CN103914835B - A kind of reference-free quality evaluation method for fuzzy distortion stereo-picture - Google Patents

Abstract

The invention discloses a kind of reference-free quality evaluation method for fuzzy distortion stereo-picture, it is in the training stage, select several undistorted stereo-pictures and corresponding fuzzy distortion stereo-picture composing training image set, use Bidimensional Empirical Mode Decomposition that fuzzy distortion stereo-picture carries out decomposition and obtain intrinsic mode functions image, and use K means clustering method to construct visual dictionary table；By obtaining the objective evaluation metric of the pixel in fuzzy distortion stereo-picture, construct visual quality table；At test phase, use Bidimensional Empirical Mode Decomposition that test stereo-picture is carried out decomposition and obtain intrinsic mode functions image, then according to visual dictionary table and visual quality table, obtain testing the picture quality objective evaluation predicted value of image；Advantage is to need not complicated machine learning training process in the training stage, only just need to can obtain picture quality objective evaluation predicted value by simple visual dictionary search procedure at test phase, and preferable with the uniformity of subjective assessment value.

Description

No-reference quality evaluation method for fuzzy distortion stereo image

Technical Field

The invention relates to an image quality evaluation method, in particular to a no-reference quality evaluation method for a fuzzy distortion stereo image.

Background

With the rapid development of image coding technology and stereoscopic display technology, the stereoscopic image technology has received more and more extensive attention and application, and has become a current research hotspot. The stereoscopic image technology utilizes the binocular parallax principle of human eyes, the left viewpoint image and the right viewpoint image from the same scene are respectively and independently received by the two eyes, and the binocular parallax is formed through brain fusion, so that the stereoscopic image with depth perception and reality perception is appreciated. Compared with a single-channel image, the stereo image needs to ensure the image quality of two channels at the same time, so that the quality evaluation of the stereo image is of great significance. However, currently, there is no effective objective evaluation method for evaluating the quality of stereoscopic images. Therefore, establishing an effective objective evaluation model of the quality of the stereo image has very important significance.

Because there are many factors that affect the quality of a stereoscopic image, such as the quality distortion condition of the left viewpoint and the right viewpoint, the stereoscopic perception condition, and the visual fatigue of an observer, how to effectively perform non-reference quality evaluation is a difficult problem that needs to be solved urgently. At present, machine learning is generally adopted for predicting an evaluation model for non-reference quality evaluation, the calculation complexity is high, and the training model needs to predict subjective evaluation values of evaluation images, so that the method is not suitable for practical application occasions and has certain limitations. Sparse representation decomposes a signal on a known function set, strives to approximate an original signal on a transform domain by using a small amount of basis functions, and currently research mainly focuses on dictionary construction and sparse decomposition. One key issue with sparse representations is how to efficiently construct dictionaries to characterize the essential features of images. The dictionary construction algorithm proposed so far includes: 1) the dictionary construction method with the learning process comprises the following steps: dictionary information is obtained through machine learning training, such as a support vector machine and the like; 2) the dictionary construction method without the learning process comprises the following steps: and constructing a dictionary, such as a multi-scale Gabor dictionary, a multi-scale Gaussian dictionary and the like, by directly utilizing the features of the image. Therefore, how to construct a dictionary without a learning process and how to estimate the quality without reference from the dictionary are all technical problems that need to be solved in the quality evaluation research without reference.

Disclosure of Invention

The invention aims to provide a no-reference quality evaluation method for a fuzzy distortion stereo image, which can effectively improve the correlation between objective evaluation results and subjective perception.

The technical scheme adopted by the invention for solving the technical problems is as follows: a no-reference quality evaluation method for a fuzzy distortion stereo image is characterized by comprising a training stage and a testing stage, and specifically comprising the following steps:

① selecting N original undistorted stereo images, and forming training image set by the selected N original undistorted stereo images and the blurred and distorted stereo images corresponding to each original undistorted stereo image, and recording as { S_i,org,S_i,dis|1≤i≤N}，S_i,orgRepresenting a set of training images S_i,org,S_i,disI 1 is not less than i not more than N_i,disRepresenting a set of training images S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and the ith original undistorted stereo image corresponds to the blurred distorted stereo image; then the S is mixed_i,orgIs recorded as L_i,orgWill S_i,orgIs recorded as R_i,orgWill S_i,disIs recorded as L_i,disWill S_i,disIs recorded as R_i,dis；

② pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, respectively implementing two-dimensional empirical mode decomposition on the left viewpoint image and the right viewpoint image of each fuzzy distortion stereo image to obtain a training image set { S_i,org,S_i,disL1 is not more than i is not more than N) and the intrinsic mode function image of each of the left viewpoint image and the right viewpoint image of each of the blurred and distorted stereo images_i,disIs recorded as the intrinsic mode function imageR is to be_i,disIs recorded as the intrinsic mode function imageWherein 1. ltoreq. x.ltoreq.W, 1. ltoreq. y.ltoreq.H, where W representsAndis shown here as HAndthe height of (a) of (b),to representThe middle coordinate position is the pixel value of the pixel point of (x, y),to representThe middle coordinate position is the pixel value of the pixel point of (x, y);

then, for the training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N), and the intrinsic mode function image of the left viewpoint image and the intrinsic mode function image of the right viewpoint image of each blurred and distorted stereo image are subjected to linear weighting to obtain a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and S is compared with S_i,disIs recorded as the intrinsic mode function imageWill be provided withThe pixel value of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{IMF}}_i^{\mathrm{dis}}(x,y)=w_L\×{\mathrm{IMF}}_i^{L,\mathrm{dis}}(x,y)+w_R\×{\mathrm{IMF}}_i^{R,\mathrm{dis}}(x,y),$ Wherein, w_LIs composed ofWeight ratio of (1), w_RIs composed ofWeight ratio of (1), w_L+w_R=1；

③ pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and carrying out non-overlapping blocking processing on the intrinsic mode function image of each fuzzy distortion stereo image; then, clustering a set formed by all sub-blocks in each intrinsic mode function image by adopting a K-means clustering method to obtain K clusters of each intrinsic mode function image, wherein K represents the total number of clusters contained in each intrinsic mode function image; then, acquiring a visual dictionary table of each intrinsic mode function image according to K clusters of each intrinsic mode function image; then, obtaining a training image set { S ] according to the visual dictionary table of all intrinsic mode function images_i,org,S_i,disA visual dictionary table of |1 ≦ i ≦ N, denoted G, G = { G = ≦ G ≦ C ≦ N }_iI is more than or equal to 1 and less than or equal to N, wherein G_iTo representVisual dictionary table of G_i={g_i,k|1≤k≤K}，g_i,kTo representThe visual dictionary of the kth cluster, g_i,kAlso showsThe centroid of the kth cluster of (1);

④ training image set by calculating S_i,org,S_i,disI is not less than 1 and not more than N), and obtaining the objective evaluation metric value of each pixel point in each blurred and distorted stereo image; then obtaining a visual quality table of each fuzzy distortion stereo image according to the objective evaluation metric value of each pixel point in each fuzzy distortion stereo image; then, obtaining a training image set { S) according to the visual quality table of all the fuzzy distortion stereo images_i,org,S_i,disThe visual quality table of I1 ≦ i ≦ N, denoted Q, Q = { Q = ≦ Q ≦ N }_iI is more than or equal to 1 and less than or equal to N, wherein Q_iDenotes S_i,disVisual quality table of (2), Q_i={q_i,k|1≤k≤K}，q_i,kTo representThe visual quality of the kth cluster of (1);

⑤ for any one test stereo image S_testFrom a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and calculating to obtain S_testObjectively evaluating the predicted value of the image quality.

W in said step ②_L=0.9，w_R=0.1。

Said step ③The process of obtaining the visual dictionary table Gi is as follows:

③ -1, willIs divided intoThe non-overlapping sub-blocks of size 16 × 16 are formed byThe set of all sub-blocks in (1) is denoted asWherein x is_i,tIs represented byThe column vector, x, composed of all the pixel points in the t-th sub-block_i,tHas a dimension of 256;

③ -2, adopting K-means clustering method to pairPerforming clustering operation to obtainThen will be clusteredUsing the centroid of each cluster as a visual dictionary to obtainVisual dictionary table, denoted G_i，G_i={g_i,kL 1 is less than or equal to K, wherein K representsTotal number of clusters contained, g_i,kTo representThe visual dictionary of the kth cluster, g_i,kAlso showsThe centroid of the kth cluster, g_i,kHas a dimension of 256.

S in the step ④_i,disVisual quality table Q_iThe acquisition process comprises the following steps:

④ -1, respectively using Gabor filters to the L_i,org、R_i,org、L_i,disAnd R_i,disFiltering to obtain L_i,org、R_i,org、L_i,disAnd R_i,disThe frequency response of each pixel point in (1) under different central frequencies and different direction factors, the frequency response of Li,_orgthe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ}),$ R is to be_i,orgThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ}),$ Mixing L with_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ}),$ R is to be_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ}),$ Wherein x is 1. ltoreq. x.ltoreq.W is 1. ltoreq. y.ltoreq.H, where W represents L_i,_org、R_i,_org、L_i,_disAnd R_i,_disWhere H represents L_i,_org、R_i,_org、L_i,_disAnd R_i,_disω ∈ {1.74,2.47,3.49,4.93,6.98,9.87}, θ represents the orientation factor of the Gabor filter, 1 ≦ θ ≦ 4,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofJ is an imaginary unit;

④ -2, according to L_i,orgAnd R_i,orgCalculating the frequency response of each pixel point in the S under the selected center frequency and different direction factors_i,orgAmplitude of each pixel point in (1), will S_i,orgThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{LA}}_i^{\mathrm{org}}(x,y)=\sqrt{{\left(F_i^{\mathrm{org}}(x,y)\right)}^2+{\left(H_i^{\mathrm{org}}(x,y)\right)}^2},$ Wherein, $F_i^{\mathrm{org}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{e}_{i,\mathrm{org}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+e_{i,\mathrm{org}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ $H_i^{\mathrm{org}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{o}_{i,\mathrm{org}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+o_{i,\mathrm{org}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ ω_mfor a selected center frequency, ω_m∈{1.74,2.47,3.49,4.93,6.98,9.87}，Represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaAn imaginary part of (d);

also according to L_i,disAnd R_i,disCalculating the frequency response of each pixel point in the S under the selected center frequency and different direction factors_i,disAmplitude of each pixel point in (1), will S_i,disThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{LA}}_i^{\mathrm{dis}}(x,y)=\sqrt{{\left(F_i^{\mathrm{dis}}(x,y)\right)}^2+{\left(H_i^{\mathrm{dis}}(x,y)\right)}^2},$ Wherein, $F_i^{\mathrm{dis}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{e}_{i,\mathrm{dis}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+e_{i,\mathrm{dis}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ $H_i^{\mathrm{dis}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{o}_{i,\mathrm{dis}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+o_{i,\mathrm{dis}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ ω_mfor a selected center frequency, ω_m∈{1.74,2.47,3.49,4.93,6.98,9.87}，Represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,disThe pixel point with the (x, y) middle coordinate position is at the center frequencyRate of omega_mAnd the frequency response at a directional factor of thetaAn imaginary part of (d);

④ -3, according to S_i,orgAnd S_i,disCalculating S from the amplitude of each pixel point_i,disThe objective evaluation metric value of each pixel point in S_i,disThe objective evaluation metric value of the pixel point with the middle coordinate position (x, y) is recorded as rho_i(x,y)， ${\mathrm{\ρ}}_i(x,y)=\frac{1+\cos (2\·{\mathrm{\ψ}}_i(x,y))}{2},$ ${\mathrm{\ψ}}_i(x,y)=\arccos \left(\frac{{\mathrm{GX}}_i^{\mathrm{org}}(x,y)\·{\mathrm{GX}}_i^{\mathrm{dis}}(x,y)+{\mathrm{GY}}_i^{\mathrm{org}}(x,y)\·{\mathrm{GY}}_i^{\mathrm{dis}}(x,y)+T_1}{\sqrt{{\left({\mathrm{GX}}_i^{\mathrm{org}}(x,y)\right)}^2+{\left({\mathrm{GY}}_i^{\mathrm{org}}(x,y)\right)}^2}\·\sqrt{{\left({\mathrm{GX}}_i^{\mathrm{dis}}(x,y)\right)}^2+{\left({\mathrm{GY}}_i^{\mathrm{dis}}(x,y)\right)}^2}+T_1}\right),$ Wherein cos () is a cosine-taken function, arccos () is an inverse cosine-taken function,is composed ofThe horizontal gradient value of (a) is,is composed ofThe vertical gradient value of (a) is,is composed ofThe horizontal gradient value of (a) is,is composed ofVertical gradient value of, T₁Is a control parameter;

④ -4, according to S_i,disObtaining S according to the objective evaluation metric value of each pixel point_i,disIs marked as Q_i，Q_i={q_i,kL 1 is more than or equal to K and less than or equal to K, wherein q is equal to or less than K_i,kTo representThe visual quality of the k-th cluster of (c),Ω_kdenotes S_i,disNeutralization ofThe set of coordinate positions of pixel points having the same coordinate position of all pixel points included in the kth cluster,to representThe total number of pixel points included in the kth cluster.

The concrete process of the fifth step is as follows:

⑤ -1, mixing S_testIs recorded as L_testWill S_testIs recorded as R_testTo L for_testAnd R_testRespectively carrying out two-dimensional empirical mode decomposition to obtain L_testAnd R_testRespective intrinsic mode function images, corresponding notationAndthen toAndlinear weighting is carried out to obtain S_testIs denoted as { IMF [ ], in the intrinsic mode function image_test(x, y) }, will { IMF_test(x,_y) The pixel value of the pixel point with the coordinate position (x, y) in the pixel is recorded as IMF_test(x,y)， ${\mathrm{IMF}}_{\mathrm{test}}(x,y)={w_L}^{\′}\×{\mathrm{IMF}}_{\mathrm{test}}^L(x,y)+{w_R}^{\′}\×{\mathrm{IMF}}_{\mathrm{test}}^R(x,y),$ Wherein 1. ltoreq. x.ltoreq.W ', 1. ltoreq. y.ltoreq.H ', where W ' representsAndis shown here as HAndthe height of (a) of (b),to representThe middle coordinate position is the pixel value of the pixel point of (x, y),to representThe pixel value, w, of the pixel point with the middle coordinate position (x, y)_L' isWeight ratio of (1), w_R' isWeight ratio of (1), w_L'+w_R'=1；

⑤ -2, will { IMF_test(x, y) } division intoThe non-overlapping sub-blocks of size 16 × 16 are defined by IMF_testThe set of all subblocks in (x, y) } is denoted asWherein, y_tIs represented by { IMF_testThe column vector formed by all pixel points in the t-th sub-block in (x, y) }, y_tHas a dimension of 256;

⑤ -3, calculation of { IMF_testThe minimum Euclidean distance of each sub-block in (x, y) } from G, will be { IMF_testThe minimum Euclidean distance between the t-th sub-block and G in (x, y) } is recorded as_t，Wherein, the symbol "| | |" is a euclidean distance symbol, and the min () is a minimum function;

⑤ -4, calculation of { IMF_test(x, y) } the objective evaluation metric for each sub-block, will be { IMF_testThe objective evaluation metric value for the t-th sub-block in (x, y) } is denoted as zt,wherein,in the representation of Q_tThe visual quality corresponding to the corresponding visual dictionary is more than or equal to 1 and less than or equal to N, more than or equal to 1 and less than or equal to K, exp () represents an exponential function with e as a base, e =2.71828183, and lambda is a control parameter;

⑤ -5, according to { IMF_test(x, y) } calculating S the objective evaluation metric value for each sub-block_testThe image quality objective evaluation predicted value of (1) is marked as Q,

compared with the prior art, the invention has the advantages that:

1) the method constructs the visual dictionary table and the visual quality table in an unsupervised learning mode, so that a complex machine learning training process is avoided, and the method does not need to predict subjective evaluation values of all training images in a training stage, so that the method is more suitable for practical application occasions.

2) In the testing stage, the method can predict and obtain the image quality objective evaluation predicted value only through a simple visual dictionary searching process, thereby greatly reducing the calculation complexity of the testing process, and keeping better consistency between the predicted image quality objective evaluation predicted value and the subjective evaluation value.

Drawings

Fig. 1 is a block diagram of the overall implementation of the method of the present invention.

Detailed Description

The invention is described in further detail below with reference to the accompanying examples.

The general implementation block diagram of the no-reference quality evaluation method for the blurred and distorted stereo image provided by the invention is shown in fig. 1, and the method comprises two processes of a training stage and a testing stage: in the training stage, selecting a plurality of original distortion-free stereo images and corresponding fuzzy distortion stereo images to form a training image set, decomposing each fuzzy distortion stereo image in the training image set by adopting two-dimensional empirical mode decomposition to obtain intrinsic mode function images, then carrying out non-overlapping blocking processing on each intrinsic mode function image, and constructing a visual dictionary table by adopting a K-means clustering method; the method comprises the steps of obtaining an objective evaluation predicted value of the image quality of each pixel point in each fuzzy distortion stereo image by calculating the frequency response of each original undistorted stereo image in a training image set and each pixel point in the corresponding fuzzy distortion stereo image under the selected central frequency and different direction factors, and constructing a visual quality table corresponding to a visual dictionary table. In the testing stage, for any pair of testing stereo images, decomposing the testing stereo images by adopting two-dimensional empirical mode decomposition to obtain intrinsic mode function images, then carrying out non-overlapping blocking processing on the intrinsic mode function images, and calculating to obtain the image quality objective evaluation predicted value of the testing images according to the constructed visual dictionary table and visual quality table. The non-reference quality evaluation method comprises the following specific steps:

① selecting N original undistorted stereo images, and forming training image set by the selected N original undistorted stereo images and the blurred and distorted stereo images corresponding to each original undistorted stereo image, and recording as { S_i,org,S_i,dis|1≤i≤N}，S_i,orgRepresenting a set of training images S_i,org,S_i,disI 1 is not less than i not more than N_i,disRepresenting a set of training images S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and the ith original undistorted stereo image corresponds to the blurred distorted stereo image; then the S is mixed_i,orgIs recorded as L_i,orgWill S_i,orgIs recorded as R_i,orgWill S_i,disIs recorded as L_i,disWill S_i,disRight viewpoint diagram ofLike as R_i,dis(ii) a If the value of N is larger, the precision of the visual dictionary table and the visual quality table obtained through training is higher, but the computational complexity is higher, so that the compromise consideration is that half of the blurred and distorted images in the adopted image library can be selected for processing, and the symbol "{ }" is a set representing a symbol.

Here, experiments were performed using blur-distorted stereoscopic images in the ningbo university stereoscopic image library and LIVE stereoscopic image library. The blurred and distorted stereo images in the Ningbo university stereo image library are composed of 12 undistorted stereo images and 60 distorted stereo images under different degrees of Gaussian blur, and the blurred and distorted stereo images in the LIVE stereo image library are composed of 19 undistorted stereo images and 45 distorted stereo images under different degrees of Gaussian blur. In the present embodiment, a 50% blurred and distorted stereo image is used to construct a training image set, that is, for a training image set constructed from a Ningbo university stereo image library, N =30 is taken; for the training image set constructed from LIVE stereo image library, take N = 22.

② pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, respectively implementing two-dimensional empirical mode decomposition on the left viewpoint image and the right viewpoint image of each fuzzy distortion stereo image to obtain a training image set { S_i,org,S_i,disL1 is not more than i is not more than N) and the intrinsic mode function image of each of the left viewpoint image and the right viewpoint image of each of the blurred and distorted stereo images_i,disIs recorded as the intrinsic mode function imageR is to be_i,disIs recorded as the intrinsic mode function imageWherein 1. ltoreq. x.ltoreq.W, 1. ltoreq. y.ltoreq.H, where W representsAndis shown here as HAndthe height of (a) of (b),to representThe middle coordinate position is the pixel value of the pixel point of (x, y),to representThe middle coordinate position is the pixel value of the pixel point of (x, y).

Then, for the training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N), and the intrinsic mode function image of the left viewpoint image and the intrinsic mode function image of the right viewpoint image of each blurred and distorted stereo image are subjected to linear weighting to obtain a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and S is compared with S_i,disIs recorded as the intrinsic mode function imageWill be provided withThe pixel value of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{IMF}}_i^{\mathrm{dis}}(x,y)=w_L\×{\mathrm{IMF}}_i^{L,\mathrm{dis}}(x,y)+w_R\×{\mathrm{IMF}}_i^{R,\mathrm{dis}}(x,y),$ Wherein, w_LIs composed ofWeight ratio of (1), w_RIs composed ofWeight ratio of (1), w_L+w_R=1, in this example w_L=0.9，w_R=0.1。

③ pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and carrying out non-overlapping blocking processing on the intrinsic mode function image of each fuzzy distortion stereo image; then, performing clustering operation on a set formed by all sub-blocks in each intrinsic mode function image by adopting the conventional K-means clustering method to obtain K clusters of each intrinsic mode function image, wherein K represents the total number of clusters contained in each intrinsic mode function image, the K value is too large and the K value is too small, and the K value is under-clustered, and if the K value is too small, the K =30 is taken in the embodiment; then, acquiring a visual dictionary table of each intrinsic mode function image according to K clusters of each intrinsic mode function image; then, obtaining a training image set { S ] according to the visual dictionary table of all intrinsic mode function images_i,org,S_i,disA visual dictionary table of |1 ≦ i ≦ N, denoted G, G = { G = ≦ G ≦ C ≦ N }_iI is less than or equal to 1 and less than or equal to N, wherein the symbol is a set representing a symbol, G_iTo representVisual dictionary table of G_i={g_i,k|1≤k≤K}，g_i,kTo representThe visual dictionary of the kth cluster, g_i,kAlso showsThe centroid of the kth cluster.

In this embodiment, step ③Visual dictionary table G_iThe acquisition process comprises the following steps:

③ -1, willIs divided intoThe non-overlapping sub-blocks of size 16 × 16 are formed byThe set of all sub-blocks in (1) is denoted asWherein x is_i,tIs represented byThe column vector, x, composed of all the pixel points in the t-th sub-block_i,tHas a dimension of 256.

③ -2, adopting the existing K-means clustering method to pairPerforming clustering operation to obtainThen will be clusteredUsing the centroid of each cluster as a visual dictionary to obtainVisual dictionary table, denoted G_i，G_i={g_i,kL 1 is less than or equal to K, wherein K representsThe total number of clusters contained, the phenomenon of over-clustering will occur when the value of K is too large, and the phenomenon of under-clustering will occur when the value of K is too small, such as K =30 g in this embodiment_i,kTo representThe visual dictionary of the kth cluster, g_i,kAlso showsThe centroid of the kth cluster, g_i,kHas a dimension of 256.

④ training image set by calculating S_i,org,S_i,disI is not less than 1 and not more than N), and obtaining the objective evaluation metric value of each pixel point in each blurred and distorted stereo image; then obtaining a visual quality table of each fuzzy distortion stereo image according to the objective evaluation metric value of each pixel point in each fuzzy distortion stereo image; then, obtaining a training image set { S) according to the visual quality table of all the fuzzy distortion stereo images_i,org,S_i,disThe visual quality table of I1 ≦ i ≦ N, denoted Q, Q = { Q = ≦ Q ≦ N }_i|1≤i≤N}，Wherein Q is_iDenotes S_i,disVisual quality table of (2), Q_i={q_i,k|1≤k≤K}，q_i,kTo representThe visual quality of the kth cluster.

In this embodiment, S in step ④_i,disVisual quality table Q_iThe acquisition process comprises the following steps:

④ -1, respectively using Gabor filters to the L_i,org、R_i,org、L_i,disAnd R_i,disFiltering to obtain L_i,org、R_i,org、L_i,disAnd R_i,disUnder different central frequencies and different direction factors, each pixel point in the L-shaped array has a frequency response of L_i,orgThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{org}}^L(x,y;\mathrm{\ω},\mathrm{\θ}),$ R is to be_i,orgThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{org}}^R(x,y;\mathrm{\ω},\mathrm{\θ}),$ Mixing L with_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{dis}}^L(x,y;\mathrm{\ω},\mathrm{\θ}),$ R is to be_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as $G_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ})=e_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ})+j{o}_{i,\mathrm{dis}}^R(x,y;\mathrm{\ω},\mathrm{\θ}),$ Wherein x is 1. ltoreq. x.ltoreq.W is 1. ltoreq. y.ltoreq.H, where W represents L_i,org、R_i,org、L_i,disAnd R_i,disWhere H represents L_i,org、R_i,org、L_i,disAnd R_i,disω ∈ {1.74,2.47,3.49,4.93,6.98,9.87}, θ represents the orientation factor of the Gabor filter, 1 ≦ θ ≦ 4,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofJ is an imaginary unit.

④ -2, according to L_i,orgAnd R_i,orgCalculating the frequency response of each pixel point in the S under the selected center frequency and different direction factors_i,orgAmplitude of each pixel point in (1), will S_i,orgThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{LA}}_i^{\mathrm{org}}(x,y)=\sqrt{{\left(F_i^{\mathrm{org}}(x,y)\right)}^2+{\left(H_i^{\mathrm{org}}(x,y)\right)}^2},$ Wherein, $F_i^{\mathrm{org}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{e}_{i,\mathrm{org}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+e_{i,\mathrm{org}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ $H_i^{\mathrm{org}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{o}_{i,\mathrm{org}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+o_{i,\mathrm{org}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ ω_mfor a selected center frequency, ω_m∈ {1.74,2.47,3.49,4.93,6.98,9.87}, in this example, take ω_m=4.93，Represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (c).

Also according to L_i,disAnd R_i,disCalculating the frequency response of each pixel point in the S under the selected center frequency and different direction factors_i,disAmplitude of each pixel point in (1), will S_i,disThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as ${\mathrm{LA}}_i^{\mathrm{dis}}(x,y)=\sqrt{{\left(F_i^{\mathrm{dis}}(x,y)\right)}^2+{\left(H_i^{\mathrm{dis}}(x,y)\right)}^2},$ Wherein, $F_i^{\mathrm{dis}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{e}_{i,\mathrm{dis}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+e_{i,\mathrm{dis}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ $H_i^{\mathrm{dis}}(x,y)=\underset{\mathrm{\θ}=1}{\overset{4}{\mathrm{\Σ}}}{o}_{i,\mathrm{dis}}^L(x,y;{\mathrm{\ω}}_m,\mathrm{\θ})+o_{i,\mathrm{dis}}^R(x,y;{\mathrm{\ω}}_m,\mathrm{\θ}),$ ω_mfor a selected center frequency, ω_m∈ {1.74,2.47,3.49,4.93,6.98,9.87}, in this example, take ω_m=4.93，Represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of theta

④ -3, according to S_i,orgAnd S_i,disCalculating S from the amplitude of each pixel point_i,disThe objective evaluation metric value of each pixel point in S_i,disThe objective evaluation metric value of the pixel point with the middle coordinate position (x, y) is recorded as rho_i(x,y)， ${\mathrm{\ρ}}_i(x,y)=\frac{1+\cos (2\·{\mathrm{\ψ}}_i(x,y))}{2},$ ${\mathrm{\ψ}}_i(x,y)=\arccos \left(\frac{{\mathrm{GX}}_i^{\mathrm{org}}(x,y)\·{\mathrm{GX}}_i^{\mathrm{dis}}(x,y)+{\mathrm{GY}}_i^{\mathrm{org}}(x,y)\·{\mathrm{GY}}_i^{\mathrm{dis}}(x,y)+T_1}{\sqrt{{\left({\mathrm{GX}}_i^{\mathrm{org}}(x,y)\right)}^2+{\left({\mathrm{GY}}_i^{\mathrm{org}}(x,y)\right)}^2}\·\sqrt{{\left({\mathrm{GX}}_i^{\mathrm{dis}}(x,y)\right)}^2+{\left({\mathrm{GY}}_i^{\mathrm{dis}}(x,y)\right)}^2}+T_1}\right),$ Wherein cos () is a cosine-taken function, arccos () is an inverse cosine-taken function,is composed ofThe horizontal gradient value of (a) is,is composed ofThe vertical gradient value of (a) is,is composed ofThe horizontal gradient value of (a) is,is composed ofVertical gradient value of, T₁For controlling the parameters, T is taken in this example₁=0.85。

④ -4, according to S_i,disObtaining S according to the objective evaluation metric value of each pixel point_i,disIs marked as Q_i，Q_i={q_i,kL 1 is more than or equal to K and less than or equal to K, wherein q is equal to or less than K_i,kTo representThe visual quality of the k-th cluster of (c),Ω_kdenotes S_i,disNeutralization ofThe set of coordinate positions of pixel points having the same coordinate position of all pixel points included in the kth cluster,to representThe total number of pixel points included in the kth cluster.

⑤ for any one test stereo image S_testFrom a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and calculating to obtain S_testObjectively evaluating the predicted value of the image quality.

In this embodiment, the specific process of the fifth step is as follows:

⑤ -1, mixing S_testIs recorded as L_testWill S_testIs recorded as R_testTo L for_testAnd R_testRespectively carrying out two-dimensional empirical mode decomposition to obtain L_testAnd R_testRespective intrinsic mode function images, corresponding notationAndthen toAndlinear weighting is carried out to obtain S_testIs denoted as { IMF [ ], in the intrinsic mode function image_test(x, y) }, will { IMF_testThe pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as IMF_test(x,y)， ${\mathrm{IMF}}_{\mathrm{test}}(x,y)={w_L}^{\′}\×{\mathrm{IMF}}_{\mathrm{test}}^L(x,y)+{w_R}^{\′}\×{\mathrm{IMF}}_{\mathrm{test}}^R(x,y),$ Wherein 1. ltoreq. x.ltoreq.W ', 1. ltoreq. y.ltoreq.H ', where W ' representsAndis shown here as HAndw 'may not be equal to W, H' may not be equal to H,to representThe middle coordinate position is the pixel value of the pixel point of (x, y),to representThe pixel value, w, of the pixel point with the middle coordinate position (x, y)_L' isWeight ratio of (1), w_R' isWeight ratio of (1), w_L'+w_R' =1, in this example w_L'=0.9，w_R'=0.1。

⑤ -2, will { IMF_test(x, y) } division intoThe non-overlapping sub-blocks of size 16 × 16 are defined by IMF_testThe set of all subblocks in (x, y) } is denoted asWherein, y_tIs represented by { IMF_testThe column vector formed by all pixel points in the t-th sub-block in (x, y) }, y_tHas a dimension of 256.

⑤ -3, calculation of { IMF_testThe minimum Euclidean distance of each sub-block in (x, y) } from G, will be { IMF_testThe minimum Euclidean distance between the t-th sub-block and G in (x, y) } is recorded as_t，Wherein, the symbol "| | |" is a euclidean distance symbol, and min () is a minimum function.

⑤ -4, calculation of { IMF_test(x, y) } the objective evaluation metric for each sub-block, will be { IMF_testThe objective evaluation metric value of the t-th sub-block in (x, y) } is recorded as z_t，Wherein,in the representation of Q_tAnd the visual quality corresponding to the corresponding visual dictionary is 1 ≦ i ≦ N,1 ≦ K, exp () represents an exponential function with e as a base, e =2.71828183, λ is a control parameter, and λ =300 is taken in the embodiment.

⑤ -5, according to { IMF_test(x, y) } calculating S the objective evaluation metric value for each sub-block_testThe image quality objective evaluation predicted value of (1) is marked as Q,

here, the Ningbo university stereo image library and the LIVE stereo image library are used to analyze the correlation between the image quality objective evaluation prediction value of the blurred and distorted stereo image obtained in the present embodiment and the average subjective score difference value. Here, 4 common objective parameters of the evaluation method for evaluating image quality are used as evaluation indexes, that is, Pearson correlation coefficient (PLCC), Spearman correlation coefficient (SRCC), Kendall correlation coefficient (KRCC), mean square error (RMSE), accuracy of the distorted stereoscopic image objective evaluation result is reflected by PLCC and RMSE, and monotonicity thereof is reflected by SRCC and KRCC.

The method is used for calculating the image quality objective evaluation predicted value of each fuzzy distortion stereo image in the Ningbo university stereo image library and the image quality objective evaluation predicted value of each fuzzy distortion stereo image in the LIVE stereo image library, and then the average subjective score difference value of each fuzzy distortion stereo image in the Ningbo university stereo image library and the average subjective score difference value of each fuzzy distortion stereo image in the LIVE stereo image library are obtained by using the existing subjective evaluation method. The image quality objective evaluation predicted value of the fuzzy distortion stereo image calculated according to the method is subjected to five-parameter Logistic function nonlinear fitting, and the higher the PLCC, SRCC and KRCC values are, the lower the RMSE value is, the better the correlation between the objective evaluation method and the average subjective score difference is. The correlation coefficients of PLCC, SRCC, KRCC and RMSE that reflect the quality evaluation performance of the method of the present invention are shown in Table 1. As can be seen from the data listed in table 1, the correlation between the final objective evaluation prediction value of image quality of the blurred and distorted stereo image obtained according to the present embodiment and the average subjective score difference is very good, which indicates that the objective evaluation result is more consistent with the result of subjective perception of human eyes, and is sufficient to explain the effectiveness of the method of the present invention.

Table 1 correlation between the image quality objective evaluation prediction value of the blurred and distorted stereo image obtained in this embodiment and the average subjective score difference value

Claims (3)

1. A no-reference quality evaluation method for a fuzzy distortion stereo image is characterized by comprising a training stage and a testing stage, and specifically comprising the following steps:

① selecting N original undistorted stereo images, and forming training image set by the selected N original undistorted stereo images and the blurred and distorted stereo images corresponding to each original undistorted stereo image, and recording as { S_i,org,S_i,dis|1≤i≤N}，S_i,orgRepresenting a set of training images S_i,org,S_i,disI < i > 1 < i < N >Undistorted stereo image of S_i,disRepresenting a set of training images S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and the ith original undistorted stereo image corresponds to the blurred distorted stereo image; then the S is mixed_i,orgIs recorded as L_i,orgWill S_i,orgIs recorded as R_i,orgWill S_i,disIs recorded as L_i,disWill S_i,disIs recorded as R_i,dis；

② pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, respectively implementing two-dimensional empirical mode decomposition on the left viewpoint image and the right viewpoint image of each fuzzy distortion stereo image to obtain a training image set { S_i,org,S_i,disL1 is not more than i is not more than N) and the intrinsic mode function image of each of the left viewpoint image and the right viewpoint image of each of the blurred and distorted stereo images_i,disIs expressed as { IMF [ ], the intrinsic mode function image_i ^L,dis(x, y) }, adding R_i,disIs expressed as { IMF [ ], the intrinsic mode function image_i ^R,dis(x, y) }, wherein 1. ltoreq. x.ltoreq.W, 1. ltoreq. y.ltoreq.H, where W denotes { IMF ≦ H_i ^L,dis(x, y) } and { IMF_i ^R,dis(x, y) }, where H denotes { IMF }_i ^{L ,dis}(x, y) } and { IMF_i ^R,disHeight of (x, y) }, IMF_i ^L,dis(x, y) denotes { IMF_i ^L,disThe pixel value, IMF, of a pixel point whose coordinate position is (x, y) in (x, y) } is_i ^R,dis(x, y) denotes { IMF_i ^R，disThe coordinate position in (x, y) is the pixel value of the pixel point of (x, y);

then, for the training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N), and the intrinsic mode function image of the left viewpoint image and the intrinsic mode function image of the right viewpoint image of each blurred and distorted stereo image are subjected to linear weighting to obtain a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and S is compared with S_i,disIs expressed as { IMF [ ], the intrinsic mode function image_i ^dis(x, y) }, will { IMF_i ^disThe pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as IMF_i ^dis(x,y)，IMF_i ^dis(x,y)＝w_L×IMF_i ^L,dis(x,y)+w_R×IMF_i ^R,dis(x, y) wherein w_LIs IMF_i ^L,disWeight ratio of (x, y), w_RIs IMF_i ^R,disWeight ratio of (x, y), w_L+w_R＝1；

③ pairs of training image sets S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and carrying out non-overlapping blocking processing on the intrinsic mode function image of each fuzzy distortion stereo image; then, clustering a set formed by all sub-blocks in each intrinsic mode function image by adopting a K-means clustering method to obtain K clusters of each intrinsic mode function image, wherein K represents the total number of clusters contained in each intrinsic mode function image; then, acquiring a visual dictionary table of each intrinsic mode function image according to K clusters of each intrinsic mode function image; then, obtaining a training image set { S ] according to the visual dictionary table of all intrinsic mode function images_i,org,S_i,disA visual dictionary table of |1 ≦ i ≦ N ≦ G, G ═ G_iI is more than or equal to 1 and less than or equal to N, wherein G_iExpression { IMF_i ^dis(x, y) } visual dictionary Table, G_i＝{g_i,k|1≤k≤K}，g_i,kExpression { IMF_i ^disVisual dictionary of the kth cluster of (x, y) }, g_i,kAlso indicates { IMF_i ^disThe centroid of the kth cluster of (x, y) };

④ training image set by calculating S_i,org,S_i,disI is not less than 1 and not more than N), and obtaining the objective evaluation metric value of each pixel point in each blurred and distorted stereo image; then distorting each of the stereo images according to each of the blursObjectively evaluating the metric value of each pixel point to obtain a visual quality table of each fuzzy distortion stereo image; then, obtaining a training image set { S) according to the visual quality table of all the fuzzy distortion stereo images_i,org,S_i,disThe visual quality table of I1 ≦ i ≦ N, denoted as Q, Q ═ Q ≦ Q_iI is more than or equal to 1 and less than or equal to N, wherein Q_iDenotes S_i,disVisual quality table of (2), Q_i＝{q_i,k|1≤k≤K}，q_i,kExpression { IMF_i ^dis(x, y) } visual quality of the kth cluster;

s in the step ④_i,disVisual quality table Q_iThe acquisition process comprises the following steps:

④ -1, respectively using Gabor filters to the L_i,org、R_i,org、L_i,disAnd R_i,disFiltering to obtain L_i,org、R_i,org、L_i,disAnd R_i,disUnder different central frequencies and different direction factors, each pixel point in the L-shaped array has a frequency response of L_i,orgThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as R is to be_i,orgThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as Mixing L with_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as R is to be_i,disThe frequency response of the pixel point with the middle coordinate position (x, y) under the condition that the center frequency is omega and the direction factor is theta is recorded as Wherein x is 1. ltoreq. x.ltoreq.W is 1. ltoreq. y.ltoreq.H, where W represents L_i,org、R_i,org、L_i,disAnd R_i,disWhere H represents L_i,org、R_i,org、L_i,disAnd R_i,disω ∈ {1.74,2.47,3.49,4.93,6.98,9.87}, θ represents the orientation factor of the Gabor filter, 1 ≦ θ ≦ 4,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofThe imaginary part of (a) is,is composed ofThe real part of (a) is,is composed ofJ is an imaginary unit;

④ -2, according to L_i,orgAnd R_i,orgCalculating the frequency response of each pixel point in the S under the selected center frequency and different direction factors_i,orgAmplitude of each pixel point in (1), will S_i,orgThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as Wherein, ω_mfor a selected center frequency, ω_m∈{1.74,2.47,3.49,4.93,6.98,9.87}，Represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,orgThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaAn imaginary part of (d);

also according to L_i,disAnd R_i,disEach of which isCalculating the frequency response of the pixel points under the selected center frequency and different direction factors, and calculating S_i,disAmplitude of each pixel point in (1), will S_i,disThe amplitude of the pixel point with the middle coordinate position (x, y) is recorded as Wherein, ω_mfor a selected center frequency, ω_m∈{1.74,2.47,3.49,4.93,6.98,9.87}，Represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents R_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe real part of (a) is,represents L_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaThe imaginary part of (a) is,represents R_i,disThe central frequency of the pixel point with the (x, y) middle coordinate position is omega_mAnd the frequency response at a directional factor of thetaAn imaginary part of (d);

④ -3, according to S_i,orgAnd S_i,disCalculating S from the amplitude of each pixel point_i,disThe objective evaluation metric value of each pixel point in S_i,disThe objective evaluation metric value of the pixel point with the middle coordinate position (x, y) is recorded as rho_i(x,y)， Wherein cos () is a cosine-taken function, arccos () is an inverse cosine-taken function,is composed ofThe horizontal gradient value of (a) is,is composed ofThe vertical gradient value of (a) is,is composed ofThe horizontal gradient value of (a) is,is composed ofVertical gradient value of, T₁Is a control parameter;

④ -4, according to S_i,disObtaining S according to the objective evaluation metric value of each pixel point_i,disIs marked as Q_i，Q_i＝{q_i,kL 1 is more than or equal to K and less than or equal to K, wherein q is equal to or less than K_i,kExpression { IMF_i ^dis(x, y) } visual quality of the kth cluster,Ω_kdenotes S_i,disNeutralization { IMF_i ^dis(x, y) } a set of coordinate positions of pixel points whose coordinate positions are the same for all pixel points included in the kth cluster,expression { IMF_i ^dis(x, y) } total number of pixel points included in the kth cluster;

⑤ for any one test stereo image S_testFrom a training image set { S_i,org,S_i,disI is more than or equal to 1 and less than or equal to N, and calculating to obtain S_testObjectively evaluating a predicted value of the image quality;

the concrete process of the fifth step is as follows:

⑤ -1, mixing S_testIs recorded as L_testWill S_testIs recorded as R_testTo L for_testAnd R_testRespectively carrying out two-dimensional empirical mode decomposition to obtain L_testAnd R_testRespective intrinsic mode function images, corresponding notationAndthen toAndlinear weighting is carried out to obtain S_testIs denoted as { IMF [ ], in the intrinsic mode function image_test(x, y) }, will { IMF_testThe pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as IMF_test(x,y)，Wherein 1. ltoreq. x.ltoreq.W ', 1. ltoreq. y.ltoreq.H ', where W ' representsAndis shown here as HAndthe height of (a) of (b),to representThe middle coordinate position is the pixel value of the pixel point of (x, y),to representThe pixel value, w, of the pixel point with the middle coordinate position (x, y)_L' isWeight ratio of (1), w_R' isWeight ratio of (1), w_L'+w_R'＝1；

⑤ -2, will { IMF_test(x, y) } division intoThe non-overlapping sub-blocks of size 16 × 16 are defined by IMF_testThe set of all subblocks in (x, y) } is denoted asWherein, y_tIs represented by { IMF_testThe column vector formed by all pixel points in the t-th sub-block in (x, y) }, y_tHas a dimension of 256;

⑤ -3, calculation of { IMF_testThe minimum Euclidean distance of each sub-block in (x, y) } from G, will be { IMF_testThe minimum Euclidean distance between the t-th sub-block and G in (x, y) } is recorded as_t，Wherein, the symbol "| | |" is a euclidean distance symbol, and the min () is a minimum function;

⑤ -4, calculation of { IMF_test(x, y) } the objective evaluation metric for each sub-block, will be { IMF_testThe objective evaluation metric value of the t-th sub-block in (x, y) } is recorded as z_t，Wherein,in the representation of Q_tThe visual quality corresponding to the corresponding visual dictionary is more than or equal to 1 and less than or equal to N, more than or equal to 1 and less than or equal to K, exp () represents an exponential function with e as a base, e is 2.71828183, and lambda is a control parameter;

⑤ -5, according to { IMF_test(x, y) } calculating S the objective evaluation metric value for each sub-block_testThe image quality objective evaluation predicted value of (1) is marked as Q,

2. the method as claimed in claim 1, wherein w in step ② is taken as w_L＝0.9，w_R＝0.1。

3. The method for reference-free quality evaluation of blurred and distorted stereo images as claimed in claim 1 or 2, wherein { IMF ] in step ③_i ^disThe acquisition process of the visual dictionary table Gi of (x, y) } is as follows:

③ -1, will { IMF_i ^dis(x, y) } division intoThe non-overlapping sub-blocks of size 16 × 16 are defined by IMF_i ^disThe set of all subblocks in (x, y) } is denoted asWherein x is_i,tIs represented by { IMF_i ^disThe column vector formed by all pixel points in the t-th sub-block in (x, y) }, x_i,tHas a dimension of 256;

③ -2, adopting K-means clustering method to pairClustering operation is carried out to obtain { IMF_i ^disK clusters of (x, y) }, then the { IMF_i ^disThe centroid of each cluster of (x, y) } serves as a visual dictionary, resulting in { IMF_i ^dis(x, y) } visual dictionary, denoted G_i，G_i＝{g_i,kL 1 is less than or equal to K, wherein K represents { IMF ≦ K }, and_i ^dis(x, y) } total number of clusters contained, g_i,kExpression { IMF_i ^disVisual dictionary of the kth cluster of (x, y) }, g_i,kAlso indicates { IMF_i ^disCentroid of the kth cluster of (x, y) }, g_i,kHas a dimension of 256.