiframe noise reduction algorithm, wherein, the difference of the face information of any two frames described image is respectively less than the first given threshold in the Z two field pictures, the N, the Z are natural number, and N≤M, Z≤N.Therefore, even if people is kept in motion when shooting, but because the face information difference of select Z two field pictures is smaller, there is fuzzy probability so as to reduce the image human face region obtained after multiframe noise reduction.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of facial image noise-reduction method, device, storage are situated between
Matter and computer equipment.
Background technology
Tradition is usually using the method for multiframe noise reduction algorithm synthesis facial image：Multiframe (such as four frames) image is inputted,
By multiframe noise reduction algorithm, the less facial image of a frame noise is obtained.However, in shooting process, if people is in motion
State, the fuzzy defect of human face region occurs in the image obtained using above-mentioned conventional method.
The content of the invention
The present invention provides a kind of facial image noise-reduction method, device, storage medium and computer equipment, can improve tradition
The fuzzy defect of human face region occurs in the image that method is obtained.
A kind of facial image noise-reduction method, including：
Obtain M frames and shoot the image for having face；The M is natural number, and M >=2；And
The face information that each frame described image is included in identification N two field pictures respectively, and pick out Z from the N two field pictures
Two field picture as multiframe noise reduction algorithm input picture；Wherein, in the Z two field pictures any two frames described image face information
Difference be respectively less than the first given threshold；The N, the Z are natural number, and N≤M, Z≤N.
In one of the embodiments, the face information that includes of each frame described image in identification N two field pictures respectively, and from institute
State and Z two field pictures are picked out in N two field pictures include as the input picture of multiframe noise reduction algorithm：
The face information that each frame described image is included in identification N two field pictures respectively, and will a wherein frame described image conduct
Benchmark image, picks out Z two field pictures as the input picture of multiframe noise reduction algorithm；Wherein, scheme in the Z two field pictures described in each frame
Difference between the face information of picture and the face information of the benchmark image is respectively less than the second given threshold；Second setting
Threshold value is less than or equal to first given threshold.
In one of the embodiments, the face information that includes of each frame described image in identification N two field pictures respectively, and by its
In a frame described image as benchmark image, pick out Z two field pictures includes as the input picture of multiframe noise reduction algorithm：
The first two field picture is selected from the M two field pictures as benchmark image, and recognizes the face letter of the benchmark image
Breath；
The second two field picture is selected from the M two field pictures, and recognizes the face information of second two field picture；
The face information and the face information of the benchmark image of second two field picture are compared, if this two frame
The difference of the face information of image is less than second given threshold, regard second two field picture as image to be synthesized；And
When judging that the sum of image to be synthesized is not up to Z frames, continuation selects a two field picture from the M two field pictures, and holds
Row and the second two field picture identical processing procedure, are circulated successively, until the sum of the image to be synthesized reaches Z frames.
In one of the embodiments, the face information is the positional information of face area-of-interest.
In one of the embodiments, if the difference of the face information of this two field pictures is less than the described second setting threshold
Value, be as image to be synthesized using second two field picture：
If the face area-of-interest the position of the benchmark image with the position of second two field picture it
Between distance be less than setpoint distance, then regard second two field picture as image to be synthesized.
In one of the embodiments, the N two field pictures are the image being continuously shot.
A kind of facial image denoising device, including：
Image collection module, obtains M frames and shoots the image for having face；The M is natural number, and M >=2；And
Image Choosing module, for recognizing each frame described image is included in N two field pictures face information respectively, and from described
Z two field pictures are picked out in N two field pictures as the input picture of multiframe noise reduction algorithm；Wherein, any two frames institute in the Z two field pictures
The difference for stating the face information of image is respectively less than the first given threshold；The N, the Z are natural number, and N≤M, Z≤N.
In one of the embodiments, described image Choosing module is used for each frame described image in identification N two field pictures respectively
Comprising face information, and will a wherein frame described image as benchmark image, pick out Z two field pictures as multiframe noise reduction algorithm
Input picture；Wherein, in the Z two field pictures face information of each frame described image and the benchmark image face information it
Between difference be respectively less than the second given threshold；Second given threshold is less than or equal to first given threshold.
A kind of storage medium, is stored thereon with computer program, and power is realized when the computer program is executed by processor
Profit requires the method described in any claim in 1 to 6.
A kind of computer equipment, including memory, processor and be stored on the memory and can be in the processor
The computer program of upper operation, realizes that any right will in claim 1 to 6 described in the computing device during computer program
Seek described method.
In above-mentioned facial image noise-reduction method, device, storage medium and computer equipment, there is face obtaining M frames and shooting
Image after, the face information that includes of each two field picture in N two field pictures is recognized respectively, and pick out from N two field pictures Z two field pictures work
For the input picture of multiframe noise reduction algorithm, wherein, the difference of the face information of any two field pictures is respectively less than first in Z two field pictures
Given threshold, even if therefore when shooting, people is kept in motion, but due to the face information difference of select Z two field pictures
It is smaller, there is fuzzy probability so as to reduce the image human face region obtained after multiframe noise reduction.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
The accompanying drawing of other embodiment is obtained according to these accompanying drawings.
The flow chart for the facial image noise-reduction method that Fig. 1 provides for an embodiment；
Fig. 2 is the interior of the electronic equipment of the facial image noise-reduction method of execution Fig. 1 illustrated embodiments in one embodiment
Portion's structural representation；
Fig. 3 is one of embodiment flow chart of the facial image noise-reduction method of Fig. 1 illustrated embodiments；
Fig. 4 is the step S210 of the facial image noise-reduction method of embodiment illustrated in fig. 3 one of embodiment flow chart；
The block diagram for the facial image denoising device that Fig. 5 provides for another embodiment；
Fig. 6 for Fig. 5 illustrated embodiments facial image denoising device in image Choosing module one of embodiment
Block diagram；
The block diagram of the part-structure of the mobile phone for the computer equipment correlation that Fig. 7 provides for another embodiment.
Embodiment
For the ease of understanding the present invention, the present invention is described more fully below with reference to relevant drawings.In accompanying drawing
Give presently preferred embodiments of the present invention.But, the present invention can be realized in many different forms, however it is not limited to this paper institutes
The embodiment of description.On the contrary, the purpose for providing these embodiments is to make the understanding to the disclosure more thorough
Comprehensively.
Unless otherwise defined, the skill of technical field of all of technologies and scientific terms used here by the article with belonging to invention
The implication that art personnel are generally understood that is identical.Herein description is intended merely in the term used in the description of invention specifically
The purpose of embodiment, it is not intended that the limitation present invention.Term as used herein "and/or" includes one or more related institutes
The arbitrary and all combination of list of items.
One embodiment provide a kind of facial image noise-reduction method, as shown in figure 1, can by mobile phone, tablet personal computer or
The electronic equipment such as person's personal digital assistant or Wearable is realized.Fig. 2 is the internal junction of electronic equipment in one embodiment
Structure schematic diagram.The electronic equipment is included by the processor of system bus connection, non-volatile memory medium, camera device, interior
Memory, display screen and input unit.Wherein, the non-volatile memory medium of electronic equipment is stored with operating system and computer
Readable instruction.To realize a kind of facial image noise-reduction method when the computer-readable instruction is executed by processor.The processor is used
Calculated and control ability in providing, support the operation of whole electronic equipment.Camera device in electronic equipment can with shooting image,
For example, camera.Built-in storage in electronic equipment carries for the operation of the computer-readable instruction in non-volatile memory medium
For environment.The display screen of electronic equipment can be LCDs or electric ink display screen etc., and input unit can be aobvious
The button, trace ball or the Trackpad that are set on the touch layer or electronic equipment casing covered in display screen or outer
Keyboard, Trackpad or mouse for connecing etc..It will be understood by those skilled in the art that the structure shown in Fig. 2, is only and the application
The block diagram of the related part-structure of scheme, does not constitute the restriction for the electronic equipment being applied thereon to application scheme, has
The electronic equipment of body can include, than more or less parts shown in figure, either combining some parts or with difference
Part arrangement.
Next the facial image noise-reduction method of Fig. 1 illustrated embodiments, including herein below will be introduced.
Step S100, obtains M frames and shoots the image for having face.Wherein, M is natural number, and M >=2.
Wherein, M frames shoot the image for having face, refer to that each two field picture includes the face of same target person.Also, can
To be carried out continuously shooting to the face of target person by above-mentioned camera device, and each two field picture of shooting is stored in non-volatile
Storage medium, processor can obtain these images.In addition, if target person is kept in motion in shooting process, then
Each action of target person corresponds to the image that some frames are continuously shot, in other words, in all images, difference group figure
As (each group image include some two field pictures) corresponds to the image of target person difference action respectively, therefore, difference group images it
Between differ greatly, and the difference in each group of image between each two field picture is smaller.
Step S200, recognizes the face information that each two field picture is included in N two field pictures, and pick out Z from N two field pictures respectively
Two field picture as multiframe noise reduction algorithm input picture.Wherein, the difference of the face information of any two field pictures is equal in Z two field pictures
Less than the first given threshold.N, Z are natural number, and N≤M, Z≤N.
Wherein, face information is, for example, positional information of face characteristic etc..Also, people of the target person under different actions
Face information gap is larger, therefore the less multiple image of difference can be picked out according to face information.Furthermore it is possible to utilize people
Face recognizer recognizes face information, and face recognition algorithms are, for example, the recognizer based on human face characteristic point, based on template
Recognizer, the algorithm that is identified using neutral net etc..
The difference of the face information of any two field pictures is respectively less than the first given threshold in Z two field pictures, in other words, this Z frame
The difference of image is smaller.It is corresponding when the first given threshold is in same action for target person to compare threshold value, as long as two frames
The difference of the face information of image is less than the first given threshold, represents this two field pictures and same action shooting is formed,
At this moment, the Z two field pictures picked out are exactly that same action is carried out shooting obtained each two field picture.Z two field pictures drop as multiframe
Make an uproar the input picture of algorithm, refer to that this Z two field picture so as to follow-up will carry out multiframe noise reduction process as input picture, so that finally
Synthesize after a frame noise reduction and the image comprising face.Specifically, Z two field pictures can be sent directly into multiframe synthesis storehouse.Wherein,
Multiframe noise reduction algorithm can use traditional multiframe noise reduction algorithm, for example, Z two field pictures can be overlapped and are averaged, due to
Noise has randomness, orthogonal, therefore the average of noise is usually zero, therefore can remove after Z two field pictures are averaged and make an uproar
Sound is so as to improve the signal to noise ratio of image.Therefore, if Z two field pictures are shot when being in same action to target person, i.e. this Z
The pixel of two field picture remaining effective image in addition to noise is almost identical with pixel value in the position of each two field picture, then
Carry out after multiframe noise reduction, can not only remove noise, and the pixel of effective image is also not in distortion or fuzzy showed
As original state still can be kept, so that the human face region of the image obtained after noise reduction is remained in that clearly.
In addition, Z quantity will meet the demand of multiframe noise reduction algorithm, for example, 4 frames, 5 frames, 6 frames etc..Z≤N, represents N frames
There may be the image differed greatly with the face information of Z two field pictures in image, these images will be abandoned.N≤M, is represented
Face information is all not necessarily recognized to all M two field pictures, as long as Z frames can be found in N two field pictures meets the image of demand i.e.
Can.
In summary, the above-mentioned facial image noise-reduction method that embodiment of the present invention is provided, even if people is in when shooting
Motion state, but because the face information difference of select Z two field pictures is smaller, so as to be obtained after reducing multiframe noise reduction
Image human face region there is fuzzy probability.
In one of the embodiments, Fig. 3 is refer to, above-mentioned steps S200 includes herein below.
Step S210, recognizes the face information that each two field picture is included in N two field pictures respectively, and will a wherein two field picture conduct
Benchmark image, picks out Z two field pictures as the input picture of multiframe noise reduction algorithm.Wherein, in Z two field pictures each two field picture face
Difference between information and the face information of benchmark image is respectively less than the second given threshold.Second given threshold is less than or equal to the
One given threshold.
Wherein, because the difference in Z two field pictures between the face information of each two field picture and the face information of benchmark image is equal
Less than the second given threshold, therefore, during Z two field pictures are selected, it is only necessary to by each two field picture in N two field pictures respectively with
Benchmark image is compared, so as to simplify election process, improves efficiency.
In addition, it is necessary to explanation, because the second given threshold is less than or equal to the first given threshold, as long as therefore respectively
It is that (such as the second given threshold is 1 to suitable value, and the first given threshold is with the first given threshold to set the second given threshold
3), then the Z two field pictures picked out using the step S210 methods provided, it becomes possible to meet the face information of any two field pictures
Difference be respectively less than the first given threshold.
It is understood that the specific method that Z two field pictures are selected from N two field pictures is not limited to above-mentioned situation, for example, choosing
When selecting next two field picture, the previous frame image just chosen can be regard as the benchmark image for comparing, i.e. benchmark image
It is not limited to a two field picture of fixation.
In one of the embodiments, above-mentioned steps S210 includes herein below, refer to Fig. 4.
Step S211, selects the first two field picture as benchmark image from M two field pictures, and recognizes the face letter of benchmark image
Breath.
Specifically, face information is the positional information of face area-of-interest (ROI, region of interest).Its
In, face area-of-interest refers to after detecting face and positioning facial key feature points know using face recognition algorithms
The human face region not gone out.The coordinate value of the positional information of face area-of-interest, such as each summit of face area-of-interest.That
, if face area-of-interest is rectangle, the coordinate value on 4 summits is included altogether.
Step S212, selects the second two field picture, and recognize the face information of the second two field picture from M two field pictures.
Step S213, the face information of the face information of the second two field picture and benchmark image is compared, if this two
The difference of the face information of two field picture is less than the second given threshold, regard the second two field picture as image to be synthesized.
Wherein, using the second two field picture as image to be synthesized, refer to the second two field picture as a wherein frame for Z two field pictures.
Specifically, if using the second two field picture as image to be synthesized, during can first the deposit of the second two field picture be cached.In addition, if
The difference of the face information of second two field picture and the face information of benchmark image is more than the second given threshold, then abandons the second frame figure
Picture.
Specifically, if face information is the positional information of face area-of-interest, if the face of this two field pictures
The difference of information is less than the second given threshold, is using the second two field picture as image to be synthesized：If face area-of-interest exists
The position of benchmark image and distance between the position of the second two field picture are less than setpoint distance, then using the second two field picture as treating
Composograph.
