CN107507158A - A kind of image processing method and device - Google Patents
A kind of image processing method and device Download PDFInfo
- Publication number
- CN107507158A CN107507158A CN201610414797.9A CN201610414797A CN107507158A CN 107507158 A CN107507158 A CN 107507158A CN 201610414797 A CN201610414797 A CN 201610414797A CN 107507158 A CN107507158 A CN 107507158A
- Authority
- CN
- China
- Prior art keywords
- image
- scaling
- primary election
- gray
- gray level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000007704 transition Effects 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 description 15
- 230000006870 function Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method, it is characterised in that methods described includes：Obtain the positional information of original image and the original image；Searched and the original image location information identical primary election image in prestored images storehouse；The picture characteristics of the original image and the picture characteristics of the primary election image are contrasted, is filtered out from the primary election image and meets that the end of preparatory condition selects image；Select image to carry out image co-registration the original image and the end, obtain the original image after improving.The embodiment of the present invention also discloses a kind of image processing apparatus simultaneously.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of image processing method and device.
Background technology
With the popularization of network and various intelligent terminals, taken pictures using intelligent terminals such as mobile phone, tablet personal computers
Have become the means of the most frequently used acquisition image of user.Intelligent terminal is constantly updated, and the function of taking pictures is also continuous therewith
Renewal, while camera function is weeded out the old and bring forth the new, how reasonable integration resource, lifting the effect taken pictures becomes most crucial pass
Key point.
In the prior art, the effect of taking pictures of intelligent terminal is improved by lifting existing optical device, but acceptor
The limitation of the factors such as product, the method for the effect of taking pictures of intelligent terminal is lifted by improving existing optical device, cost compared with
Height, and effect is limited.In addition, it is conventional by the optimization to software algorithm to the image captured by intelligent terminal
The method that effect is lifted, its lifting to image effect can only be typically improved to single effect, and only be passed through
Algorithm is handled the current captured image of user, and image synthesis quality is not carried using other reasonable resources
Rise.
The content of the invention
In order to solve the above technical problems, the embodiment of the present invention it is expected to provide a kind of image processing method and device, do not increase
While hardware cost, terminal device effect of taking pictures is set to get a promotion using resources such as networks.
The technical proposal of the invention is realized in this way：
In a first aspect, the embodiments of the invention provide a kind of image processing method, methods described includes：
Obtain the positional information of original image and the original image；
Searched and the original image location information identical primary election image in prestored images storehouse；
The picture characteristics of the original image and the picture characteristics of the primary election image are contrasted, from the primary election figure
Filtered out as in and meet that the end of preparatory condition selects image；
Select image to carry out image co-registration the original image and the end, obtain the original image after improving.
In such scheme, the original image and the primary election image are subjected to size scaling, obtain scaling original image
With scaling primary election image；
The scaling original image and the scaling primary election image are subjected to greyscale transformation, obtain the scaling original image
Gray level image with it is described scaling primary election image gray level image；
According to preset strategy, by the gray level image of the gray level image of the scaling original image and the scaling primary election image
Be converted to corresponding black white image；Wherein, black white image corresponding to the gray level image of the scaling original image is the first black and white
Image, black white image corresponding to the gray level image of the scaling primary election image is the second black white image；
First comparison value of first black white image and the second comparison value of the second black white image are contrasted, from institute
State to obtain in scaling primary election image and meet that the end of preparatory condition selects image.
In such scheme, by the gray value of each pixel and the scaling in the gray level image of the scaling original image
The average gray of all pixels is contrasted in the gray level image of original image, by the gray level image of the scaling original image
It is converted into the first black white image；
By the gray value of each pixel in the gray level image of the scaling primary election image and the scaling primary election image
The average gray of all pixels is contrasted in gray level image, by the greyscale image transitions of the scaling primary election image into second
Black white image.
In such scheme, when grey scale pixel value is more than or equal to the scaling original in the gray level image of the scaling original image
In the gray level image of beginning image during the average gray of all pixels, the pixel is labeled as first state；
When grey scale pixel value is less than the gray-scale map of the scaling original image in the gray level image of the scaling original image
As in during the average gray of all pixels, the pixel is labeled as the second state.
In such scheme, at the beginning of grey scale pixel value is more than or equal to the scaling in the gray level image of the scaling primary election image
When selecting the average gray of all pixels in the gray level image of image, the pixel is labeled as first state；
When grey scale pixel value is less than the gray-scale map of the scaling primary election image in the gray level image of the scaling primary election image
As in during the average gray of all pixels, the pixel is labeled as the second state.
