CN110516680A - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN110516680A CN110516680A CN201910718432.9A CN201910718432A CN110516680A CN 110516680 A CN110516680 A CN 110516680A CN 201910718432 A CN201910718432 A CN 201910718432A CN 110516680 A CN110516680 A CN 110516680A
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- pixel value
- value
- region
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 239000000463 material Substances 0.000 abstract description 6
- 238000000034 method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 206010047571 Visual impairment Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The present embodiments relate to field of image processing, a kind of image processing method and device are disclosed.In the present invention, the pixel value of each pixel of initial pictures and the initial pictures is obtained;Calculate pixel value variable quantity of each pixel relative to adjacent pixel;Wherein, adjacent pixel is specially pixel adjacent on preset direction;The region that the pixel that pixel value variable quantity is greater than preset threshold is formed is as interference region;Denoising is carried out to interference region, removes the interference signal of interference region;The image after denoising will be carried out to interference region as final image.The interference signal in image is filtered out in such a way that software algorithm calculates, so that it is more clear the picture material of final shooting image, the discrimination of the image after improving filtering processing.On the other hand, the interference stripes in image are removed by way of software, are relatively low cost and easy to realize.
Description
Technical field
The present embodiments relate to field of image processing, in particular to a kind of image processing method and device.
Background technique
Currently, the extensive use of the identification with the analysis and video content of video image, item present in video image
Surface noise is increasingly becoming focus concerned by people.Surface noise in video image may make the Intellectualized monitorings such as image recognition by
To limitation, the further analysis to the information in image is limited, therefore, is needed before video image is identified or analyzed
By the striped noise removal in image, to guarantee the reliability of the result of identification or analysis.
At least there are the following problems in the related technology for inventor's discovery: usually logical at present for the surface noise in image
The improvement to the hardware circuit of picture pick-up device is crossed, to avoid the presence of a surface noise in the image of shooting, doing so can not produced
The interference of noise is removed when carded sliver surface noise.In addition, the improving cost to hardware circuit is higher.
Summary of the invention
Embodiment of the present invention is designed to provide a kind of image processing method and device, is filtered out by way of software
Interference signal, so that the picture material obtained is more clear, the effect of filtering interference signals is more preferable, and cost is relatively low.
In order to solve the above technical problems, embodiments of the present invention provide a kind of image processing method, comprising: obtain just
The pixel value of each pixel of beginning image and the initial pictures;Calculate pixel value of each pixel relative to adjacent pixel
Variable quantity;Wherein, adjacent pixel is specially pixel adjacent on preset direction;Pixel value variable quantity is greater than default threshold
The region of the pixel composition of value is as interference region;Denoising is carried out to interference region, removes the interference letter of interference region
Number;The image after denoising will be carried out to interference region as final image.
Embodiments of the present invention additionally provide a kind of image processing apparatus, comprising: obtain module, computing module, denoising
Processing module;Module is obtained for obtaining initial pictures;Computing module is for calculating each pixel relative to adjacent pixel
Pixel value variable quantity;Wherein, adjacent pixel is specially pixel adjacent on preset direction;Pixel value variable quantity is big
In the region that the pixel of preset threshold forms as interference region;Denoising module is for carrying out at denoising interference region
Reason, and the image after denoising will be carried out to interference region as final image.
Embodiment of the present invention in terms of existing technologies, due in image interference stripes (band or vertical line) and its
The image of surrounding has biggish value differences, so the picture material of script can be interfered, in order to remove the interference stripe in image
Line can analyze the pixel value of each pixel in image, finds out and differs biggish pixel with the pixel value of surrounding pixel point,
The pixel value for all and surrounding pixel point found out is differed to region that biggish pixel is constituted as interference region, to figure
The interference region of picture carries out denoising, removes the interference stripes in interference region, obtains the final image of removal interference stripes.
The interference signal filtered out in image in such a way that software algorithm calculates is done so, to make in the image of final shooting image
Appearance is more clear, the discrimination of the image after improving filtering processing.On the other hand, it is removed in image by way of software
Interference stripes are relatively low cost and easy to realize.