Wherein, the value type of the first given threshold and the second given threshold is all distance, and the second given threshold is less than
Or equal to the first given threshold.If benchmark image and the second two field picture are shot when being all and being in same action to target person
, the face area-of-interest of this two field pictures is just hardly shifted over, i.e. face area-of-interest is in reference map
The position of picture and the distance between the position of the second two field picture are less than setpoint distance；If benchmark image and the second two field picture point
Do not shoot and form when target person is in different actions, then the face area-of-interest of this two field pictures can then occur
Displacement, at this moment face area-of-interest can then be more than in the position of benchmark image and the distance between the position of the second two field picture
Setpoint distance.Therefore, by judging the displacement situation of area-of-interest, it is easy to pick out the Z shot to same action
Two field picture.
It is understood that judging that the method for the difference of the face information of two field pictures is not limited to that above-mentioned to compare face sense emerging
A kind of situation of the position in interesting region, for example can also be by judging face key feature points (such as eyeball central point, canthus
Point, corners of the mouth point etc.) position judge the difference of the face information of two field pictures.
Step S214, when judging that the sum of image to be synthesized is not up to Z frames, a two field picture is selected in continuation from M two field pictures,
And perform and the second two field picture identical processing procedure, circulate successively, until the sum of image to be synthesized reaches Z frames.
The step refers to, if the sum of image to be synthesized is not reaching to Z frames, continues to select the 3rd from M two field pictures
Two field picture, then recognizes the face information of the 3rd two field picture, and by the face information of the 3rd two field picture and the face of benchmark image
Information is compared, if the difference of the face information of this two field pictures is less than the second given threshold, the 3rd two field picture is same
3rd two field picture is also stored in caching by sample as image to be synthesized；Continue to judge afterwards image to be synthesized it is total whether
Z frames are reached, if not having, other two field pictures are selected in continuation from M two field pictures, are circulated successively, until the sum of image to be synthesized reaches
Untill Z frames.
After total number of images to be synthesized reaches Z frames, the total number of images selected altogether from M two field pictures is then N frames, i.e. N frames figure
As including Z two field pictures and the image being abandoned.In addition, if all images to be synthesized are all stored in into caching before, then treating
The sum of composograph is reached after Z frames, and the Z two field pictures in caching are sent in multiframe synthesis storehouse, multiframe is carried out so as to follow-up
Noise reduction.
Therefore, above-described embodiment is only not reaching to Z during Z two field pictures are selected in the sum of image to be synthesized
During frame, image is just selected again from M two field pictures, and identification face information, judgement and benchmark image are performed to the image selected
Between difference these steps, so as to avoid wasting computing resource, improve operation efficiency.
In one of the embodiments, above-mentioned N two field pictures are the image being continuously shot.In other words, chosen from M two field pictures
It is to select the continuous each two field picture of shooting time successively when selecting image.If target person is kept in motion, target person
Each action can be reflected in some two field pictures (i.e. one group image) being continuously shot.Therefore, above-mentioned N two field pictures are company
The continuous image shot, the Z two field pictures for the same action of correspondence of being more convenient for picking out.
Another embodiment provides a kind of facial image denoising device, including herein below, refer to Fig. 5.
Image collection module 510, obtains M frames and shoots the image for having face.The M is natural number, and M >=2.
Image Choosing module 520, for recognizing each frame described image is included in N two field pictures face information respectively, and from
Z two field pictures are picked out in the N two field pictures as the input picture of multiframe noise reduction algorithm.Wherein, any two in the Z two field pictures
The difference of the face information of frame described image is respectively less than the first given threshold.The N, the Z are natural number, and N≤M, Z≤
N。
In one of the embodiments, image Choosing module 520 is used for each frame described image bag in identification N two field pictures respectively
The face information contained, and will a wherein frame described image as benchmark image, pick out Z two field pictures as multiframe noise reduction algorithm
Input picture.Wherein, in the Z two field pictures between the face information of each frame described image and the face information of the benchmark image
Difference be respectively less than the second given threshold.Second given threshold is less than or equal to first given threshold.
In one of the embodiments, image Choosing module 520 includes herein below, refer to Fig. 6.
Benchmark image module of selection 521, for selecting the first two field picture as benchmark image from the M two field pictures, and
Recognize the face information of the benchmark image.
Face information recognition unit 522, for selecting the second two field picture from the M two field pictures, and recognizes described second
The face information of two field picture.
Face information comparing unit 523, for by the people of the face information of second two field picture and the benchmark image
Face information is compared, if the difference of the face information of this two field pictures is less than second given threshold, by described second
Two field picture is used as image to be synthesized.
Other image module of selection 524, during for judging that the sum of image to be synthesized is not up to Z frames, continue from the M frames
A two field picture is selected in image, and is performed and the second two field picture identical processing procedure, is circulated successively, until described wait to close
Sum into image reaches Z frames.
In one of the embodiments, the face information is the positional information of face area-of-interest.
In one of the embodiments, face information comparing unit 523 is used for the face information of second two field picture
Be compared with the face information of the benchmark image, if the face area-of-interest the position of the benchmark image with
Distance between the position of second two field picture is less than setpoint distance, then regard second two field picture as figure to be synthesized
Picture.
