CN106791801A - The quality evaluating method and system of a kind of 3-D view - Google Patents
The quality evaluating method and system of a kind of 3-D view Download PDFInfo
- Publication number
- CN106791801A CN106791801A CN201611042805.8A CN201611042805A CN106791801A CN 106791801 A CN106791801 A CN 106791801A CN 201611042805 A CN201611042805 A CN 201611042805A CN 106791801 A CN106791801 A CN 106791801A
- Authority
- CN
- China
- Prior art keywords
- dimensional image
- singular value
- evaluated
- matrix
- diagonal matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 138
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 14
- 241000023320 Luma <angiosperm> Species 0.000 claims 1
- OSWPMRLSEDHDFF-UHFFFAOYSA-N methyl salicylate Chemical compound COC(=O)C1=CC=CC=C1O OSWPMRLSEDHDFF-UHFFFAOYSA-N 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 4
- 238000013441 quality evaluation Methods 0.000 description 14
- 238000013210 evaluation model Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
- G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The applicable technical field of image processing of the present invention, there is provided the quality evaluating method and system of 3-D view, the method include：When 3-D view to be evaluated is received,Obtain original three-dimensional image and the neighborhood block position for obtaining is matched by viewpoint,Corresponding neighborhood block is obtained in 3-D view to be evaluated according to neighborhood block position,Obtain a left side for each neighborhood block in 3-D view to be evaluated,The luminance component of right visual point image,Represented according to the complex matrix that luminance component obtains neighborhood block,Each complex matrix is represented carries out singular value decomposition,Corresponding first singular value diagonal matrix is represented to obtain complex matrix,Obtain the second singular value diagonal matrix of original three-dimensional image,According to the first singular value diagonal matrix and the second singular value diagonal matrix,Calculate the distance between neighborhood block of same position in 3-D view to be evaluated and original three-dimensional image,According to the quality scale that distance obtains 3-D view to be evaluated that obtains for calculating,So as to realize the accurate evaluation of three-dimensional image quality.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a quality evaluation method and system for a three-dimensional image.
Background
With the rapid development of content generation and display technologies, three-dimensional image applications are becoming more and more popular. The three-dimensional image output by the three-dimensional display equipment brings brand-new and more vivid entertainment experience to viewers, so that the three-dimensional image display attracts the attention of a large number of researchers and is favored by the industry. The quality of the three-dimensional video directly affects the visual experience of the user, and further affects the popularization of three-dimensional display application. However, with limited resources, noise is inevitably introduced into the three-dimensional video in the acquisition, processing, encoding, conversion, reconstruction and other links of the video system. On the other hand, the visual perception characteristics of the Human Visual System (HVS) on three-dimensional video images are significantly different compared to conventional two-dimensional video. Therefore, how to automatically and efficiently evaluate the image quality of the three-dimensional image video is a challenging problem in consideration of the above-mentioned situation.
The existing binocular stereo image quality evaluation methods can be roughly divided into two types, one is an extended model based on the traditional two-dimensional image quality evaluation (IQA), and the other is a quality evaluation model specially used for binocular stereo images. The first type of evaluation model is to directly apply a traditional two-dimensional IQA model on a stereo image, namely: separating left and right viewpoints of the stereo image, predicting the quality of each viewpoint image by independently utilizing a two-dimensional IQA model, and fusing the quality scores of the left and right viewpoint images to finally obtain the quality score of the stereo image. However, such methods do not consider binocular visual characteristics, reducing the prediction performance of the evaluation model. A second type of evaluation model attempts to incorporate HVS visual characteristics, e.g., depth perception characteristics, at the time of evaluation. However, the evaluation model processes the left and right viewpoint images of human separately, and considers the difference between the left and right images less, which fails to effectively reflect the quality preference of human eyes to the stereo image.
Disclosure of Invention
The invention aims to provide a method and a system for evaluating the quality of a three-dimensional image, and aims to solve the problems that the quality evaluation accuracy of the three-dimensional image is low and the quality of the three-dimensional image cannot be truly reflected due to the fact that an effective method for evaluating the quality of the three-dimensional image cannot be provided in the prior art.
In one aspect, the present invention provides a method for evaluating quality of a three-dimensional image, the method comprising the steps of:
when a three-dimensional image to be evaluated is received, acquiring the position of a neighborhood block obtained by matching the viewpoint of an original three-dimensional image corresponding to the three-dimensional image to be evaluated;
acquiring a corresponding neighborhood block in the three-dimensional image to be evaluated according to the position of the neighborhood block;
acquiring brightness components of left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated, and acquiring complex matrix representation of the neighborhood blocks according to the brightness components;
performing singular value decomposition on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, recording the singular value diagonal matrix as a first singular value diagonal matrix, acquiring a singular value diagonal matrix of the original three-dimensional image, and recording the singular value diagonal matrix as a second singular value diagonal matrix;
and calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image according to the first singular value diagonal matrix and the second singular value diagonal matrix and a preset distance calculation formula, and acquiring the quality level of the three-dimensional image to be evaluated according to the calculated distance.
In another aspect, the present invention provides a quality evaluation system for a three-dimensional image, the system including:
the position acquisition unit is used for acquiring the position of a neighborhood block obtained by matching the viewpoint of an original three-dimensional image corresponding to the three-dimensional image to be evaluated when the three-dimensional image to be evaluated is received;
the neighborhood acquiring unit is used for acquiring a corresponding neighborhood block in the three-dimensional image to be evaluated according to the position of the neighborhood block;
the matrix representation unit is used for acquiring the brightness component of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated and acquiring the complex matrix representation of the neighborhood blocks according to the brightness component;
the singular value decomposition unit is used for performing singular value decomposition on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, marking the singular value diagonal matrix as a first singular value diagonal matrix, acquiring a singular value diagonal matrix of the original three-dimensional image and marking the singular value diagonal matrix as a second singular value diagonal matrix; and
and the quality obtaining unit is used for calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image through a preset distance calculation formula according to the first singular value diagonal matrix and the second singular value diagonal matrix, and obtaining the quality level of the three-dimensional image to be evaluated according to the calculated distance.
After receiving the three-dimensional image to be evaluated, the invention obtains the position of a neighborhood block obtained by matching the original three-dimensional image corresponding to the three-dimensional image to be evaluated through the viewpoint, acquiring neighborhood blocks at corresponding positions in the three-dimensional image to be evaluated, acquiring the brightness component of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated, further acquiring the complex matrix representation of the neighborhood blocks according to the brightness component, performing singular value decomposition on each complex matrix to obtain a first singular value diagonal matrix corresponding to the complex matrix, calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image through a preset distance calculation formula according to the first singular value diagonal matrix and the second singular value diagonal matrix of the original three-dimensional image, therefore, the quality grade of the three-dimensional image to be evaluated is accurately obtained, and the accurate evaluation of the quality of the three-dimensional image is realized.
Drawings
Fig. 1 is a flowchart illustrating an implementation of a method for evaluating quality of a three-dimensional image according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a three-dimensional image quality evaluation system according to a second embodiment of the present invention; and
fig. 3 is a schematic diagram of a preferred structure of a three-dimensional image quality evaluation system according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific implementations of the present invention is provided in conjunction with specific embodiments:
the first embodiment is as follows:
fig. 1 shows an implementation flow of a three-dimensional image quality evaluation method provided in the first embodiment of the present invention, and for convenience of description, only the portions related to the first embodiment of the present invention are shown, which are detailed as follows:
in step S101, when the three-dimensional image to be evaluated is received, the position of the neighborhood block obtained by performing viewpoint matching on the original three-dimensional image corresponding to the three-dimensional image to be evaluated is obtained.
The embodiment of the invention is suitable for the three-dimensional image quality evaluation equipment or system so as to evaluate the image quality of the three-dimensional image or the three-dimensional video input by the user. In the embodiment of the invention, the neighborhood blocks obtained by the original three-dimensional image through viewpoint matching are obtained in advance, and the positions of the neighborhood blocks are further obtained.
Preferably, when a neighborhood block obtained by matching the viewpoint of the original three-dimensional image is obtained, the original three-dimensional image is subjected to viewpoint matching by using a Scale-invariant Feature Transform (SIFT) algorithm, and then the neighborhood block of each matched pixel point is obtained from the original three-dimensional image, so that the left and right viewpoint images are subjected to parallelization processing in a manner similar to a human binocular vision system, and the accuracy of viewpoint matching is improved on the basis of reducing the computational complexity. Specifically, when the position of the neighborhood block is obtained, the position of the neighborhood block is obtained by taking the matched pixel point as the center according to the set size of the neighborhood block, and the positions of the neighborhood blocks are stored.
In step S102, a corresponding neighborhood block is obtained in the three-dimensional image to be evaluated according to the position of the neighborhood block.
In step S103, a luminance component of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated is obtained, and a complex matrix representation of the neighborhood block is obtained according to the luminance component.
In the embodiment of the invention, according to the position of a neighborhood block obtained after the original three-dimensional image viewpoint is matched, a corresponding neighborhood block is obtained at the same position in the three-dimensional image to be evaluated, the brightness component of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated is obtained, and then the complex matrix representation of the neighborhood block is obtained according to the brightness component, so that the complex matrix representing the neighborhood block is obtained.
Preferably, the complex matrix representation of the neighborhood block is obtained from the luminance component by a formulaComputing complex matrix representations of neighborhood blocksWherein, thereinAndrespectively representing the brightness components, mu, of the left and right viewpoint images of the neighborhood block i in the three-dimensional image to be evaluated1 21, thereby realizing a neighborhood blockIs precisely represented.
In step S104, singular value decomposition is performed on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, the singular value diagonal matrix is recorded as a first singular value diagonal matrix, and a singular value diagonal matrix of the original three-dimensional image is obtained and recorded as a second singular value diagonal matrix.
In the embodiment of the present invention, when acquiring the singular value diagonal matrix of the three-dimensional image to be evaluated, singular value decomposition may be performed on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, and for convenience of description, the singular value diagonal matrix is referred to as a first singular value diagonal matrix.
In particular, according to the formulaSingular value decomposition is carried out on a complex matrix of an adjacent domain block in a three-dimensional image to be evaluated to obtain a first singular value diagonal matrixWherein Ui and Vi respectively represent left and right singular value matrixes, and singular values in a first singular value diagonal matrixArranged in descending order, w represents the size of the neighborhood block. In addition, the singular value diagonal matrix of the original three-dimensional image can be calculated in advance and stored in the three-dimensional image quality evaluation equipment or system, and the acquisition mode of the singular value diagonal matrix of the original three-dimensional image can be the same as or different from that of the singular value diagonal matrix of the three-dimensional image to be evaluated.
In step S105, according to the first singular value diagonal matrix and the second singular value diagonal matrix, calculating a distance between the three-dimensional image to be evaluated and a neighborhood block at the same position in the original three-dimensional image by using a preset distance calculation formula, and obtaining a quality level of the three-dimensional image to be evaluated according to the calculated distance.
In the embodiment of the invention, the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image reflects the distortion condition of the three-dimensional image to be evaluated in the neighborhood block range. In calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image, preferably, a distance calculation formula is usedCalculating the distance d between the three-dimensional image to be evaluated and the neighborhood blocks i at the same position in the original three-dimensional imageiWhereinrepresenting the jth singular value on the diagonal of the first diagonal matrix of singular values,representing the jth singular value on the diagonal of the second diagonal matrix of singular values.
Then, the quality level of the three-dimensional image to be evaluated is obtained after the calculated distance, preferably according to a formulaCalculating the quality score q of the three-dimensional image to be evaluated, wherein n is the number of neighborhood blocks with the same position in the three-dimensional image to be evaluated and the original three-dimensional image, and mean ({ d }i}) is the median value of di. The method can accurately obtain the difference between the whole three-dimensional image to be evaluated and the original three-dimensional image, namely the whole distortion condition of the three-dimensional image to be evaluated. Furthermore, the quality grade of the three-dimensional image to be evaluated can be output according to the quality score and the preset quality grade, so that the quality of the three-dimensional image can be obtained more directly.
In the embodiment of the invention, after receiving the three-dimensional image to be evaluated, the neighborhood blocks at corresponding positions are obtained in the three-dimensional image to be evaluated, and the brightness components of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated are obtained, so that in a manner similar to a human binocular vision system, the left and right viewpoint images are processed in parallel, the matching accuracy is improved on the basis of reducing the computational complexity, then the complex matrix representation of the neighborhood block is obtained according to the brightness component, performing singular value decomposition on each complex matrix to obtain a first singular value diagonal matrix corresponding to the complex matrix, and according to the first singular value diagonal matrix and the second singular value diagonal matrix of the original three-dimensional image, calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image through a preset distance calculation formula, thereby accurately and comprehensively obtaining the quality of the three-dimensional image to be evaluated.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by relevant hardware instructed by a program, and the program may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc.
