CN106874878A - A kind of image denoising method and terminal - Google Patents
A kind of image denoising method and terminal Download PDFInfo
- Publication number
- CN106874878A CN106874878A CN201710093193.3A CN201710093193A CN106874878A CN 106874878 A CN106874878 A CN 106874878A CN 201710093193 A CN201710093193 A CN 201710093193A CN 106874878 A CN106874878 A CN 106874878A
- Authority
- CN
- China
- Prior art keywords
- terminal
- noise reduction
- processor
- image
- frequency reducing
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011946 reduction process Methods 0.000 claims abstract description 51
- 230000009467 reduction Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of image denoising method, including：Under the shooting preview pattern of terminal, the human face region of the target image that identification imageing sensor is captured；Judge whether the processor of the terminal works in frequency reducing state；If the processor works in frequency reducing state, the human face region to the target image carries out local noise reduction process.Separately, the embodiment of the present invention also provides a kind of terminal.Described image noise-reduction method can lift noise reduction process speed of the terminal under processor frequency reducing state, and ensure the noise reduction process quality of human face region, optimize image imaging effect.
Description
Technical field
The present invention relates to field of terminal technology, more particularly to a kind of image denoising method and the application image denoising method
Terminal.
Background technology
At present, camera is configured with the portable terminals such as mobile phone, panel computer, the day of user can be met substantially
Often shoot demand.Due to the limitation of the hardware physical capability of imageing sensor, the imaging matter of image can be caused under low light environment
Amount is poor, such as brightness is low, noise is big etc..It is more when existing in image to improve image quality of the terminal under low light environment
Noise when, noise reduction process is generally carried out to whole image using noise reduction algorithm, as often as possible to remove the noise in image.So
And, when noise reduction process is carried out to whole image, required data volume to be processed can be than larger, and process time and speed are depended on
The performance of system.When system resource is nervous, temperature rise or it is low electric when, the processor of terminal can automatically switch can frequency reducing state, in drop
Under frequency state, the disposal ability of processor declines, so as to the noise reduction process time for causing image increases, it is impossible to ensure imaging speed
Degree, influence user shoots experience.
The content of the invention
The embodiment of the present invention provides a kind of image denoising method and terminal, to lift terminal under processor frequency reducing state
Noise reduction process speed, and ensure the noise reduction process quality of human face region, optimize image imaging effect.
In a first aspect, the embodiment of the present invention provides a kind of image denoising method, including：
Under the shooting preview pattern of terminal, the human face region of the target image that identification imageing sensor is captured；
Judge whether the processor of the terminal works in frequency reducing state；
If the processor works in frequency reducing state, the human face region to the target image is carried out at local noise reduction
Reason.
Second aspect, the embodiment of the present invention provides a kind of terminal, including：
Face identification unit, under the shooting preview pattern of terminal, recognizing the target figure that imageing sensor is captured
The human face region of picture；
Whether frequency reducing judging unit, the processor for judging the terminal works in frequency reducing state；
Noise reduction processing unit, under conditions of working in frequency reducing state in the processor, to the target image
Human face region carries out local noise reduction process.
Described image noise-reduction method is judging the treatment of terminal by obtaining the human face region of target image when autodyning
When device works in frequency reducing state, the human face region to the target image carries out local noise reduction process, such that it is able to lift terminal
Noise reduction process speed under processor frequency reducing state, quickening image taking speed, and ensure the noise reduction process quality of human face region, it is excellent
Change image imaging effect.Simultaneously as the data volume of noise reduction process is substantially reduced, such that it is able to reduce the temperature rise of processor, and
Reduce the power consumption of processor.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is the first pass schematic diagram of image denoising method provided in an embodiment of the present invention；
Fig. 2 is the second procedure schematic diagram of image denoising method provided in an embodiment of the present invention；
Fig. 3 is the 3rd schematic flow sheet of image denoising method provided in an embodiment of the present invention；
Fig. 4 is the 4th schematic flow sheet of image denoising method provided in an embodiment of the present invention；
Fig. 5 is the first structure schematic diagram of terminal provided in an embodiment of the present invention；
Fig. 6 is the second structural representation of terminal provided in an embodiment of the present invention；
Fig. 7 is the 3rd structural representation of terminal provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It should be appreciated that when using in this specification and in the appended claims, term " including " and "comprising" instruction
The presence of described feature, entirety, step, operation, element and/or component, but it is not precluded from one or more of the other feature, whole
The presence or addition of body, step, operation, element, component and/or its set.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, " one " and " being somebody's turn to do " is intended to include plural form.
It will be further appreciated that, the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more in the associated item listed and be possible to combination, and including these combinations.
As in this specification and in the appended claims as use, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In implementing, the terminal described in the embodiment of the present invention including but not limited to such as has touch sensitive surface
Other of the mobile phone of (for example, touch-screen display and/or touch pad), laptop computer or tablet PC etc are just
Portable device.It is to be further understood that in certain embodiments, the equipment not portable communication device, but with touching
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, describe to include the terminal of display and touch sensitive surface.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
The various application programs that can be performed in terminal can be public using at least one of such as touch sensitive surface
Physical user-interface device.Can be adjusted among applications and/or in corresponding application programs and/or changed and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch
Sensing surface) can support that there are the various application programs of user interface directly perceived and transparent for a user.
Fig. 1 is referred to, in an embodiment of the invention, there is provided a kind of image denoising method, be applied to mobile phone, flat board electricity
The portable terminals such as brain, digital camera, to lift noise reduction process speed of the terminal under processor frequency reducing state, and ensure face
The noise reduction process quality in region, optimizes image imaging effect.Described image noise-reduction method at least comprises the following steps：
Step 101：Under the shooting preview pattern of terminal, the face area of the target image that identification imageing sensor is captured
Domain；
Step 102：Judge whether the processor of the terminal works in frequency reducing state；
Step 103：If the processor works in frequency reducing state, the human face region to the target image carries out part
Noise reduction process.
Under the shooting preview pattern of terminal, terminal can capture the mesh in camera viewfinder range by imageing sensor
Logo image.When photographed scene is under low light condition, due to the limitation of the hardware physical capability of imageing sensor, mesh can be caused
There is more noise in logo image, have a strong impact on the image quality of terminal.Therefore, be lifting terminal under low light condition into
As quality, it is necessary to the target image captured to imageing sensor carries out noise reduction process.Whole target image is carried out at noise reduction
Reason needs the more processor resource of consumption, consequently, it is possible to causing the problems such as imaging time increase and serious terminal heating.Together
When, because the working frequency of the processor of terminal can be according to environmental factors such as temperature, supply voltage or system resource occupancies
Change and change, when the environmental factor for having one or more influence processor working frequencies cannot meet certain condition, treatment
Device can automatically switch to frequency reducing state, i.e., the automatic frequency for reducing processor, so as to realize self-protection.If processor is worked in
Frequency reducing state, its process performance is lowered, so as to the time required for processing same amount of data can be caused to increase.
In the present embodiment, the noise reduction process speed for lifting terminal under processor frequency reducing state, and ensure face area
The noise reduction process quality in domain, optimizes the image imaging effect of terminal, by the way that under the shooting preview pattern of terminal, identification image is passed
The human face region of the target image that sensor is captured, and then when the processor for judging terminal works in frequency reducing state, to described
The human face region of target image carries out local noise reduction process, relative to traditional scheme that noise reduction process is carried out to whole image,
So that the data volume of noise reduction process is substantially reduced, be conducive to lifting the noise reduction process speed under frequency reducing state, and ensure face area
The imaging effect in domain, image taking Consumer's Experience of the lifting terminal under processor frequency reducing state.
Fig. 2 is referred to, in one embodiment, whether the processor for judging the terminal works in frequency reducing shape
State, including：
Step 201：Obtain the operating temperature of the processor of the terminal；
Step 202：Judge the operating temperature whether higher than preset temperature threshold value；
Step 203：If the operating temperature is higher than preset temperature threshold value, confirm that the processor of the terminal works in drop
Frequency state.
Wherein, the operating temperature of processor can be obtained by obtaining the temperature data of processor.At present, the treatment of terminal
Device uses multi-core, high-frequency framework mostly, and the core number of processor operation and the running frequency of certain core are according to being
The load condition of system is determined.During the full core high-speed cruising of processor, its power consumption can also rise, so as to cause the temperature of processor
Degree can accordingly increase.When the temperature of processor reaches to a certain degree, in order to protect processor not by high temperature failure, system can be certainly
The dynamic running frequency for reducing processor, one or more cores for example closed in multi-core processor switch processor
It is frequency reducing state, the operation power consumption and temperature of processor is reduced so as to reach.It is appreciated that due to the reduction meeting of processor frequencies
Causing the time required for processing identical data volume accordingly increases, so as to cause system running speed slack-off.
In the present embodiment, terminal can be under shooting preview pattern, the operating temperature of real-time monitoring processor, if monitoring
Operating temperature to processor is higher than preset temperature threshold value (such as 50 degrees Celsius), then confirm that processor works in frequency reducing state.
Now, terminal is carried out at human face region part noise reduction according to the human face region recognized under preview mode to the target image
Reason, so as to ensure target image anti-acoustic capability and image taking speed of the terminal under processor frequency reducing state.
Fig. 3 is referred to, in one embodiment, whether the processor for judging the terminal works in frequency reducing shape
State, including：
Step 301：Obtain the dump energy of the battery of the terminal；
Step 302：Judge the dump energy whether less than default power threshold；
Step 303：If the dump energy is less than default power threshold, confirm that the processor of the terminal works in drop
Frequency state.
At present, due to terminal screen size is larger and it is processor core increase, cause electricity in the running of terminal
Pond electric quantity consumption is very fast.When the dump energy of battery is less than default power threshold, to ensure the normal operation of terminal, lifting is continuous
Boat ability, usual system can automatically switch to battery saving mode, in a power-save mode, terminal can by reduce processor frequencies,
The modes such as screen intensity reduce the power consumption of terminal.When under processor work is for frequency reducing state, its disposal ability is limited, so that
So that the time required for treatment identical data volume accordingly increases, so as to cause system running speed slack-off.
In the present embodiment, terminal can be under shooting preview pattern, the dump energy of real-time monitoring battery, if monitoring
The dump energy of battery is less than default power threshold (such as the 15% of battery rated capacity), then confirm the processor work of terminal
In frequency reducing state.Now, terminal carries out human face region according to the human face region recognized under preview mode to the target image
Local noise reduction process, so as to ensure target image anti-acoustic capability and image taking speed of the terminal under processor frequency reducing state.
It is appreciated that whether the processor for judging the terminal works in frequency reducing state being not limited to by monitoring
The dump energy of the operating temperature or battery of managing device realizes, can with the real-time working frequency of processor described in direct access,
And compare the real-time working frequency with the rated operation frequency of processor, if the real-time working frequency of processor is less than specified frequency
Rate, then can confirm that processor works in frequency reducing state.
Fig. 4 is referred to, in one embodiment, the face area of the target image that the identification imageing sensor is captured
Domain, including：
Step 401：The target image is continuously reduced according to pre-set zoom ratio, multiple various sizes of figures are generated
Picture；
Step 402：The image of each size is divided into several size identical subwindows, and by all sizes
The default human-face detector of subwindow input of image；Whether the default human-face detector is used for judging each described subwindow
It is human face region；
Step 403：According to the output of the default human-face detector, the human face region of the target image is determined.
Specifically, it is assumed that the initial proportion of the target image is 1, and the pre-set zoom ratio is 0.9, then according to 0.9
Scaling, the target image is reduced successively, generate multiple various sizes of images, and then by each size
Image be divided into several size identical subwindows.In the present embodiment, the size of the subwindow can be 20 × 20
Pixel.The human-face detector is as training sample, by Ha Er using thousands of face pictures and up to ten thousand background pictures
Feature (Haar-like features) is extracted and Adaboost (Adaptive Boosting, self adaptation enhancing) machine learning
What Algorithm for Training was obtained.
Wherein, it is a kind of digital picture feature for object identification that Lis Hartel is levied, and Lis Hartel is levied using in detection window
Two adjacent rectangles of specified location, calculate each rectangle pixel and, and take two differences of the pixel sum of rectangle.Then
This difference threshold value precalculated with is compared, target and non-target area are separated.For example, currently having one
Individual face image set, by observation it can be found that eye color than two cheeks depth, therefore, for the Kazakhstan of Face datection
You are characterized in two adjacent rectangles for being individually positioned in eyes and cheek, by calculate the two adjacent rectangles pixel and between
Difference, and the difference and predetermined threshold value are compared, so as to judge to be detected whether region is human face region.
Adaboost machine learning algorithms are a kind of iterative algorithms, a new Weak Classifier are added in each round, directly
Reach certain predetermined sufficiently small error rate.Each training sample is endowed a weight, shows it by certain point
Class device is selected into the probability of training set.If certain sample point is classified exactly, then under construction in a training set,
Its selected probability is just lowered；If conversely, certain sample point is not classified exactly, then its weight is just obtained
Improve.By such mode, AdaBoost methods " can be focused on " on those the more difficult point sample of (richer information).Specific
In realization, initially make the weight of each sample equal, for kth time iterative operation, sample can be chosen according to these weights
This point, and then train grader Ck.Then improved according to this grader by the weight of the sample of its misclassification, and reduce quilt
The sample weights of correct classification.Then, the updated sample set of weight be used to train next grader Ck.Entirely trained
Journey is so made iteratively down.
In the present embodiment, the default human-face detector can build in the following way：
Represent facial image using Harr-like rectangular characteristics, realized using integrogram rectangular characteristic pixel sum it is fast
Speed is calculated；Wherein, integrogram is a look-up table for two-dimensional rectangle, has a same size with original image, integrogram it is every
One element be original image in correspondence position upper left corner all pixels and；
Using Adaboost machine learning algorithms pick out part can most represent face Harr-like rectangular characteristics it is (weak
Grader), Weak Classifier is configured to a strong classifier according to the mode of weighting；
The some strong classifiers for obtaining will be trained to be composed in series a cascade filtering for cascade structure, the cascade structure
Cascade filtering is the default human-face detector.It is appreciated that the inspection of grader can be effectively improved using cascade structure
Degree of testing the speed.
In one embodiment, the human face region to the target image carries out local noise reduction process, including：
Using the human face region as the noise reduction process region of the target image, and extracted from the target image
The view data in the noise reduction process region；
Call default noise reduction process program carries out noise reduction process to the view data in the noise reduction process region.
It is appreciated that the purpose of noise reduction process is to improve target image, solution causes target image due to noise jamming
The problem of Quality Down.The noise included in target image can include but is not limited to additive noise, multiplicative noise, quantization and make an uproar
Sound, " spiced salt " noise etc..The default noise reduction process program can be prepared in advance good according to specific image noise reduction algorithm
Program module, it can be called by the camera application program of the terminal, to realize that the image photographed to camera carries out noise reduction
Treatment.Wherein, the image noise reduction algorithm that the default noise reduction process program is used can be but not limited to based in spatial domain
Value filtering algorithm, the wavelet threshold denoising algorithm based on wavelet field, based on PDE (Partial Differential
Equation, partial differential equation) Image denoising algorithm, full variation Image denoising algorithm etc..
Fig. 5 is referred to, in an embodiment of the invention, there is provided a kind of terminal 50, including：
Face identification unit 51, under the shooting preview pattern of terminal, recognizing the target that imageing sensor is captured
The human face region of image；
Whether frequency reducing judging unit 53, the processor for judging the terminal works in frequency reducing state；
Noise reduction processing unit 55, under conditions of working in frequency reducing state in the processor, to the target image
Human face region carry out local noise reduction process.
In one embodiment, the face identification unit 51 includes：
Image scaling unit 511, for the target image continuously to be reduced according to pre-set zoom ratio, generates multiple not
With the image of size；
Image detecting element 513, for the image of each size to be divided into several size identical subwindows, and
By the default human-face detector of subwindow input of the image of all sizes；The default human-face detector is used to judge each institute
State whether subwindow is human face region；
Face determining unit 515, for the output according to the default human-face detector, determines the people of the target image
Face region.
In one embodiment, the frequency reducing judging unit 53 includes：
Temperature acquiring unit 531, the operating temperature of the processor for obtaining the terminal；
Temperature judging unit 533, for judging the operating temperature whether higher than preset temperature threshold value；
Frequency reducing confirmation unit 535, under conditions of being higher than preset temperature threshold value in the operating temperature, judges the end
The processor at end works in frequency reducing state.
In one embodiment, the noise reduction processing unit 55 includes：
Noise reduction area determination unit 551, for using the human face region as the noise reduction process region of the target image,
And the view data in the noise reduction process region is extracted from the target image；
Noise reduction program call unit 553, for calling default noise reduction process program to the image in the noise reduction process region
Data carry out noise reduction process.
Fig. 6 is referred to, in one embodiment, the frequency reducing judging unit 53 includes：
Electricity acquiring unit 532, the dump energy of the battery for obtaining the terminal；
Electricity judging unit 534, for judging the dump energy whether less than default power threshold；
Frequency reducing confirmation unit 536, for being less than under conditions of default power threshold in the dump energy, confirms the end
The processor at end works in frequency reducing state.
It is appreciated that the function of each unit of the terminal 50 and its implement can also referring to figs. 1 to shown in Fig. 4 side
Associated description in method embodiment, here is omitted.
Fig. 7 is referred to, in an embodiment of the invention, there is provided a kind of terminal 70, including：
At least one input equipment 701；At least one output equipment 702；At least one processor 703, such as CPU；With
Memory 704, the input equipment 701, output equipment 702, processor 703 and memory 704 are connected by bus 705.
Wherein, the input equipment 701 concretely physical button, contact panel or mouse.
The concretely display screen of the output equipment 702.
The memory 704 can be high-speed RAM memory, or non-labile memory (non-volatile
Memory), such as magnetic disk storage.The memory 704 is used to store one group of executable program code, the processor 703
For calling the executable program code stored in the memory 704, and perform following operation：
Under the shooting preview pattern of terminal, the human face region of the target image that identification imageing sensor is captured；
Judge whether the processor of the terminal works in frequency reducing state；
If the processor works in frequency reducing state, the human face region to the target image is carried out at local noise reduction
Reason.
In one embodiment, whether the processor for judging the terminal works in frequency reducing state, including：
Obtain the operating temperature of the processor of the terminal；
Judge the operating temperature whether higher than preset temperature threshold value；
If the operating temperature is higher than preset temperature threshold value, confirm that the processor of the terminal works in frequency reducing state.
In one embodiment, whether the processor for judging the terminal works in frequency reducing state, including：
Obtain the dump energy of the battery of the terminal；
Judge the dump energy whether less than default power threshold；
If the dump energy is less than default power threshold, confirm that the processor of the terminal works in frequency reducing state.
In one embodiment, the human face region of the target image that the identification imageing sensor is captured, including：
The target image is continuously reduced according to pre-set zoom ratio, multiple various sizes of images are generated；
The image of each size is divided into several size identical subwindows, and by the son of the image of all sizes
The default human-face detector of window input；The default human-face detector is used to judge whether each described subwindow is face area
Domain；
According to the output of the default human-face detector, the human face region of the target image is determined.
In one embodiment, the human face region to the target image carries out local noise reduction process, including：
Using the human face region as the noise reduction process region of the target image, and extracted from the target image
The view data in the noise reduction process region；
Call default noise reduction process program carries out noise reduction process to the view data in the noise reduction process region.
It is appreciated that the processor 703 described in the embodiment of the present invention can perform method shown in Fig. 1 to Fig. 4 of the present invention
Implementation described in embodiment, also can perform the realization side described in terminal embodiment shown in Fig. 5 to Fig. 6 of the present invention
Formula, specifically can refer to the associated description in Fig. 1 to embodiment illustrated in fig. 6, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed terminal and method, can be by it
Its mode is realized.For example, terminal embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed phase
Coupling or direct-coupling or communication connection between mutually can be INDIRECT COUPLING or the communication by some interfaces, device or unit
Connection, or electricity, machinery or other forms connections.
Step in present invention method can according to actual needs carry out order adjustment, merge and delete.
Unit in embodiment of the present invention terminal can according to actual needs be merged, divides and deleted.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize embodiment of the present invention scheme
Purpose.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or use
When, can store in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part for being contributed to prior art in other words, or all or part of the technical scheme can be in the form of software product
Embody, the computer software product is stored in a storage medium, including some instructions are used to so that a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the invention
Portion or part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, specific embodiment only of the invention, but protection scope of the present invention is not limited thereto, and it is any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or replacement should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (10)
1. a kind of image denoising method, it is characterised in that including：
Under the shooting preview pattern of terminal, the human face region of the target image that identification imageing sensor is captured；
Judge whether the processor of the terminal works in frequency reducing state；
If the processor works in frequency reducing state, the human face region to the target image carries out local noise reduction process.
2. the method for claim 1, it is characterised in that whether the processor for judging the terminal works in frequency reducing
State, including：
Obtain the operating temperature of the processor of the terminal；
Judge the operating temperature whether higher than preset temperature threshold value；
If the operating temperature is higher than preset temperature threshold value, confirm that the processor of the terminal works in frequency reducing state.
3. the method for claim 1, it is characterised in that whether the processor for judging the terminal works in frequency reducing
State, including：
Obtain the dump energy of the battery of the terminal；
Judge the dump energy whether less than default power threshold；
If the dump energy is less than default power threshold, confirm that the processor of the terminal works in frequency reducing state.
4. the method as described in any one of claims 1 to 3, it is characterised in that the mesh that the identification imageing sensor is captured
The human face region of logo image, including：
The target image is continuously reduced according to pre-set zoom ratio, multiple various sizes of images are generated；
The image of each size is divided into several size identical subwindows, and by the subwindow of the image of all sizes
The default human-face detector of input；The default human-face detector is used to judge whether each described subwindow is human face region；
According to the output of the default human-face detector, the human face region of the target image is determined.
5. the method as described in any one of claims 1 to 3, it is characterised in that the human face region to the target image
Local noise reduction process is carried out, including：
Using the human face region as the noise reduction process region of the target image, and extracted from the target image described
The view data in noise reduction process region；
Call default noise reduction process program carries out noise reduction process to the view data in the noise reduction process region.
6. a kind of terminal, it is characterised in that including：
Face identification unit, under the shooting preview pattern of terminal, recognizing the target image that imageing sensor is captured
Human face region；
Whether frequency reducing judging unit, the processor for judging the terminal works in frequency reducing state；
Noise reduction processing unit, under conditions of working in frequency reducing state in the processor, to the face of the target image
Region carries out local noise reduction process.
7. terminal as claimed in claim 6, it is characterised in that the frequency reducing judging unit includes：
Temperature acquiring unit, the operating temperature of the processor for obtaining the terminal；
Temperature judging unit, for judging the operating temperature whether higher than preset temperature threshold value；
Frequency reducing confirmation unit, under conditions of being higher than preset temperature threshold value in the operating temperature, judges the place of the terminal
Reason device works in frequency reducing state.
8. terminal as claimed in claim 6, it is characterised in that the frequency reducing judging unit includes：
Electricity acquiring unit, the dump energy of the battery for obtaining the terminal；
Electricity judging unit, for judging the dump energy whether less than default power threshold；
Frequency reducing confirmation unit, for being less than under conditions of default power threshold in the dump energy, confirms the place of the terminal
Reason device works in frequency reducing state.
9. the terminal as described in any one of claim 6 to 8, it is characterised in that the face identification unit includes：
Image scaling unit, for the target image continuously to be reduced according to pre-set zoom ratio, generates multiple different sizes
Image；
Image detecting element, for the image of each size to be divided into several size identical subwindows, and will be all
The default human-face detector of subwindow input of the image of size；The default human-face detector is used to judge each described sub- window
Whether mouth is human face region；
Face determining unit, for the output according to the default human-face detector, determines the human face region of the target image.
10. the terminal as described in any one of claim 6 to 8, it is characterised in that the noise reduction processing unit includes：
Noise reduction area determination unit, for using the human face region as the noise reduction process region of the target image, and from institute
State the view data that the noise reduction process region is extracted in target image；
Noise reduction program call unit, for calling default noise reduction process program to carry out the view data in the noise reduction process region
Noise reduction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710093193.3A CN106874878A (en) | 2017-02-21 | 2017-02-21 | A kind of image denoising method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710093193.3A CN106874878A (en) | 2017-02-21 | 2017-02-21 | A kind of image denoising method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106874878A true CN106874878A (en) | 2017-06-20 |
Family
ID=59166916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710093193.3A Withdrawn CN106874878A (en) | 2017-02-21 | 2017-02-21 | A kind of image denoising method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106874878A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476741A (en) * | 2020-04-28 | 2020-07-31 | 北京金山云网络技术有限公司 | Image denoising method and device, electronic equipment and computer readable medium |
| CN111507358A (en) * | 2020-04-01 | 2020-08-07 | 浙江大华技术股份有限公司 | Method, device, equipment and medium for processing face image |
-
2017
- 2017-02-21 CN CN201710093193.3A patent/CN106874878A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507358A (en) * | 2020-04-01 | 2020-08-07 | 浙江大华技术股份有限公司 | Method, device, equipment and medium for processing face image |
| CN111507358B (en) * | 2020-04-01 | 2023-05-16 | 浙江大华技术股份有限公司 | Face image processing method, device, equipment and medium |
| CN111476741A (en) * | 2020-04-28 | 2020-07-31 | 北京金山云网络技术有限公司 | Image denoising method and device, electronic equipment and computer readable medium |
| CN111476741B (en) * | 2020-04-28 | 2024-02-02 | 北京金山云网络技术有限公司 | Image denoising method, image denoising device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816663B (en) | Image processing method, device and equipment | |
| US20200372692A1 (en) | Method and apparatus for generating cartoon face image, and computer storage medium | |
| WO2020140986A1 (en) | Image denoising method and apparatus, storage medium and terminal | |
| CN109961453B (en) | Image processing method, device and equipment | |
| CN107423699B (en) | Biopsy method and Related product | |
| CN103098078B (en) | Smile's detecting system and method | |
| CN107172345A (en) | A kind of image processing method and terminal | |
| CN104182721A (en) | Image processing system and image processing method capable of improving face identification rate | |
| CN102956029B (en) | Image processing apparatus and image processing method | |
| WO2019011098A1 (en) | Unlocking control method and relevant product | |
| CN105516585A (en) | Apparatus and method for automatically regulating skin colors | |
| CN106774796A (en) | A kind of screen lighting method and terminal | |
| CN109752870A (en) | Electrophoresis electronic paper ghost detection system and detection method | |
| CN111612723B (en) | Image restoration method and device | |
| CN106874878A (en) | A kind of image denoising method and terminal | |
| CN106600524A (en) | Image processing method and terminal | |
| WO2015196681A1 (en) | Picture processing method and electronic device | |
| CN109672829B (en) | Image brightness adjusting method and device, storage medium and terminal | |
| CN110473156A (en) | Processing method, device, storage medium and the electronic equipment of image information | |
| WO2023001110A1 (en) | Neural network training method and apparatus, and electronic device | |
| CN115525188A (en) | Shooting method and electronic equipment | |
| CN111476740A (en) | Image processing method, image processing apparatus, storage medium, and electronic device | |
| Subramanian et al. | Fuzzy logic based content protection for image resizing by seam carving | |
| CN107026976A (en) | A kind of image processing method and terminal | |
| RU2791810C2 (en) | Method, equipment and device for image processing |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170620 |
|
| WW01 | Invention patent application withdrawn after publication |