CN105069783B - Fuzzy picture identification method and device - Google Patents
Fuzzy picture identification method and device Download PDFInfo
- Publication number
- CN105069783B CN105069783B CN201510438070.XA CN201510438070A CN105069783B CN 105069783 B CN105069783 B CN 105069783B CN 201510438070 A CN201510438070 A CN 201510438070A CN 105069783 B CN105069783 B CN 105069783B
- Authority
- CN
- China
- Prior art keywords
- picture
- target photo
- pixel
- gray scale
- pixel value
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000003708 edge detection Methods 0.000 claims description 19
- 230000000717 retained effect Effects 0.000 claims description 7
- 238000012805 post-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 8
- 238000009434 installation Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a fuzzy picture identification method and a fuzzy picture identification device. A blurred picture recognition method can comprise the following steps: obtaining a target picture; obtaining a gray level picture corresponding to the target picture; carrying out sharpening processing on the gray level picture to obtain a sharpened picture; determining the pixel value of each pixel point of the sharpened picture; determining a standard deviation of the pixel value of the target picture according to the pixel value of each pixel point of the sharpened picture; and if the standard deviation is lower than a preset standard deviation threshold value, determining the target picture as a fuzzy picture. By applying the technical scheme provided by the embodiment of the invention, the process of identifying the fuzzy picture is simpler, and the identification rate of identifying a large number of pictures can be ensured.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of blurred picture recognition methods and device.
Background technique
Nowadays, in the work and life of people, the camera installation that can be used is more and more, such as camera, with taking the photograph
As mobile phone, the tablet computer etc. of head, people can indiscriminately ad. as one wishes take pictures.With the accumulation of time, the figure taken pictures
Piece is more and more, and the memory space needed is increasing.In fact, can inevitably be generated fuzzy or unclear during taking pictures
Clear picture, if these pictures all stored, it will waste more memory space, and camera installation or computer etc.
The memory space of terminal is all limited, and in many cases, needs to carry out these pictures to delete or other are handled.
Before carrying out deletion or other processing to these blurred pictures at present, need manually to identify which picture is mould
Photo is pasted, if there are many quantity of picture, the process of this identification is relatively complicated, and recognition rate is lower.
Summary of the invention
To solve the above problems, the embodiment of the invention discloses a kind of blurred picture recognition methods and devices.Technical solution
It is as follows:
A kind of blurred picture recognition methods, comprising:
Obtain Target Photo；
Obtain the corresponding gray scale picture of the Target Photo；
Processing is sharpened to the gray scale picture, obtains and sharpens picture；
Determine the pixel value of each pixel for sharpening picture；
According to the pixel value of each pixel for sharpening picture, the mark of the pixel value for the Target Photo is determined
It is quasi- poor；
If the standard deviation is lower than preset standard deviation threshold method, the Target Photo is determined as blurred picture.
In a kind of specific embodiment of the invention, the pixel according to each pixel for sharpening picture
Value determines the standard deviation of the pixel value for the Target Photo, comprising:
For described each pixel for sharpening picture, judge the pixel value of the pixel whether in preset numerical value model
In enclosing, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel value of the pixel；
Calculate the standard deviation of the pixel value of the pixel retained；
The standard deviation being calculated is determined as to the standard deviation of the pixel value for the Target Photo.
It is described to obtain the corresponding gray scale picture of the Target Photo in a kind of specific embodiment of the invention, comprising:
According to preset first proportionate relationship, diminution processing is carried out to the Target Photo, treated to diminution is carried out
Picture carries out gray proces, obtains the corresponding gray scale picture of the Target Photo；
Alternatively,
Obtain with Target Photo gray scale picture of the same size, according to preset second proportionate relationship, to being obtained
Gray scale picture carry out diminution processing, obtain the corresponding gray scale picture of the Target Photo.
In a kind of specific embodiment of the invention, it is described the Target Photo is determined as blurred picture after, also
Include:
Whether output deletes the prompt information of the Target Photo, the selection of the prompt information is directed to according to user, really
It is fixed whether to execute the operation for deleting the Target Photo；
Alternatively,
Directly delete the Target Photo；
Alternatively,
The Target Photo is put into preset Photo folder to be deleted.
It is described that processing is sharpened to the gray scale picture in a kind of specific embodiment of the invention, it is sharpened
Picture, comprising:
Processing is sharpened to the gray scale picture using edge detection operator, obtains and sharpens picture；
Wherein, the edge detection operator is Laplce Laplacian operator, Sobel Sobel operator, Robert
One of Roberts operator, triumphant Buddhist nun Canny operator.
A kind of blurred picture identification device, comprising:
Target Photo obtains module, for obtaining Target Photo；
Gray scale picture obtains module, for obtaining the corresponding gray scale picture of the Target Photo；
It sharpens picture and obtains module, for being sharpened processing to the gray scale picture, obtain and sharpen picture；
Pixel value determining module, for determining the pixel value of each pixel for sharpening picture；
Standard deviation determining module is determined for the pixel value according to each pixel for sharpening picture for described
It is true to trigger blurred picture if the standard deviation is lower than preset standard deviation threshold method for the standard deviation of the pixel value of Target Photo
Cover half block；
The blurred picture determining module, for the Target Photo to be determined as blurred picture.
In a kind of specific embodiment of the invention, the standard deviation determining module, comprising:
Judging submodule, for judging that the pixel value of the pixel is for described each pixel for sharpening picture
It is no in preset numberical range, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel
Pixel value；
Computational submodule, the standard deviation of the pixel value for calculating the pixel retained；
Standard deviation determines submodule, for the standard deviation being calculated to be determined as to the pixel value for the Target Photo
Standard deviation.
In a kind of specific embodiment of the invention, the gray scale picture obtains module, is specifically used for:
According to preset first proportionate relationship, diminution processing is carried out to the Target Photo, treated to diminution is carried out
Picture carries out gray proces, obtains the corresponding gray scale picture of the Target Photo；
Alternatively,
Obtain with Target Photo gray scale picture of the same size, according to preset second proportionate relationship, to being obtained
Gray scale picture carry out diminution processing, obtain the corresponding gray scale picture of the Target Photo.
Further include post-processing module in a kind of specific embodiment of the invention:
The post-processing module, for after the Target Photo is determined as blurred picture, whether output to delete described
The prompt information of Target Photo is directed to the selection of the prompt information according to user, it is determined whether executes and deletes the target figure
The operation of piece；
Alternatively,
Directly delete the Target Photo；
Alternatively,
The Target Photo is put into preset Photo folder to be deleted.
In a kind of specific embodiment of the invention, the sharpening picture obtains module, is specifically used for:
Processing is sharpened to the gray scale picture using edge detection operator, obtains and sharpens picture；
Wherein, the edge detection operator is Laplce Laplacian operator, Sobel Sobel operator, Robert
One of Roberts operator, triumphant Buddhist nun Canny operator.
Using technical solution provided by the embodiment of the present invention, the corresponding gray scale picture of the Target Photo of acquisition is carried out sharp
After change processing, according to the pixel value for each pixel for sharpening picture, the standard deviation of the pixel value of Target Photo, standard deviation are determined
Lower than preset standard deviation threshold method, then it may indicate that the object edge of the Target Photo is not clear enough, it can be by the Target Photo
It is determined as blurred picture, identifies that the process of blurred picture is relatively simple, it is ensured that the identification identified to a large amount of picture
Rate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of implementation flow chart of blurred picture recognition methods in the embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of gray scale picture in the embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of blurred picture identification device in the embodiment of the present invention.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in the embodiment of the present invention, below in conjunction with this hair
Attached drawing in bright embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described
Embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field
Those of ordinary skill's every other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
It is shown in Figure 1, it is a kind of implementation flow chart of blurred picture recognition methods provided by the embodiment of the present invention, it should
Method may comprise steps of:
S110: Target Photo is obtained；
It is understood that Target Photo be it is to be identified its whether be blurred picture picture.
Technical solution provided by the embodiment of the present invention can be applied to client, can also be applied to server.
In practical applications, Target Photo can be client according to the identification of user instruct determined by picture, with
It may include the identification information of Target Photo or the store path information of Target Photo in the identification instruction at family.For example, user
When arranging photo on a storage device, if issuing identification instruction to client for the photo being stored in some file,
Then client can one by one by this document press from both sides in photo be determined as Target Photo.
Alternatively, being taken pictures in user using camera installation, when obtaining a new photo, client is directly by the photo
It is determined as Target Photo.
Alternatively, user will store the photo upload in equipment to server by client, server one by one will be on user
The photo of biography is determined as Target Photo.
It is, of course, also possible to obtain Target Photo by other means, the embodiment of the present invention is without limitation.
S120: the corresponding gray scale picture of the Target Photo is obtained；
Gray proces, the gray scale picture of the available picture are done to any picture.It should be noted that this field skill
Art personnel can according to the common knowledge of this field and common technology side section, to picture carry out gray proces, the present invention to this not
It limits.For example, the picture of yuv format is opened to Mr. Yu, can obtain the figure directly according to the Y-component information of the picture
The gray scale picture of piece.
It, can be according to preset first proportionate relationship, to the target figure in a kind of specific embodiment of the invention
Piece carries out diminution processing, carries out gray proces to carrying out reducing treated picture, obtains the corresponding gray scale of the Target Photo
Picture.
For example, Target Photo is the picture of 512*512 size, Target Photo can be first reduced into the figure of 64*64 size
Then piece carries out gray proces to carrying out reducing treated picture again, can be obtained the corresponding gray scale picture of the Target Photo.
In another specific embodiment of the invention, can first it obtain and Target Photo gray scale of the same size
Picture carries out diminution processing to gray scale picture obtained, obtains the Target Photo according still further to preset second proportionate relationship
Corresponding gray scale picture.
For example, Target Photo is the picture of 512*512 size, after carrying out gray proces to the picture, it can be obtained and be somebody's turn to do
Gray scale picture obtained, is reduced into the picture of 64*64 size by Target Photo gray scale picture of the same size, can will be reduced
Gray scale picture afterwards is as the corresponding gray scale picture of the Target Photo.
In view of technical solution provided by the embodiment of the present invention is either still taking in the client executing of terminal side
Business device executes, and all may be subjected to the influence of the factors such as computing capability and hardware performance, the especially client in terminal side
It influences to become apparent when execution, so carrying out diminution processing to Target Photo or with Target Photo gray scale picture of the same size
Afterwards, then carry out further operate can reduce calculation amount, improve the recognition rate of picture.
Theoretically, the pixel of Target Photo is more, and recognition accuracy is higher.In practical applications, certain to guarantee
Recognition accuracy, can from Target Photo or with 64*x is proportionally extracted in Target Photo gray scale picture of the same size
Pixel, that is, the length of the corresponding gray scale picture of the Target Photo obtained or it is wide in smaller's pixel quantity be 64, separately
Outer one side is a value more than or equal to 64 according to the quantity of its pixel of length-width ratio.
It should be noted that above-mentioned preset first proportionate relationship and preset second proportionate relationship can be according to practical need
It is configured and adjusts.
S130: processing is sharpened to the gray scale picture, obtains and sharpens picture；
S140: the pixel value of each pixel for sharpening picture is determined；
For convenience of description, above-mentioned two step is combined and is illustrated.
It is understood that blurred picture has such a common ground: object edge is unintelligible, marginal portion intermediate color
Pixel quantity it is more.After obtaining the corresponding gray scale picture of Target Photo, although losing color information, edge transition
Feature, that is, fuzzy message still be retained.It can effectively be filtered in picture using the edge detection operator in graph image
The marginal information of object can extract the marginal information of object in gray scale picture by edge detection operator.
In a kind of specific embodiment of the invention, it is sharp to gray scale picture progress that edge detection operator can be used
Change processing, obtains and sharpens picture；Wherein, the edge detection operator is Laplce Laplacian operator, Sobel Sobel
One of operator, Robert Roberts operator, triumphant Buddhist nun Canny operator.Of course, it is possible to which the edge detection operator used is unlimited
In above-mentioned several, the embodiment of the present invention is without limitation.
To use Laplace operator to be sharpened processing to the gray scale picture, obtains and said for sharpening picture
It is bright.
Have direction unrelated and dual edge characteristic when carrying out edge detection using Laplace operator, that is, passes through Laplce
Corresponding positive and negative two class value is presented in the pixel at the edge of object in picture after operator processing, and the absolute value of this two class value is got over
The gray scale difference value of the small pixel for illustrating edge is smaller.
For the gray scale picture shown in Fig. 2,16*x pixel in the gray scale picture is proportionally extracted, what is obtained is each
The pixel matrix of pixel, i.e. grayscale image information are as follows:
[58,89,63,41,54,54,158,177,190,200,214,211,218,223,230,232]
[69,78,61,61,61,45,55,124,188,198,201,210,218,227,230,231]
[78,98,41,76,58,63,42,40,211,183,219,199,153,224,235,237]
[84,86,70,61,71,182,149,145,122,146,103,120,235,237,232,133]
[77,207,203,197,185,126,34,133,149,98,146,163,148,234,237,144]
[41,73,51,172,173,84,140,147,231,142,23,58,143,145,144,231]
[247,211,162,167,163,145,36,30,140,142,143,93,117,144,144,145]
[249,249,42,35,147,151,147,13,146,140,136,136,29,47,27,73]
[245,246,199,117,143,144,140,134,18,33,22,24,65,61,100,113]
[247,245,158,33,138,142,24,18,18,56,62,60,58,104,110,116]
[246,245,229,199,16,57,55,55,18,61,66,88,9,18,31,241]
[246,244,244,91,14,54,54,55,20,72,49,16,17,104,121,241]
[246,243,241,183,23,51,53,59,13,59,69,76,36,118,91,239]
[244,244,243,211,66,17,23,58,19,67,82,81,24,102,220,231]
[245,245,247,233,109,59,85,140,23,42,40,77,85,93,212,222]
[249,249,248,238,205,61,60,13,26,71,73,102,155,172,177,212]
[250,251,249,245,226,22,61,63,32,113,148,150,163,170,173,186]
[252,252,251,248,233,55,59,104,137,145,150,159,163,165,166,177]
[251,250,248,248,237,221,126,131,139,147,154,159,160,166,168,173]
[246,248,247,246,239,227,178,135,146,154,160,158,165,167,169,171]
[239,241,245,243,238,226,203,168,152,153,155,162,163,166,167,168]
Laplace operator pattern matrix is passed through to the pixel value of each pixel in above-mentioned pixel matrix
The numerical matrix obtained after operation is as follows:
[5,-1,-5,-26,53,149,-36,-29,-20,37,-11,-64,-13,3]
[-109,141,-83,39,75,139,362,-311,42,-190,-94,264,-44,-17]
[115,111,170,202,-319,-193,-136,163,-78,219,220,-282,-23,-86]
[-389,-287,-167,-173,-19,412,-57,-12,191,-197,-180,183,-169,-194]
[218,406,-100,-88,248,-259,-54,-346,-74,397,190,-104,85,181]
[-113,-177,-136,-20,-146,318,216,-11,-3,-178,82,-59,-123,-116]
[-248,477,333,-96,-21,-248,405,-273,-103,-103,-262,249,73,256]
[-46,-233,-58,-26,0,-111,-347,259,104,167,187,-88,72,-89]
[-84,74,480,-218,-205,259,159,38,-50,-44,-8,6,-169,-89]
[-16,-70,-427,344,39,-30,-74,82,-32,-4,-201,145,176,366]
[2,-171,276,128,-40,1,-32,78,-99,27,166,97,-142,-17]
[3,-51,-166,222,-57,-25,-57,105,-15,-10,-102,91,-139,334]
[-1,-29,-119,96,131,121,9,85,-66,-71,-65,208,47,-244]
[5,-19,-127,127,36,-58,-381,135,33,114,0,9,199,-136]
[-3,-9,-21,-186,102,-20,237,35,-30,69,47,-98,-93,61]
[-4,-1,-19,-199,315,-40,-42,211,-56,-106,-28,-14,-7,7]
[-4,-7,-15,-166,315,110,-26,-128,-33,6,-14,-5,5,19]
[-1,4,-13,-7,-239,85,-20,5,4,0,-5,13,-4,2]
[-8,-1,-7,-8,-44,-21,83,-4,-10,-19,14,-12,-2,-3]
It can be seen that the gray value difference of the object edge part of picture is larger from upper group of pixel matrix.It is above-mentioned be with
The explanation carried out for 16*x pixel, in practical applications, as previously mentioned, comprehensively considering the calculating of terminal or server
Ability, hardware performance and recognition accuracy can choose 64*x pixel as statistical sample, to retain effective obscure
Information.It obtains after sharpening picture, that is, can determine the pixel value for sharpening each pixel of picture.
S150: according to the pixel value of each pixel for sharpening picture, the pixel for being directed to the Target Photo is determined
The standard deviation of value；
In statistics, variance or standard deviation represent distribution dispersion degree, and the smaller representative distribution of value is more concentrated, and fluctuation is got over
It is small.In step S130, processing is sharpened to gray scale picture, it, can be with after the pixel value for obtaining sharpening each pixel of picture
The variance or standard deviation of the pixel value of pixel in the sharpening picture are calculated, value is smaller to be illustrated in gray scale picture between pixel
Pixel value difference it is smaller, the edge for representing object in the Target Photo is not clear enough, that is, the standard deviation being calculated can be used
Index whether judge Target Photo is fuzzy.
In a kind of specific embodiment of the invention, step S150 be may comprise steps of:
First step: for it is described sharpen picture each pixel, judge the pixel pixel value whether
In preset numberical range, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel of the pixel
Value；
Second step: the standard deviation of the pixel value of the pixel of reservation is calculated；
Third step: the standard deviation being calculated is determined as to the standard deviation of the pixel value for the Target Photo.
For convenience of description, above three step is combined and is illustrated.
In step S140, it is determined that sharpen the pixel value of each pixel of picture.In practical applications, it is examined by edge
After surveying operator operation, the pixel value for sharpening non-edge pixels point in picture is concentrated in certain numberical range, to target
The gray scale picture of picture carries out operation using different edge detection operators, and the pixel value of obtained non-edge pixels point is concentrated
Numberical range may be different, can rule of thumb or largely test result is verified to obtain the numberical range, for example pass through
It crosses after Laplace operator operation, the pixel value of non-edge pixels point concentrates between [- 10,10], can filter out these
The pixel value of non-edge pixels point, i.e. these pixels can be without statistics.For each pixel for sharpening picture, sentence
Break the pixel pixel value whether in preset numberical range, if it is, filter out the pixel value of the pixel, if
It is no, then retain the pixel value of the pixel.
To the pixel of reservation, the standard deviation of the pixel value of these pixels is calculated, formula one or formula two can be used
One of calculated.
Formula one:
Wherein, σ is the pixel value x of the pixel counted1、x2、……、xnStandard deviation, n is the picture counted
Vegetarian refreshments number, x are the average value of the pixel value of the pixel counted.
Formula two:
σ=sqrt (E (x2)-[E(x)]2)；
Wherein, σ is the standard deviation of the pixel value of the pixel counted, and E (x) is the pixel of the pixel counted
The desired value of value, E (x2) be the pixel value of pixel counted square desired value.
The standard deviation being calculated can be determined as to the standard deviation of the pixel value for Target Photo.
S160: if the standard deviation is lower than preset standard deviation threshold method, the Target Photo is determined as fuzzy graph
Piece.
Standard deviation threshold method can be verified to obtain by a large amount of test experiments.
For example, shooting jobbie in same position, gray proces, Edge contrast are carried out to the clear pictures of the object
Afterwards, the standard deviation for calculating the pixel value for the pixel that pixel number is 5146 is 69.48, carries out ash to the fuzzy photo of the object
After degree processing, Edge contrast, the standard deviation for calculating the pixel value for the pixel that pixel number is 5146 is 25.53.
Alternatively, gray proces, Edge contrast and after filtering out non-edge pixels point are carried out to the clear pictures of the object,
The standard deviation for calculating the pixel value for the pixel that pixel number is 2743 is 95.07, carries out gray scale to the fuzzy photo of the object
Processing, Edge contrast and after filtering out edge pixel point, calculate the standard deviation of the pixel value for the pixel that pixel number is 1971
It is 40.79.
A large amount of test experiments are carried out using the above method, can determine that standard deviation threshold method is set as 50~60 proper,
I.e. if the Target Photo can be determined as by the standard deviation of the corresponding pixel value of Target Photo lower than the standard deviation threshold method of setting
Blurred picture.
Certainly, using different gray scale processing methods, different Edge contrast methods, obtained standard deviation threshold method may not
Together, which can be set and be adjusted according to the actual situation.Fuzzy itself is also relative concept, at image quality
Not high camera installation of amount itself, can suitably debase the standard poor threshold value, or can according to the resolution ratio of camera installation and
Ladder threshold value is arranged in image quality.
After Target Photo is determined as blurred picture, further operating can be carried out.
For example, the Target Photo can be marked, so that user checks.
Alternatively, the prompt information for whether deleting the Target Photo can be exported, the prompt information is directed to according to user
Selection, it is determined whether execute the operation for deleting the Target Photo.It, can should if receiving the deletion instruction of user
Target Photo carries out delete processing.
Alternatively, determining blurred picture can be deleted directly.Once Target Photo is determined as blurred picture, directly carry out
Delete processing.
Alternatively, the Target Photo can be put into preset Photo folder to be deleted, user can be in this document
The picture for being determined as blurred picture is checked in folder.
Using technical solution provided by the embodiment of the present invention, the corresponding gray scale picture of the Target Photo of acquisition is carried out sharp
After change processing, according to the pixel value for each pixel for sharpening picture, the standard deviation of the pixel value of Target Photo, standard deviation are determined
Lower than preset standard deviation threshold method, then it may indicate that the object edge of the Target Photo is not clear enough, it can be by the Target Photo
It is determined as blurred picture, identifies that the process of blurred picture is relatively simple, it is ensured that the identification identified to a large amount of picture
Rate.
Corresponding to above method embodiment, the embodiment of the invention also provides a kind of blurred picture identification devices, referring to Fig. 3
Shown, the apparatus may include with lower module:
Target Photo obtains module 310, for obtaining Target Photo；
Gray scale picture obtains module 320, for obtaining the corresponding gray scale picture of the Target Photo；
It sharpens picture and obtains module 330, for being sharpened processing to the gray scale picture, obtain and sharpen picture；
Pixel value determining module 340, for determining the pixel value of each pixel for sharpening picture；
Standard deviation determining module 350 determines for the pixel value according to each pixel for sharpening picture and is directed to institute
The standard deviation of the pixel value of Target Photo is stated, if the standard deviation is lower than preset standard deviation threshold method, triggers blurred picture
Determining module 360；
The blurred picture determining module 360, for the Target Photo to be determined as blurred picture.
It is understood that Target Photo be it is to be identified its whether be blurred picture picture.
Device provided by the embodiment of the present invention can be applied to client, can also be applied to server.
In practical applications, Target Photo can be client according to the identification of user instruct determined by picture, with
It may include the identification information of Target Photo or the store path information of Target Photo in the identification instruction at family.For example, user
When arranging photo on a storage device, if issuing identification instruction to client for the photo being stored in some file,
Then client can one by one by this document press from both sides in photo be determined as Target Photo.
Alternatively, being taken pictures in user using camera installation, when obtaining a new photo, client is directly by the photo
It is determined as Target Photo.
Alternatively, user will store the photo upload in equipment to server by client, server one by one will be on user
The photo of biography is determined as Target Photo.
Certainly, Target Photo obtains module can also obtain Target Photo by other means, and the embodiment of the present invention is to this
With no restrictions.
Gray proces, the gray scale picture of the available picture are done to any picture.It should be noted that this field skill
Art personnel can according to the common knowledge of this field and common technology side section, to picture carry out gray proces, the present invention to this not
It limits.For example, the picture of yuv format is opened to Mr. Yu, can obtain the figure directly according to the Y-component information of the picture
The gray scale picture of piece.
It is understood that blurred picture has such a common ground: object edge is unintelligible, marginal portion intermediate color
Pixel quantity it is more.After obtaining the corresponding gray scale picture of Target Photo, although losing color information, edge transition
Feature, that is, fuzzy message still be retained.It can effectively be filtered in picture using the edge detection operator in graph image
The marginal information of object can extract the marginal information of object in gray scale picture by edge detection operator.
In statistics, variance or standard deviation represent distribution consistency degree, and the smaller representative distribution of value is more concentrated.To grayscale image
Piece is sharpened processing, after obtaining the pixel value of each pixel of sharpening picture, can calculate pixel in the sharpening picture
Pixel value variance or standard deviation, it is not clear enough to be worth the smaller edge for illustrating object in the corresponding gray scale picture of the Target Photo
It is clear.If standard deviation is lower than preset standard deviation threshold method, which is determined as blurred picture.
In a kind of specific embodiment of the invention, the standard deviation determining module 350 may include following submodule
Block:
Judging submodule, for judging that the pixel value of the pixel is for described each pixel for sharpening picture
It is no in preset numberical range, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel
Pixel value；
Computational submodule, the standard deviation of the pixel value for calculating the pixel retained；
Standard deviation determines submodule, for the standard deviation being calculated to be determined as to the pixel value for the Target Photo
Standard deviation.
In practical applications, after edge detection operator operation, the pixel value for sharpening non-edge pixels point in picture is
It concentrates in certain numberical range, operation is carried out using different edge detection operators to the gray scale picture of Target Photo,
The numberical range that the pixel value of obtained non-edge pixels point is concentrated may be different, can rule of thumb or largely test knot
Fruit is verified to obtain the numberical range, for example passes through after Laplace operator operation, the pixel value collection of non-edge pixels point
In between [- 10,10], the pixel value of these non-edge pixels points can be filtered out, i.e., these pixels can be without system
Meter.For each pixel for sharpening picture, whether judging submodule judges the pixel value of the pixel in preset numerical value
In range, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel value of the pixel.
To the pixel of reservation, computational submodule calculates the standard deviation of the pixel value of these pixels.Standard deviation determines son
The standard deviation being calculated can be determined as the standard deviation of the pixel value for Target Photo by module.
In a kind of specific embodiment of the invention, the gray scale picture obtains module 320, can be specifically used for:
According to preset first proportionate relationship, diminution processing is carried out to the Target Photo, treated to diminution is carried out
Picture carries out gray proces, obtains the corresponding gray scale picture of the Target Photo；
Alternatively,
Obtain with Target Photo gray scale picture of the same size, according to preset second proportionate relationship, to being obtained
Gray scale picture carry out diminution processing, obtain the corresponding gray scale picture of the Target Photo.
In view of device provided by the embodiment of the present invention is either in the client operation of terminal side or in server
Operation all may be subjected to the influence of the factors such as computing capability and hardware performance, and the especially client in terminal side is run
When influence to become apparent, so after carrying out diminution processing to Target Photo or with Target Photo gray scale picture of the same size,
It carries out further operating again and can reduce calculation amount, improve the recognition rate of picture.
Theoretically, the pixel of Target Photo is more, and recognition accuracy is higher.In practical applications, certain to guarantee
Recognition accuracy, can from Target Photo or with 64*x is proportionally extracted in Target Photo gray scale picture of the same size
Pixel, that is, the length of the corresponding gray scale picture of the Target Photo obtained or it is wide in smaller's pixel quantity be 64, separately
Outer one side is a value more than or equal to 64 according to the quantity of its pixel of length-width ratio.
It should be noted that above-mentioned preset first proportionate relationship and preset second proportionate relationship can be according to practical need
It is configured and adjusts.
In one embodiment of the invention, which can also include post-processing module:
The post-processing module, after the Target Photo is determined as blurred picture, whether output deletes the mesh
It marks on a map the prompt information of piece, the selection of the prompt information is directed to according to user, it is determined whether execute and delete the Target Photo
Operation；
Alternatively,
Directly delete the Target Photo；
Alternatively,
The Target Photo is put into preset Photo folder to be deleted.
In a kind of specific embodiment of the invention, the sharpening picture obtains module 330, can be specifically used for:
Processing is sharpened to the gray scale picture using edge detection operator, obtains and sharpens picture；
Wherein, the edge detection operator is Laplce Laplacian operator, Sobel Sobel operator, Robert
One of Roberts operator, triumphant Buddhist nun Canny operator.
Using device provided by the embodiment of the present invention, place is sharpened to the corresponding gray scale picture of the Target Photo of acquisition
After reason, according to the pixel value for each pixel for sharpening picture, determine that the standard deviation of the pixel value of Target Photo, standard deviation are lower than
Preset standard deviation threshold method then may indicate that the object edge of the Target Photo is not clear enough, which can be determined
For blurred picture, identify that the process of blurred picture is relatively simple, it is ensured that the recognition rate identified to a large amount of picture.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
Those of ordinary skill in the art will appreciate that all or part of the steps in realization above method embodiment is can
It is completed with instructing relevant hardware by program, the program can store in computer-readable storage medium,
The storage medium designated herein obtained, such as: ROM/RAM, magnetic disk, CD.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (8)
1. a kind of blurred picture recognition methods characterized by comprising
Obtain Target Photo；
Obtain the corresponding gray scale picture of the Target Photo；
Processing is sharpened to the gray scale picture, obtains and sharpens picture；
Determine the pixel value of each pixel for sharpening picture；
For described each pixel for sharpening picture, judge the pixel value of the pixel whether in preset numberical range
It is interior, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel value of the pixel；
Calculate the standard deviation of the pixel value of the pixel retained；
The standard deviation being calculated is determined as to the standard deviation of the pixel value for the Target Photo；
If the standard deviation is lower than preset standard deviation threshold method, the Target Photo is determined as blurred picture.
2. the method according to claim 1, wherein described obtain the corresponding gray scale picture of the Target Photo,
Include:
According to preset first proportionate relationship, diminution processing is carried out to the Target Photo, to carrying out reducing treated picture
Gray proces are carried out, the corresponding gray scale picture of the Target Photo is obtained；
Alternatively,
Acquisition and Target Photo gray scale picture of the same size, according to preset second proportionate relationship, to ash obtained
Degree picture carries out diminution processing, obtains the corresponding gray scale picture of the Target Photo.
3. the method according to claim 1, wherein the Target Photo is determined as blurred picture described
Afterwards, further includes:
Whether output deletes the prompt information of the Target Photo, and the selection of the prompt information is directed to according to user, and determination is
It is no to execute the operation for deleting the Target Photo；
Alternatively,
Directly delete the Target Photo；
Alternatively,
The Target Photo is put into preset Photo folder to be deleted.
4. method according to any one of claims 1 to 3, which is characterized in that described to be sharpened to the gray scale picture
Processing obtains and sharpens picture, comprising:
Processing is sharpened to the gray scale picture using edge detection operator, obtains and sharpens picture.
5. a kind of blurred picture identification device characterized by comprising
Target Photo obtains module, for obtaining Target Photo；
Gray scale picture obtains module, for obtaining the corresponding gray scale picture of the Target Photo；
It sharpens picture and obtains module, for being sharpened processing to the gray scale picture, obtain and sharpen picture；
Pixel value determining module, for determining the pixel value of each pixel for sharpening picture；
Judging submodule, for for it is described sharpen picture each pixel, judge the pixel pixel value whether
In preset numberical range, if it is, the pixel value of the pixel is filtered out, if it is not, then retaining the pixel of the pixel
Value；
Computational submodule, the standard deviation of the pixel value for calculating the pixel retained；
Standard deviation determines submodule, for the standard deviation being calculated to be determined as to the mark of the pixel value for the Target Photo
It is quasi- poor；
The blurred picture determining module, for the Target Photo to be determined as blurred picture.
6. device according to claim 5, which is characterized in that the gray scale picture obtains module, is specifically used for:
According to preset first proportionate relationship, diminution processing is carried out to the Target Photo, to carrying out reducing treated picture
Gray proces are carried out, the corresponding gray scale picture of the Target Photo is obtained；
Alternatively,
Acquisition and Target Photo gray scale picture of the same size, according to preset second proportionate relationship, to ash obtained
Degree picture carries out diminution processing, obtains the corresponding gray scale picture of the Target Photo.
7. device according to claim 5, which is characterized in that further include post-processing module:
The post-processing module, for after the Target Photo is determined as blurred picture, whether output to delete the target
The prompt information of picture is directed to the selection of the prompt information according to user, it is determined whether executes and deletes the Target Photo
Operation；
Alternatively,
Directly delete the Target Photo；
Alternatively,
The Target Photo is put into preset Photo folder to be deleted.
8. according to the described in any item devices of claim 5 to 7, which is characterized in that the sharpening picture obtains module, specific to use
In:
Processing is sharpened to the gray scale picture using edge detection operator, obtains and sharpens picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438070.XA CN105069783B (en) | 2015-07-23 | 2015-07-23 | Fuzzy picture identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438070.XA CN105069783B (en) | 2015-07-23 | 2015-07-23 | Fuzzy picture identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105069783A CN105069783A (en) | 2015-11-18 |
| CN105069783B true CN105069783B (en) | 2019-03-01 |
Family
ID=54499140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510438070.XA Expired - Fee Related CN105069783B (en) | 2015-07-23 | 2015-07-23 | Fuzzy picture identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105069783B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512221A (en) * | 2015-11-30 | 2016-04-20 | 上海斐讯数据通信技术有限公司 | Fuzzy photo processing method and processing system |
| CN106920266B (en) * | 2015-12-28 | 2019-11-05 | 腾讯科技（深圳）有限公司 | The Background Generation Method and device of identifying code |
| CN105808663B (en) * | 2016-02-29 | 2019-12-03 | 北京金山安全软件有限公司 | Image classification method and device and electronic equipment |
| CN106373121A (en) * | 2016-09-18 | 2017-02-01 | 广东小天才科技有限公司 | Blurred image recognition method and device |
| CN106407441A (en) * | 2016-09-28 | 2017-02-15 | 北京小米移动软件有限公司 | Mistaken photo identification method and device |
| CN106357982B (en) * | 2016-11-11 | 2023-04-07 | 北京佳艺徕经贸有限责任公司 | Image service device and method |
| CN110458790B (en) * | 2018-05-03 | 2022-07-12 | 阿里巴巴（中国）有限公司 | Image detection method and device and computer storage medium |
| CN109214995A (en) * | 2018-08-20 | 2019-01-15 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of picture quality |
| CN109829859B (en) * | 2018-12-05 | 2024-05-24 | 平安科技（深圳）有限公司 | Image processing method and terminal equipment |
| CN110704380A (en) * | 2019-08-27 | 2020-01-17 | 努比亚技术有限公司 | Automatic picture deleting method, terminal and computer readable storage medium |
| CN111738282A (en) * | 2019-10-22 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Image recognition method based on artificial intelligence and related equipment |
| CN112396050B (en) * | 2020-12-02 | 2023-09-15 | 度小满科技(北京)有限公司 | Image processing method, device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5166722A (en) * | 1990-08-14 | 1992-11-24 | Nikon Corporation | Camera image shake detecting apparatus |
| CN102509285A (en) * | 2011-09-28 | 2012-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Processing method and system for shot fuzzy picture and shooting equipment |
| CN102598687A (en) * | 2009-10-10 | 2012-07-18 | 汤姆森特许公司 | Method and device for calculating blur in video images |
| CN102665088A (en) * | 2010-12-22 | 2012-09-12 | 特克特朗尼克公司 | Blur detection with local sharpness map |
| CN103413311A (en) * | 2013-08-19 | 2013-11-27 | 厦门美图网科技有限公司 | Edge-based fuzzy detection method |
| CN104200480A (en) * | 2014-09-17 | 2014-12-10 | 西安电子科技大学宁波信息技术研究院 | Image fuzzy degree evaluation method and system applied to intelligent terminal |
| CN104268888A (en) * | 2014-10-09 | 2015-01-07 | 厦门美图之家科技有限公司 | Method for detecting image blurring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005309559A (en) * | 2004-04-19 | 2005-11-04 | Fuji Photo Film Co Ltd | Image processing method, device and program |
-
2015
- 2015-07-23 CN CN201510438070.XA patent/CN105069783B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5166722A (en) * | 1990-08-14 | 1992-11-24 | Nikon Corporation | Camera image shake detecting apparatus |
| CN102598687A (en) * | 2009-10-10 | 2012-07-18 | 汤姆森特许公司 | Method and device for calculating blur in video images |
| CN102665088A (en) * | 2010-12-22 | 2012-09-12 | 特克特朗尼克公司 | Blur detection with local sharpness map |
| CN102509285A (en) * | 2011-09-28 | 2012-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Processing method and system for shot fuzzy picture and shooting equipment |
| CN103413311A (en) * | 2013-08-19 | 2013-11-27 | 厦门美图网科技有限公司 | Edge-based fuzzy detection method |
| CN104200480A (en) * | 2014-09-17 | 2014-12-10 | 西安电子科技大学宁波信息技术研究院 | Image fuzzy degree evaluation method and system applied to intelligent terminal |
| CN104268888A (en) * | 2014-10-09 | 2015-01-07 | 厦门美图之家科技有限公司 | Method for detecting image blurring |
Non-Patent Citations (3)
| Title |
|---|
| A non-parametric blur measure based on edge analysis for image processing applications;Chung Yun-Chung 等;《IEEE Conference on Cybernetics & Intelligent Systems》;20041203;第356-360页 |
| Efficient Method of Detecting Globally Blurry or Sharp Images;Elena Tsomko 等;《Ninth International Workshop on Images Analysis for Multimedia Interactive Services》;20080509;第1节、第2.2节 |
| 无参考模糊图像质量评价改进算法;李鸿林 等;《计算机应用》;20140310;第34卷(第3期);第797-800页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105069783A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105069783B (en) | Fuzzy picture identification method and device | |
| US10032258B2 (en) | Automatically suggesting regions for blur kernel estimation | |
| AU2017261537B2 (en) | Automated selection of keeper images from a burst photo captured set | |
| JP4351911B2 (en) | Method and apparatus for evaluating photographic quality of captured images in a digital still camera | |
| US8639028B2 (en) | Automatic stacking based on time proximity and visual similarity | |
| US7860332B2 (en) | Method and system for determining an indication of focus of an image | |
| CN108366203B (en) | Composition method, composition device, electronic equipment and storage medium | |
| US9466096B2 (en) | Deblurring images having spatially varying blur | |
| CN107613202B (en) | Shooting method and mobile terminal | |
| US9576220B2 (en) | Automatically determining the size of a blur kernel | |
| US7869064B2 (en) | Printing device | |
| WO2016009421A1 (en) | Automatic image composition | |
| CN112036209A (en) | Portrait photo processing method and terminal | |
| CN105447846B (en) | Image processing method and electronic equipment | |
| WO2015196681A1 (en) | Picture processing method and electronic device | |
| US8417068B2 (en) | Image processing apparatus | |
| CN113225451B (en) | Image processing method and device and electronic equipment | |
| CN111669492A (en) | Method for processing shot digital image by terminal and terminal | |
| CN113010738A (en) | Video processing method and device, electronic equipment and readable storage medium | |
| CN112330728A (en) | Image processing method, image processing device, electronic equipment and readable storage medium | |
| WO2018000299A1 (en) | Method for assisting acquisition of picture by device | |
| CN108537799B (en) | Color sampling method based on pixel type and weight statistics | |
| US10037459B2 (en) | Real-time font edge focus measurement for optical character recognition (OCR) | |
| US9632679B2 (en) | User interface for managing blur kernels | |
| WO2023019681A1 (en) | Image content extraction method and apparatus, and terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190301 |