Example two:
fig. 2 shows a structure of a three-dimensional image quality evaluation system according to a second embodiment of the present invention, and for convenience of description, only a part related to the second embodiment of the present invention is shown, including:
the position obtaining unit 21 is configured to obtain, when receiving a three-dimensional image to be evaluated, a position of a neighborhood block obtained by performing viewpoint matching on an original three-dimensional image corresponding to the three-dimensional image to be evaluated;
the neighborhood acquiring unit 22 is configured to acquire a corresponding neighborhood block from the three-dimensional image to be evaluated according to the position of the neighborhood block;
the complex matrix representation unit 23 is configured to obtain a luminance component of a left viewpoint image and a right viewpoint image of each neighborhood block in the three-dimensional image to be evaluated, and obtain a complex matrix representation of the neighborhood block according to the luminance component;
the singular value decomposition unit 24 is configured to perform singular value decomposition on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, record the singular value diagonal matrix as a first singular value diagonal matrix, obtain a singular value diagonal matrix of the original three-dimensional image, and record the singular value diagonal matrix as a second singular value diagonal matrix; and
and the quality obtaining unit 25 is configured to calculate, according to the first singular value diagonal matrix and the second singular value diagonal matrix, a distance between the three-dimensional image to be evaluated and a neighborhood block at the same position in the original three-dimensional image through a preset distance calculation formula, and obtain a quality level of the three-dimensional image to be evaluated according to the calculated distance.
Preferably, as shown in fig. 3, the matrix representation unit 23 includes:
a matrix calculation unit 231 for calculating a matrix according to the formulaComputing complex matrix representations of neighborhood blocksWherein, thereinAndrespectively representing the brightness components, mu, of the left and right viewpoint images of the neighborhood block i in the three-dimensional image to be evaluated1 2＝-1。
Preferably, the singular value decomposition unit 24 includes:
a singular value decomposition subunit 241 for decomposing the singular value according to the formulaPerforming singular value decomposition on the complex matrix to obtain a first singular value diagonal matrixAnd Ui and Vi respectively represent a left singular value matrix and a right singular value matrix, and singular values in the first singular value diagonal matrix are arranged according to a descending order.
Preferably, the quality acquisition unit 25 includes:
a distance calculation unit 251 for calculating a formula according to the distanceCalculating the distance d between the three-dimensional image to be evaluated and the neighborhood blocks i at the same position in the original three-dimensional imageiWhere w is the size of the neighborhood block,representing the jth singular value on the diagonal of the first diagonal matrix of singular values,representing the jth singular value on the diagonal of the second diagonal matrix of singular values.
Preferably, the quality acquiring unit 25 further includes:
a score calculating unit 252 for calculating a score according to the formulaCalculating the quality fraction q of the three-dimensional image to be evaluated, wherein n is the number of neighborhood blocks with the same position in the three-dimensional image to be evaluated and the original three-dimensional image; and
and the quality level output unit 253 is used for outputting the quality level of the three-dimensional image to be evaluated according to the quality score and the preset quality level division.
In the embodiment of the present invention, each unit of the three-dimensional image quality evaluation system may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein. The detailed implementation of each unit can refer to the description of the first embodiment, and is not repeated herein.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for evaluating the quality of a three-dimensional image, the method comprising the steps of:
when a three-dimensional image to be evaluated is received, acquiring the position of a neighborhood block obtained by matching the viewpoint of an original three-dimensional image corresponding to the three-dimensional image to be evaluated;
acquiring a corresponding neighborhood block in the three-dimensional image to be evaluated according to the position of the neighborhood block;
acquiring brightness components of left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated, and acquiring complex matrix representation of the neighborhood blocks according to the brightness components;
performing singular value decomposition on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, recording the singular value diagonal matrix as a first singular value diagonal matrix, acquiring a singular value diagonal matrix of the original three-dimensional image, and recording the singular value diagonal matrix as a second singular value diagonal matrix;
and calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image according to the first singular value diagonal matrix and the second singular value diagonal matrix and a preset distance calculation formula, and acquiring the quality level of the three-dimensional image to be evaluated according to the calculated distance.