In such scheme, when first black white image the first comparison value and the second black white image the second comparison value not
When identical digit is less than or equal to the first predetermined threshold value, the zoomed image corresponding with second black white image is default to meet
The end of condition selects image；
When the digit that the first comparison value of first black white image and the second comparison value of the second black white image differ
During more than the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
Second aspect, the embodiment of the present invention additionally provide a kind of image processing apparatus, and described device includes：
The acquisition module, for obtaining the positional information of original image and the original image；
The searching modul, for being searched and the original image location information identical primary election in prestored images storehouse
Image；
The screening module, for the picture characteristics of the picture characteristics of the original image and the primary election image to be carried out
Contrast, filters out from the primary election image and meets that the end of preparatory condition selects image；
The acquisition module, it is additionally operable to select image to carry out image co-registration the original image and the end, obtaining improves
Original image afterwards.
In such scheme, the acquisition module, for the original image and the primary election image to be carried out into size scaling,
Obtain scaling original image and scaling primary election image；
And the scaling original image and the scaling primary election image are subjected to greyscale transformation, it is former to obtain the scaling
The gray level image of the gray level image of beginning image and the scaling primary election image；
The modular converter, for according to preset strategy, by the gray level image of the scaling original image and the scaling
The greyscale image transitions of primary election image are corresponding black white image；Wherein, corresponding to the gray level image of the scaling original image
Black white image is the first black white image, and black white image corresponding to the gray level image of the scaling primary election image is the second artwork master
Picture；
The acquisition module, it is additionally operable to second by the first comparison value of first black white image and the second black white image
Comparison value is contrasted, and is obtained from the scaling primary election image and is met that the end of preparatory condition selects image.
In such scheme, the modular converter, for by it is described scaling original image gray level image in each pixel
Gray value and the scaling original image gray level image in the average gray of all pixels contrasted, by the scaling
The greyscale image transitions of original image are into the first black white image；
And the gray value of each pixel in the gray level image of the scaling primary election image is scaled into primary election figure with described
The average gray of all pixels is contrasted in the gray level image of picture, by it is described scaling primary election image greyscale image transitions into
Second black white image.
In such scheme, the mark module, for when grey scale pixel value in the gray level image of the scaling original image
More than or equal in the gray level image of the scaling original image during average gray of all pixels, by the pixel labeled as the
One state；
And when it is described scaling original image gray level image in grey scale pixel value be less than it is described scaling original image ash
When spending the average gray of all pixels in image, the pixel is labeled as the second state.
In such scheme, the mark module, for when grey scale pixel value in the gray level image of the scaling primary election image
More than or equal in the gray level image of the scaling primary election image during average gray of all pixels, by the pixel labeled as the
One state；
And when it is described scaling primary election image gray level image in grey scale pixel value be less than it is described scaling primary election image ash
When spending the average gray of all pixels in image, the pixel is labeled as the second state.
In such scheme, the acquisition module, for when the first comparison value and the second black and white of first black white image
It is corresponding with second black white image when digit that second comparison value of image differs is less than or equal to the first predetermined threshold value
Zoomed image is to select image at the end for meeting preparatory condition；
And differed when the first comparison value of first black white image with the second comparison value of the second black white image
When digit is more than the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
The embodiments of the invention provide a kind of image processing method and device, using terminal device get original image and
Its positional information, the image in the image libraries such as network with same position information is then found, the image found is carried out
Further screening obtains the image image the most approximate got with terminal device, finally carries out image co-registration and obtains effect most
Excellent image deposit terminal device, takes full advantage of the resources such as network, the increase of no hardware cost so that terminal device photographs
Image co-registration multiple image the advantages of so that terminal device effect of taking pictures is improved.
Brief description of the drawings
Fig. 1 is the image processing method schematic flow sheet that inventive embodiments one provide；
Fig. 2 is the method flow schematic diagram that image is selected in the acquisition that inventive embodiments one provide eventually；
Fig. 3 is the gray level image by coloured image after greyscale transformation that inventive embodiments one provide；
Fig. 4 is the black white image by gray level image after conversion that inventive embodiments one provide；
Fig. 5 is the method flow schematic diagram by greyscale image transitions into black white image that inventive embodiments one provide；
Fig. 6 is the image processing apparatus structural representation that inventive embodiments two provide.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes.
The basic thought of the embodiment of the present invention is：In terminal device, first with the own configuration of terminal device, open
Positioning function, taken pictures afterwards with terminal device.Then it will take a picture and go out figure from network preliminary screening according to location information
As to reduce follow-up work amount, required qualitative picture further being obtained in the image gone out afterwards from network preliminary screening, most
Merged afterwards using the qualitative picture got with original image, obtain better image data, finally realize that camera is clapped
According to the larger lifting of effect.
Embodiment one
Referring to Fig. 1, it illustrates the embodiment of the present invention to provide a kind of image processing method, and methods described can include：
S101, the positional information for obtaining original image and the original image.
Specifically, being taken pictures using the terminal device with camera function, original image is obtained.In the front opening taken pictures
The positioning function of terminal device, such as GPS location function, the positional information for shooting original image is got while taking pictures.Institute
The positional information for stating original image can be latitude and longitude coordinates or specified place title etc..
The specific positional information in original image spot for photography, which is obtained, using positioning function is used for acquisition and original image location
Information identical image.
S102, searched and the original image location information identical primary election image in prestored images storehouse.
Preferably, pre-stored image library can be from NetFind to image.User can pass through terminal device
Network is connected, from the positional information identical image of web search and shooting original image.Can also directly it be utilized by backstage
Original image location information goes out the image of same position information in web search, the as primary election figure obtained by the above method
Picture.Wherein, pre-stored image library can also be that server, cloud disk, PC, mobile hard disk etc. have setting for store function
The image with positional information of standby middle storage.
Can be by accessed primary election image storage in specific server.For example, from Network Capture to primary election
Image, it is contemplated that the limitation of terminal device memory space, can by from Network Capture to primary election image storage specifically taking
It is engaged in device, to do further screening with comparing with original image.
S103, the picture characteristics of the original image and the picture characteristics of the primary election image contrasted, from described
Filtered out in primary election image and meet that the end of preparatory condition selects image.
Contrasted using the picture characteristics and the picture characteristics of the primary election image of the original image, it is full to obtain
The end of sufficient preparatory condition selects image.
It should be noted that after getting original image and primary election image, it is necessary to using picture characteristics to original image with
Primary election image carries out a contrast, is further screened.The purpose further screened is to choose and original image institute
The immediate image of image of shooting.
Original image is colored image with primary election image, and the utilization to picture characteristics, the embodiment of the present invention is to pass through
Original image and primary election image are first subjected to size scaling, then turned the original image after size scaling and primary election image
Change gray-scale map into, then described gray-scale map be converted into corresponding artwork master, finally corresponding artwork master is analyzed,
Obtain the image for meeting preparatory condition.
Here, it is closest with original image to meet that the image of preparatory condition refers to further to filter out from primary election image
Image.
Specifically, it can include referring to Fig. 2, step S103：S1031 to S1034：
S1031, the original image and the primary election image are carried out to size scaling, acquisition scaling original image and scaling
Primary election image.
For compatible various sizes of image, it is necessary first to the original image of terminal device shooting with from prestored images
The primary election image got in storehouse carries out size scaling, by above-mentioned image scaling to unified size.
Preferably, most image scaled is 4 at present:3, the statistic of integrated information and the speed of search etc. because
Element, the original image captured by terminal device uniformly zooms to the primary election image got from prestored images storehouse to 16 ×
The image of 12 sizes, the image of 16 × 12 sizes are made up of 192 pixels.
Here pass through the original image captured by the terminal device of scaling and got from prestored images storehouse first
It is still coloured image to select image.
S1032, the scaling original image and the scaling primary election image be subjected to greyscale transformation, it is former to obtain the scaling
The gray level image of the gray level image of beginning image and the scaling primary election image.
It should be noted that carry out greyscale transformation to each pixel of original image and primary election image, then each width figure
As can all obtain 192 gray values.
Due to the color that each pixel is made up of Red Green Blue in coloured image, directly to coloured image
Computation complexity can be increased by carrying out processing, therefore first color image into gray level image.
Assuming that the color of some pixel is RGB (R, G, B) in coloured image, then, following five kinds of sides can be passed through
Method colors image into gray level image：
1st, floating-point arithmetic：Gray=R × 0.3+G × 0.59+B × 0.11；
2nd, integer arithmetic：Gray=(R × 30+G × 59+B × 11)/100；
3rd, shifting algorithm：Gray=(R × 76+G × 151+B × 28)>>8；
4th, mean value method：Gray=(R+G+B)/3；
5th, green is only taken：Gray=G.
It should be noted that above-mentioned operator>>Represent shift right operation, move to right one equivalent to divided by 2, it is suitable to move to right n positions
In divided by 2 n powers.Shifting algorithm is due to no faster than integer arithmetic using direct division process, algorithm speed.Here adopt
With moving to right 8, equivalent to by floating-point operation divided by 28 powers, therefore, it is necessary to the coefficient of floating-point arithmetic is multiplied by 8 times of 2
Side keeps the result of former floating-point operation.Above-mentioned example multiplies the coefficient of floating-point arithmetic using the coefficient of 8 precision respectively
With 28 power, i.e., 256.
After three coefficients are multiplied by 256 respectively in above-mentioned floating-point arithmetic, transformation of coefficient is：
0.3 × 256=76.8 ≈ 76；0.59 × 256=151.04 ≈ 151；0.11 × 256=28.16 ≈ 28
Shifting algorithm is obtained by floating-point arithmetic by above-mentioned conversion can, wherein, shifting algorithm except 8 precision, 2 to
The coefficient of 20 precision is all desirable.
After trying to achieve Gray by any of the above-described kind of method, by the R in original RGB (R, G, B), G, B are unified to be replaced with Gray
Change, form new color space RGB (Gray, Gray, Gray).With new color space RGB (Gray, Gray, Gray) by original
The RGB (R, G, B) come is replaced, and cromogram originally has reformed into gray-scale map, as shown in figure 3, Fig. 3, which is coloured image, passes through gray scale
The gray level image obtained after conversion.
The method that above-mentioned coloured image is converted into gray level image is applied to the scaling original image after size scaling
With scaling primary election image, obtain scaling original image with scaling the gray level image corresponding to primary election image.
S1033, according to preset strategy, by the ash of the gray level image of the scaling original image and the scaling primary election image
Degree image is converted to corresponding black white image.
Wherein, black white image corresponding to the gray level image of the scaling original image is the first black white image, the scaling
Black white image corresponding to the gray level image of primary election image is the second black white image
It should be noted that scaling original image and scaling primary election image are needed to carry out the conversion of black white image respectively,
As shown in figure 4, Fig. 4 is that the gray-scale map shown in Fig. 3 is converted into the image after artwork master.
Specifically, include S10331 and S10332 referring to Fig. 5, step S1033：
S10331, by it is described scaling original image gray level image in each pixel gray value with it is described scale it is original
The average gray of all pixels is contrasted in the gray level image of image, by the greyscale image transitions of the scaling original image
Into the first black white image.
Specifically, step S10331 includes：
When grey scale pixel value is more than or equal to the ash of the scaling original image in the gray level image of the scaling original image
When spending the average gray of all pixels in image, the pixel is labeled as first state.
When grey scale pixel value is less than the gray-scale map of the scaling original image in the gray level image of the scaling original image
As in during the average gray of all pixels, the pixel is labeled as the second state.
In embodiments of the present invention, the first state is represented with " 1 ", and second state is represented with " 0 ".With " 0 " table
Show black, white represented with " 1 ", thus, scale original image gray level image be converted into one it is binary first black
White image.
S10332, gray value and the scaling primary election by each pixel in the gray level image of the scaling primary election image
The average gray of all pixels is contrasted in the gray level image of image, by the greyscale image transitions of the scaling primary election image
Into the second black white image.
Specifically, step S10332 includes：
When grey scale pixel value is more than or equal to the ash of the scaling primary election image in the gray level image of the scaling primary election image
When spending the average gray of all pixels in image, the pixel is labeled as first state.
When grey scale pixel value is less than the gray-scale map of the scaling primary election image in the gray level image of the scaling primary election image
As in during the average gray of all pixels, the pixel is labeled as the second state.
It is to be appreciated that it is identical into the method for the first black white image with the greyscale image transitions of above-mentioned scaling original image,
The greyscale image transitions of primary election image will be scaled into binary second black white image.
S1034, the second comparison value of the first comparison value of first black white image and the second black white image carried out pair
Than being obtained from the scaling primary election image and meeting that the end of preparatory condition selects image.
It should be noted that if two pictures are much like, its black and white profile should be similar, by comparing scaling original
First comparison value of the first black white image of beginning image and the second comparison value of the second black white image of scaling primary election image, can be with
Acquisition meets that the end of preparatory condition selects image.
After the gray level image of scaling original image obtains binary first black white image, it is recorded as one 16 and enters
First comparison value of system.Likewise, after the black white image of binary system second that the gray level image of scaling primary election image obtains, remembered
Record as hexadecimal second comparison value.
Above-mentioned first comparison value is used to that the first black white image and the scaling primary election of original image will to be scaled with the second comparison value
Second black white image of image is contrasted, to determine to scale the first black white image and the of scaling primary election image of original image
The similitude of two black white images.
Specifically, step S1034 includes：
When the digit that the first comparison value of first black white image and the second comparison value of the second black white image differ
During less than or equal to the first predetermined threshold value, the zoomed image corresponding with second black white image is the whole choosing for meeting preparatory condition
Image.
When the digit that the first comparison value of first black white image and the second comparison value of the second black white image differ
During more than the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
Preferably, the first predetermined threshold value can be set to 10.First when the first black white image of scaling original image compares
When the digit that value and the second comparison value of the second black white image of scaling primary election image differ is less than or equal to 10, illustrate original graph
As much like with primary election image, the primary election image selection is selected into image to be whole；When the first black white image for scaling original image
When the digit that first comparison value and the second comparison value of the second black white image of scaling primary election image differ is more than 10, illustrate original
Beginning image is not high with primary election image similarity, and it is terminal image not select the primary election image.Here, acquisition meets preparatory condition
Terminal image quantity be likely to be a width it could also be possible that a few width.
S104, the original image and the end for meeting preparatory condition are selected to image progress image co-registration, obtaining improves
Original image afterwards.
It should be noted that by the original image taken by terminal device with filtering out from pre-stored image library
One width or a few width select image to carry out image co-registration eventually, obtain the original image after a width improves, and by the image storage in terminal
In equipment.
The purpose of image co-registration is the information of the multiple images of comprehensive same scene, the result is that being more suitable for the vision of people
With the piece image of computer vision.Image Fusion is relatively more at present, including Multi-Sensory Image Fusion at Pixel Level, weighted average
The image co-registration of method and Wavelet Transform, wherein Pixel-level is the image co-registration of lowest level, but the fusion of the level is accurate
Property highest, using the teaching of the invention it is possible to provide the detailed information not available for fusion on other levels.Due to current algorithm comparison maturation herein
No longer it is described in detail.
The embodiments of the invention provide a kind of image processing method, and original image and its position are got using terminal device
Information, the image in the image libraries such as network with same position information is then found, the image found is carried out further
Screening obtains the image image the most approximate got with terminal device, finally carries out image co-registration and obtains the optimal figure of effect
As deposit terminal device, the resources such as network, the increase of no hardware cost are taken full advantage of so that the image that terminal device photographs
The advantages of having merged multiple image so that terminal device effect of taking pictures is improved.
Embodiment two
Referring to Fig. 6, it illustrates the embodiment of the present invention to provide a kind of image processing apparatus, and described device includes：Obtain mould
Block 601, searching modul 602 and screening module 603；Wherein
The acquisition module 601, for obtaining the positional information of original image and the original image；
The searching modul 602, for being searched and the original image location information identical in prestored images storehouse
Primary election image；
The screening module 603, for by the picture characteristics of the picture characteristics of the original image and the primary election image
Contrasted, filtered out from the primary election image and meet that the end of preparatory condition selects image；
The acquisition module 601, it is additionally operable to select image to carry out image co-registration the original image and the end, acquisition changes
The original image dealt with problems arising from an accident.
Further, described device also includes：Modular converter 604；
The acquisition module 601, for the original image and the primary election image to be carried out into size scaling, obtain scaling
Original image and scaling primary election image；
And the scaling original image and the scaling primary election image are subjected to greyscale transformation, it is former to obtain the scaling
The gray level image of the gray level image of beginning image and the scaling primary election image；
The modular converter 604, for according to preset strategy, by the gray level image of the scaling original image and the contracting
The greyscale image transitions for putting primary election image are corresponding black white image；Wherein, the gray level image of the scaling original image is corresponding
Black white image be the first black white image, it is described scaling primary election image gray level image corresponding to black white image be the second artwork master
Picture；
The acquisition module 601, it is additionally operable to the first comparison value of first black white image and the second black white image
Second comparison value is contrasted, and is obtained from the scaling primary election image and is met that the end of preparatory condition selects image.
Further, the modular converter 604, for by it is described scaling original image gray level image in each pixel
Gray value and the scaling original image gray level image in the average gray of all pixels contrasted, by the scaling
The greyscale image transitions of original image are into the first black white image；
And the gray value of each pixel in the gray level image of the scaling primary election image is scaled into primary election figure with described
The average gray of all pixels is contrasted in the gray level image of picture, by it is described scaling primary election image greyscale image transitions into
Second black white image.
Further, described device also includes：Mark module 605；
The mark module 605, for when it is described scaling original image gray level image in grey scale pixel value be more than or equal to
In the gray level image of the scaling original image during average gray of all pixels, the pixel is labeled as first state；
And when it is described scaling original image gray level image in grey scale pixel value be less than it is described scaling original image ash
When spending the average gray of all pixels in image, the pixel is labeled as the second state.
Further, the mark module 605, for when grey scale pixel value in the gray level image of the scaling primary election image
More than or equal in the gray level image of the scaling primary election image during average gray of all pixels, by the pixel labeled as the
One state；
And when it is described scaling primary election image gray level image in grey scale pixel value be less than it is described scaling primary election image ash
When spending the average gray of all pixels in image, the pixel is labeled as the second state.
Further, the acquisition module 601, for when the first comparison value and the second black and white of first black white image
It is corresponding with second black white image when digit that second comparison value of image differs is less than or equal to the first predetermined threshold value
Zoomed image is to select image at the end for meeting preparatory condition；
And differed when the first comparison value of first black white image with the second comparison value of the second black white image
When digit is more than the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
Specifically, the explanation of image processing apparatus provided in an embodiment of the present invention may be referred to the image procossing of embodiment one
The explanation of method, the embodiment of the present invention will not be repeated here.
In actual applications, the acquisition module 601, searching modul 602, screening module 603, modular converter 604 and mark
Remember module 605 can by the central processing unit (Central Processing Unit, CPU) in image processing apparatus 6,
Microprocessor (Micro Processor Unit, MPU), digital signal processor (Digital Signal Processor,
DSP) or field programmable gate array (Field Programmable Gate Array, FPGA) etc. is realized.
The embodiments of the invention provide a kind of image processing apparatus, and original image and its position are got using terminal device
Information, the image in the image libraries such as network with same position information is then found, the image found is carried out further
Screening obtains the image image the most approximate got with terminal device, finally carries out image co-registration and obtains the optimal figure of effect
As deposit terminal device, the resources such as network, the increase of no hardware cost are taken full advantage of so that the image that terminal device photographs
The advantages of having merged multiple image so that terminal device effect of taking pictures is improved.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the shape of the embodiment in terms of the present invention can use hardware embodiment, software implementation or combination software and hardware
Formula.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more to use storage
The form for the computer program product that medium is implemented on (including but is not limited to magnetic disk storage and optical memory etc.).
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention.
Claims (12)
1. a kind of image processing method, it is characterised in that methods described includes：
Obtain the positional information of original image and the original image；
Searched and the original image location information identical primary election image in prestored images storehouse；
The picture characteristics of the original image and the picture characteristics of the primary election image are contrasted, from the primary election image
Filter out and meet that the end of preparatory condition selects image；
Select image to carry out image co-registration the original image and the end, obtain the original image after improving.
2. according to the method for claim 1, it is characterised in that the picture characteristics by the original image with it is described just
Select the picture characteristics of image to be contrasted, filtered out from the primary election image and meet that the end of preparatory condition selects image, including：
The original image and the primary election image are subjected to size scaling, obtain scaling original image and scaling primary election image；
The scaling original image and the scaling primary election image are subjected to greyscale transformation, obtain the ash of the scaling original image
Spend the gray level image of image and the scaling primary election image；
According to preset strategy, by the greyscale image transitions of the gray level image of the scaling original image and the scaling primary election image
For corresponding black white image；Wherein, black white image corresponding to the gray level image of the scaling original image is the first black white image,
Black white image corresponding to the gray level image of the scaling primary election image is the second black white image；
First comparison value of first black white image and the second comparison value of the second black white image are contrasted, from the contracting
Put to obtain in primary election image and meet that the end of preparatory condition selects image.
3. according to the method for claim 2, it is characterised in that it is described according to preset strategy, by the scaling original image
Gray level image with it is described scaling primary election image greyscale image transitions be corresponding black white image, including：
By the gray scale of the gray value of each pixel and the scaling original image in the gray level image of the scaling original image
The average gray of all pixels is contrasted in image, by the greyscale image transitions of the scaling original image into the first black and white
Image；
By the gray scale of the gray value of each pixel and the scaling primary election image in the gray level image of the scaling primary election image
The average gray of all pixels is contrasted in image, by the greyscale image transitions of the scaling primary election image into the second black and white
Image.
4. according to the method for claim 3, it is characterised in that it is described will be every in the gray level image of the scaling original image
The gray value of one pixel and the average gray of all pixels in the gray level image of the scaling original image are contrasted, will
It is described scaling original image greyscale image transitions into the first black white image, including：
When grey scale pixel value is more than or equal to the gray-scale map of the scaling original image in the gray level image of the scaling original image
As in during the average gray of all pixels, the pixel is labeled as first state；
When grey scale pixel value is less than in the gray level image of the scaling original image in the gray level image of the scaling original image
During the average gray of all pixels, the pixel is labeled as the second state.
5. according to the method for claim 3, it is characterised in that it is described will be every in the gray level image of the scaling primary election image
The gray value of one pixel and the average gray of all pixels in the gray level image of the scaling primary election image are contrasted, will
It is described scaling primary election image greyscale image transitions into the second black white image, including：
When grey scale pixel value is more than or equal to the gray-scale map of the scaling primary election image in the gray level image of the scaling primary election image
As in during the average gray of all pixels, the pixel is labeled as first state；
When grey scale pixel value is less than in the gray level image of the scaling primary election image in the gray level image of the scaling primary election image
During the average gray of all pixels, the pixel is labeled as the second state.
6. according to the method for claim 2, it is characterised in that first comparison value by first black white image with
Second comparison value of the second black white image is contrasted, and the whole choosing figure for meeting preparatory condition is obtained from the scaling primary election image
Picture, including：
When the digit that the first comparison value of first black white image differs with the second comparison value of the second black white image is less than
During equal to the first predetermined threshold value, the zoomed image corresponding with second black white image is the whole choosing figure for meeting preparatory condition
Picture；
When the digit that the first comparison value of first black white image differs with the second comparison value of the second black white image is more than
During the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
7. a kind of image processing apparatus, it is characterised in that described device includes：Acquisition module, searching modul and screening module；Its
In
The acquisition module, for obtaining the positional information of original image and the original image；
The searching modul, for being searched and the original image location information identical primary election figure in prestored images storehouse
Picture；
The screening module, for the picture characteristics of the picture characteristics of the original image and the primary election image to be carried out pair
Than being filtered out from the primary election image and meeting that the end of preparatory condition selects image；
The acquisition module, it is additionally operable to select image to carry out image co-registration the original image and the end, obtains after improving
Original image.
8. device according to claim 7, it is characterised in that described device also includes：Modular converter；
The acquisition module, for the original image and the primary election image to be carried out into size scaling, obtain scaling original graph
As with scaling primary election image；
And the scaling original image and the scaling primary election image are subjected to greyscale transformation, obtain the scaling original graph
The gray level image of the gray level image of picture and the scaling primary election image；
The modular converter, for according to preset strategy, by the gray level image of the scaling original image and the scaling primary election
The greyscale image transitions of image are corresponding black white image；Wherein, black and white corresponding to the gray level image of the scaling original image
Image is the first black white image, and black white image corresponding to the gray level image of the scaling primary election image is the second black white image；
The acquisition module, it is additionally operable to compare the first comparison value of first black white image and the second of the second black white image
Value is contrasted, and is obtained from the scaling primary election image and is met that the end of preparatory condition selects image.
9. device according to claim 8, it is characterised in that
The modular converter, for by gray value and the contracting of each pixel in the gray level image of the scaling original image
The average gray for putting all pixels in the gray level image of original image is contrasted, by the gray-scale map of the scaling original image
As being converted into the first black white image；
And by the gray value of each pixel in the gray level image of the scaling primary election image and the scaling primary election image
The average gray of all pixels is contrasted in gray level image, by the greyscale image transitions of the scaling primary election image into second
Black white image.
10. device according to claim 9, it is characterised in that described device also includes：Mark module；
The mark module, for when it is described scaling original image gray level image in grey scale pixel value be more than or equal to the scaling
In the gray level image of original image during the average gray of all pixels, the pixel is labeled as first state；
And when it is described scaling original image gray level image in grey scale pixel value be less than it is described scaling original image gray-scale map
As in during the average gray of all pixels, the pixel is labeled as the second state.
11. device according to claim 9, it is characterised in that
The mark module, for when it is described scaling primary election image gray level image in grey scale pixel value be more than or equal to the scaling
In the gray level image of primary election image during the average gray of all pixels, the pixel is labeled as first state；
And when it is described scaling primary election image gray level image in grey scale pixel value be less than it is described scaling primary election image gray-scale map
As in during the average gray of all pixels, the pixel is labeled as the second state.
12. device according to claim 8, it is characterised in that
The acquisition module, for when the first comparison value and the second comparison value of the second black white image of first black white image
When the digit differed is less than or equal to the first predetermined threshold value, the zoomed image corresponding with second black white image is pre- to meet
If the end of condition selects image；
And the digit differed when the first comparison value of first black white image and the second comparison value of the second black white image
During more than the first predetermined threshold value, the corresponding zoomed image of second black white image is unsatisfactory for preparatory condition.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610414797.9A CN107507158A (en) | 2016-06-14 | 2016-06-14 | A kind of image processing method and device |
| PCT/CN2016/107004 WO2017215194A1 (en) | 2016-06-14 | 2016-11-23 | Image processing method and device and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610414797.9A CN107507158A (en) | 2016-06-14 | 2016-06-14 | A kind of image processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107507158A true CN107507158A (en) | 2017-12-22 |
Family
ID=60663436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610414797.9A Withdrawn CN107507158A (en) | 2016-06-14 | 2016-06-14 | A kind of image processing method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107507158A (en) |
| WO (1) | WO2017215194A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473249A (en) * | 2019-07-12 | 2019-11-19 | 平安普惠企业管理有限公司 | A kind of control methods, device and the terminal device of web user interface and design original text |
| CN112532856A (en) * | 2019-09-17 | 2021-03-19 | 中兴通讯股份有限公司 | Shooting method, device and system |
| WO2021115483A1 (en) * | 2019-12-13 | 2021-06-17 | 华为技术有限公司 | Image processing method and related apparatus |
| CN114697543A (en) * | 2020-12-31 | 2022-07-01 | 华为技术有限公司 | An image reconstruction method, related device and system |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648340B (en) * | 2019-09-29 | 2023-03-17 | 惠州学院 | Method and device for processing image based on binary system and level set |
| CN114357239B (en) * | 2022-01-07 | 2025-01-24 | 重庆紫光华山智安科技有限公司 | An automated view library service guarantee system and method |
| CN119850655B (en) * | 2025-03-20 | 2025-05-30 | 中国人民解放军总医院海南医院 | Gray image processing system, gray image processing device and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7720851B2 (en) * | 2006-05-16 | 2010-05-18 | Eastman Kodak Company | Active context-based concept fusion |
| CN101566994B (en) * | 2008-04-22 | 2011-02-16 | 王磊 | Image and video retrieval method |
| CN102915326A (en) * | 2012-08-30 | 2013-02-06 | 杭州藕根科技有限公司 | Mobile terminal scenery identifying system based on GPS (Global Positioning System) and image search technique |
| CN103440318B (en) * | 2013-08-29 | 2016-08-17 | 王靖洲 | The landscape identifying system of mobile terminal |
| CN104537608A (en) * | 2014-12-31 | 2015-04-22 | 深圳市中兴移动通信有限公司 | Image processing method and device |
| CN105046676A (en) * | 2015-08-27 | 2015-11-11 | 上海斐讯数据通信技术有限公司 | Image fusion method and equipment based on intelligent terminal |
-
2016
- 2016-06-14 CN CN201610414797.9A patent/CN107507158A/en not_active Withdrawn
- 2016-11-23 WO PCT/CN2016/107004 patent/WO2017215194A1/en active Application Filing
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473249A (en) * | 2019-07-12 | 2019-11-19 | 平安普惠企业管理有限公司 | A kind of control methods, device and the terminal device of web user interface and design original text |
| CN112532856A (en) * | 2019-09-17 | 2021-03-19 | 中兴通讯股份有限公司 | Shooting method, device and system |
| CN112532856B (en) * | 2019-09-17 | 2023-10-17 | 中兴通讯股份有限公司 | Shooting method, device and system |
| US12125168B2 (en) | 2019-09-17 | 2024-10-22 | Zte Corporation | Photographing method, apparatus and system, and computer readable storage medium |
| WO2021115483A1 (en) * | 2019-12-13 | 2021-06-17 | 华为技术有限公司 | Image processing method and related apparatus |
| US12154251B2 (en) | 2019-12-13 | 2024-11-26 | Huawei Technologies Co., Ltd. | Image processing method and related apparatus |
| CN114697543A (en) * | 2020-12-31 | 2022-07-01 | 华为技术有限公司 | An image reconstruction method, related device and system |
| CN114697543B (en) * | 2020-12-31 | 2023-05-19 | 华为技术有限公司 | An image reconstruction method, related device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017215194A1 (en) | 2017-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107507158A (en) | A kind of image processing method and device | |
| CN109919869B (en) | Image enhancement method and device and storage medium | |
| CN106504220B (en) | A kind of image processing method and device | |
| CN113034348B (en) | Image processing method, device, storage medium and equipment | |
| CN113012081B (en) | Image processing method, device and electronic system | |
| US20170285916A1 (en) | Camera effects for photo story generation | |
| CN104704807B (en) | Image processing apparatus, camera device and image processing method | |
| SE1150505A1 (en) | Method and apparatus for taking pictures | |
| CN109801279B (en) | Method and device for detecting target in image, electronic equipment and storage medium | |
| CN105809643B (en) | A kind of image enchancing method based on adaptive block channel extrusion | |
| CN103971134B (en) | Image classification, retrieval and bearing calibration, and related device | |
| CN106713696A (en) | Image processing method and device | |
| CN107948733A (en) | Method of video image processing and device, electronic equipment | |
| CN112037160B (en) | Image processing method, device and equipment | |
| CN107464251A (en) | The black edge detection method and device of a kind of image | |
| CN111369431A (en) | Image processing method and device, readable medium and electronic equipment | |
| CN104809716A (en) | Method and equipment for determining image offset | |
| CN108304839A (en) | A kind of image processing method and device | |
| CN112788329A (en) | Video static frame detection method and device, television and storage medium | |
| CN105760040A (en) | Method and device for previewing effect through windows | |
| CN106210446A (en) | saturation enhancement method and device | |
| CN110248147B (en) | Image display method and device | |
| CN115731143A (en) | Image processing method, device, electronic device, and computer-readable storage medium | |
| CN104335571B (en) | Image processing apparatus, camera head, computer and image processing method | |
| CN112419218A (en) | Image processing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171222 |
|
| WW01 | Invention patent application withdrawn after publication |