In one of the embodiments, the N two field pictures are the image being continuously shot.
The division of modules is only used for for example, in other embodiments in above-mentioned facial image denoising device, can
Facial image denoising device is divided into different modules as required, with complete above-mentioned facial image denoising device whole or
Partial function.
It should be noted that facial image denoising device and above-mentioned facial image noise-reduction method that above-mentioned embodiment is provided
Correspond, just repeat no more here.
It is another to be stored thereon with computer program embodiment further provides a kind of storage medium, the computer program quilt
The facial image noise-reduction method that above-mentioned embodiment is provided is realized during computing device.
It is another that embodiment further provides a kind of computer equipment.As shown in fig. 7, for convenience of description, illustrate only with
The related part of embodiment of the present invention, particular technique details is not disclosed, refer to embodiment of the present invention method part.Should
Computer equipment can be to include mobile phone, tablet personal computer, PDA (Personal Digital Assistant, individual digital is helped
Reason), POS (Point of Sales, point-of-sale terminal), vehicle-mounted computer, any terminal device such as Wearable, set with computer
For for exemplified by mobile phone：
Fig. 7 for the part-structure of the mobile phone related to the computer equipment that embodiment of the present invention is provided block diagram.With reference to
Fig. 7, mobile phone includes：Radio frequency (Radio Frequency, RF) circuit 710, memory 720, input block 730, display unit
740th, sensor 750, voicefrequency circuit 770, Wireless Fidelity (wireless fidelity, WiFi) module 770, processor 780,
And the grade part of power supply 790.It will be understood by those skilled in the art that the handset structure shown in Fig. 7 does not constitute the limit to mobile phone
It is fixed, it can include than illustrating more or less parts, either combine some parts or different parts arrangement.
Wherein, RF circuits 710 can be used for receive and send messages or communication process in, the reception and transmission of signal can be by base stations
After downlink information is received, handled to processor 780；Up data can also be sent to base station.Generally, RF circuits include but
Be not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (Low Noise Amplifier,
LNA), duplexer etc..In addition, RF circuits 710 can also be communicated by radio communication with network and other equipment.Above-mentioned channel radio
Letter can use any communication standard or agreement, including but not limited to global system for mobile communications (Global System of
Mobile communication, GSM), general packet radio service (General Packet Radio Service,
GPRS), CDMA (Code Division Multiple Access, CDMA), WCDMA (Wideband Code
Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE)), Email,
Short Message Service (Short Messaging Service, SMS) etc..
Memory 720 can be used for storage software program and module, and processor 780 is stored in memory 720 by operation
Software program and module, so as to perform various function application and the data processing of mobile phone.Memory 720 can mainly include
Program storage area and data storage area, wherein, the application journey that program storage area can be needed for storage program area, at least one function
Sequence (application program of such as sound-playing function, application program of image player function etc.) etc.；Data storage area can store root
Created data (such as voice data, address list etc.) etc. are used according to mobile phone.In addition, memory 720 can be included at a high speed
Random access memory, can also include nonvolatile memory, for example, at least one disk memory, flush memory device or
Other volatile solid-state parts.
Input block 730 can be used for the numeral or character information for receiving input, and generation and the user of mobile phone 700 to set
And the relevant key signals input of function control.Specifically, input block 730 may include contact panel 731 and other inputs
Equipment 732.Contact panel 731, alternatively referred to as touch-screen, collect touch operation (such as user of the user on or near it
Use the operation of any suitable object such as finger, stylus or annex on contact panel 731 or near contact panel 731),
And corresponding attachment means are driven according to formula set in advance.In one embodiment, contact panel 731 may include to touch inspection
Survey two parts of device and touch controller.Wherein, touch detecting apparatus detects the touch orientation of user, and detects touch operation
The signal brought, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and will
It is converted into contact coordinate, then gives processor 780, and the order sent of reception processing device 780 and can be performed.In addition,
Contact panel 731 can be realized using polytypes such as resistance-type, condenser type, infrared ray and surface acoustic waves.Except touch surface
Plate 731, input block 730 can also include other input equipments 732.Specifically, other input equipments 732 can be included but not
It is limited to the one or more in physical keyboard, function key (such as volume control button, switch key etc.) etc..
Display unit 740 can be used for the various of the information that is inputted by user of display or the information for being supplied to user and mobile phone
Menu.Display unit 740 may include display panel 741.In one embodiment, liquid crystal display (Liquid can be used
Crystal Display, LCD), the form such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED)
To configure display panel 741.In one embodiment, contact panel 731 can cover display panel 741, when contact panel 731 is examined
Measure after the touch operation on or near it, processor 780 is sent to determine the type of touch event, with preprocessor
780 provide corresponding visual output according to the type of touch event on display panel 741.Although in the figure 7, contact panel
731 and display panel 741 are input and the input function that mobile phone is realized as two independent parts, but are implemented some
, can be by contact panel 731 and the input that is integrated and realizing mobile phone of display panel 741 and output function in example.
Mobile phone 700 may also include at least one sensor 750, such as optical sensor, motion sensor and other sensings
Device.Specifically, optical sensor may include ambient light sensor and proximity transducer, wherein, ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 741, and proximity transducer can close display panel when mobile phone is moved in one's ear
741 and/or backlight.Motion sensor may include acceleration transducer, can detect and adds in all directions by acceleration transducer
The size of speed, can detect that size and the direction of gravity when static, application (the such as horizontal/vertical screen available for identification mobile phone posture
Switching), Vibration identification correlation function (such as pedometer, tap) etc.；In addition, mobile phone can also configure gyroscope, barometer, humidity
Other sensors such as meter, thermometer, infrared ray sensor etc..
Voicefrequency circuit 770, loudspeaker 771 and microphone 772 can provide the COBBAIF between user and mobile phone.Audio-frequency electric
Electric signal after the voice data received conversion can be transferred to loudspeaker 771, sound is converted to by loudspeaker 771 by road 770
Signal output；On the other hand, the voice signal of collection is converted to electric signal by microphone 772, by voicefrequency circuit 770 receive after turn
It is changed to voice data, then after voice data output processor 780 is handled, another mobile phone can be sent to through RF circuits 710, or
Person exports voice data to memory 720 so as to subsequent treatment.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronicses postal by WiFi module 770
Part, browse webpage and access streaming video etc., it has provided the user wireless broadband internet and accessed.Although Fig. 7 is shown
WiFi module 770, but it is understood that, it is simultaneously not belonging to must be configured into for mobile phone 700, can omit as needed.
Processor 780 is the control centre of mobile phone, using various interfaces and the various pieces of connection whole mobile phone, is led to
Cross operation or perform and be stored in software program and/or module in memory 720, and call and be stored in memory 720
Data, perform the various functions and processing data of mobile phone, so as to carry out integral monitoring to mobile phone.In one embodiment, handle
Device 780 may include one or more processing units.In one embodiment, processor 780 can integrated application processor and modulation
Demodulation processor, wherein, application processor mainly handles operating system, user interface and application program etc.；Modulation /demodulation is handled
Device mainly handles radio communication.It is understood that above-mentioned modem processor can not also be integrated into processor 780.
Mobile phone 700 also includes the power supply 790 (such as battery) powered to all parts, it is preferable that power supply can pass through electricity
Management system and processor 780 are logically contiguous, so as to realize management charging, electric discharge and power consumption by power-supply management system
The functions such as management.
In one embodiment, mobile phone 700 can also include camera, bluetooth module etc..
In embodiments of the present invention, the processor 780 included by the mobile terminal performs the meter of storage on a memory
The facial image noise-reduction method that above-mentioned embodiment is provided is realized during calculation machine program.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can be read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
It should be noted that the schematic flow sheet of Fig. 1, Fig. 3 and Fig. 4 for the method for each embodiment of embodiment of the present invention.
It should be understood that although each step in Fig. 1, Fig. 3 and Fig. 4 flow chart is shown successively according to the instruction of arrow,
These steps are not that the inevitable order indicated according to arrow is performed successively.Unless expressly stated otherwise herein, these steps
The strict order limitation of execution, it can be performed in the other order.Moreover, at least one in Fig. 1, Fig. 3 and Fig. 4
Part steps can include many sub-steps or multiple stages, and these sub-steps or stage are not necessarily in synchronization
Perform completion, but can perform different at the time of, its execution sequence is also not necessarily to be carried out successively, but can be with other
At least a portion of the sub-step or stage of step or other steps is performed in turn or alternately.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope of this specification record is all considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and it describes more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that coming for one of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of facial image noise-reduction method, including：
Obtain M frames and shoot the image for having face；The M is natural number, and M >=2；And
The face information that includes of each frame described image in identification N two field pictures respectively, and pick out from the N two field pictures Z frame figures
As the input picture as multiframe noise reduction algorithm；Wherein, in the Z two field pictures face information of any two frames described image difference
It is different to be respectively less than the first given threshold；The N, the Z are natural number, and N≤M, Z≤N.
2. according to the method described in claim 1, it is characterised in that recognize that each frame described image in N two field pictures is included respectively
Face information, and pick out Z two field pictures from the N two field pictures and include as the input picture of multiframe noise reduction algorithm：
The face information that each frame described image is included in identification N two field pictures respectively, and wherein a frame described image will be used as benchmark
Image, picks out Z two field pictures as the input picture of multiframe noise reduction algorithm；Wherein, each frame described image in the Z two field pictures
Difference between face information and the face information of the benchmark image is respectively less than the second given threshold；Second given threshold
Less than or equal to first given threshold.
3. method according to claim 2, it is characterised in that recognize that each frame described image in N two field pictures is included respectively
Face information, and will a wherein frame described image as benchmark image, pick out Z two field pictures as the input of multiframe noise reduction algorithm
Image includes：
The first two field picture is selected from the M two field pictures as benchmark image, and recognizes the face information of the benchmark image；
The second two field picture is selected from the M two field pictures, and recognizes the face information of second two field picture；
The face information and the face information of the benchmark image of second two field picture are compared, if this two field pictures
Face information difference be less than second given threshold, regard second two field picture as image to be synthesized；And
When judging that the sum of image to be synthesized is not up to Z frames, a two field picture is selected in continuation from the M two field pictures, and perform with
The second two field picture identical processing procedure, is circulated successively, until the sum of the image to be synthesized reaches Z frames.
4. method according to claim 3, it is characterised in that the face information is believed for the position of face area-of-interest
Breath.
5. method according to claim 4, it is characterised in that if the difference of the face information of this two field pictures is less than institute
The second given threshold is stated, is as image to be synthesized using second two field picture：
If the face area-of-interest is in the position of the benchmark image and between the position of second two field picture
Distance is less than setpoint distance, then regard second two field picture as image to be synthesized.
6. the method according to any claim in claim 1 to 5, it is characterised in that the N two field pictures are continuous bat
The image taken the photograph.
7. a kind of facial image denoising device, it is characterised in that including：
Image collection module, obtains M frames and shoots the image for having face；The M is natural number, and M >=2；And
Image Choosing module, for recognizing each frame described image is included in N two field pictures face information respectively, and from the N frames
Z two field pictures are picked out in image as the input picture of multiframe noise reduction algorithm；Wherein, in the Z two field pictures described in any two frame
The difference of the face information of image is respectively less than the first given threshold；The N, the Z are natural number, and N≤M, Z≤N.
8. facial image denoising device according to claim 7, it is characterised in that described image Choosing module is used to distinguish
The face information that each frame described image is included in identification N two field pictures, and wherein a frame described image as benchmark image, will select
Go out Z two field pictures as the input picture of multiframe noise reduction algorithm；Wherein, in the Z two field pictures each frame described image face information
Difference between the face information of the benchmark image is respectively less than the second given threshold；Second given threshold is less than or waited
In first given threshold.
9. a kind of storage medium, is stored thereon with computer program, it is characterised in that the computer program is executed by processor
Method in Shi Shixian claims 1 to 6 described in any claim.
10. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, it is characterised in that realized described in the computing device during computer program in claim 1 to 6
Method described in any claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401502.9A CN107220951A (en) | 2017-05-31 | 2017-05-31 | Facial image noise-reduction method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401502.9A CN107220951A (en) | 2017-05-31 | 2017-05-31 | Facial image noise-reduction method, device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107220951A true CN107220951A (en) | 2017-09-29 |
Family
ID=59947297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710401502.9A Pending CN107220951A (en) | 2017-05-31 | 2017-05-31 | Facial image noise-reduction method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220951A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109151323A (en) * | 2018-10-18 | 2019-01-04 | Oppo广东移动通信有限公司 | A kind of photographic method and device, terminal, storage medium |
| CN109995964A (en) * | 2019-02-21 | 2019-07-09 | 西安万像电子科技有限公司 | Image processing method and device |
| WO2019228456A1 (en) * | 2018-05-31 | 2019-12-05 | 杭州海康威视数字技术股份有限公司 | Image processing method, apparatus and device, and machine-readable storage medium |
| CN111026263A (en) * | 2019-11-26 | 2020-04-17 | 维沃移动通信有限公司 | Audio playing method and electronic equipment |
| US10825146B2 (en) | 2017-11-30 | 2020-11-03 | Guangdong Oppo Mobile Telecommunications Corp., Ltd | Method and device for image processing |
| CN111917993A (en) * | 2019-05-07 | 2020-11-10 | 株式会社摩如富 | Image processing apparatus, image processing method, image capturing apparatus, and recording medium for program for image capturing apparatus |
| CN112241670A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Image processing method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1713730A (en) * | 2004-06-16 | 2005-12-28 | 三星电子株式会社 | Method of and apparatus for estimating noise of input image, and method and recording media of eliminating noise |
| CN101296315A (en) * | 2007-04-23 | 2008-10-29 | 三星电子株式会社 | Image noise reduction apparatus and method |
| CN101895685A (en) * | 2010-07-15 | 2010-11-24 | 杭州华银视讯科技有限公司 | Video capture control device and method |
