KR20130081835A - Method and system for analyzing a quality of three-dimensional image - Google Patents

Abstract

PURPOSE: Quality analysis apparatus and method of three-dimension check the quality about the depth level among the three-dimensional effect as numerical value, produce 7 coefficient values about stability, evaluate the stability, and objectively evaluate error to check the quality of three-dimensional image. CONSTITUTION: A three-dimensional effect analysis unit (120) produces a three-dimensional value from depth information about a two-dimensional image. A stability analysis unit (130) produces a final stability factor value through liner combination of 7 coefficient values obtained using the depth information and parallax information. An error analysis unit (140) uses the depth information or other information to detect image processing error. Each weighted value and constant [constant] are applied to the three-dimensional effect about each sequence image, stability, and the count value of error in case An analysis result unit (150) applies each weighted value and constant to the three-dimensional effect, stability, and coefficient values of error about each sequence image to produce the total point and generates a list by using the total point, when transforming the two-dimensional image into three-dimensional image. [Reference numerals] (110) Input unit; (120) Three-dimensional effect analysis unit; (130) Stability analysis unit; (140) Error analysis unit; (150) Analysis result unit; (160) Output unit; (AA) Original sequence image; (BB) Depthmap sequence image

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and method for analyzing three-

The present invention relates to an apparatus and method for analyzing the quality of a three-dimensional image, and more particularly, to a method and apparatus for analyzing the quality of a three-dimensional image using a depth map generated when a two- The degree of stereoscopic effect on the presence or absence of the stereoscopic effect is expressed by a numerical value, and seven factors that affect the stability of the three-dimensional stereoscopic image are obtained to show how severe the visual fatigue is, To perform an objective quality evaluation as to whether there is an error in processing an object as an object.

Recently, interest in stereoscopic images has increased, and various types of stereoscopic image acquisition devices and display devices have been developed. One method for acquiring a stereoscopic image signal for displaying a stereoscopic image is to use a pair of left and right cameras at the time of acquiring the stereoscopic image. This method is advantageous in that it can display natural stereoscopic images, but it requires not only two cameras for image acquisition but also problems in filming or encoding of acquired left and right images and frame rate of left and right images And the like, and the like.

Another method for acquiring a stereoscopic image signal is to convert a two-dimensional image signal acquired by one camera into a three-dimensional image signal. According to this method, since a three-dimensional image, that is, a left image and a right image are generated by performing predetermined signal processing on the acquired two-dimensional image (original image), when a stereoscopic image signal is acquired using the left and right cameras The above-mentioned problem to be caused does not occur. However, since this method generates two images using one image, it is difficult to display a stereoscopic image having a natural and stable stereoscopic effect. Therefore, in converting a two-dimensional image signal into a three-dimensional image signal, it is very important to display a three-dimensional image having a more natural and stable three-dimensional image by using the converted three-dimensional image signal.

However, researchers have studied the dizziness and visual fatigue that the viewer has experienced when they encountered 3D stereoscopic images, and have found objectivity and reasonable research results regarding the viewing angle and stereoscopic viewing distance which are most suitable for human being. However, Tools and devices for measuring the quality of 3D stereoscopic images have not yet been developed.

Korean Patent Publication No. 10-2008-0047673 (Published on May 30, 2008)

Disclosure of Invention Technical Problem [8] The present invention has been conceived to solve the above-described problems, and it is an object of the present invention to provide a 3D depth image Dimensional visual image, and the seven factors that affect the stability of the three-dimensional stereoscopic image are displayed to indicate how severe the visual fatigue is, and whether there is an error processing the object as a background or processing the background as an object Dimensional stereoscopic image quality analyzing apparatus and method capable of performing an objective quality evaluation on a 3D stereoscopic image.

According to an aspect of the present invention, there is provided an apparatus for analyzing quality of a three-dimensional image, the apparatus comprising: an input unit for inputting an original sequence image and a depth map sequence image for a two-dimensional image; Extracts depth values for each pixel for each frame from the depth information of the two-dimensional image, and generates a depth information histogram representing a depth map distribution map according to a depth gray value for each depth value per extracted frame A three-dimensional analysis unit for generating a three-dimensional (DF) value by analyzing the similarity of the depth information histogram and the uniformity histogram using a Batarya coefficient; The parallax information is generated using the depth information of the two-dimensional image, and the parallax information is generated by using the depth information and the parallax information to calculate the parallax range, the maximum value of the parallax absolute value, The seven coefficients on the Scale Movement of the squares of the average of the disparity, the Spatial Complexity of the screen, the Depth Position of the screen and the square of the distance, the temporal complexity, A stability analyzer for obtaining a final stability factor (CF) value by linear combination; An error analysis unit that detects an error of processing a background as an object or an error of processing an object as a background by using depth information of the 2D image or using information other than the depth information; When converting the 2D image into a 3D stereoscopic image, the total evaluation score is calculated by giving weights and constants to the values of the stereoscopic sense, stability, and error of the sequence images for each sequence image. An analysis result unit having a total evaluation score and providing the list according to a ranking; And output coefficient values related to stereoscopic effect, stability, and error for each sequence image on the screen in numerical values and on a graph, and output a list according to the total evaluation score for each sequence image and the rank of each total evaluation score on the screen. It includes an output unit.

In addition, the analysis result section may output a total evaluation score (QM) by calculating a linear combination of the three-dimensional sensation and the stability with respect to the total evaluation score according to the following equation (1).

[Equation 1]

는 가중치(coefficient)를 나타내며,

는 상수(costant)를 나타낸다. Here, QM represents the overall total evaluation score of the 3D image, DF represents the 3D value of the 3D image, CF represents the stability coefficient of the 3D image,

Represents a weight coefficient,

Denotes a cost.

The result of the analysis may be determined by a logarithmic function of the histogram stereo value and the parallax product according to the following equation (2) with respect to the stereoscopic value DF.

&Quot; (2) "

The stereoscopic analysis unit may further include: a histogram generation unit that generates a depth information histogram indicating a depth map distribution map corresponding to a depth gray value with respect to depth information per frame; And a stereo value calculating unit for calculating a stereo value DF using the Battacharyya coefficient based on the similarity of the depth map histogram and the uniform distribution histogram.

Also, the histogram generator may convert a depth value of each pixel per frame into a depth gray value of 0 to 255, and a depth information histogram showing a distribution of depth gray values for each pixel in one frame Can be generated.

Also, the stereoscopic value calculator may normalize the frequency of the depth map histogram by the number of all pixels, normalize the i-th value of the depth information histogram (x [i]), The i-th value of the depth information histogram can be calculated by dividing the i-th value of the depth information histogram by the entire pixel value according to the following equation (4).

&Quot; (4) "

The stability analysis unit may extract depth values for each pixel per frame from a depth map of the 2D image and store depth information for each frame by dividing the depth values for each pixel. part; A parallax information generation unit generating parallax information using the generated depth map; And a stability calculator for calculating seven factor values using the depth information and the parallax information and generating a final stability factor CF by linear combination.

Also, the stability calculator may calculate the final stability coefficient CF for one frame by performing linear combination of the seven coefficient values according to the following equation (12).

&Quot; (12) "

Here, omega 1 to omega 7 represent weight values for seven respective coefficient values.

In addition, the stability calculation unit calculates seven coefficient values according to Equation 10 for each frame for every frame in the same process of calculating the stability coefficient value CF for one frame, for each frame for every frame. The total stability factor (T _CF ) is arranged by arranging the seven coefficient values of N as the number of frames according to the following equation (13), and the weights for the seven coefficient values for each frame according to the following equation (14). The weighting coefficient X values (ω1 to ω7) arranged as (ω) values can be calculated.

&Quot; (13) "

&Quot; (14) "

Here, X denotes a weight coefficient value composed of a 7x1 matrix, S denotes a matrix vector relating to Nx1 subjective evaluation, and N denotes the number of frames.