In addition, calculating pixel value variable quantity of each pixel relative to adjacent pixel, specifically include: to each pixel
Pixel value be based on position coordinates seek first derivative, the image after obtaining single treatment;Pixel value variable quantity is greater than default threshold
The region of the pixel composition of value is specifically included as interference region: in the image after single treatment, pixel value being selected to be greater than
The all pixels point of preset threshold;Using region composed by all pixels point as interference region.Pass through one to each pixel
The calculating of order derivative obtains change rate of each pixel on preset direction, by the change rate of each pixel of initial pictures with
The pixel value of each pixel of image after single treatment indicates that the image after single treatment intuitively and can be obtained easily
To interference region, consequently facilitating carrying out denoising to interference region.
In addition, after obtaining the image after single treatment, further includes: each pixel of the image after judging single treatment
Pixel value whether be greater than preset upper limit value;The pixel value that pixel value is less than the pixel of preset upper limit value is adjusted to 0;By picture
The pixel value for the pixel that plain value is greater than or equal to preset upper limit value remains unchanged;Using the image after adjustment pixel value as secondary
Treated image;Image after secondary treatment is filtered, the image that obtains that treated three times;After single treatment
Image in, select pixel value to be greater than all pixels point of preset threshold, specifically: in treated three times image, selection
Pixel value is greater than all pixels point of preset threshold.Threshold calculations are done to the image after single treatment, preset upper limit value will be less than
Pixel be disposed as black, to increase the value differences of interference region and background image;Again to secondary treatment after
Image be filtered, keep the difference of black region and white area more obvious.
In addition, be filtered to the image after secondary treatment, the image that obtains that treated three times is specifically included: meter
The average value of the data of the corresponding default filter field of each pixel of image after calculating secondary treatment;Wherein, filtering area is preset
The data in domain are specially the pixel value of all pixels point of the rectangular area centered on pixel;Using the average value of calculating as
The pixel value of each pixel of treated three times image.Each pixel of image and surrounding pixel after calculating secondary treatment
The average value of the pixel value of point, and using the average value of calculating as the pixel value of each point of treated three times image, to make
The interface of interference region and background area is more obvious, to be more advantageous to the judgement of interference region.
In addition, after the image that obtains that treated three times, further includes: to each pixel of treated three times image with
Each pixel of initial pictures seeks common ground, and obtains four times treated image;In treated three times image, pixel value is selected
Greater than all pixels point of preset threshold, specifically: in treated at four times image, pixel value is selected to be greater than preset threshold
All pixels point.Doing so makes finally obtained interference region closer in the region where the interference signal of initial pictures, makes
The accuracy of final denoising is higher.
In addition, denoising is carried out to interference region, specifically: the previous frame image for obtaining initial pictures in advance, as
Compare image;Control pixel is obtained in control image;Wherein, each picture of the interference region of pixel and initial pictures is compareed
Vegetarian refreshments corresponds;The pixel value of each pixel of interference region is replaced with to the pixel value of control pixel.Utilize initial graph
The pixel value of the pixel of the previous frame image of picture replaces the pixel value of the pixel of the interference region of initial pictures, operation letter
It is singly easily achieved, and the content of the image after finally obtained denoising is more clear, completely, the effect of filtering interference signals
More preferably.
Detailed description of the invention
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the image processing method flow chart in first embodiment according to the present invention;
Fig. 2 is the schematic diagram of initial pictures in first embodiment according to the present invention;
Fig. 3 is the schematic diagram of the image in first embodiment after single treatment according to the present invention;
Fig. 4 is the image processing method flow chart in second embodiment according to the present invention;
Fig. 5 is the schematic diagram of the image in second embodiment after secondary treatment according to the present invention;
The schematic diagram of Fig. 6 is that treated three times in second embodiment according to the present invention image;
Fig. 7 is the image processing method flow chart in third embodiment according to the present invention;
The schematic diagram of Fig. 8 is that four times treated in third embodiment according to the present invention image;
Fig. 9 is the schematic diagram of final image in third embodiment according to the present invention;
Figure 10 is the structural schematic diagram of the image processing apparatus in the 4th embodiment according to the present invention;
Figure 11 is the structural schematic diagram of the image processing apparatus in the 5th embodiment according to the present invention;
Figure 12 is the structural schematic diagram of the electronic equipment in sixth embodiment according to the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, the application technical solution claimed also may be implemented.
The division of each embodiment is for convenience, should not to constitute to specific implementation of the invention any below
It limits, each embodiment can be combined with each other mutual reference under the premise of reconcilable.
The first embodiment of the present invention is related to a kind of image processing method, initial pictures and the initial pictures are obtained
The pixel value of each pixel;Calculate pixel value variable quantity of each pixel relative to adjacent pixel;Wherein, adjacent pixel
Point is specially pixel adjacent on preset direction;The region that the pixel that pixel value variable quantity is greater than preset threshold forms is made
For interference region;Denoising is carried out to interference region, removes the interference signal of interference region;Interference region will be denoised
Treated image is as final image.The realization details of the image processing method of present embodiment is carried out specifically below
Bright, the following contents only for convenience of the realization details provided is understood, not implements the necessary of this programme, detailed process is as shown in Figure 1.
Step 101, the pixel value of each pixel of initial pictures and initial pictures is obtained.Specifically, in camera etc.
When picture pick-up device is acquired image, if there are interference signals in the image of acquisition, for example, there are horizontal stripe or being erected in image
Striped, then to there are the images of interference signal to carry out image procossing.Electronic equipment obtain there are the image of interference signal be used as to
The initial pictures of processing, and read the pixel value of each pixel of initial pictures.The image of acquisition can be color image, can also
To be gray level image.In practical applications, the effect for preferably removing interference signal in order to obtain, can be in the initial graph of acquisition
When seeming color image, initial pictures are converted into gray level image.
Step 102, pixel value variable quantity of each pixel relative to adjacent pixel is calculated.Specifically, each pixel
The adjacent pixel of point is specially pixel adjacent on preset direction.For example, when being filtered to nicking, each pixel
The pixel that the adjacent pixel of point can take the pixel left and right directions adjacent;When being filtered to horizontal stripe, each picture
The pixel that the adjacent pixel of vegetarian refreshments can take the pixel up and down direction adjacent.Generally, adjacent on preset direction
Pixel in, preset direction is and the different any direction in the direction of interference stripes usually setting in practical applications
Direction be left and right directions (horizontal direction) or up and down direction (vertical direction).
It, can be by two adjacent pixels when calculating pixel value variable quantity of each pixel relative to adjacent pixel
The pixel value of point substitutes into first derivative calculation formulaf
‘(x0) indicate the pixel value variable quantity of pixel calculated, x0Indicate the pixel value of pixel calculated, Δ x expression is counted
The distance of the pixel of calculation pixel adjacent thereto, Δ y indicate the pixel of pixel calculated pixel adjacent thereto
The difference of value, f (x0+ Δ x) indicates the pixel value of the pixel adjacent with the pixel calculated, f (x0) indicate pixel calculated
The pixel value of point.The mode of calculating is specific as follows, each pixel when filtering out the nicking in image, in certain level direction
Pixel value be respectively 153,156,250,257,154 ... ..., calculate pixel value be 153 pixel pixel value variation
When amount, by the pixel value 153 of pixel calculated, the pixel value 156 of adjacent pixel, two adjacent pixels away from
It substitutes into above-mentioned first derivative calculation formula, obtains from 1Therefore, above-mentioned pixel value is 153
The pixel value variable quantity that is calculated of pixel be 3, similarly other pixels are respectively calculated, are obtained above-mentioned each
The pixel value variable quantity of point is respectively 3,94,7,103 ... ....In practical applications can using the process of above-mentioned calculating as pair
The single treatment of image, using the pixel value variable quantity of each pixel obtained after processing as each picture of the image after single treatment
The pixel value of vegetarian refreshments.Assuming that the initial pictures obtained disturb user and draw to image as shown in Fig. 2, there are nicking on image
The viewing experience of the content in face, after carrying out first derivation processing to initial pictures, image after obtaining single treatment is such as schemed
Shown in 3, in the image after single treatment, it is apparent poor that the region of the nicking in initial pictures has with remaining background area
Not, that is to say, that the region where nicking differs larger with the size of the pixel value of each pixel of background area.
Step 103, the region pixel that pixel value variable quantity is greater than preset threshold formed is as interference region.Specifically
Ground is said, since the pixel value of interference region and each point of picture material region has biggish difference, in Fig. 2 or Fig. 3
, it is apparent that the closer white of the pixel value of each pixel of interference stripes region, and each pixel of background area
The pixel value of point is closer to black.Assuming that preset threshold is 80, by taking the pixel value variable quantity of above-mentioned calculating as an example, wherein pixel
Two pixels that value variable quantity is 94 and 103 are in interference region, and rest of pixels value variable quantity is 3 and 7 two pixels
Point is in background area.
Step 104, denoising is carried out to interference region, removes the interference signal of interference region.Specifically, obtaining in advance
The previous frame image for taking initial pictures, as control image;Control pixel is obtained in control image;Wherein, pixel is compareed
Each pixel of point and the interference region of initial pictures corresponds;The pixel value of each pixel of interference region is replaced with pair
The pixel value of photograph vegetarian refreshments.Since the image that electronic equipment is recorded is dynamic image, the figure of the previous frame of the initial pictures of acquisition
As changing smaller, the picture of each pixel of the image and initial pictures of the previous frame of initial pictures with the picture material of initial pictures
The variation of element value is smaller, it is possible to using the same position of previous frame pixel pixel value to the interference regions of initial pictures
Interior pixel is replaced, for example, the certain point of interference region is in initial pictures with coordinate (20,4) expression, in initial pictures
Previous frame, that is, control image in find coordinate position be (20,4) pixel, obtain the pixel value of the point, and will obtain
Pixel value of the pixel value got as the pixel that the coordinate of interference region in initial pictures is (20,4).It similarly, will be initial
The pixel value of each pixel in image is replaced, and obtains the final image of removal interference signal.
In addition, in practical applications, denoising can also be carried out to interference region by other means, for example, can be with
By the arrangement rule of each pixel of background area in analysis initial pictures, the pixel of each pixel of interference region is estimated
Value;It can also be by the pixel value of each point in initial pictures, based on the position coordinates of each pixel, to the pixel value of interference region
It is fitted, to obtain more smooth image, plays the purpose of removal interference signal.Removal interference region is done at this
Disturb the concrete mode of the denoising of signal with no restriction.
Step 105, the image after denoising will be carried out to interference region as final image.
Embodiment of the present invention in terms of existing technologies, due in image interference stripes (band or vertical line) and its
The image of surrounding has biggish value differences, so the picture material of script can be interfered, in order to remove the interference stripe in image
Line can analyze the pixel value of each pixel in image, finds out and differs biggish pixel with the pixel value of surrounding pixel point,
The pixel value for all and surrounding pixel point found out is differed to region that biggish pixel is constituted as interference region, to figure
The interference region of picture carries out denoising, removes the interference stripes in interference region, obtains the final image of removal interference stripes.
The interference signal filtered out in image in such a way that software algorithm calculates is done so, to make in the image of final shooting image
Appearance is more clear, the discrimination of the image after improving filtering processing.On the other hand, it is removed in image by way of software
Interference stripes are relatively low cost and easy to realize.
Second embodiment of the present invention is related to a kind of image processing method.In second embodiment of the invention, to first
Beginning image handle for the first time, has handled and handle for the third time for second, and selection is met the requirements in image after treatment
Pixel, using all pixels met the requirements point composition region as interference region, detailed process is as shown in Figure 4.
Step 401, the pixel value of each pixel of initial pictures and the initial pictures is obtained.
Step 402, position coordinates are based on to the pixel value of each pixel and seek first derivative, the figure after obtaining single treatment
Picture.
Step 403, the pixel value that pixel value is less than to the pixel of preset upper limit value is adjusted to 0;Pixel value is greater than or
Pixel value equal to the pixel of preset upper limit value remains unchanged.
Step 404, using the image after adjustment pixel value as the image after secondary treatment.
Specifically, carrying out secondary treatment to the image after single treatment, the image after secondary treatment will be as shown in figure 5, will
The pixel value that pixel value is less than the pixel of preset upper limit value is adjusted to 0, i.e., is black by the image completion of background area;By picture
The pixel value for the pixel that plain value is greater than or equal to preset upper limit value remains unchanged, and doing so can be by pixel value in background area
Lesser pixel and the pixel of interference signal region distinguish.
Step 405, the image after secondary treatment is filtered, the image that obtains that treated three times.Specifically,
Image after secondary treatment is filtered, the corresponding default filter of each pixel of the image after secondary treatment can be calculated
The average value of the data in wave region;Wherein, rectangular area of the data of filter field specially centered on pixel is preset
The pixel value of all pixels point;Finally using the average value of calculating as the pixel value of each pixel of treated three times image,
Treated three times, and image effect is as shown in Figure 6.Below with a specific example, to the picture of each point of treated three times image
The calculation of plain value is specifically described, it is assumed that in the image after secondary treatment, a certain pixel and surrounding rectangle
The pixel value of each pixel in region is respectivelyThe pixel value of the pixel is 5 centers for being located at rectangular area,
Afterimage vegetarian refreshments is arranged separately on the surrounding of the pixel, and above-mentioned all pixels constitute default filter field, using pre-
If the pixel value of each pixel in filter field, the average value (2+3+4+4+5+6+7+8+9)/9 of all pixels point is found out, about
It is 5, the pixel value of the pixel is 5 in treated three times image, can also choose each pixel value in default filter field
Median, the pixel value as the pixel in treated three times image.Herein to preset filter field as the rectangle of 3*3
For region, in practical applications, the form and dimension of default filter field is adjusted according to the actual situation, is not limited herein
System.
In addition, in practical applications, the calculating of average value can also be carried out to default filter field by other means, with
The numerical value that filter field is preset in the example above is illustrated other modes for calculating average value, the figure after secondary treatment
As in, the pixel value of each pixel of a certain pixel and surrounding rectangular area is respectivelyThe then pixel
Average value can be the ratio of the sum of all pixels value in the pixel value of the point and default filter field, i.e. the pixel is average
Value are as follows: 5/ (2+3+4+4+5+6+7+8+9)=5/48, the interface for making interference region and background area can equally be played by doing so
More obvious effect carries out the mode of the calculating of average value at this with no restriction to default filter field.
Step 406, in treated three times image, pixel value is selected to be greater than all pixels point of preset threshold, and will
The region of all pixels point composition selected is as interference region.
Step 407, denoising is carried out to the interference region, removes the interference signal of the interference region.
Step 408, image after denoising is carried out as final image to the interference region using described.
Step 407,408 are corresponded with step 104,105 in first embodiment, and details are not described herein.
In the present embodiment, threshold calculations are done to the image after single treatment, the pixel of preset upper limit value will be less than
It is disposed as black, to increase the value differences of interference region and background image;Again to the image after secondary treatment into
Row filtering processing, the difference of black region and white area is more obvious in the image that makes that treated three times.
Third embodiment of the present invention is related to a kind of image processing method.In third embodiment of the invention, to three
Secondary treated image carries out four processing, by four times treated interference region that image obtains closer in initial pictures
Interference signal where region, keep the accuracy of final denoising higher.Detailed process is as shown in Figure 7.
Step 701, the pixel value of each pixel of initial pictures and the initial pictures is obtained.
Step 702, position coordinates are based on to the pixel value of each pixel and seek first derivative, the figure after obtaining single treatment
Picture.
Step 703, the pixel value that pixel value is less than to the pixel of preset upper limit value is adjusted to 0;Pixel value is greater than or
Pixel value equal to the pixel of preset upper limit value remains unchanged.
Step 704, using the image after adjustment pixel value as the image after secondary treatment.
Step 705, the image after secondary treatment is filtered, the image that obtains that treated three times.
Step 701 is corresponded to 705 with step 401 in second embodiment to 405, and details are not described herein.
Step 706, it seeks common ground to treated three times each pixel of image and each pixel of initial pictures, obtains four
Secondary treated image.Specifically, treated three times image is as shown in fig. 6, after threshold calculations and filtering processing
Image is for initial pictures, and interference region is obviously big compared with interference signal region, and the region where interference signal
Within the interference region for the image that is in that treated three times, to each pixel of treated three times image and initial pictures
It seeks common ground, picks out the identical pixel of pixel value in two images, and the pixel value for the pixel that will be singled out retains, remaining
The pixel value of pixel is adjusted to 0, i.e., is filled with black to rest of pixels point, obtains four times treated image, such as
Shown in Fig. 8, doing so keeps finally obtained interference region final closer to making in the region where the interference signal of initial pictures
Denoising accuracy it is higher.
Step 707, in treated at four times image, pixel value is selected to be greater than all pixels point of preset threshold, and will
The region of all pixels point composition selected is as interference region.
Step 708, denoising is carried out to the interference region, removes the interference signal of the interference region.
Step 709, image after denoising is carried out as final image to the interference region using described.
Specifically, can use four times treated image as masking-out, denoising is carried out to initial pictures.By four
The region of the corresponding initial pictures of black region of secondary treated image is ignored, by the white area of four times treated image
The region of corresponding initial pictures carries out denoising as interference region.
In the present embodiment, friendship is asked to treated three times each pixel of image and each pixel of initial pictures
Collection obtains four times treated image, and using four times treated, image is used as masking-out, to initial pictures progress denoising,
Doing so makes finally obtained interference region closer in the region where the interference signal of initial pictures, makes at final denoising
The accuracy of reason is higher.
The step of various methods divide above, be intended merely to describe it is clear, when realization can be merged into a step or
Certain steps are split, multiple steps are decomposed into, as long as including identical logical relation, all in the protection scope of this patent
It is interior;To adding inessential modification in algorithm or in process or introducing inessential design, but its algorithm is not changed
Core design with process is all in the protection scope of the patent.
Four embodiment of the invention is related to a kind of image processing apparatus, as shown in Figure 10, comprising: module 1001 is obtained,
Computing module 1002, denoising module 1003;Module 1001 is obtained for obtaining initial pictures;Computing module 1002 is based on
Calculate pixel value variable quantity of each pixel relative to adjacent pixel;Wherein, adjacent pixel is specially on preset direction
Adjacent pixel;The region that the pixel that pixel value variable quantity is greater than preset threshold is formed is as interference region;At denoising
It manages module 1003 to be used to carry out denoising to interference region, and the image after denoising will be carried out to interference region as most
Whole image.
It is not difficult to find that present embodiment is system embodiment corresponding with first embodiment, present embodiment can be with
First embodiment is worked in coordination implementation.The relevant technical details mentioned in first embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In first embodiment.
It is noted that each module involved in present embodiment is logic module, and in practical applications, one
A logic unit can be a physical unit, be also possible to a part of a physical unit, can also be with multiple physics lists
The combination of member is realized.In addition, in order to protrude innovative part of the invention, it will not be with solution institute of the present invention in present embodiment
The technical issues of proposition, the less close unit of relationship introduced, but this does not indicate that there is no other single in present embodiment
Member.
Fifth embodiment of the invention is related to a kind of image processing apparatus.In the 5th embodiment, computing module is specific
It include: single treatment module 10021, secondary treatment module 10022, processing module 10023 and four processing modules three times
10024。
Single treatment module 10021 is used to be based on position coordinates to the pixel value of each pixel to seek first derivative, obtains one
Secondary treated image;
Secondary treatment module 10022 is for the image after obtaining the image after single treatment, after judging single treatment
The pixel value of each pixel whether be greater than preset upper limit value;Pixel value is less than to the pixel value tune of the pixel of preset upper limit value
Whole is 0;The pixel value that pixel value is greater than or equal to the pixel of preset upper limit value is remained unchanged;By the figure after adjustment pixel value
As the image after secondary treatment;
Processing module 10023 is for being filtered the image after secondary treatment three times, obtains three times that treated
Image;
Four processing modules 10024 are used for after the image that obtains that treated three times, to treated three times image
Each pixel of each pixel and initial pictures seeks common ground, and obtains four times treated image.
Since third embodiment is corresponded to each other with present embodiment, present embodiment can be mutual with third embodiment
Match implementation.The relevant technical details mentioned in third embodiment are still effective in the present embodiment, implement in third
The attainable technical effect of institute similarly may be implemented in the present embodiment in mode, no longer superfluous here in order to reduce repetition
It states.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in third embodiment.
Sixth embodiment of the invention is related to a kind of electronic equipment, as shown in figure 12, including at least one processor 1201;
And the memory 1202 with the communication connection of at least one processor 1201;Wherein, be stored with can be by least one for memory 1202
The instruction that a processor 1201 executes, instruction is executed by least one processor 1201, so that at least one 1201 energy of processor
Enough execute above-mentioned image processing method.
Wherein, memory 1202 is connected with processor 1201 using bus mode, and bus may include any number of mutual
The bus and bridge of connection, bus is by one or more processors 1201 together with the various circuit connections of memory 1202.Bus
Can also be by such as peripheral equipment, voltage-stablizer together with various other circuit connections of management circuit or the like, these
It is all it is known in the art, therefore, it will not be further described herein.Bus interface is between bus and transceiver
Interface is provided.Transceiver can be an element, is also possible to multiple element, such as multiple receivers and transmitter, provides use
In the unit communicated over a transmission medium with various other devices.The data handled through processor pass through antenna on the radio medium
It is transmitted, further, antenna also receives data and transfers data to processor 1201.
Processor 1201 is responsible for management bus and common processing, can also provide various functions, including timing, periphery connects
Mouthful, voltage adjusting, power management and other control functions.And memory 1202 can be used for storage processor 1201 and hold
Used data when row operation.
Seventh embodiment of the invention is related to a kind of computer readable storage medium, is stored with computer program.Computer
Above method embodiment is realized when program is executed by processor.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are to make
It obtains an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) executes side described in each embodiment of the application
The all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (10)
1. a kind of image processing method characterized by comprising
Obtain the pixel value of each pixel of initial pictures and the initial pictures;
Calculate pixel value variable quantity of each pixel relative to adjacent pixel;Wherein, the adjacent pixel tool
Body is pixel adjacent on preset direction;
The region that the pixel that the pixel value variable quantity is greater than preset threshold is formed is as interference region;
Denoising is carried out to the interference region, removes the interference signal of the interference region;
Image after denoising is carried out as final image to the interference region using described.
2. image processing method according to claim 1, which is characterized in that described to calculate each pixel relative to phase
The pixel value variable quantity of adjacent pixel, specifically includes:
Position coordinates are based on to the pixel value of each pixel and seek first derivative, the image after obtaining single treatment;
The region that the pixel that the pixel value variable quantity is greater than preset threshold forms is specific to wrap as interference region
It includes:
In the image after the single treatment, pixel value is selected to be greater than all pixels point of preset threshold;
Using region composed by all pixels point as the interference region.
3. image processing method according to claim 2, which is characterized in that the image obtained after single treatment it
Afterwards, further includes:
Whether the pixel value of each pixel of the image after judging the single treatment is greater than preset upper limit value;
The pixel value that pixel value is less than the pixel of the preset upper limit value is adjusted to 0;
The pixel value that pixel value is greater than or equal to the pixel of the preset upper limit value is remained unchanged;
Using the image after the adjustment pixel value as the image after secondary treatment;
Image after the secondary treatment is filtered, the image that obtains that treated three times;
In the image after the single treatment, pixel value is selected to be greater than all pixels point of preset threshold, specifically:
In treated the image described three times, pixel value is selected to be greater than all pixels point of preset threshold.
4. image processing method according to claim 3, which is characterized in that the image to after the secondary treatment into
Row filtering processing, the image that obtains that treated three times specifically include:
The average value of the data of the corresponding default filter field of each pixel of image after calculating the secondary treatment;Wherein,
The data of the default filter field are specially the pixel value of all pixels point of the rectangular area centered on the pixel;
Using the average value of the calculating as the pixel value of each pixel of treated the three times image.
5. image processing method according to claim 3, which is characterized in that the image that obtains that treated three times it
Afterwards, further includes:
It seeks common ground, obtains at four times with each pixel of the initial pictures to treated each pixel of image described three times
Image after reason;
It is described to select pixel value to be greater than all pixels point of preset threshold in treated the image described three times, specifically:
In treated at described four times image, pixel value is selected to be greater than all pixels point of preset threshold.
6. image processing method according to claim 1, which is characterized in that described to be carried out at denoising to the interference region
Reason, specifically:
The previous frame image for obtaining the initial pictures in advance, as control image;
Control pixel is obtained in the control image;Wherein, the control pixel and the described of the initial pictures do
Each pixel for disturbing region corresponds;
The pixel value of each pixel of the interference region is replaced with to the pixel value of the control pixel.
7. a kind of image processing apparatus characterized by comprising obtain module, computing module, denoising module;
The pixel value for obtaining module and being used to obtain each pixel of initial pictures and the initial pictures;
The computing module is for calculating pixel value variable quantity of each pixel relative to adjacent pixel;Wherein, institute
Stating adjacent pixel is specially pixel adjacent on preset direction;The pixel value variable quantity is greater than to the picture of preset threshold
The region of vegetarian refreshments composition is as interference region;
The denoising module is used to carry out denoising to the interference region according to the initial pictures, removes described dry
The interference signal in region is disturbed, and image after denoising is carried out as final image to the interference region using described.
8. image processing apparatus according to claim 7, which is characterized in that the computing module includes at least: primary place
Manage module and selection interference region module;
The single treatment module is used to be based on position coordinates to the pixel value of each pixel to seek first derivative, obtains primary
Treated image;In the image after the single treatment, pixel value is selected to be greater than all pixels point of preset threshold;
It is described to select interference region module for using region composed by all pixels point as the interference region.
9. image processing apparatus according to claim 8, which is characterized in that the computing module further include: secondary treatment
Module and three times processing module;
The secondary treatment module is used for after obtaining the image after single treatment, the image after judging the single treatment
Whether the pixel value of each pixel is greater than preset upper limit value;Pixel value is less than to the pixel value of the pixel of the preset upper limit value
It is adjusted to 0;The pixel value that pixel value is greater than or equal to the pixel of the preset upper limit value is remained unchanged;By the adjustment picture
Image after element value is as the image after secondary treatment;
The processing module three times is for being filtered the image after the secondary treatment, the figure that obtains that treated three times
Picture, and in treated the image described three times, select pixel value to be greater than all pixels point of preset threshold.
10. image processing apparatus according to claim 9, which is characterized in that the computing module further include: four processing
Module;
Four processing modules are used for after the image that obtains that treated three times, to each of treated the image described three times
Each pixel of pixel and the initial pictures seeks common ground, and obtains four times treated image, and after described four times processing
Image in, select pixel value be greater than preset threshold all pixels point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910718432.9A CN110516680B (en) | 2019-08-05 | 2019-08-05 | Image processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910718432.9A CN110516680B (en) | 2019-08-05 | 2019-08-05 | Image processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110516680A true CN110516680A (en) | 2019-11-29 |
CN110516680B CN110516680B (en) | 2023-04-07 |
Family
ID=68624481
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910718432.9A Active CN110516680B (en) | 2019-08-05 | 2019-08-05 | Image processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110516680B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112399150A (en) * | 2020-11-16 | 2021-02-23 | 广州顶新时代电子系统科技有限公司 | Method for optimizing imaging picture of monitoring camera |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894460A (en) * | 2015-12-14 | 2016-08-24 | 乐视云计算有限公司 | Image filtering method and device |
WO2018019128A1 (en) * | 2016-07-29 | 2018-02-01 | 努比亚技术有限公司 | Method for processing night scene image and mobile terminal |
-
2019
- 2019-08-05 CN CN201910718432.9A patent/CN110516680B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894460A (en) * | 2015-12-14 | 2016-08-24 | 乐视云计算有限公司 | Image filtering method and device |
WO2018019128A1 (en) * | 2016-07-29 | 2018-02-01 | 努比亚技术有限公司 | Method for processing night scene image and mobile terminal |
Non-Patent Citations (1)
Title |
---|
李秀明等: "局部自交干扰的无参模糊图像自适应去燥仿真", 《计算机仿真》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112399150A (en) * | 2020-11-16 | 2021-02-23 | 广州顶新时代电子系统科技有限公司 | Method for optimizing imaging picture of monitoring camera |
CN112399150B (en) * | 2020-11-16 | 2023-04-11 | 广州顶新时代电子系统科技有限公司 | Method for optimizing imaging picture of monitoring camera |
Also Published As
Publication number | Publication date |
---|---|
CN110516680B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110473242B (en) | Texture feature extraction method, texture feature extraction device and terminal equipment | |
CN105005973B (en) | A kind of method and device of the quick denoising of image | |
Yu et al. | Fast single image fog removal using edge-preserving smoothing | |
CN104835164B (en) | A kind of processing method and processing device of binocular camera depth image | |
CN111402170B (en) | Image enhancement method, device, terminal and computer readable storage medium | |
CN106570472B (en) | A kind of skin color detection method, device and terminal | |
EP1969560A1 (en) | Edge comparison in segmentation of video sequences | |
CN108830892A (en) | Face image processing process, device, electronic equipment and computer readable storage medium | |
CN106203326B (en) | A kind of image processing method, device and mobile terminal | |
CN110288553A (en) | Image beautification method, device and electronic equipment | |
CN109214996A (en) | A kind of image processing method and device | |
CN111144337A (en) | Fire detection method and device and terminal equipment | |
CN110288521A (en) | Image beautification method, device and electronic equipment | |
CN111429371B (en) | Image processing method and device and terminal equipment | |
CN108805838A (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
CN103607589A (en) | Level selection visual attention mechanism-based image JND threshold calculating method in pixel domain | |
CN111383178A (en) | Image enhancement method and device and terminal equipment | |
Wang et al. | An efficient method for image dehazing | |
CN112991197A (en) | Low-illumination video enhancement method and device based on detail retention of dark channel | |
CN110516680A (en) | Image processing method and device | |
CN112435182B (en) | Image noise reduction method and device | |
CN113052923A (en) | Tone mapping method, tone mapping apparatus, electronic device, and storage medium | |
CN105959512B (en) | 3D noise reduction implementation method and device | |
CN111222446A (en) | Face recognition method, face recognition device and mobile terminal | |
CN110633705A (en) | Low-illumination imaging license plate recognition method and device |
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 |