| CN102348056A (en) * | 2010-07-23 | 2012-02-08 | 卡西欧计算机株式会社 | Image synthesizing device and image synthesizing method |
| CN103098456A (en) * | 2010-07-08 | 2013-05-08 | 株式会社理光 | Image processing unit, image processing method, and image processing program |
| CN103985106A (en) * | 2014-05-16 | 2014-08-13 | 三星电子（中国）研发中心 | Equipment and method used for multi-frame fusion of strong noise images |
| CN104205804A (en) * | 2012-03-30 | 2014-12-10 | 富士胶片株式会社 | Image processing device, photographing device, program, and image processing method |
| CN105513021A (en) * | 2015-11-27 | 2016-04-20 | 努比亚技术有限公司 | Image noise reduction device and method |
-
2017
- 2017-05-31 CN CN201710401502.9A patent/CN107220951A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1713730A (en) * | 2004-06-16 | 2005-12-28 | 三星电子株式会社 | Method of and apparatus for estimating noise of input image, and method and recording media of eliminating noise |
| CN101296315A (en) * | 2007-04-23 | 2008-10-29 | 三星电子株式会社 | Image noise reduction apparatus and method |
| CN103098456A (en) * | 2010-07-08 | 2013-05-08 | 株式会社理光 | Image processing unit, image processing method, and image processing program |
| CN101895685A (en) * | 2010-07-15 | 2010-11-24 | 杭州华银视讯科技有限公司 | Video capture control device and method |
| CN102348056A (en) * | 2010-07-23 | 2012-02-08 | 卡西欧计算机株式会社 | Image synthesizing device and image synthesizing method |
| CN104205804A (en) * | 2012-03-30 | 2014-12-10 | 富士胶片株式会社 | Image processing device, photographing device, program, and image processing method |
| CN103985106A (en) * | 2014-05-16 | 2014-08-13 | 三星电子（中国）研发中心 | Equipment and method used for multi-frame fusion of strong noise images |
| CN105513021A (en) * | 2015-11-27 | 2016-04-20 | 努比亚技术有限公司 | Image noise reduction device and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10825146B2 (en) | 2017-11-30 | 2020-11-03 | Guangdong Oppo Mobile Telecommunications Corp., Ltd | Method and device for image processing |
| WO2019228456A1 (en) * | 2018-05-31 | 2019-12-05 | 杭州海康威视数字技术股份有限公司 | Image processing method, apparatus and device, and machine-readable storage medium |
| CN109151323A (en) * | 2018-10-18 | 2019-01-04 | Oppo广东移动通信有限公司 | A kind of photographic method and device, terminal, storage medium |
| CN109151323B (en) * | 2018-10-18 | 2021-06-04 | Oppo广东移动通信有限公司 | Photographing method and device, terminal and storage medium |
| CN109995964A (en) * | 2019-02-21 | 2019-07-09 | 西安万像电子科技有限公司 | Image processing method and device |
| CN111917993A (en) * | 2019-05-07 | 2020-11-10 | 株式会社摩如富 | Image processing apparatus, image processing method, image capturing apparatus, and recording medium for program for image capturing apparatus |
| CN112241670A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Image processing method and device |
| CN112241670B (en) * | 2019-07-18 | 2024-03-01 | 杭州海康威视数字技术股份有限公司 | Image processing method and device |
| CN111026263A (en) * | 2019-11-26 | 2020-04-17 | 维沃移动通信有限公司 | Audio playing method and electronic equipment |
| CN111026263B (en) * | 2019-11-26 | 2021-10-15 | 维沃移动通信有限公司 | Audio playing method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220951A (en) | Facial image noise-reduction method, device, storage medium and computer equipment | |
| CN107230192A (en) | Image processing method, device, computer-readable recording medium and mobile terminal | |
| CN107731146A (en) | Brightness adjusting method and related product | |
| CN107566748A (en) | A kind of image processing method, mobile terminal and computer-readable recording medium | |
| CN107038681A (en) | Image weakening method, device, computer-readable recording medium and computer equipment | |
| CN108270919A (en) | A kind of terminal brightness adjusting method, terminal and computer readable storage medium | |
| CN107707729A (en) | A kind of terminal go out screen or bright screen method, terminal and computer-readable recording medium | |
| CN107506732A (en) | Method, equipment, mobile terminal and the computer-readable storage medium of textures | |
| CN107734260A (en) | A kind of image processing method and mobile terminal | |
| CN107483836A (en) | A kind of image pickup method and mobile terminal | |
| CN107566749A (en) | Image pickup method and mobile terminal | |
| CN107730433A (en) | One kind shooting processing method, terminal and computer-readable recording medium | |
| CN104699501B (en) | A kind of method and device for running application program | |
| CN107886321A (en) | A kind of method of payment and mobile terminal | |
| CN108172161A (en) | Display methods, mobile terminal and computer readable storage medium based on flexible screen | |
| CN108040209A (en) | A kind of image pickup method and mobile terminal | |
| CN110209332A (en) | A kind of information processing method and terminal device | |
| CN108257104A (en) | A kind of image processing method and mobile terminal | |
| CN107800879A (en) | A kind of audio regulation method, terminal and computer-readable recording medium | |
| CN108196777A (en) | A kind of flexible screen application process, equipment and computer readable storage medium | |
| CN108197206A (en) | Expression packet generation method, mobile terminal and computer readable storage medium | |
| CN107317918A (en) | Parameter setting method and related product | |
| CN107330867A (en) | Image combining method, device, computer-readable recording medium and computer equipment | |
| CN107977261A (en) | Method, equipment, mobile terminal and the computer-readable storage medium of limiting process | |
| CN108234893A (en) | A kind of brightness adjusting method, equipment and computer readable 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: 20170929 |
|
| RJ01 | Rejection of invention patent application after publication |