2. The method of claim 1, wherein obtaining the complex matrix representation of the neighborhood block based on the luma component comprises:
according to the formulaComputing a complex matrix representation of the neighborhood blockWherein,andrespectively representing the brightness components, mu, of the left and right viewpoint images of the neighborhood block i in the three-dimensional image to be evaluated1 2＝-1。
3. The method of claim 1, wherein the step of performing a singular value decomposition on each of the complex matrices to obtain a singular value diagonal matrix corresponding to the complex matrix comprises:
according to the formulaPerforming singular value decomposition on the complex matrix to obtain the first singular value diagonal matrixAnd Ui and Vi respectively represent a left singular value matrix and a right singular value matrix, and singular values in the first singular value diagonal matrix are arranged according to a descending order.
4. The method according to claim 3, wherein the step of calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks of the same position in the original three-dimensional image comprises:
according to the distance calculation formulaCalculating the distance d between the three-dimensional image to be evaluated and the neighborhood blocks i at the same position in the original three-dimensional imageiWhere w is the size of the neighborhood block,representing the jth singular value on the diagonal of the first diagonal matrix of singular values,representing the jth singular value on the diagonal of the second diagonal matrix of singular values.
5. The method according to claim 4, wherein the step of obtaining the quality level of the three-dimensional image to be evaluated from the calculated resulting distance comprises:
according to the formulaCalculating the evaluation to be madeThe quality score q of the three-dimensional image is obtained, wherein n is the number of neighborhood blocks with the same position in the three-dimensional image to be evaluated and the original three-dimensional image;
and outputting the quality level of the three-dimensional image to be evaluated according to the quality score and the preset quality level division.
6. A system for evaluating the quality of a three-dimensional image, the system comprising:
the position acquisition unit is used for acquiring the position of a neighborhood block obtained by matching the viewpoint of an original three-dimensional image corresponding to the three-dimensional image to be evaluated when the three-dimensional image to be evaluated is received;
the neighborhood acquiring unit is used for acquiring a corresponding neighborhood block in the three-dimensional image to be evaluated according to the position of the neighborhood block;
the matrix representation unit is used for acquiring the brightness component of the left and right viewpoint images of each neighborhood block in the three-dimensional image to be evaluated and acquiring the complex matrix representation of the neighborhood blocks according to the brightness component;
the singular value decomposition unit is used for performing singular value decomposition on each complex matrix to obtain a singular value diagonal matrix corresponding to the complex matrix, marking the singular value diagonal matrix as a first singular value diagonal matrix, acquiring a singular value diagonal matrix of the original three-dimensional image and marking the singular value diagonal matrix as a second singular value diagonal matrix; and
and the quality obtaining unit is used for calculating the distance between the three-dimensional image to be evaluated and the neighborhood blocks at the same position in the original three-dimensional image through a preset distance calculation formula according to the first singular value diagonal matrix and the second singular value diagonal matrix, and obtaining the quality level of the three-dimensional image to be evaluated according to the calculated distance.
7. The system of claim 6, wherein the matrix representation unit comprises:
a matrix calculation unit for calculating a matrix according to a formulaComputing a complex matrix representation of the neighborhood blockWherein,andrespectively representing the brightness components, mu, of the left and right viewpoint images of the neighborhood block i in the three-dimensional image to be evaluated1 2＝-1。
8. The system of claim 6, wherein the singular value decomposition unit comprises:
singular value decomposition subunit for decomposing the singular value according to a formulaPerforming singular value decomposition on the complex matrix to obtain the first singular value diagonal matrixAnd Ui and Vi respectively represent a left singular value matrix and a right singular value matrix, and singular values in the first singular value diagonal matrix are arranged according to a descending order.
9. The system of claim 8, wherein the quality acquisition unit comprises:
a distance calculation unit for calculating a formula based on the distanceCalculating the distance d between the three-dimensional image to be evaluated and the neighborhood blocks i at the same position in the original three-dimensional imageiWhere w is the size of the neighborhood block,representing the jth singular value on the diagonal of the first diagonal matrix of singular values,representing the jth singular value on the diagonal of the second diagonal matrix of singular values.
10. The system of claim 9, wherein the quality acquisition unit further comprises:
a score calculating unit for calculating a score according to a formulaCalculating the quality score q of the three-dimensional image to be evaluated, wherein n is the number of neighborhood blocks with the same position in the three-dimensional image to be evaluated and the original three-dimensional image; and
and the quality grade output unit is used for outputting the quality grade of the three-dimensional image to be evaluated according to the quality fraction and the preset quality grade division.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611042805.8A CN106791801A (en) | 2016-11-22 | 2016-11-22 | The quality evaluating method and system of a kind of 3-D view |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611042805.8A CN106791801A (en) | 2016-11-22 | 2016-11-22 | The quality evaluating method and system of a kind of 3-D view |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106791801A true CN106791801A (en) | 2017-05-31 |
Family
ID=58975661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611042805.8A Pending CN106791801A (en) | 2016-11-22 | 2016-11-22 | The quality evaluating method and system of a kind of 3-D view |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106791801A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147906A (en) * | 2017-06-12 | 2017-09-08 | 中国矿业大学 | A kind of virtual perspective synthetic video quality without referring to evaluation method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595185A (en) * | 2012-02-27 | 2012-07-18 | 宁波大学 | Stereo image quality objective evaluation method |
| CN102750695A (en) * | 2012-06-04 | 2012-10-24 | 清华大学 | Machine learning-based stereoscopic image quality objective assessment method |
| CN103338379A (en) * | 2013-06-05 | 2013-10-02 | 宁波大学 | Stereoscopic video objective quality evaluation method based on machine learning |
| CN103400378A (en) * | 2013-07-23 | 2013-11-20 | 清华大学 | Method for objectively evaluating quality of three-dimensional image based on visual characteristics of human eyes |
| CN103678569A (en) * | 2013-12-09 | 2014-03-26 | 北京航空航天大学 | Construction method of virtual scene generation-oriented video image material library |
| CN103763552A (en) * | 2014-02-17 | 2014-04-30 | 福州大学 | Stereoscopic image non-reference quality evaluation method based on visual perception characteristics |
| CN103873854A (en) * | 2014-02-26 | 2014-06-18 | 天津大学 | Method for determining number of stereoscopic image subjective assessment testees and experiment data |
| CN104036502A (en) * | 2014-06-03 | 2014-09-10 | 宁波大学 | No-reference fuzzy distorted stereo image quality evaluation method |
| CN104243974A (en) * | 2014-09-12 | 2014-12-24 | 宁波大学 | Stereoscopic video quality objective evaluation method based on three-dimensional discrete cosine transformation |
| CN104811691A (en) * | 2015-04-08 | 2015-07-29 | 宁波大学 | Stereoscopic video quality objective evaluation method based on wavelet transformation |
| CN104820988A (en) * | 2015-05-06 | 2015-08-05 | 宁波大学 | Method for objectively evaluating quality of stereo image without reference |
| CN105282543A (en) * | 2015-10-26 | 2016-01-27 | 浙江科技学院 | Total blindness three-dimensional image quality objective evaluation method based on three-dimensional visual perception |
| CN105376563A (en) * | 2015-11-17 | 2016-03-02 | 浙江科技学院 | No-reference three-dimensional image quality evaluation method based on binocular fusion feature similarity |
| CN105635727A (en) * | 2015-12-29 | 2016-06-01 | 北京大学 | Subjective image quality evaluation method based on paired comparison and device thereof |
| CN105701140A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Method for constructing holographic image material library |
-
2016
- 2016-11-22 CN CN201611042805.8A patent/CN106791801A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595185A (en) * | 2012-02-27 | 2012-07-18 | 宁波大学 | Stereo image quality objective evaluation method |
| CN102750695A (en) * | 2012-06-04 | 2012-10-24 | 清华大学 | Machine learning-based stereoscopic image quality objective assessment method |
| CN103338379A (en) * | 2013-06-05 | 2013-10-02 | 宁波大学 | Stereoscopic video objective quality evaluation method based on machine learning |
| CN103400378A (en) * | 2013-07-23 | 2013-11-20 | 清华大学 | Method for objectively evaluating quality of three-dimensional image based on visual characteristics of human eyes |
| CN103678569A (en) * | 2013-12-09 | 2014-03-26 | 北京航空航天大学 | Construction method of virtual scene generation-oriented video image material library |
| CN103763552A (en) * | 2014-02-17 | 2014-04-30 | 福州大学 | Stereoscopic image non-reference quality evaluation method based on visual perception characteristics |
| CN103873854A (en) * | 2014-02-26 | 2014-06-18 | 天津大学 | Method for determining number of stereoscopic image subjective assessment testees and experiment data |
| CN104036502A (en) * | 2014-06-03 | 2014-09-10 | 宁波大学 | No-reference fuzzy distorted stereo image quality evaluation method |
| CN104243974A (en) * | 2014-09-12 | 2014-12-24 | 宁波大学 | Stereoscopic video quality objective evaluation method based on three-dimensional discrete cosine transformation |
| CN104811691A (en) * | 2015-04-08 | 2015-07-29 | 宁波大学 | Stereoscopic video quality objective evaluation method based on wavelet transformation |
| CN104820988A (en) * | 2015-05-06 | 2015-08-05 | 宁波大学 | Method for objectively evaluating quality of stereo image without reference |
| CN105282543A (en) * | 2015-10-26 | 2016-01-27 | 浙江科技学院 | Total blindness three-dimensional image quality objective evaluation method based on three-dimensional visual perception |
| CN105376563A (en) * | 2015-11-17 | 2016-03-02 | 浙江科技学院 | No-reference three-dimensional image quality evaluation method based on binocular fusion feature similarity |
| CN105701140A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Method for constructing holographic image material library |
| CN105635727A (en) * | 2015-12-29 | 2016-06-01 | 北京大学 | Subjective image quality evaluation method based on paired comparison and device thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147906A (en) * | 2017-06-12 | 2017-09-08 | 中国矿业大学 | A kind of virtual perspective synthetic video quality without referring to evaluation method |
| CN107147906B (en) * | 2017-06-12 | 2019-04-02 | 中国矿业大学 | A kind of virtual perspective synthetic video quality without reference evaluation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9378583B2 (en) | Apparatus and method for bidirectionally inpainting occlusion area based on predicted volume | |
| Moorthy et al. | Visual quality assessment algorithms: what does the future hold? | |
| CN104658001B (en) | Non-reference asymmetric distorted stereo image objective quality assessment method | |
| CN101610425B (en) | Method for evaluating stereo image quality and device | |
| CN104036501B (en) | A kind of objective evaluation method for quality of stereo images based on rarefaction representation | |
| CN105338343B (en) | It is a kind of based on binocular perceive without refer to stereo image quality evaluation method | |
| CN107635136B (en) | View-based access control model perception and binocular competition are without reference stereo image quality evaluation method | |
| CN104243976B (en) | A kind of three-dimensional image objective quality evaluation method | |
| CN104394403B (en) | A kind of stereoscopic video quality method for objectively evaluating towards compression artefacts | |
| CN104036502B (en) | A kind of without with reference to fuzzy distortion stereo image quality evaluation methodology | |
| TW201029443A (en) | Method and device for generating a depth map | |
| JP2013527646A5 (en) | ||
| CN104954778B (en) | Objective stereo image quality assessment method based on perception feature set | |
| CN109429051B (en) | Non-reference stereo video quality objective evaluation method based on multi-view feature learning | |
| CN108074241B (en) | Quality scoring method and device for target image, terminal and storage medium | |
| EP3001382B1 (en) | Method and apparatus for generating disparity map based on image frames photographed by stereo camera | |
| Geng et al. | A stereoscopic image quality assessment model based on independent component analysis and binocular fusion property | |
| CN114648482A (en) | Quality evaluation method and system for three-dimensional panoramic image | |
| Jeong et al. | Visual comfort assessment of stereoscopic images using deep visual and disparity features based on human attention | |
| CN104243970A (en) | 3D drawn image objective quality evaluation method based on stereoscopic vision attention mechanism and structural similarity | |
| US10298914B2 (en) | Light field perception enhancement for integral display applications | |
| EP2391135A1 (en) | Method and device for processing depth image sequence | |
| Ko et al. | A ParaBoost stereoscopic image quality assessment (PBSIQA) system | |
| CN106682599B (en) | Sparse representation-based stereo image visual saliency extraction method | |
| CN106960432B (en) | A kind of no reference stereo image quality evaluation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |