CN110213462A - Image processing method, device, electronic equipment and image processing circuit - Google Patents
Image processing method, device, electronic equipment and image processing circuit Download PDFInfo
- Publication number
- CN110213462A CN110213462A CN201910509584.8A CN201910509584A CN110213462A CN 110213462 A CN110213462 A CN 110213462A CN 201910509584 A CN201910509584 A CN 201910509584A CN 110213462 A CN110213462 A CN 110213462A
- Authority
- CN
- China
- Prior art keywords
- image
- region
- noise reduction
- noise
- image processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 39
- 238000003672 processing method Methods 0.000 title claims abstract description 26
- 230000009467 reduction Effects 0.000 claims abstract description 90
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000015654 memory Effects 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 25
- 238000003384 imaging method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 239000000872 buffer Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000005622 photoelectricity Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000001228 spectrum Methods 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/81—Camera processing pipelines; Components thereof for suppressing or minimising disturbance in the image signal generation
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The application proposes a kind of image processing method, device, electronic equipment and image processing circuit, and this method includes obtaining original image；In conjunction with default feature, original image is divided to obtain multiple images region, each image-region, the characteristic value difference based on default feature；It is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise-reduced image.The noise characteristic of each image characteristic region in image can be accurately identified by the application, realizes and characteristics of image is combined to carry out targetedly noise reduction, promote noise reduction effect.
Description
Technical field
This application involves technical field of image processing more particularly to a kind of image processing method, device, electronic equipment and figures
As processing circuit.
Background technique
Image noise reduction, artificial intelligence are carried out in the artificial intelligence noise reduction model that image noise reduction field is generally basede on deep learning
Noise reduction model can carry out characteristic identification to the noise in image, use corresponding noise reduction mode according to the noise characteristic identified
Noise reduction is carried out to image, that is, noise reduction process is carried out using same artificial intelligence noise reduction model to same image.
Under this mode, the noise characteristic of each image characteristic region in image can not be recognized accurately, noise reduction does not have
Targetedly, noise reduction effect is bad.
Summary of the invention
The application is intended to solve at least some of the technical problems in related technologies.
For this purpose, the purpose of the application is to propose a kind of image processing method, device, electronic equipment and image procossing electricity
Road can accurately identify the noise characteristic of each image characteristic region in image, realize and characteristics of image is combined to be directed to
Property noise reduction, promoted noise reduction effect.
In order to achieve the above objectives, the image processing method that the application first aspect embodiment proposes, comprising: obtain original graph
Picture；In conjunction with default feature, the original image is divided to obtain multiple images region, each described image region is based on institute
The characteristic value for stating default feature is different；It is based respectively on artificial intelligence noise reduction for each described image region, to obtain target noise reduction
Image.
The image processing method that the application first aspect embodiment proposes by obtaining original image, and combines default spy
Sign divides original image to obtain multiple images region, and each image-region, the characteristic value based on default feature is different, with
And it is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise-reduced image, it can accurately identify image
In each image characteristic region noise characteristic, realize and characteristics of image combined to carry out targetedly noise reduction, promote noise reduction effect.
In order to achieve the above objectives, the image processing apparatus that the application second aspect embodiment proposes, comprising: module is obtained,
For obtaining original image；Division module is divided to obtain multiple images for combining default feature to the original image
Region, each described image region, the characteristic value based on the default feature are different；Noise reduction module, for being directed to each described image
Region is based respectively on artificial intelligence noise reduction, to obtain target noise-reduced image.
The image processing apparatus that the application second aspect embodiment proposes by obtaining original image, and combines default spy
Sign divides original image to obtain multiple images region, and each image-region, the characteristic value based on default feature is different, with
And it is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise-reduced image, it can accurately identify image
In each image characteristic region noise characteristic, realize and characteristics of image combined to carry out targetedly noise reduction, promote noise reduction effect.
In order to achieve the above objectives, the electronic equipment that the application third aspect embodiment proposes, comprising: imaging sensor is deposited
Reservoir, processor and storage are on a memory and the computer program that can run on a processor, described image sensor and institute
Processor electrical connection is stated, when the processor executes described program, at the image that realization the application first aspect embodiment proposes
Reason method.
The electronic equipment that the application third aspect embodiment proposes by obtaining original image, and combines default feature, right
Original image is divided to obtain multiple images region, and each image-region, the characteristic value based on default feature is different, and is directed to
Each image-region is based respectively on artificial intelligence noise reduction, to obtain target noise-reduced image, can accurately identify each in image
The noise characteristic of image characteristic region is realized and characteristics of image is combined to carry out targetedly noise reduction, and noise reduction effect is promoted.
In order to achieve the above objectives, the image processing circuit that the application fourth aspect embodiment proposes, comprising: believe including image
Number processing ISP processor and graphics processor GPU；The ISP processor, is electrically connected with imaging sensor, described for controlling
Imaging sensor obtains original image；The GPU is electrically connected with the ISP processor, for combining default feature, to described
Original image is divided to obtain multiple images region, each described image region, the characteristic value difference based on the default feature；
It is based respectively on artificial intelligence noise reduction for each described image region, to obtain target noise-reduced image.
The image processing circuit that the application fourth aspect embodiment proposes by obtaining original image, and combines default spy
Sign divides original image to obtain multiple images region, and each image-region, the characteristic value based on default feature is different, with
And it is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise-reduced image, it can accurately identify image
In each image characteristic region noise characteristic, realize and characteristics of image combined to carry out targetedly noise reduction, promote noise reduction effect.
In order to achieve the above objectives, the computer readable storage medium that the 5th aspect embodiment of the application proposes, stores thereon
There is computer program, the image processing method proposed such as the application first aspect embodiment is realized when which is executed by processor
Method.
The computer readable storage medium that the 5th aspect embodiment of the application proposes by obtaining original image, and combines
Default feature, divides original image to obtain multiple images region, each image-region, the characteristic value based on default feature is not
Together, and for each image-region it is based respectively on artificial intelligence noise reduction, to obtain target noise-reduced image, can accurately identified
The noise characteristic of each image characteristic region in image is realized and characteristics of image is combined to carry out targetedly noise reduction, and noise reduction effect is promoted
Fruit.
The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow diagram for the image processing method that one embodiment of the application proposes；
Fig. 2 is that image divides schematic diagram in the embodiment of the present application；
Fig. 3 is the flow diagram for the image processing method that another embodiment of the application proposes；
Fig. 4 is the structural schematic diagram for the image processing apparatus that one embodiment of the application proposes；
Fig. 5 is the structural schematic diagram for the image processing apparatus that another embodiment of the application proposes；
Fig. 6 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application；
Fig. 7 is the principle exemplary diagram of a kind of electronic equipment provided by the embodiments of the present application；
Fig. 8 is a kind of schematic illustration of image processing circuit provided by the embodiments of the present application.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and should not be understood as the limitation to the application.On the contrary, this
The embodiment of application includes all changes fallen within the scope of the spiritual and intension of attached claims, modification and is equal
Object.
In order to solve to be recognized accurately the noise characteristic of each image characteristic region in image in the related technology, drop
It makes an uproar and does not have specific aim, the bad technical problem of noise reduction effect, the embodiment of the present application provides a kind of image processing method, by obtaining
Original image is taken, and combines default feature, original image is divided to obtain multiple images region, each image-region is based on
The characteristic value of default feature is different, and is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise reduction figure
Picture can accurately identify the noise characteristic of each image characteristic region in image, realize and characteristics of image is combined to be directed to
Property noise reduction, promoted noise reduction effect.
Fig. 1 is the flow diagram for the image processing method that one embodiment of the application proposes.
The image processing method based on multiple image of the embodiment of the present application is applied to electronic equipment, which can
Think that there is the hardware of various operating systems, imaging device to set for mobile phone, tablet computer, personal digital assistant, wearable device etc.
It is standby.
Referring to Fig. 1, this method comprises:
S101: original image is obtained.
Wherein, original image for example can not do any processing by what the imaging sensor of electronic equipment collected
RAW format-pattern, with no restriction to this.
Wherein, RAW format-pattern is exactly that the light signal captured is converted the original of digital signal by imaging sensor
Image.RAW format-pattern has recorded the raw information of digital camera sensor, while having recorded one caused by camera shooting
A little metadata, such as the setting of sensitivity, shutter speed, f-number, white balance.
It can be by the preview image of acquisition present filming scene, to determine whether present filming scene belongs to night scene field
Scape.Since ambient brightness value is different under different scenes, preview image content is not also identical, can be according to present filming scene preview
The ambient brightness value in the image content of image and each region after determining that present filming scene belongs to night scene scene, starts night scene
Screening-mode obtains original image.
For example, the image content of preview image includes night sky perhaps each area of night scene lamp source etc. or preview image
Ambient brightness value meets the Luminance Distribution characteristic of image under night scene environment in domain, that is, can determine that present filming scene belongs to night scene field
Scape.
S102: in conjunction with default feature, original image is divided to obtain multiple images region, each image-region is based on
The characteristic value of default feature is different.
Optionally, default feature can be, for example, the characteristics of image such as picture contrast, sensitivity, white balance.
And it is brightness of image that feature is preset in the embodiment of the present application, realizes and brightness of image is combined to carry out targetedly noise reduction,
Since the general noise characteristic of image-region with different brightness differs greatly, it can relatively significantly promote drop
It makes an uproar effect, promotes user experience degree.
Optionally, the characteristic value based on default feature of image-region is that the brightness of whole pixels in image-region is equal
Value, or, or the brightness variance yields of pixel, algorithm in the image-region being calculated based on common statistic algorithm
It realizes simply, as a result precisely, and reduces the operation power consumption of electronic equipment as much as possible.
During specific execute, the brightness value of wherein each pixel can be counted for original image, it will be each
The brightness value of the brightness value of pixel is compared with preset first luminance threshold and the second luminance threshold, wherein the first brightness
Threshold value less than the second luminance threshold, according to compare it is obtaining as a result, by original image be divided into bright area, bright dark transitional region,
Dark areas, referring to fig. 2, Fig. 2 are that image divides schematic diagram in the embodiment of the present application, the luminance mean value of whole pixels in bright area
More than or equal to the second luminance threshold, the luminance mean values of whole pixels of bright dark transitional region less than the second luminance threshold,
And it is more than or equal to the first luminance threshold, the luminance mean value of whole pixels is less than the first luminance threshold in dark areas.
In further embodiments, some other image partitioning algorithms are also based on, multiple figures are divided an image into
As region, and make each image-region, the characteristic value based on default feature is different, with no restriction to this.
S103: being based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise-reduced image.
Due to the imaging sensor in electronic equipment will receive during shooting it is different degrees of from peripheral circuit
Photoelectricity magnetic disturbance between pixel itself, therefore inevitably there is noise in the original image that shooting obtains, also, interfere journey
The difference of degree, the clarity of the image shot be not also identical.Therefore the original image of acquisition also certainly exists noise, can be with
It is based respectively on artificial intelligence noise reduction further directed to each image-region, to obtain target noise-reduced image.
Optionally, in some embodiments, referring to Fig. 3, artificial intelligence noise reduction is based respectively on for each image-region, comprising:
S301: using neural network model, in conjunction with the corresponding characteristic value of each image-region, carries out noise to each image-region
Characteristic identification；Wherein, neural network model has learnt to obtain the mapping between the characteristic value and noise characteristic of each image-region and has closed
System.
Optionally, neural network model is to be trained using the sample image of each characteristic value to neural network model, directly
When the noise characteristic identified to neural network model and the noise characteristic marked in respective sample image match, neural network mould
Type training is completed.
As a kind of possible implementation, due to neural network model learnt to obtain the characteristic value of each image-region with
Mapping relations between noise characteristic.Therefore, each image-region can be inputted in neural network model respectively, using nerve
Network model carries out noise characteristic identification to each image-region respectively, to identify that noise corresponding with each image-region is special
Property, to achieve the purpose that specific aim noise reduction, noise reduction effect is improved, and utmostly reduce the power consumption of noise reduction.
Certainly, neural network model is only a kind of possible implementation for realizing the noise reduction based on artificial intelligence,
In practical implementation, the noise reduction based on artificial intelligence can be realized by other any possible modes, for example, can be with
It is realized using traditional programming technique (simulation and ergonomic method), it for another example, can also be using genetic algorithm and artificial
The method of neural network is realized.
S302: according to the noise characteristic identified, to each image-region noise reduction.
In the embodiment of the present application, noise characteristic can be the statistical property of the random noise due to caused by imaging sensor.
Noise said herein mainly includes thermal noise and shot noise, wherein thermal noise meets Gaussian Profile, and shot noise meets Poisson
It is distributed, the statistical property in the embodiment of the present application can refer to the variance yields of noise, naturally it is also possible to it is the value of other possible situations,
It is not limited here.
In the embodiment of the present application, it can also will be dropped after each image-region noise reduction according to the noise characteristic identified
The image-region made an uproar is synthesized as target noise reduction region, and to each target noise reduction region, obtains target noise-reduced image.
Wherein, the region obtained to each image-region noise reduction can be referred to as target noise reduction region, target noise reduction region
Quantity is identical as the above-mentioned quantity for being divided to obtain image-region to original image.
During specific execute, each target noise reduction region can be synthesized based on stitching algorithm, obtain target
Noise-reduced image, with no restriction to this.
In the present embodiment, by obtaining original image, and default feature is combined, original image is divided to obtain multiple
Image-region, each image-region, the characteristic value based on default feature is different, and is based respectively on artificial intelligence for each image-region
Energy noise reduction can accurately identify the noise characteristic of each image characteristic region in image to obtain target noise-reduced image, real
Targetedly noise reduction is carried out now in conjunction with characteristics of image, promotes noise reduction effect.
Fig. 4 is the structural schematic diagram for the image processing apparatus that one embodiment of the application proposes.
Referring to fig. 4, which includes:
Module 401 is obtained, for obtaining original image；
Division module 402 divides original image to obtain multiple images region, each figure for combining default feature
As region, the characteristic value based on default feature is different；
Noise reduction module 403, for being based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise reduction figure
Picture.
Optionally, in some embodiments, noise reduction module 403 is specifically used for:
Using neural network model, in conjunction with the corresponding characteristic value of each image-region, noise characteristic is carried out to each image-region
Identification；Wherein, neural network model has learnt to obtain the mapping relations between the characteristic value and noise characteristic of each image-region；
According to the noise characteristic identified, to each image-region noise reduction.
Optionally, in some embodiments, neural network model is the sample image using each characteristic value to neural network mould
Type is trained, until the noise characteristic marked in noise characteristic and respective sample image that neural network model identifies matches
When, neural network model training is completed.
Optionally, in some embodiments, referring to Fig. 5, further includes:
Synthesis module 404, the image-region for obtaining noise reduction is as target noise reduction region, and to each target noise reduction area
Domain is synthesized, and target noise-reduced image is obtained.
Optionally, in some embodiments, presetting feature is brightness of image.
Optionally, in some embodiments, the characteristic value based on default feature of image-region is whole pictures in image-region
The luminance mean value of vegetarian refreshments.
It should be noted that the aforementioned image for being also applied for the embodiment to the explanation of image processing method embodiment
Processing unit 400, details are not described herein again.
In the present embodiment, by obtaining original image, and default feature is combined, original image is divided to obtain multiple
Image-region, each image-region, the characteristic value based on default feature is different, and is based respectively on artificial intelligence for each image-region
Energy noise reduction can accurately identify the noise characteristic of each image characteristic region in image to obtain target noise-reduced image, real
Targetedly noise reduction is carried out now in conjunction with characteristics of image, promotes noise reduction effect.
In order to realize above-described embodiment, the application also proposes a kind of electronic equipment 200, is that the application is real referring to Fig. 6, Fig. 6
Apply the structural schematic diagram of a kind of electronic equipment of example offer, comprising: imaging sensor 210, memory 230, processor 220 and deposit
The computer program that can be run on memory 230 and on processor 220 is stored up, imaging sensor 210 is electrically connected with processor 220
It connects, when processor 220 executes program, realizes above-mentioned image processing method.
As a kind of possible situation, processor 220 may include: image signal process ISP processor.
Wherein, ISP processor obtains original image for controlling imaging sensor.
As alternatively possible situation, processor 220 can also include: the graphics processor connecting with ISP processor
(Graphics Processing Unit, abbreviation GPU).
Wherein, GPU is used to combine default feature, is divided to obtain multiple images region, each image district to original image
Domain, the characteristic value based on default feature are different；It is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise reduction
Image.
As an example, it referring to Fig. 7, on the basis of Fig. 6 electronic equipment, is provided in Fig. 7 for the embodiment of the present application
A kind of electronic equipment principle exemplary diagram.The memory 230 of electronic equipment 200 includes nonvolatile memory 60, interior storage
Device 62 and processor 220.Computer-readable instruction is stored in memory 230.When computer-readable instruction is stored by execution,
So that processor 220 executes the image processing method of any of the above-described embodiment.
As shown in fig. 7, the electronic equipment 200 includes the processor 220 connected by system bus 61, non-volatile memories
Device 60, built-in storage 62, display screen 63 and input unit 64.Wherein, the nonvolatile memory 60 of electronic equipment 200 is stored with
Operating system and computer-readable instruction.The computer-readable instruction can be executed by processor 220, to realize the application embodiment party
The image processing method of formula.The processor 220 supports the operation of entire electronic equipment 200 for providing calculating and control ability.
The built-in storage 62 of electronic equipment 200 provides environment for the operation of the computer-readable instruction in nonvolatile memory 60.Electricity
The display screen 63 of sub- equipment 200 can be liquid crystal display or electric ink display screen etc., and input unit 64 can be display
The touch layer that covers on screen 63, is also possible to key, trace ball or the Trackpad being arranged on 200 shell of electronic equipment, can also be with
It is external keyboard, Trackpad or mouse etc..The electronic equipment 200 can be mobile phone, tablet computer, laptop, individual
Digital assistants or wearable device (such as Intelligent bracelet, smartwatch, intelligent helmet, intelligent glasses) etc..
It will be understood by those skilled in the art that structure shown in Fig. 7, only part relevant to application scheme is tied
The schematic diagram of structure does not constitute the restriction for the electronic equipment 200 being applied thereon to application scheme, specific electronic equipment
200 may include perhaps combining certain components or with different component cloth than more or fewer components as shown in the figure
It sets.
In order to realize above-described embodiment, the application also proposes a kind of image processing circuit, referring to Fig. 8, Fig. 8 is the application
The schematic illustration for a kind of image processing circuit that embodiment provides, as shown in figure 8, image processing circuit 70 includes picture signal
Handle ISP processor 71 (ISP processor 71 is used as processor 220) and graphics processor GPU.
ISP processor, is electrically connected with imaging sensor, obtains original image for controlling imaging sensor；
GPU is electrically connected with ISP processor, for combining default feature, is divided to obtain multiple images to original image
Region, each image-region, the characteristic value based on default feature are different；It is based respectively on artificial intelligence noise reduction for each image-region,
To obtain target noise-reduced image.
The image data that camera 73 captures is handled by ISP processor 71 first, and ISP processor 71 carries out image data
It analyzes to capture the image statistics for the one or more control parameters that can be used for determining camera 73.Camera module 310 can
Including one or more lens 732 and imaging sensor 734.Imaging sensor 734 may include colour filter array (such as Bayer
Filter), imaging sensor 734 can obtain the luminous intensity and wavelength information that each imaging pixel captures, and provide and can be handled by ISP
One group of raw image data of the processing of device 71.Sensor 74 (such as gyroscope) can be based on 74 interface type of sensor the figure of acquisition
As the parameter (such as stabilization parameter) of processing is supplied to ISP processor 71.74 interface of sensor can be SMIA (Standard
Mobile Imaging Architecture, Standard Mobile Imager framework) interface, other serial or parallel camera interfaces or
The combination of above-mentioned interface.
In addition, raw image data can also be sent to sensor 74 by imaging sensor 734, sensor 74 can be based on sensing
Raw image data is supplied to ISP processor 71 or sensor 74 and arrives raw image data storage by 74 interface type of device
In video memory 75.
ISP processor 71 handles raw image data pixel by pixel in various formats.For example, each image pixel can have
There is the bit depth of 8,10,12 or 14 bits, ISP processor 71 can carry out one or more image procossing behaviour to raw image data
Make, statistical information of the collection about image data.Wherein, image processing operations can by identical or different bit depth precision into
Row.
ISP processor 71 can also receive image data from video memory 75.For example, 74 interface of sensor is by original image
Data are sent to video memory 75, and the raw image data in video memory 75 is available to ISP processor 71 for place
Reason.Video memory 75 can be independent in memory 330, a part of memory 330, storage equipment or electronic equipment
Private memory, and may include DMA (Direct Memory Access, direct direct memory access (DMA)) feature.
When receiving the original from 734 interface of imaging sensor or from 74 interface of sensor or from video memory 75
When beginning image data, ISP processor 71 can carry out one or more image processing operations, such as time-domain filtering.Treated image
Data can be transmitted to video memory 75, to carry out other processing before shown.ISP processor 71 is stored from image
Device 75 receives processing data, and carries out at the image data in original domain and in RGB and YCbCr color space to processing data
Reason.Treated that image data may be output to display 77 (display 77 may include display screen 63) for ISP processor 71, for
Family is watched and/or is further processed by graphics engine or GPU.It is stored in addition, the output of ISP processor 71 also can be transmitted to image
Device 75, and display 77 can read image data from video memory 75.In one embodiment, video memory 75 can be matched
It is set to the one or more frame buffers of realization.In addition, the output of ISP processor 71 can be transmitted to encoder/decoder 76, so as to
Encoding/decoding image data.The image data of coding can be saved, and decompress before being shown in 77 equipment of display.
Encoder/decoder 76 can be realized by CPU or GPU or coprocessor.
The statistical data that ISP processor 71 determines, which can be transmitted, gives control logic device Unit 72.For example, statistical data may include
The imaging sensors such as automatic exposure, automatic white balance, automatic focusing, flicker detection, black level compensation, 732 shadow correction of lens
734 statistical informations.Control logic device 72 may include the processing element and/or microcontroller for executing one or more routines (such as firmware)
Device, one or more routines can statistical data based on the received, determine the control parameter of camera 73 and the control of ISP processor 71
Parameter processed.For example, the control parameter of camera 73 may include 74 control parameter of sensor (such as the integral of gain, spectrum assignment
Time, stabilization parameter etc.), camera flash control parameter, 732 control parameter of lens (such as focus or zoom focal length) or
The combination of these parameters.ISP control parameter may include for automatic white balance and color adjustment (for example, during RGB processing)
732 shadow correction parameter of gain level and color correction matrix and lens.
The following are realize image processing method with image processing techniques in Fig. 8: ISP processor controls image and passes
Sensor obtains original image；GPU combines default feature, is divided to obtain multiple images region, each image district to original image
Domain, the characteristic value based on default feature are different；It is based respectively on artificial intelligence noise reduction for each image-region, to obtain target noise reduction
Image.
In order to realize above-described embodiment, the embodiment of the present application also provides a kind of storage mediums, when the finger in storage medium
When order is executed by processor, so that processor executes following steps: obtaining original image；In conjunction with default feature, to original image
It is divided to obtain multiple images region, each image-region, the characteristic value difference based on default feature；For each image-region point
Not Ji Yu artificial intelligence noise reduction, to obtain target noise-reduced image.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, program can be stored in a non-volatile computer storage can be read
In medium, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) etc..
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is interpreted as the limitation to the application the scope of the patents.It should be pointed out that for those of ordinary skill in the art,
Without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection model of the application
It encloses.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
It should be noted that term " first ", " second " etc. are used for description purposes only in the description of the present application, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present application, unless otherwise indicated, the meaning of " multiple "
It is two or more.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (17)
1. a kind of image processing method characterized by comprising
Obtain original image；
In conjunction with default feature, the original image is divided to obtain multiple images region, each described image region is based on institute
The characteristic value for stating default feature is different；
It is based respectively on artificial intelligence noise reduction for each described image region, to obtain target noise-reduced image.
2. image processing method as described in claim 1, which is characterized in that described to be based respectively on for each described image region
Artificial intelligence noise reduction, comprising:
Using neural network model, in conjunction with the corresponding characteristic value in each described image region, noise is carried out to each described image region
Characteristic identification；Wherein, the neural network model has learnt to obtain between the characteristic value and noise characteristic in each described image region
Mapping relations；
According to the noise characteristic identified, to each described image region noise reduction.
3. image processing method as claimed in claim 2, which is characterized in that the neural network model is using each feature
The sample image of value is trained the neural network model, until the noise characteristic that identifies of the neural network model with
When the noise characteristic matching marked in respective sample image, the neural network model training is completed.
4. image processing method as claimed in claim 1 or 2, which is characterized in that further include:
The image-region that noise reduction is obtained is as target noise reduction region；
Each target noise reduction region is synthesized, the target noise-reduced image is obtained.
5. image processing method according to any one of claims 1-4, which is characterized in that the default feature is that image is bright
Degree.
6. image processing method as claimed in claim 5, which is characterized in that described image region based on the default feature
Characteristic value, be the luminance mean value of whole pixels in described image region.
7. a kind of image processing apparatus characterized by comprising
Module is obtained, for obtaining original image；
Division module divides the original image to obtain multiple images region, each figure for combining default feature
As region, the characteristic value based on the default feature is different；
Noise reduction module, for being based respectively on artificial intelligence noise reduction for each described image region, to obtain target noise-reduced image.
8. image processing apparatus as claimed in claim 7, which is characterized in that the noise reduction module is specifically used for:
Using neural network model, in conjunction with the corresponding characteristic value in each described image region, noise is carried out to each described image region
Characteristic identification；Wherein, the neural network model has learnt to obtain between the characteristic value and noise characteristic in each described image region
Mapping relations；
According to the noise characteristic identified, to each described image region noise reduction.
9. image processing apparatus as claimed in claim 8, which is characterized in that the neural network model is using each feature
The sample image of value is trained the neural network model, until the noise characteristic that identifies of the neural network model with
When the noise characteristic matching marked in respective sample image, the neural network model training is completed.
10. image processing apparatus as claimed in claim 7 or 8, which is characterized in that further include:
Synthesis module, the image-region for obtaining noise reduction is as target noise reduction region, and to each target noise reduction region
It is synthesized, obtains the target noise-reduced image.
11. such as the described in any item image processing apparatus of claim 7-10, which is characterized in that the default feature is that image is bright
Degree.
12. image processing apparatus as claimed in claim 11, which is characterized in that described image region based on the default spy
The characteristic value of sign is the luminance mean value of whole pixels in described image region.
13. a kind of electronic equipment characterized by comprising imaging sensor, memory, processor and storage are on a memory
And the computer program that can be run on a processor, described image sensor are electrically connected with the processor, the processor is held
When row described program, such as image processing method as claimed in any one of claims 1 to 6 is realized.
14. electronic equipment according to claim 13, which is characterized in that the processor includes image signal process ISP
Processor；
The ISP processor obtains original image for controlling described image sensor.
15. electronic equipment according to claim 14, which is characterized in that the processor includes and the ISP processor
The graphics processor GPU of connection；
Wherein, the GPU divides the original image to obtain multiple images region, each institute for combining default feature
Image-region is stated, the characteristic value based on the default feature is different；Artificial intelligence drop is based respectively on for each described image region
It makes an uproar, to obtain target noise-reduced image.
16. a kind of image processing circuit, which is characterized in that described image processing circuit includes image signal process ISP processor
With graphics processor GPU；
The ISP processor, is electrically connected with imaging sensor, obtains original image for controlling described image sensor；
The GPU is electrically connected with the ISP processor, for combining default feature, is divided to obtain to the original image
Multiple images region, each described image region, the characteristic value based on the default feature are different；For each described image region point
Not Ji Yu artificial intelligence noise reduction, to obtain target noise-reduced image.
17. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as image processing method as claimed in any one of claims 1 to 6 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509584.8A CN110213462B (en) | 2019-06-13 | 2019-06-13 | Image processing method, image processing device, electronic apparatus, image processing circuit, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509584.8A CN110213462B (en) | 2019-06-13 | 2019-06-13 | Image processing method, image processing device, electronic apparatus, image processing circuit, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110213462A true CN110213462A (en) | 2019-09-06 |
| CN110213462B CN110213462B (en) | 2022-01-04 |
Family
ID=67792317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910509584.8A Active CN110213462B (en) | 2019-06-13 | 2019-06-13 | Image processing method, image processing device, electronic apparatus, image processing circuit, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110213462B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131716A (en) * | 2019-12-31 | 2020-05-08 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN113628124A (en) * | 2020-05-08 | 2021-11-09 | 深圳清华大学研究院 | ISP and visual task joint optimization method, system, medium and electronic equipment |
| CN113763275A (en) * | 2021-09-09 | 2021-12-07 | 深圳市文立科技有限公司 | Adaptive image noise reduction method and system and readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973990A (en) * | 2014-05-05 | 2014-08-06 | 浙江宇视科技有限公司 | Wide dynamic fusion method and device |
| CN104134191A (en) * | 2014-07-11 | 2014-11-05 | 三星电子（中国）研发中心 | Image denoising method and image denoising device |
| CN105005973A (en) * | 2015-06-30 | 2015-10-28 | 广东欧珀移动通信有限公司 | Fast image denoising method and apparatus |
| CN106127729A (en) * | 2016-06-08 | 2016-11-16 | 浙江传媒学院 | A kind of picture noise level estimation method based on gradient |
| CN106331433A (en) * | 2016-08-25 | 2017-01-11 | 上海交通大学 | Video denoising method based on deep recursive neural network |
| US20180144208A1 (en) * | 2016-11-18 | 2018-05-24 | Salesforce.Com, Inc. | Adaptive attention model for image captioning |
| CN108122206A (en) * | 2016-11-29 | 2018-06-05 | 深圳市中兴微电子技术有限公司 | A kind of low-light (level) image denoising method and device |
| CN108876737A (en) * | 2018-06-06 | 2018-11-23 | 武汉大学 | A kind of image de-noising method of joint residual error study and structural similarity |
| CN109544477A (en) * | 2018-11-23 | 2019-03-29 | 南通大学 | Image denoising algorithm based on self-adapting dictionary study rarefaction representation |
| CN109658344A (en) * | 2018-11-12 | 2019-04-19 | 哈尔滨工业大学（深圳） | Image de-noising method, device, equipment and storage medium based on deep learning |
| WO2019084492A1 (en) * | 2017-10-26 | 2019-05-02 | Essenlix Corporation | Devices and methods for monitoring liquid-solid contact time |
| CN109859147A (en) * | 2019-03-01 | 2019-06-07 | 武汉大学 | A kind of true picture denoising method based on generation confrontation network noise modeling |
-
2019
- 2019-06-13 CN CN201910509584.8A patent/CN110213462B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973990A (en) * | 2014-05-05 | 2014-08-06 | 浙江宇视科技有限公司 | Wide dynamic fusion method and device |
| CN104134191A (en) * | 2014-07-11 | 2014-11-05 | 三星电子（中国）研发中心 | Image denoising method and image denoising device |
| CN105005973A (en) * | 2015-06-30 | 2015-10-28 | 广东欧珀移动通信有限公司 | Fast image denoising method and apparatus |
| CN106127729A (en) * | 2016-06-08 | 2016-11-16 | 浙江传媒学院 | A kind of picture noise level estimation method based on gradient |
| CN106331433A (en) * | 2016-08-25 | 2017-01-11 | 上海交通大学 | Video denoising method based on deep recursive neural network |
| US20180144208A1 (en) * | 2016-11-18 | 2018-05-24 | Salesforce.Com, Inc. | Adaptive attention model for image captioning |
| CN108122206A (en) * | 2016-11-29 | 2018-06-05 | 深圳市中兴微电子技术有限公司 | A kind of low-light (level) image denoising method and device |
| WO2019084492A1 (en) * | 2017-10-26 | 2019-05-02 | Essenlix Corporation | Devices and methods for monitoring liquid-solid contact time |
| CN108876737A (en) * | 2018-06-06 | 2018-11-23 | 武汉大学 | A kind of image de-noising method of joint residual error study and structural similarity |
| CN109658344A (en) * | 2018-11-12 | 2019-04-19 | 哈尔滨工业大学（深圳） | Image de-noising method, device, equipment and storage medium based on deep learning |
| CN109544477A (en) * | 2018-11-23 | 2019-03-29 | 南通大学 | Image denoising algorithm based on self-adapting dictionary study rarefaction representation |
| CN109859147A (en) * | 2019-03-01 | 2019-06-07 | 武汉大学 | A kind of true picture denoising method based on generation confrontation network noise modeling |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131716A (en) * | 2019-12-31 | 2020-05-08 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN113628124A (en) * | 2020-05-08 | 2021-11-09 | 深圳清华大学研究院 | ISP and visual task joint optimization method, system, medium and electronic equipment |
| CN113628124B (en) * | 2020-05-08 | 2024-01-16 | 深圳清华大学研究院 | ISP and visual task joint optimization method, system, medium and electronic equipment |
| CN113763275A (en) * | 2021-09-09 | 2021-12-07 | 深圳市文立科技有限公司 | Adaptive image noise reduction method and system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110213462B (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110290289B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
| CN110072052B (en) | Image processing method and device based on multi-frame image and electronic equipment | |
| CN109068067A (en) | Exposal control method, device and electronic equipment | |
| CN110248106B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
| CN110062160A (en) | Image processing method and device | |
| CN110191291B (en) | Image processing method and device based on multi-frame images | |
| CN109005364A (en) | Image formation control method, device, electronic equipment and computer readable storage medium | |
| CN110166708B (en) | Night scene image processing method and device, electronic equipment and storage medium | |
| WO2020207261A1 (en) | Image processing method and apparatus based on multiple frames of images, and electronic device | |
| CN109005342A (en) | Panorama shooting method, device and imaging device | |
| CN109040609A (en) | Exposal control method, device and electronic equipment | |
| CN108200354A (en) | Control method and device, imaging device, computer equipment and readable storage medium storing program for executing | |
| CN110166707B (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN109788207A (en) | Image composition method, device, electronic equipment and readable storage medium storing program for executing | |
| CN109005369B (en) | Exposure control method, exposure control device, electronic apparatus, and computer-readable storage medium | |
| CN108833804A (en) | Imaging method, device and electronic equipment | |
| CN110033418A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN110166706B (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN108833802A (en) | Exposal control method, device and electronic equipment | |
| CN109089046A (en) | Image denoising method, device, computer readable storage medium and electronic equipment | |
| CN109167930A (en) | Image display method, device, electronic equipment and computer readable storage medium | |
| CN108900785A (en) | Exposal control method, device and electronic equipment | |
| CN109151333B (en) | Exposure control method, exposure control device and electronic equipment | |
| CN109672819A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN110213462A (en) | Image processing method, device, electronic equipment and image processing circuit |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |