Summary of the invention
Technical problem to be solved by this invention is to provide a kind of objective evaluation method for quality of stereo images that can effectively improve the correlation of objective evaluation result and subjective perception.
The present invention solves the problems of the technologies described above the technical scheme that adopts: a kind of objective evaluation method for quality of stereo images based on visually-perceptible is characterized in that comprising the following steps:
1. make S
orgUndistorted stereo-picture for original makes S
disFor the stereo-picture of distortion to be evaluated, with S
orgLeft visual point image be designated as { L
org(x, y) }, with S
orgRight visual point image be designated as { R
org(x, y) }, with S
disLeft visual point image be designated as { L
dis(x, y) }, with S
disRight visual point image be designated as { R
dis(x, y) }, wherein, the coordinate position of pixel in (x, y) left visual point image of expression and right visual point image, 1≤x≤W, 1≤y≤H, W represent the width of left visual point image and right visual point image, H represents the height of left visual point image and right visual point image, L
org(x, y) represents S
orgLeft visual point image { L
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), R
org(x, y) represents S
orgRight visual point image { R
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), L
dis(x, y) represents S
disLeft visual point image { L
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y), R
dis(x, y) represents S
disRight visual point image { R
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y);
2. utilize human vision to the visual masking effect of background illumination and texture, extract respectively undistorted left visual point image { L
org(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image, with undistorted left visual point image { L
org(x, y) } minimum discernable distorted image be designated as { J
L(x, y) }, with undistorted right visual point image { R
org(x, y) } minimum discernable distorted image be designated as { J
R(x, y) }, wherein, J
L(x, y) represents { J
L(x, y) } in coordinate position be the pixel value of the pixel of (x, y), J
R(x, y) represents { J
R(x, y) } in coordinate position be the pixel value of the pixel of (x, y);
3. obtain respectively undistorted left visual point image { L by regional detection algorithm
org(x, y) } and the left visual point image { L of distortion
dis(x, y) }, undistorted right visual point image { R
org(x, y) } and the right visual point image { R of distortion
dis(x, y) } in the block type of each 8 * 8 sub-block, be designated as p, wherein, p ∈ 1,2,3,4}, p=1 represents Strong edge blocks, p=2 represents weak edge block, p=3 represents smooth block, p=4 represents texture block;
4. according to undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) }, by the left visual point image { L of calculated distortion
dis(x, y) } in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for reflection picture quality and be used for the space structure intensity of reflection picture quality, and the right visual point image { R of distortion
dis(x, y) } in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for reflection picture quality and be used for the space structure intensity of reflection picture quality, obtain respectively the left visual point image { L of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality and the right visual point image { R of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality, then to the left visual point image { L of distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality carry out linear weighted function, obtain S
disThe characteristic vector that is used for reflection picture quality, be designated as F
q
5. according to undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) }, by the left visual point image { L of calculated distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } absolute difference image in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for the reflection depth perception and be used for the space structure intensity of reflection depth perception, obtain S
disThe characteristic vector that is used for the reflection depth perception, be designated as F
s
6. with S
disThe characteristic vector F that is used for reflection picture quality
qWith the characteristic vector F that is used for the reflection depth perception
sForm the New Characteristics vector, as S
disCharacteristic vector, be designated as X, X=[F
q, F
s], " [] " is the vector representation symbol, [F
q, F
s] represent characteristic vector F
qWith characteristic vector F
sCouple together and form a New Characteristics vector;
7. adopt n undistorted stereo-picture, set up its distortion stereo-picture set under the different distortion levels of different type of distortion, this distortion stereo-picture set comprises the stereo-picture of several distortions, utilizes the subjective quality assessment method to obtain respectively the average subjective scoring difference of the stereo-picture of every width distortion in the set of distortion stereo-picture, is designated as DMOS, DMOS=100-MOS, wherein, MOS represents the subjective scoring average, DMOS ∈ [0,100], n 〉=1;
8. adopt and calculate S
disThe identical method of characteristic vector X, the characteristic vector of the stereo-picture of every width distortion in the set of calculated distortion stereo-picture respectively, the characteristic vector for the stereo-picture of i width distortion in the set of distortion stereo-picture is designated as X with it
i, wherein, 1≤i≤n ', the width number of the stereo-picture of the distortion that comprises in the set of n ' expression distortion stereo-picture;
9. adopt support vector regression that the characteristic vector of the stereo-picture of all distortions of identical type of distortion in the set of distortion stereo-picture is trained, and the support vector regression training pattern of utilizing training to obtain is tested the stereo-picture of every width distortion of same type of distortion, calculate the evaluating objective quality predicted value of the stereo-picture of every width distortion of identical type of distortion in the set of distortion stereo-picture, evaluating objective quality predicted value for the stereo-picture of i width distortion in the set of distortion stereo-picture is designated as Q with it
i, Q
i=f (X
i), f () is the function representation form, Q
i=f (X
i) expression Q
iBe X
iFunction, wherein, 1≤i≤n ', the width number of the stereo-picture of the distortion that comprises in the set of n ' expression distortion stereo-picture.
Described step detailed process 2. is:
2.-1, calculate undistorted left visual point image { L
org(x, y) } the visual threshold value set of visual masking effect of background illumination, be designated as { T
l(x, y) },
Wherein, T
l(x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be the visual threshold value of visual masking effect of background illumination of the pixel of (x, y),
Represent undistorted left visual point image { L
org(x, y) } in the average brightness of all pixels in 5 * 5 windows centered by pixel take coordinate position as (x, y);
2.-2, calculate undistorted left visual point image { L
org(x, y) } the visual threshold value set of visual masking effect of texture, be designated as { T
t(x, y) }, T
t(x, y)=η * G (x, y) * W
e(x, y), wherein, T
t(x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be the visual threshold value of visual masking effect of texture of the pixel of (x, y), η is the controlling elements greater than 0, G (x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be that the pixel of (x, y) carries out the maximum weighted mean value that directed high-pass filtering obtains, W
e(x, y) expression is to undistorted left visual point image { L
org(x, y) } edge image in coordinate position be that the pixel of (x, y) carries out the Weighted Edges value that Gassian low-pass filter obtains;
2.-3, to undistorted left visual point image { L
org(x, y) } the visual threshold value set { T of visual masking effect of background illumination
l(x, y) } and the visual threshold value set { T of the visual masking effect of texture
t(x, y) } merge, obtain undistorted left visual point image { L
org(x, y) } minimum discernable distorted image, be designated as { J
L(x, y) }, J
L(x, y)=T
l(x, y)+T
t(x, y)-C
L, t* min{T
l(x, y), T
t(x, y) }, wherein, C
L, tThe parameter of the visual masking effect eclipse effect of background illumination and texture, 0<C are controlled in expression
L, t<1, min{} is for getting minimum value function;
2. undistorted right visual point image { R is obtained in-4, the employing operation identical with step 2.-1 to 2.-3
org(x, y) } minimum discernable distorted image, be designated as { J
R(x, y) }.
The detailed process of the regional detection algorithm of described step in 3. is:
3.-1, respectively with undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } be divided into
8 * 8 sub-blocks of individual non-overlapping copies define undistorted left visual point image { L
org(x, y) } in l 8 * 8 sub-blocks be current the first sub-block, be designated as
Left visual point image { the L of definition distortion
dis(x, y) } in l 8 * 8 sub-blocks be current the second sub-block, be designated as
Wherein,
(x
2, y
2) current the first sub-block of expression
With current the second sub-block
The coordinate position of middle pixel, 1≤x
2≤ 8,1≤y
2≤ 8,
Represent current the first sub-block
Middle coordinate position is (x
2, y
2) the pixel value of pixel,
Represent current the second sub-block
Middle coordinate position is (x
2, y
2) the pixel value of pixel;
3.-2, calculate respectively current the first sub-block
With current the second sub-block
In the Grad of all pixels, for current the first sub-block
Middle coordinate position is (x
2', y
2') pixel, its Grad is designated as P
o(x
2', y
2'), P
o(x
2', y
2')=| G
ox(x
2', y
2') |+| G
oy(x
2', y
2') |, for current the second sub-block
Middle coordinate position is (x
2', y
2') pixel, its Grad is designated as P
d(x
2', y
2'), P
d(x
2', y
2')=| G
dx(x
2', y
2') |+| G
dy(x
2', y
2') |, wherein, 1≤x
2'≤8,1≤y
2'≤8, G
ox(x
2', y
2') current the first sub-block of expression
Middle coordinate position is (x
2', y
2') the horizontal gradient value of pixel, G
oy(x
2', y
2') current the first sub-block of expression
Middle coordinate position is (x
2', y
2') the vertical gradient value of pixel, G
dx(x
2', y
2') current the second sub-block of expression
Middle coordinate position is (x
2', y
2') the horizontal gradient value of pixel, G
dy(x
2', y
2') current the second sub-block of expression
Middle coordinate position is (x
2', y
2') the vertical gradient value of pixel, " || " is for asking absolute value sign;
3.-3, find out current the first sub-block
In the maximum of Grad of all pixels, be designated as G
max, then according to G
maxCalculate the first Grads threshold and the second Grads threshold, be designated as respectively T
1And T
2, T
1=0.12 * G
max, T
2=0.06 * G
max
3.-4, for current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel, the judgement P
o(x
2', y
2')>T
1And P
d(x
2', y
2')>T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be strong fringe region, Num
1=Nun
1+ 1, then execution in step 3.-8, otherwise, execution in step 3.-5, wherein, Num
1Initial value be 0;
3.-5, judgement P
o(x
2', y
2')>T
1And P
d(x
2', y
2')<=T
1, perhaps P
d(x
2', y
2')>T
1And P
o(x
2', y
2')<=T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be weak fringe region, Num
2=Num
2+ 1, then execution in step 3.-8, otherwise, execution in step 3.-6, wherein, Num
2Initial value be 0;
3.-6, judgement P
o(x
2', y
2')<T
2And P
d(x
2', y
2')<T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be smooth region, Num
3=Num
3+ 1, then execution in step 3.-8, otherwise, execution in step 3.-7, wherein, Num
3Initial value be 0;
3.-7, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be texture region, Num
4=Num
4+ 1, wherein, Num
4Initial value be 0;
3.-8, returning to step 3.-4 continues current the first sub-block
With current the second sub-block
In remaining pixel process, until current the first sub-block
With current the second sub-block
In 8 * 8 pixels all be disposed;
3.-9, with Num
1, Num
2, Num
3And Num
4In the corresponding area type of maximum as current the first sub-block
With current the second sub-block
Block type, be designated as p, wherein, p ∈ 1,2,3,4}, p=1 represents Strong edge blocks, p=2 represents weak edge block, p=3 represents smooth block, p=4 represents texture block;
3.-10, make l "=l+1, l=l ", with undistorted left visual point image { L
org(x, y) } in the next one 8 * 8 sub-blocks as current the first sub-block, with the left visual point image { L of distortion
dis(x, y) } in the next one 8 * 8 sub-blocks as current the second sub-block, return to step 3.-2 and continue to carry out, until undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in
8 * 8 sub-blocks of individual non-overlapping copies all are disposed, and obtain undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in the block type of all 8 * 8 sub-blocks, wherein, l " initial value be 0;
3.-11, the employing operation identical with step 3.-1 to 3.-10 obtains undistorted right visual point image { R
org(x, y) } and the right visual point image { R of distortion
dis(x, y) } in the block type of all 8 * 8 sub-blocks.
Described step detailed process 4. is:
4.-1, the left visual point image { L of calculated distortion
dis(x, y) } in all block types be the spatial noise intensity that is used for reflection picture quality of 8 * 8 sub-blocks of k, be designated as { fq
k(x
2, y
2), for the left visual point image { L of distortion
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel, use it for the reflection picture quality spatial noise intensity be designated as fq
k(x
2, y
2),
Wherein, k ∈ { p|1≤p≤4}, fq
k(x
2, y
2) expression distortion left visual point image { L
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) the spatial noise intensity that is used for reflection picture quality of pixel, 1≤x
2≤ 8,1≤y
2≤ 8, N
kLeft visual point image { the L of expression distortion
dis(x, y) } in block type be the number of 8 * 8 sub-blocks of k, ST
kFor describing the saturation threshold value of error perception, max () is for getting max function, and min () is for getting minimum value function, (x
3, y
3) expression distortion left visual point image { L
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel at undistorted left visual point image { L
org(x, y) } or undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } in coordinate position, 1≤x
3≤ W, 1≤y
3≤ H, L
org(x
3, y
3) expression { L
org(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, L
dis(x
3, y
3) expression { L
dis(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, J
L(x
3, y
3) expression { J
L(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, " || " is for asking absolute value sign;
4.-2, with the left visual point image { L of distortion
dis(x, y) } in the spatial noise intensity set expression that is used for reflection picture quality of 8 * 8 sub-blocks of various block types be { fq
k(x
2, y
2) | 1≤k≤4}, then with { fq
k(x
2, y
2) | all elements in 1≤k≤4} is arranged in order and is obtained the First Characteristic vector, is designated as F
1, wherein, F
1Dimension be 256;
4.-3, to undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in each 8 * 8 sub-block implement respectively singular value decomposition, obtain respectively undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in each self-corresponding singular value vector of each 8 * 8 sub-block, with undistorted left visual point image { L
org(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Left visual point image { L with distortion
dis(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Wherein, the dimension of singular value vector is 8,
4.-4, the left visual point image { L of calculated distortion
dis(x, y) } in all block types be the space structure intensity that is used for reflection picture quality of 8 * 8 sub-blocks of k, be designated as
Wherein, the left visual point image { L of l ' expression distortion
dis(x, y) } in block type be that 8 * 8 sub-blocks of k are at undistorted left visual point image { L
org(x, y) } or undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } in sequence number;
4.-5, with the left visual point image { L of distortion
dis(x, y) } in the space structure intensity set expression that is used for reflection picture quality of 8 * 8 sub-blocks of various block types be
Then will
In all elements arrange in order and obtain the Second Characteristic vector, be designated as F
2, wherein, F
2Dimension be 32;
4.-6, with the First Characteristic vector F
1With the Second Characteristic vector F
2Form the New Characteristics vector, as the left visual point image { L of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality, be designated as F
L, F
L=[F
1, F
2], wherein, F
LDimension be 288, " [] " is the vector representation symbol, [F
1, F
2] represent the First Characteristic vector F
1With the Second Characteristic vector F
2Couple together and form a New Characteristics vector;
4.-7, to the right visual point image { R of distortion
dis(x, y) } adopt the operation identical with step 4.-1 to 4.-6, obtain the right visual point image { R of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality, be designated as F
R, wherein, F
RDimension be 288;
4.-8, to the left visual point image { L of distortion
dis(x, y) } the characteristic vector F that is used for reflection picture quality
LRight visual point image { R with distortion
dis(x, y) } the characteristic vector F that is used for reflection picture quality
RCarry out linear weighted function, obtain S
disThe characteristic vector that is used for reflection picture quality, be designated as F
q, F
q=w
L* F
L+ w
R* F
R, wherein, w
LLeft visual point image { the L of expression distortion
dis(x, y) } weights proportion, w
RRight visual point image { the R of expression distortion
dis(x, y) } weights proportion, w
L+ w
R=1.
Described step detailed process 5. is:
5.-1, calculate respectively undistorted left visual point image { L
org(x, y) } and undistorted right visual point image { R
org(x, y) } absolute difference image, the left visual point image { L of distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } absolute difference image and undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) } absolute difference image, be designated as respectively { D
org(x, y) }, { D
dis(x, y) } and { Δ J (x, y) }, D
org(x, y)=| L
org(x, y)-R
org(x, y) |, D
dis(x, y)=| L
dis(x, y)-R
dis(x, y) |, Δ J (x, y)=| J
L(x, y)-J
R(x, y) |, wherein, D
org(x, y) represents { D
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), D
dis(x, y) represents { D
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y), the middle coordinate position of Δ J (x, y) expression { Δ J (x, y) } is the pixel value of the pixel of (x, y), " || " is for asking absolute value sign;
5. { D is obtained respectively in-2,3. identical operation of employing and step
org(x, y) } and { D
dis(x, y) } in the block type of each 8 * 8 sub-block;
5.-3, calculate { D
dis(x, y) } in all block types be the spatial noise intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of k, be designated as { fd
k(x
2, y
2), for { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel, use it for the reflection depth perception spatial noise intensity be designated as fd
k(x
2, y
2),
Wherein, fd
k(x
2, y
2) expression { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) the spatial noise intensity that is used for the reflection depth perception of pixel, 1≤x
2≤ 8,1≤y
2≤ 8, M
kExpression { D
dis(x, y) } in block type be the number of 8 * 8 sub-blocks of k, ST
kFor describing the saturation threshold value of error perception, (x
4, y
4) expression { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel at { D
org(x, y) } or { Δ J (x, y) } in coordinate position, 1≤x
4≤ W, 1≤y
4≤ H, D
org(x
4, y
4) expression { D
org(x, y) } in coordinate position be (x
4, y
4) the pixel value of pixel, D
dis(x
4, y
4) expression { D
dis(x, y) } in coordinate position be (x
4, y
4) the pixel value of pixel, Δ J (x
4, y
4) represent that in { Δ J (x, y) }, coordinate position is (x
4, y
4) the pixel value of pixel;
5.-4, with { D
dis(x, y) } in the spatial noise intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of various block types with set expression { fd
k(x
2, y
2) | 1≤k≤4}, then with { fd
k(x
2, y
2) | all elements in 1≤k≤4} is arranged in order and is obtained the 3rd characteristic vector, is designated as F
3, wherein, F
3Dimension be 256;
5.-5, to { D
org(x, y) } and { D
dis(x, y) } in each 8 * 8 sub-block implement respectively singular value decomposition, obtain respectively { D
org(x, y) } and { D
dis(x, y) } in each self-corresponding singular value vector of each 8 * 8 sub-block, with { D
org(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
With { D
dis(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Wherein, the dimension of singular value vector is 8,
5.-6, calculate { D
dis(x, y) } in all block types be the space structure intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of k, be designated as
Wherein, l " expression { D
dis(x, y) } in block type be that 8 * 8 sub-blocks of k are at { D
org(x, y) } or { Δ J (x, y) } in sequence number;
5.-7, with { D
dis(x, y) } in the space structure intensity set expression that is used for the reflection depth perception of 8 * 8 sub-blocks of various block types be
Then will
In all elements arrange in order and obtain the 4th characteristic vector, be designated as F
4, wherein, F
4Dimension be 32;
5.-8, with the 3rd characteristic vector F
3With the 4th characteristic vector F
4Form the New Characteristics vector, as S
disThe characteristic vector that is used for the reflection depth perception, be designated as F
s, F
s=[F
3, F
4], wherein, F
sDimension be 288, " [] " is the vector representation symbol, [F
3, F
4] represent the 3rd characteristic vector F
3With the 4th characteristic vector F
4Couple together and form a New Characteristics vector.
Described step detailed process 9. is:
9.-1, the stereo-picture with all distortions of same type of distortion in the set of distortion stereo-picture is divided into mutually disjoint 5 groups of subsets, selects arbitrarily 4 groups of subset composing training sample datas set wherein, is designated as Ω
q, { X
k, DMOS
k∈ Ω
q, wherein, q represents training sample data set omega
qIn the width number of stereo-picture of the distortion that comprises, X
kExpression training sample data set omega
qIn the characteristic vector of stereo-picture of k width distortion, DMOS
kExpression training sample data set omega
qIn the average subjective scoring difference of stereo-picture of k width distortion, 1≤k≤q;
9.-2, structure X
kRegression function f (X
k),
Wherein, f () is the function representation form, and w is weight vector, w
TBe the transposed matrix of w, b is bias term,
Expression training sample data set omega
qIn the characteristic vector X of stereo-picture of k width distortion
kLinear function,
D(X
k, X
l) be the kernel function in support vector regression,
X
lBe training sample data set omega
qIn the characteristic vector of stereo-picture of l width distortion, γ is nuclear parameter, is used for the scope of reflection input sample value, the scope of sample value is larger, and the γ value is also just larger, the exponential function of exp () expression take e the end of as, e=2.71828183, " || || for asking the Euclidean distance symbol;
9.-3, adopt support vector regression to training sample data set omega
qIn the characteristic vector of stereo-picture of all distortion train, make the regression function value and the error between average subjective scoring difference that obtain through training minimum, match obtains optimum weight vector w
optBias term b with optimum
opt, with the weight vector w of optimum
optBias term b with optimum
optCombination be designated as (w
opt, b
opt),
The weight vector w of the optimum that utilization obtains
optBias term b with optimum
optStructure support vector regression training pattern is designated as
Wherein, ψ represents training sample data set omega
qIn the set of combination of the characteristic vector of stereo-picture of all distortion all weight vector of training and bias term,
Expression minimizes probability density function, X
inpExpress support for the input vector of vector regression training pattern, (w
opt)
TBe w
optTransposed matrix,
Express support for the input vector X of vector regression training pattern
inpLinear function;
9.-4, according to the support vector regression training pattern, the stereo-picture that remains the every width distortion in 1 group of subset is tested, prediction obtains the evaluating objective quality predicted value of the stereo-picture of every width distortion in this group subset, evaluating objective quality predicted value for the stereo-picture of j width distortion in this group subset is designated as Q with it
j, Q
j=f (X
j),
Wherein, X
jThe characteristic vector that represents the stereo-picture of j width distortion in this group subset,
The linear function that represents the stereo-picture of j width distortion in this group subset;
9.-5, according to the process of step 9.-1 to 9.-4, respectively the stereo-picture of all distortions of different type of distortion in the set of distortion stereo-picture is trained, obtain the evaluating objective quality predicted value of the stereo-picture of every width distortion in the set of distortion stereo-picture.
Described step 4. with step 8. in the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the JPEG compression artefacts, get w
L=0.50, w
R=0.50; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the JPEG2000 compression artefacts, get w
L=0.15, w
R=0.85; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the Gaussian Blur distortion, get w
L=0.10, w
R=0.90; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the white noise distortion, get w
L=0.20, w
R=0.80; Calculating the H.264 characteristic vector process that is used for reflection picture quality of the stereo-picture of coding distortion, get w
L=0.10, w
R=0.90.
Compared with prior art, the invention has the advantages that:
1) the inventive method considers that zones of different has different responses to three-dimensional perception, stereo-picture is divided into Strong edge blocks, weak edge block, flat block and texture block and estimates respectively, simultaneously picture quality and depth perception information are attached in evaluation procedure, make evaluation result more feel to meet the human visual system.
2) the inventive method obtains minimum discernable distorted image according to the visual characteristic of human eye, and extract respectively the characteristic information of zones of different piece and form the characteristic vector of stereo-picture by computer memory noise intensity and space structure intensity, the characteristic vector information of the stereo-picture that obtains has stronger stability and can reflect preferably the mass change situation of stereo-picture, has improved the correlation of objective evaluation result and subjective perception.
Embodiment
Embodiment is described in further detail the present invention below in conjunction with accompanying drawing.
A kind of objective evaluation method for quality of stereo images based on visually-perceptible that the present invention proposes, it totally realizes block diagram as shown in Figure 1, it mainly comprises the following steps:
1. make S
orgUndistorted stereo-picture for original makes S
disFor the stereo-picture of distortion to be evaluated, with S
orgLeft visual point image be designated as { L
org(x, y) }, with S
orgRight visual point image be designated as { R
org(x, y) }, with S
disLeft visual point image be designated as { L
dis(x, y) }, with S
disRight visual point image be designated as { R
dis(x, y) }, wherein, the coordinate position of pixel in (x, y) left visual point image of expression and right visual point image, 1≤x≤W, 1≤y≤H, W represent the width of left visual point image and right visual point image, H represents the height of left visual point image and right visual point image, L
org(x, y) represents S
orgLeft visual point image { L
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), R
org(x, y) represents S
orgRight visual point image { R
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), L
dis(x, y) represents S
disLeft visual point image { L
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y), R
dis(x, y) represents S
disRight visual point image { R
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y).
2. human visual system (HVS) characteristic shows, human eye is non to changing less attribute or noise in image, unless the change intensity of this attribute or noise surpasses a certain threshold value, this threshold value is exactly minimum discernable distortion (Just noticeable distortion, JND).And the visual masking effect of human eye is a kind of local effect, is subjected to the impact of the factors such as background illuminance, Texture complication, and background is brighter, and texture is more complicated, and boundary value is just higher.Therefore the present invention utilizes human vision to the visual masking effect of background illumination and texture, extracts respectively undistorted left visual point image { L
org(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image, with undistorted left visual point image { L
org(x, y) } minimum discernable distorted image be designated as { J
L(x, y) }, with undistorted right visual point image { R
org(x, y) } minimum discernable distorted image be designated as { J
R(x, y) }, wherein, J
L(x, y) represents { J
L(x, y) } in coordinate position be the pixel value of the pixel of (x, y), J
R(x, y) represents { J
R(x, y) } in coordinate position be the pixel value of the pixel of (x, y).
In this specific embodiment, step detailed process 2. is:
2.-1, calculate undistorted left visual point image { L
org(x, y) } the visual threshold value set of visual masking effect of background illumination, be designated as { T
t(x, y) },
Wherein, T
l(x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be the visual threshold value of visual masking effect of background illumination of the pixel of (x, y),
Represent undistorted left visual point image { L
org(x, y) } in take coordinate position as (x, the average brightness of all pixels in 5 * 5 windows centered by pixel y), in actual process, also can adopt other big or small window, but through great many of experiments, result can obtain best effect when showing the window that adopts 5 * 5 sizes.
2.-2, calculate undistorted left visual point image { L
org(x, y) } the visual threshold value set of visual masking effect of texture, be designated as { T
t(x, y) }, T
t(x, y)=η * G (x, y) * W
e(x, y), wherein, T
t(x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be the visual threshold value of visual masking effect of texture of the pixel of (x, y), η is the controlling elements greater than 0, in the present embodiment, η=0.05, G (x, y) represents undistorted left visual point image { L
org(x, y) } in coordinate position be that the pixel of (x, y) carries out the maximum weighted mean value that directed high-pass filtering obtains, W
e(x, y) expression is to undistorted left visual point image { L
org(x, y) } edge image in coordinate position be that the pixel of (x, y) carries out the Weighted Edges value that Gassian low-pass filter obtains.
2.-3, to undistorted left visual point image { L
org(x, y) } the visual threshold value set { T of visual masking effect of background illumination
l(x, y) } and the visual threshold value set { T of the visual masking effect of texture
t(x, y) } merge, obtain undistorted left visual point image { L
org(x, y) } minimum discernable distorted image, be designated as { J
L(x, y) }, J
L(x, y)=T
l(x, y)+T
t(x, y)-C
L, t* min{T
l(x, y), T
t(x, y) }, wherein, C
L, tThe parameter of the visual masking effect eclipse effect of background illumination and texture, 0<C are controlled in expression
L, t<1, in the present embodiment, C
L, t=0.5, min{} is for getting minimum value function.
2. undistorted right visual point image { R is obtained in-4, the employing operation identical with step 2.-1 to 2.-3
org(x, y) } minimum discernable distorted image, be designated as { J
R(x, y) }.
3. because the human visual system has different susceptibilitys to edge, texture, the smooth region of image, zones of different also should be different to the responsiveness of three-dimensional perception, therefore, should consider respectively the contribution of zones of different to estimating in the stereo image quality evaluation.The present invention obtains respectively undistorted left visual point image { L by regional detection algorithm
org(x, y) } and the left visual point image { L of distortion
dis(x, y) }, undistorted right visual point image { R
org(x, y) } and the right visual point image { R of distortion
dis(x, y) } in the block type of each 8 * 8 sub-block, be designated as p, wherein, p ∈ 1,2,3,4}, p=1 represents Strong edge blocks, p=2 represents weak edge block, p=3 represents smooth block, p=4 represents texture block.
In this specific embodiment, the detailed process of the regional detection algorithm of step in 3. is:
3.-1, respectively with undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } be divided into
8 * 8 sub-blocks of individual non-overlapping copies define undistorted left visual point image { L
org(x, y) } in l 8 * 8 sub-blocks be current the first sub-block, be designated as
Left visual point image { the L of definition distortion
dis(x, y) } in l 8 * 8 sub-blocks be current the second sub-block, be designated as
Wherein,
(x
2, y
2) current the first sub-block of expression
With current the second sub-block
The coordinate position of middle pixel, 1≤x
2≤ 8,1≤y
2≤ 8,
Represent current the first sub-block
Middle coordinate position is (x
2, y
2) the pixel value of pixel,
Represent current the second sub-block
Middle coordinate position is (x
2, y
2) the pixel value of pixel.
3.-2, calculate respectively current the first sub-block
With current the second sub-block
In the Grad of all pixels, for current the first sub-block
Middle coordinate position is (x
2', y
2') pixel, its Grad is designated as P
o(x
2', y
2'), P
o(x
2', y
2')=| G
ox(x
2', y
2') |+| G
oy(x
2', y
2') |, for current the second sub-block
Middle coordinate position is (x
2', y
2') pixel, its Grad is designated as P
d(x
2', y
2'), P
d(x
2', y
2')=| G
dx(x
2', y
2') |+G
dy(x
2', y
2') |, wherein, 1≤x
2'≤8,1≤y
2'≤8, G
ox(x
2', y
2') current the first sub-block of expression
Middle coordinate position is (x
2', y
2') the horizontal gradient value of pixel, G
oy(x
2', y
2') current the first sub-block of expression
Middle coordinate position is (x
2', y
2') the vertical gradient value of pixel, G
dx(x
2', y
2') current the second sub-block of expression
Middle coordinate position is (x
2', y
2') the horizontal gradient value of pixel, G
dy(x
2', y
2') current the second sub-block of expression
Middle coordinate position is (x
2', y
2') the vertical gradient value of pixel, " || " is for asking absolute value sign.
3.-3, find out current the first sub-block
In the maximum of Grad of all pixels, be designated as G
max, then according to G
maxCalculate the first Grads threshold and the second Grads threshold, be designated as respectively T
1And T
2, T
1=0.12 * G
max, T
2=0.06 * G
max
3.-4, for current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel, the judgement P
o(x
2', y
2')>T
1And P
d(x
2', y
2')>T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be strong fringe region, Num
1=Num
1+ 1, then execution in step 3.-8, otherwise, execution in step 3.-5, wherein, Num
1Initial value be 0.
3.-5, judgement P
o(x
2', y
2')>T
1And P
d(x
2', y
2')<=T
1, perhaps P
d(x
2', y
2')>T
1And P
o(x
2', y
2')<=T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be weak fringe region, Num
2=Num
2+ 1, then execution in step 3.-8, otherwise, execution in step 3.-6, wherein, Num
2Initial value be 0.
3.-6, judgement P
o(x
2', y
2')<T
2And P
d(x
2', y
2')<T
1Whether set up, if so, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be smooth region, Num
3=Num
3+ 1, then execution in step 3.-8, otherwise, execution in step 3.-7, wherein, Num
3Initial value be 0.
3.-7, judge current the first sub-block
Middle coordinate position is (x
2', y
2') pixel and current the second sub-block
Middle coordinate position is (x
2', y
2') pixel be texture region, Num
4=Num
4+ 1, wherein, Num
4Initial value be 0.
3.-8, returning to step 3.-4 continues current the first sub-block
With current the second sub-block
In remaining pixel process, until current the first sub-block
With current the second sub-block
In 8 * 8 pixels all be disposed.
3.-9, with Num
1, Num
2, Num
3And Num
4In the corresponding area type of maximum as current the first sub-block
With current the second sub-block
Block type, be designated as p, wherein, p ∈ 1,2,3,4}, p=1 represents Strong edge blocks, p=2 represents weak edge block, p=3 represents smooth block, p=4 represents texture block.
3.-10, make l "=l+1, l=l ", with undistorted left visual point image { L
org(x, y) } in the next one 8 * 8 sub-blocks as current the first sub-block, with the left visual point image { L of distortion
dis(x, y) } in the next one 8 * 8 sub-blocks as current the second sub-block, return to step 3.-2 and continue to carry out, until undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in
8 * 8 sub-blocks of individual non-overlapping copies all are disposed, and obtain undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in the block type of all 8 * 8 sub-blocks, wherein, l " initial value be 0.
3.-11, the employing operation identical with step 3.-1 to 3.-10 obtains undistorted right visual point image { R
org(x, y) } and the right visual point image { R of distortion
dis(x, y) } in the block type of all 8 * 8 sub-blocks.
4. because the quality of stereo image quality is directly relevant with the left and right view-point image quality, introduce the correlation that the vision perception characteristics such as visual sensitivity, multichannel characteristic, masking effect can improve evaluation model and subjective scoring in image quality evaluation, consider distortion perceptibility and perception saturation phenomenon, with the discernable distorted image of minimum as vision perception characteristic.The present invention is according to undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) }, by the left visual point image { L of calculated distortion
dis(x, y) } in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for reflection picture quality and be used for the space structure intensity of reflection picture quality, and the right visual point image { R of distortion
dis(x, y) } in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for reflection picture quality and be used for the space structure intensity of reflection picture quality, obtain respectively the left visual point image { L of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality and the right visual point image { R of distortion
dos(x, y) } the characteristic vector that is used for reflection picture quality, then to the left visual point image { L of distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality carry out linear weighted function, obtain S
disThe characteristic vector that is used for reflection picture quality, be designated as F
q
In this specific embodiment, step detailed process 4. is:
4.-1, the left visual point image { L of calculated distortion
dis(x, y) } in all block types be the spatial noise intensity that is used for reflection picture quality of 8 * 8 sub-blocks of k, be designated as { fq
k(x
2, y
2), for the left visual point image { L of distortion
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel, use it for the reflection picture quality spatial noise intensity be designated as fq
k(x
2, y
2),
Wherein, k ∈ { p|1≤p≤4}, fq
k(x
2, y
2) expression distortion left visual point image { L
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) the spatial noise intensity that is used for reflection picture quality of pixel, 1≤x
2≤ 8,1≤y
2≤ 8, N
kLeft visual point image { the L of expression distortion
dis(x, y) } in block type be the number of 8 * 8 sub-blocks of k, ST
kFor describing the saturation threshold value of error perception, in the present embodiment, ST
k=30, max () is for getting max function, and min () is for getting minimum value function, (x
3, y
3) expression distortion left visual point image { L
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel at undistorted left visual point image { L
org(x, y) } or undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } in coordinate position, 1≤x
3≤ W, 1≤y
3≤ H, L
org(x
3, y
3) expression { L
org(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, L
dis(x
3, y
3) expression { L
dis(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, J
L(x
3, y
3) expression { J
L(x, y) } in coordinate position be (x
3, y
3) the pixel value of pixel, " || " is for asking absolute value sign.
4.-2, with the left visual point image { L of distortion
dis(x, y) } in the spatial noise intensity set expression that is used for reflection picture quality of 8 * 8 sub-blocks of various block types be { fq
k(x
2, y
2) | 1≤k≤4}, then with { fq
k(x
2, y
2) | all elements in 1≤k≤4} is arranged in order and is obtained the First Characteristic vector, is designated as F
1, wherein, F
1Dimension be 256.
4.-3, to undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in each 8 * 8 sub-block implement respectively singular value decomposition, obtain respectively undistorted left visual point image { L
org(x, y) } and the left visual point image { L of distortion
dis(x, y) } in each self-corresponding singular value vector of each 8 * 8 sub-block, with undistorted left visual point image { L
org(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Left visual point image { L with distortion
dis(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Wherein, the dimension of singular value vector is 8,
4.-4, the left visual point image { L of calculated distortion
dis(x, y) } in all block types be the space structure intensity that is used for reflection picture quality of 8 * 8 sub-blocks of k, be designated as
Wherein, the left visual point image { L of l ' expression distortion
dis(x, y) } in block type be that 8 * 8 sub-blocks of k are at undistorted left visual point image { L
org(x, y) } or undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } in sequence number.
4.-5, with the left visual point image { L of distortion
dis(x, y) } in the space structure intensity set expression that is used for reflection picture quality of 8 * 8 sub-blocks of various block types be
Then will
In all elements arrange in order and obtain the Second Characteristic vector, be designated as F
2, wherein, F
2Dimension be 32.
4.-6, with the First Characteristic vector F
1With the Second Characteristic vector F
2Form the New Characteristics vector, as the left visual point image { L of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality, be designated as F
L, F
L=[F
1, F
2], wherein, F
LDimension be 288, " [] " is the vector representation symbol, [F
1, F
2] represent the First Characteristic vector F
1With the Second Characteristic vector F
2Couple together and form a New Characteristics vector.
4.-7, to the right visual point image { R of distortion
dis(x, y) } adopt the operation identical with step 4.-1 to 4.-6, obtain the right visual point image { R of distortion
dis(x, y) } the characteristic vector that is used for reflection picture quality, be designated as F
R, wherein, F
RDimension be 288.
4.-8, to the left visual point image { L of distortion
dis(x, y) } the characteristic vector F that is used for reflection picture quality
LRight visual point image { R with distortion
dis(x, y) } the characteristic vector F that is used for reflection picture quality
RCarry out linear weighted function, obtain S
disThe characteristic vector that is used for reflection picture quality, be designated as F
q, F
q=w
L* F
L+ w
R* F
R, wherein, w
LLeft visual point image { the L of expression distortion
dis(x, y) } weights proportion, w
RRight visual point image { the R of expression distortion
dis(x, y) } weights proportion, w
L+ w
R=1.
5. existing studies show that, when the difference of the absolute difference image of the left and right visual point image of the absolute difference image of undistorted left and right visual point image and distortion surpasses some threshold values, the decline of depth perception is just easily discovered by human eye, therefore, can estimate with the similarity of the absolute difference image of the left and right visual point image of the absolute difference image of undistorted left and right visual point image and distortion the depth perception of stereo-picture, absolute difference image is more similar, and depth perception is stronger.Therefore, the present invention is according to undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) }, by the left visual point image { L of calculated distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } absolute difference image in various block types 8 * 8 sub-blocks the spatial noise intensity that is used for the reflection depth perception and be used for the space structure intensity of reflection depth perception, obtain S
disThe characteristic vector that is used for the reflection depth perception, be designated as F
s
In this specific embodiment, step detailed process 5. is:
5.-1, calculate respectively undistorted left visual point image { L
org(x, y) } and undistorted right visual point image { R
org(x, y) } absolute difference image, the left visual point image { L of distortion
dis(x, y) } and the right visual point image { R of distortion
dis(x, y) } absolute difference image and undistorted left visual point image { L
org(x, y) } minimum discernable distorted image { J
L(x, y) } and undistorted right visual point image { R
org(x, y) } minimum discernable distorted image { J
R(x, y) } absolute difference image, be designated as respectively { D
org(x, y) }, { D
dis(x, y) } and { Δ J (x, y) }, D
org(x, y)=| L
org(x, y)-R
org(x, y) |, D
dis(x, y)=| L
dis(x, y)-R
dis(x, y) |, Δ J (x, y)=| J
L(x, y)-J
R(x, y) |, wherein, D
org(x, y) represents { D
org(x, y) } in coordinate position be the pixel value of the pixel of (x, y), D
dis(x, y) represents { D
dis(x, y) } in coordinate position be the pixel value of the pixel of (x, y), the middle coordinate position of Δ J (x, y) expression { Δ J (x, y) } is the pixel value of the pixel of (x, y), " || " is for asking absolute value sign.
5. { D is obtained respectively in-2,3. identical operation of employing and step
org(x, y) } and { D
dis(x, y) } in the block type of each 8 * 8 sub-block.
5.-3, calculate { D
dis(x, y) } in all block types be the spatial noise intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of k, be designated as { fd
k(x
2, y
2), for { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel, use it for the reflection depth perception spatial noise intensity be designated as fd
k(x
2, y
2),
Wherein, fd
k(x
2, y
2) expression { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) the spatial noise intensity that is used for the reflection depth perception of pixel, 1≤x
2≤ 8,1≤y
2≤ 8, M
kExpression { D
dis(x, y) } in block type be the number of 8 * 8 sub-blocks of k, ST
kFor describing the saturation threshold value of error perception, (x
4, y
4) expression { D
dis(x, y) } in block type be that in 8 * 8 sub-blocks of k, coordinate position is (x
2, y
2) pixel at { D
org(x, y) } or { Δ J (x, y) } in coordinate position, 1≤x
4≤ W, 1≤y
4≤ H, D
org(x
4, y
4) expression { D
org(x, y) } in coordinate position be (x
4, y
4) the pixel value of pixel, D
dis(x
4, y
4) expression { D
dis(x, y) } in coordinate position be (x
4, y
4) the pixel value of pixel, Δ J (x
4, y
4) represent that in { Δ J (x, y) }, coordinate position is (x
4, y
4) the pixel value of pixel.
5.-4, with { D
dis(x, y) } in the spatial noise intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of various block types with set expression { fd
k(x
2, y
2) | 1≤k≤4}, then with { fd
k(x
2, y
2) | all elements in 1≤k≤4} is arranged in order and is obtained the 3rd characteristic vector, is designated as F
3, wherein, F
3Dimension be 256.
5.-5, to { D
org(x, y) } and { D
dis(x, y) } in each 8 * 8 sub-block implement respectively singular value decomposition, obtain respectively { D
org(x, y) } and { D
dis(x, y) } in each self-corresponding singular value vector of each 8 * 8 sub-block, with { D
org(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
With { D
dis(x, y) } in the singular value vector of l 8 * 8 sub-blocks be designated as
Wherein, the dimension of singular value vector is 8,
5.-6, calculate { D
dis(x, y) } in all block types be the space structure intensity that is used for the reflection depth perception of 8 * 8 sub-blocks of k, be designated as
Wherein, l " expression { D
dis(x, y) } in block type be that 8 * 8 sub-blocks of k are at { D
org(x, y) } or { Δ J (x, y) } in sequence number.
5.-7, with { D
dis(x, y) } in the space structure intensity set expression that is used for the reflection depth perception of 8 * 8 sub-blocks of various block types be
Then will
In all elements arrange in order and obtain the 4th characteristic vector, be designated as F
4, wherein, F
4Dimension be 32.
5.-8, with the 3rd characteristic vector F
3With the 4th characteristic vector F
4Form the New Characteristics vector, as S
disThe characteristic vector that is used for the reflection depth perception, be designated as F
s, F
s=[F
3, F
4], wherein, F
sDimension be 288, " [] " is the vector representation symbol, [F
3, F
4] represent the 3rd characteristic vector F
3With the 4th characteristic vector F
4Couple together and form a New Characteristics vector.
6. with S
disThe characteristic vector F that is used for reflection picture quality
qWith the characteristic vector F that is used for the reflection depth perception
sForm the New Characteristics vector, as S
disCharacteristic vector, be designated as X, X=[F
q, F
s], " [] " is the vector representation symbol, [F
q, F
s] represent characteristic vector F
qWith characteristic vector F
sCouple together and form a New Characteristics vector.
7. adopt n undistorted stereo-picture, set up its distortion stereo-picture set under the different distortion levels of different type of distortion, this distortion stereo-picture set comprises the stereo-picture of several distortions, utilizes the subjective quality assessment method to obtain respectively the average subjective scoring difference of the stereo-picture of every width distortion in the set of distortion stereo-picture, is designated as DMOS, DMOS=100-MOS, wherein, MOS represents the subjective scoring average, DMOS ∈ [0,100], n 〉=1.
in the present embodiment, because the stereo-picture of testing obtains by H.264 encoding, therefore the type of distortion of training sample and test sample book should be consistent in support vector regression, utilize the stereo-picture as Fig. 2 a and Fig. 2 b formation, the stereo-picture that Fig. 3 a and Fig. 3 b consist of, the stereo-picture that Fig. 4 a and Fig. 4 b consist of, the stereo-picture that Fig. 5 a and Fig. 5 b consist of, the stereo-picture that Fig. 6 a and Fig. 6 b consist of, the stereo-picture that Fig. 7 a and Fig. 7 b consist of, the stereo-picture that Fig. 8 a and Fig. 8 b consist of, the stereo-picture that Fig. 9 a and Fig. 9 b consist of, the stereo-picture that Figure 10 a and Figure 10 b consist of, the stereo-picture that Figure 11 a and Figure 11 b consist of, the stereo-picture that Figure 12 a and Figure 12 b consist of, stereo-picture that Figure 13 a and Figure 13 b the consist of undistorted stereo-picture of totally 12 width (n=12) has been set up its distortion stereo-picture set under the different distortion levels of coding distortion type H.264, the stereo-picture of distortion has 72 width in this distortion stereo-picture set.
8. adopt and calculate S
disThe identical method of characteristic vector X, the characteristic vector of the stereo-picture of every width distortion in the set of calculated distortion stereo-picture respectively, the characteristic vector for the stereo-picture of i width distortion in the set of distortion stereo-picture is designated as X with it
i, wherein, 1≤i≤n ', the width number of the stereo-picture of the distortion that comprises in the set of n ' expression distortion stereo-picture.
In this specific embodiment, according to the stereoscopic vision masking effect inconsistent characteristic of human eye to different type of distortion, left visual point image and right visual point image to the stereo-picture of different type of distortion arrange different weights proportion, in the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the JPEG compression artefacts, get w
L=0.50, w
R=0.50; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the JPEG2000 compression artefacts, get w
L=0.15, w
R=0.85; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the Gaussian Blur distortion, get w
L=0.10, w
R=0.90; In the characteristic vector process that is used for reflection picture quality of the stereo-picture that calculates the white noise distortion, get w
L=0.20, w
R=0.80; Calculating the H.264 characteristic vector process that is used for reflection picture quality of the stereo-picture of coding distortion, get w
L=0.10, w
R=0.90.
9. the characteristic vector due to the stereo-picture of distortion is the higher dimensional space vector, need to construct linear decision function and realize non-linear decision function in former space in higher dimensional space, support vector regression (Support Vector Regression, SVR) is a kind of reasonable method that realizes non-linear higher dimensional space conversion.Therefore the inventive method adopts support vector regression that the characteristic vector of the stereo-picture of all distortions of identical type of distortion in the set of distortion stereo-picture is trained, and the support vector regression training pattern of utilizing training to obtain is tested the stereo-picture of every width distortion of same type of distortion, calculate the evaluating objective quality predicted value of the stereo-picture of every width distortion of identical type of distortion in the set of distortion stereo-picture, evaluating objective quality predicted value for the stereo-picture of i width distortion in the set of distortion stereo-picture is designated as Q with it
i, Q
i=f (X
i), f () is the function representation form, Q
i=f (X
i) expression Q
iBe X
iFunction, wherein, 1≤i≤n ', the width number of the stereo-picture of the distortion that comprises in the set of n ' expression distortion stereo-picture.
In this specific embodiment, step detailed process 9. is:
9.-1, the stereo-picture with all distortions of same type of distortion in the set of distortion stereo-picture is divided into mutually disjoint 5 groups of subsets, selects arbitrarily 4 groups of subset composing training sample datas set wherein, is designated as Ω
q, { X
k, DMOS
k∈ Ω
q, wherein, q represents training sample data set omega
qIn the width number of stereo-picture of the distortion that comprises, X
kExpression training sample data set omega
qIn the characteristic vector of stereo-picture of k width distortion, DMOS
kExpression training sample data set omega
qIn the average subjective scoring difference of stereo-picture of k width distortion, 1≤k≤q.
9.-2, structure X
kRegression function f (X
k),
Wherein, f () is the function representation form, and w is weight vector, w
TBe the transposed matrix of w, b is bias term,
Expression training sample data set omega
qIn the characteristic vector X of stereo-picture of k width distortion
kLinear function,
D(X
k, X
l) be the kernel function in support vector regression,
X
lBe training sample data set omega
qIn the characteristic vector of stereo-picture of l width distortion, γ is nuclear parameter, is used for the scope of reflection input sample value, the scope of sample value is larger, and the γ value is also just larger, the exponential function of exp () expression take e the end of as, e=2.71828183, " || || for asking the Euclidean distance symbol.
In the present embodiment, JPEG compression artefacts, JPEG 2000 compression artefacts, Gaussian Blur distortion, white noise distortion and H.264 the γ value of coding distortion get respectively 42,52,54,130 and 116.
9.-3, adopt support vector regression to training sample data set omega
qIn the characteristic vector of stereo-picture of all distortion train, make the regression function value and the error between average subjective scoring difference that obtain through training minimum, match obtains optimum weight vector w
optBias term b with optimum
opt, with the weight vector w of optimum
optBias term b with optimum
optCombination be designated as (w
opt, b
opt),
The weight vector w of the optimum that utilization obtains
optBias term b with optimum
optStructure support vector regression training pattern is designated as
Wherein, ψ represents training sample data set omega
qIn the set of combination of the characteristic vector of stereo-picture of all distortion all weight vector of training and bias term,
Expression minimizes probability density function, X
inpExpress support for the input vector of vector regression training pattern, (w
opt)
TBe w
optTransposed matrix,
Express support for the input vector X of vector regression training pattern
inpLinear function.
9.-4, according to the support vector regression training pattern, the stereo-picture that remains the every width distortion in 1 group of subset is tested, prediction obtains the evaluating objective quality predicted value of the stereo-picture of every width distortion in this group subset, evaluating objective quality predicted value for the stereo-picture of j width distortion in this group subset is designated as Q with it
j, Q
j=f (X
j),
Wherein, X
jThe characteristic vector that represents the stereo-picture of j width distortion in this group subset,
The linear function that represents the stereo-picture of j width distortion in this group subset.
9.-5, according to the process of step 9.-1 to 9.-4, respectively the stereo-picture of all distortions of different type of distortion in the set of distortion stereo-picture is trained, obtain the evaluating objective quality predicted value of the stereo-picture of every width distortion in the set of distortion stereo-picture.
Adopt 12 undistorted stereo-pictures shown in Fig. 2 a to Figure 13 b to analyze objective image quality evaluation predicted value and the average correlation between the subjective scoring difference of the stereo-picture of the distortion that the present embodiment obtains at the stereo-picture of in various degree JPEG compression, JPEG2000 compression, Gaussian Blur, white noise and H.264 312 width distortions in the coding distortion situation.Here, utilize 2 objective parameters commonly used of evaluate image quality evaluating method as evaluation index, be Pearson correlation coefficient (the Correlation Coefficient under the nonlinear regression condition, CC), Spearman coefficient correlation (Rank-Order Correlation Coefficient, ROCC), the stereo-picture of CC reflection distortion is estimated the accuracy of objective models, and ROCC reflects its monotonicity.The objective image evaluation quality predicted value of the stereo-picture of the distortion that will calculate by the present embodiment is done four parameter L ogistic function nonlinear fittings, and the higher explanation method for objectively evaluating of CC and ROCC value is better with average subjective scoring difference correlation.Table 1 has been listed the image quality evaluation predicted value of stereo-picture of the distortion that the present embodiment obtains and correlation between subjective scoring, from the listed data of table 1 as can be known, correlation between the final objective image quality evaluation predicted value of the stereo-picture of the distortion that obtains by the present embodiment and average subjective scoring difference is very high, the result that shows objective evaluation result and human eye subjective perception is more consistent, is enough to illustrate the validity of the inventive method.
Table 2 has provided the image quality evaluation predicted value of the stereo-picture that adopts the distortion that the different characteristic vector obtains and correlation between subjective scoring, as can be seen from Table 2, only adopt evaluation predicted value single or that two characteristic vectors obtain all and between subjective scoring all to have larger correlation, the feature extracting method that the inventive method is described is effective, and the characteristic vector in conjunction with reflection picture quality and depth perception, the evaluation predicted value and the correlation between subjective scoring that obtain are stronger, are enough to illustrate that this method is effective.
The image quality evaluation predicted value of the stereo-picture of the distortion that table 1 the present embodiment obtains and the correlation between subjective scoring
The image quality evaluation predicted value of the stereo-picture of the distortion that table 2 employing different characteristic vector obtains and the correlation between subjective scoring