In addition, the error analysis unit, depth information for extracting the depth value for each pixel per frame from the depth map (depth map) for the two-dimensional image, the depth information for dividing and storing the depth value for each extracted pixel for each frame Storage unit; A parallax information generation unit generating parallax information using the generated depth map; And generating error coefficient values for depth reversal of processing an object as a background or processing a background as an object by using a depth value for each frame for the 2D image or using information other than the depth information. It includes an error calculation unit.

The error calculating unit may separate the background information and the object part using the depth value for each depth information per frame, and use the information other than the depth in the separated background part to determine the background object. Depth inversion to be processed can be detected to calculate the error coefficient value.

In addition, the error image calculating unit may be regarded as a background when a difference value of the difference image is smaller than a threshold value by using a difference image between a previous frame and a current frame of the 2D image as information other than the depth, and as an object if larger than the threshold value. The error count can be calculated.

The error calculator may detect an error using a motion vector with information other than the depth. The error calculator may set a global motion vector in a block unit and move in a block unit. When the calculated motion vector value differs from the motion vector of the background by a predetermined amount or more, the error coefficient value may be calculated by considering the object as an object.

According to another aspect of the present invention, there is provided a method for analyzing the quality of a three-dimensional image, the method comprising the steps of: (a) inputting an original sequence image and a depth map sequence image for a two- (b) extracting depth values for each pixel per each frame from depth information of the two-dimensional image, and extracting depth information indicating a depth map distribution according to a depth gray value with respect to depth values per extracted frame Generating a histogram, generating a stereoscopic (DF) value by analyzing the similarity between the depth information histogram and the uniform histogram using Battaria's coefficient; (c) generating parallax information using the depth information of the two-dimensional image, and generating parallax information by using the depth information and the parallax information to calculate a parallax range, a maximum value of a parallax absolute value, The average of the distance between the screen and the screen, the spatial complexity, the depth value of the screen and the square of the distance, the temporal complexity, and the mean of the squared difference Generating a final stability coefficient (CF) value by linear combination by obtaining seven coefficient values; (d) detecting an error processing an background as an object or an error processing an object as a background, using depth information of the two-dimensional image or information other than the depth information; And (e) calculating a total evaluation score by giving weights and constants to the three-dimensional, stability, and error coefficient values for each sequence image of the 2D image, or calculating the total evaluation score for each sequence image. Providing a list according to the ranking (Ranking).

Meanwhile, a program for executing the method for analyzing the quality of three-dimensional stereoscopic image according to the embodiment of the present invention can be recorded on a computer-readable medium such as a CD or a USB medium.

As described above, the apparatus and method for analyzing quality of a 3D stereoscopic image of the present invention can objectively evaluate the quality of a 3D stereoscopic image.

In other words, it is possible to confirm the quality of the degree of depth level (depth sense) in the 3D sensation, which is one element for determining the quality of the 3D stereoscopic image, as the numerical value, and to measure the stability And the quality of the 3D stereoscopic image can be confirmed by objectively evaluating the erroneousness which is a factor of the quality.

1 is a block diagram schematically showing functional blocks of a device for analyzing the quality of a three-dimensional image according to an embodiment of the present invention.
2 is a flowchart illustrating a method for analyzing quality of a three-dimensional image according to an exemplary embodiment of the present invention.
3 is a control block diagram of a three-dimensional analysis unit according to an embodiment of the present invention.
4 is a flowchart illustrating a method of analyzing a three-dimensional effect of a three-dimensional analysis unit according to an exemplary embodiment of the present invention.
5 is a diagram illustrating an example of depth values for each pixel generated from a two-dimensional image according to an embodiment of the present invention.
FIG. 6 is a diagram showing an example of a histogram showing a distribution diagram of a depth value of a pixel per one frame according to an embodiment of the present invention.
FIG. 7 is a diagram showing an example in which the degree of similarity between a depth information histogram and a uniformity histogram is expressed in terms of a stereoscopic value according to an embodiment of the present invention.
8 is a diagram showing a good example and a bad example of a three-dimensional image of one frame of a three-dimensional image based on the three-dimensional value calculated according to the embodiment of the present invention.
FIG. 9 schematically shows a functional block of the stability analysis unit according to the embodiment of the present invention.
10 is a flowchart illustrating a stability analysis method of a stability analysis unit according to an embodiment of the present invention.
11 is a diagram for explaining a range of a parallax and a maximum value Max of a parallax according to an embodiment of the present invention.
12 is a view for explaining an average value of parallax and a distance between screens according to an embodiment of the present invention.
13 is a view for explaining the spatial complexity according to an embodiment of the present invention.
FIG. 14 is a diagram for explaining an example of calculating a coefficient value with respect to a depth position according to an embodiment of the present invention.
FIG. 15 is a schematic block diagram of the error analysis unit according to the embodiment of the present invention.
16 is a flowchart illustrating an error analysis method of the error analysis unit according to the embodiment of the present invention.
17 is a view illustrating an example of dividing a two-dimensional image into a background and an object using a depth value according to an embodiment of the present invention.
18 is a diagram showing an example in which an object part and a background part are separated using a depth value for a manual conversion image and an automatic conversion image.
19 is a diagram illustrating an example of using a difference image between a previous frame and a current frame of a two-dimensional image according to an embodiment of the present invention.
FIG. 20 is a diagram illustrating an example of calculating an error count value by detecting a depth inversion in which an object is processed as a background in accordance with an embodiment of the present invention.
FIG. 21 is a diagram illustrating an example of detecting an error by considering a depth inversion according to a value of a difference image in a background portion according to an exemplary embodiment of the present invention, which is greater than a threshold value.
FIG. 22 is a diagram illustrating an example of outputting a result of three-dimensional sense, stability, and erroneousness of each sequence image by numerical values, a graph, and the like according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram schematically showing functional blocks of a device for analyzing the quality of a three-dimensional image according to an embodiment of the present invention.

Referring to FIG. 1, an apparatus 100 for analyzing the quality of a 3D stereoscopic image according to an exemplary embodiment of the present invention includes an input unit 110, a 3D effect analyzing unit 120, a stability analyzing unit 130, 140, an analysis result unit 150, an output unit 160, and the like.

The input unit 110 inputs the original sequence image and the depth information sequence image for the two-dimensional image. At this time, when sequential numbers such as "_001, _002, _003, ..." are attached to the end of the file name of the sequence image in one folder, all the images in the folder are input and inputted.

The stereoscopic analysis unit 120 extracts depth values for each pixel of each frame as shown in FIG. 5 from a depth map of the 2D image, and extracts depth gray for each extracted depth information for each frame. Depth histogram showing depth map distribution according to (depth gray) values, and the similarity between depth map histogram and uniform distribution histogram is calculated by Bhattacharyya Coefficient. ) To generate a QM factor. At this time, it is considered that the stereoscopic value is low, for example, lower than 0.3, intermediate between 0.3 and 0.8 and higher than 0.8.

The stability analyzer 130 generates parallax information using a depth map of a two-dimensional image, and uses the depth information and the parallax information to determine a range of parallax that affects the stability of the three- The maximum value of the absolute value of the parallax, the average value of the parallax and the average of the screen, the spatial complexity, the dispersion value of the screen and the square of the distance, (CF) values are obtained by linear combination by obtaining seven factors such as a temporal complexity and a mean of a square of difference in time difference.

The error analysis unit 140 divides the depth information of each frame into a background portion and an object portion using a depth value thereof and processes the object based on the threshold value Or an error in the depth map reverse processing that treats the background as an object.

The analysis result unit 150 gives a weight and a constant for each coefficient value such as stereoscopic feeling, stability, and error for each sequence image when converting a 2D image into a 3D stereoscopic image, thereby giving 1 (bad) The total evaluation score is calculated and displayed from 5 to (good), and the total evaluation score for each sequence image is provided as a list according to the ranking. That is, the analysis result unit 150 calculates a linear combination of the three-dimensional feeling and the stability according to the following Equation 1 with respect to the final quality result value, and outputs the total evaluation score QM.

는 가중치(coefficient)를 나타내는 것으로 3D 영상의 입체값에 대한 계수값과 3D 영상의 안정성에 대한 계수값을 나타내며 수학식12 내지 수학식14와 같은 방식으로 얻을 수 있고,

는 상수(costant)를 나타내는 것으로 최종 결과로 총 평가 점수가 0 ~ 5점 사이가 나올 수 있도록 일정 값을 더하여 값을 조정하기 위해 정한 값을 나타낸다. 이때, 입체값의 경우 시차(parallax)를 증가시키다 보면 입체감이 더 이상 좋아지지 않는 지점이 발생하므로, 분석 결과부(150)는 입체값 DF에 대해 다음 수학식2에 따라 히스토그램 입체값과 시차(parallax) 곱의 로그함수로 결정하게 된다.Here, QM represents a total total evaluation score of the 3D image, DF represents a stereoscopic value of the 3D image, and CF represents a stability coefficient value of the 3D image. Also,

Represents a coefficient value for the 3D image and a coefficient value for the stability of the 3D image, and can be obtained in the manner of Equations (12) to (14)

Represents a constant, and the final value indicates a value determined to adjust the value by adding a certain value so that the total evaluation score is between 0 and 5 points. In this case, when the parallax is increased, the point where the cubic effect does not improve any more occurs. Therefore, the analysis result unit 150 calculates the histogram stereo value and the parallax (for example, parallax multiplied by the logarithmic function.

The output unit 160 outputs coefficient values related to stereoscopic feeling, stability, and error for each sequence image on the screen as numerical values and graphs, and lists the total evaluation scores for each sequence image and the rank of each total evaluation score. And so on. At this time, the output unit 160 displays each score of the sequence image with a Polar Graph, so that the user can identify the score for each frame at a glance.

2 is a flowchart illustrating a method for analyzing quality of a three-dimensional image according to an exemplary embodiment of the present invention.

Referring to FIG. 2, the apparatus 100 for analyzing the quality of a 3D stereoscopic image first receives a raw sequence image and a depth map sequence image through an input unit 110 (S210 ).

Accordingly, the 3D analysis unit 120 extracts depth values for each pixel of each frame as shown in FIG. 5 from a depth map of the 2D image, and extracts depth information for each extracted frame. Create a depth information histogram that shows the depth map distribution according to the depth gray value, and calculate the similarity between the depth map histogram and the uniform distribution histogram. Analyze using Bhattacharyya Coefficient to generate a stereoscopic value (QM Factor) (S220).

In addition, the stability analysis unit 130 generates parallax information using a depth map of a two-dimensional image, and uses the depth information and the parallax information to calculate parallax information that affects the stability of the three- The maximum value of the absolute value of the parallax, the average value of the parallax and the distance between the screens, the spatial complexity, the depth value of the screen and the square of the distance, The final stability coefficient CF is generated by a linear combination of seven factors such as the temporal complexity of the time difference and the mean of the squared difference of the time difference S230.

That is, when the user clicks the button for stability, the safety analysis unit 130 calculates and outputs WeightSum of the average result value of the frames with respect to the intra-stability factors, and the resultant value for each frame is stored in a text file So that the result values for each frame can be viewed.

The error analysis unit 140 divides the depth information of each frame into a background portion and an object portion by using the depth value thereof, Or an error value for a depth reversal process for processing a background as an object (S240).

That is, when the depth reversal is detected, the error analysis unit 140 outputs a reversed depth map as a thumbnail image, and when there is an error, the user selects a corresponding frame through a UI (User Interface) The result can be excluded, and the inverted part is indicated by a white block of 8 * 8 pixel units in which position the area is inverted. In this case, the ratio of white blocks to the total number of blocks in one frame is scored to generate an error value. When there is an inversion phenomenon of 15 or more blocks in one frame, an abnormality of the corresponding frame image is displayed. It is possible to display a frame in which an inversion phenomenon occurs as an error frame.

Subsequently, the analysis result unit 150 calculates a total evaluation score from 1 (bad) to 5 (good) by giving weights and constants to respective values of stereoscopic sense, stability, and error for each sequence image. The total evaluation score for each sequence image is provided as a list according to a ranking (S250).

That is, as shown in FIG. 22, the analysis result unit 150 outputs the result values of the stereoscopic sense, stability, and error of each sequence image as a numerical value and a graph, and outputs the original sequence image and the depth sequence image as thumbnails. And outputs the resulting thumbnails for the three-dimensional and error.

Accordingly, the user can confirm the respective values of the three-dimensional sense, the stability, and the erroneousness with respect to the original sequence image, and the total evaluation score regarding the overall quality can be confirmed.

[Detailed Configuration and Operation of the Stereoscopic Analysis Unit]

3 is a control block diagram of a three-dimensional analysis unit according to an embodiment of the present invention.

3, the stereoscopic analysis unit 120 of the present invention includes a histogram generator 310, a stereoscopic value calculator 320, and a stereoscopic value storage unit 330. [

Here, the depth information per frame for a two-dimensional image is obtained by extracting depth values for each pixel per each frame as shown in FIG. 5 from a depth map for a two-dimensional image. The depth map is a data structure storing depth values of each pixel per frame for a two-dimensional image. 5 is a diagram illustrating an example of depth values for each pixel generated from a two-dimensional image according to an embodiment of the present invention. 5, the three-dimensional analysis unit 120 extracts depth values for each pixel per frame as in (a) from the depth map, and calculates depth values of the extracted pixels as shown in (b) And stores them temporarily. At this time, the three-dimensional analysis unit 120 has a storage function for temporarily storing the generated depth information.

The histogram generator 310 generates a depth information histogram representing a depth map distribution map corresponding to depth gray values for each extracted depth information per frame. That is, as shown in FIG. 6, the histogram generator 120 converts the depth values of each pixel per frame into depth gray values of 0 to 255 values to make the horizontal axis, And a histogram showing the vertical distribution of the distribution charts. FIG. 6 is a diagram showing an example of a histogram showing a distribution diagram of a depth value of a pixel per one frame according to an embodiment of the present invention.

The stereo value calculator 320 calculates the similarity between the depth map histogram and the uniform distribution histogram using the Bhattacharyya coefficient and outputs the stereo value DF. Here, the uniform distribution histogram means an ideal depth information histogram in which the depth value of the depth map is widely distributed so that the three-dimensional feeling is high. Accordingly, the three-dimensional analysis unit 120 of the present invention stores a uniform distribution histogram serving as a reference for comparison with the depth information histogram of pixels per each frame.

That is, the stereoscopic calculator 320 normalizes the number of pixels so that the sum of the depth information histogram and the equal distribution histogram values is 1, and normalizes them. The similarity between the information histogram and the uniform distribution histogram is calculated as a three-dimensional value (DF _Histogram ).

는 정규화 된(Normalized) 깊이 정보 히스토그램의 i번째 인덱스(index)의 값이고,

는 정규화 된 균등분포 히스토그램의 i번째 인덱스(index)의 값을 나타낸다.In Equation (3)

Is the value of the i-th index (index) of the normalized depth information histogram,

Represents the value of the i-th index (index) of the normalized uniform distribution histogram.

Here, the Bartaglia coefficient compares the previous frame with the current frame, finds the similarity of colors between the two frames, identifies the maximum number of similar pixels as the same as the previous frame, and tracks the values from -1 to 1 The closer to 1, the higher the correlation between the two frames, the closer to -1, the less relevant. That is, the closer to 1 the values are similar to each other, and the closer to -1 the differences are.

4 is a flowchart illustrating a method of analyzing a three-dimensional effect of a three-dimensional analysis unit according to an exemplary embodiment of the present invention.

First, the 3D effect analyzing unit 120 receives depth information per frame for a 2D image through the input unit 110 (S410).

At this time, the three-dimensional analysis unit 120 extracts depth values for each pixel per frame as shown in FIG. 5 from a depth map of the two-dimensional image, and extracts depth values of the extracted pixels for each frame And store them temporarily.

Next, the depth-of-field analyzing unit 120 obtains a depth map distribution map corresponding to the depth gray value through the histogram generating unit 310 with respect to the depth information per frame input through the input unit 110 A depth information histogram is generated (S420).

That is, as shown in FIG. 6, the histogram generator 310 converts the depth values of each pixel per frame into depth gray values of 0 to 255 values to make the horizontal axis, A depth information histogram is generated in which the vertical axis represents a distribution diagram indicating how deep gray values are distributed.

Subsequently, the stereoscopic analysis unit 120 determines the similarity between the depth map histogram and the uniform distribution histogram through the stereoscopic value calculation unit 320 by using the Bhattacharyya Coefficient. It calculates it as a value (QM Factor) (S430).

At this time, the three-dimensional value calculation unit 320 is normalized by the number of pixels so that the sum of the depth information histogram and the equal distribution histogram value is 1, respectively, and normalized as shown in Equation 1 by using the Batcharya coefficient. By multiplying each index value of the depth information histogram by each index value of the normalized uniform distribution histogram and adding the roots together, the similarity of the depth information histogram and the uniform distribution histogram is shown as a stereoscopic value (DF _Histogram ). To calculate. FIG. 7 is a diagram showing an example in which the degree of similarity between a depth information histogram and a uniformity histogram is expressed in terms of a stereoscopic value according to an embodiment of the present invention.

That is, the stereo value calculating unit 320 normalizes the frequency of the depth map histogram by dividing the frequency of the depth map histogram by the number of all the pixels. Here, the total pixel is, for example, 2,073,600 pixels in the case of Full HD of 1920 * 1080. The normalization (x [i]) of the i-th value of the depth information histogram can be calculated by dividing the i-th value of the depth information histogram by the whole pixel value according to the following equation (4).

Therefore, the sum from i th to 255 of the normalized depth histogram value is 1, and the first index of the normalized depth histogram for the depth gray value from 0 to 255. The rooted value is multiplied by the value of (index) (x1) and the value of the first index (y1) of the normalized uniform distribution histogram, and the value of the second index (x2) of the normalized depth information histogram (x2). ) Is multiplied by the value of the second index (y2) of the normalized uniform distribution histogram, and the root is obtained, and the value of the 256th index (x256) of the depth histogram normalized by the same process (x256) By multiplying the value of the 256th index (y256) of the distribution histogram, the root values are summed to calculate the stereoscopic value (DF _Histogram ).

The stereoscopic analysis unit 120 displays the stereoscopic values for each frame calculated through the stereoscopic value calculator 320 on the screen as shown in FIG. 8, or displays the stereoscopic values for each frame in the stereoscopic value storage unit 330 (S440).

That is, the stereoscopic value calculator 320 outputs the stereoscopic values per frame calculated as shown in Equation (1) together with the corresponding frames and the histogram on the screen. As a result, as shown in FIG. 8, This is a bad example. 8 is a diagram showing a good example and a bad example of a three-dimensional image of one frame of a three-dimensional image based on the three-dimensional value calculated according to the embodiment of the present invention.

Therefore, according to the three-dimensional analysis unit 120 according to the embodiment of the present invention, it is possible to confirm by numerical values how good the 3D stereoscopic effect is.

[Detailed Configuration and Operation of Stability Analysis Section]

FIG. 9 schematically shows a functional block of the stability analysis unit according to the embodiment of the present invention.

Upon receiving the original sequence image and the depth map sequence image through the input unit 110, the stability analysis unit 130 stores the input depth map sequence image in the depth information storage unit 910.

That is, the depth information storage unit 910 extracts depth values for each pixel per frame as shown in (A) of FIG. 5 from a depth map of the two-dimensional image, And stores the values separately for each frame as in (b).

Then, the parallax information generating unit 920 generates parallax information using the generated depth map. A person recognizes the sense of depth and distance of objects through two eyes. When one object is viewed, different images are generated through two eyes, and by combining these images appropriately, one recognizes the sense of depth and distance of objects. Accordingly, the three-dimensional stereoscopic image generates two images considering the visual difference of the left and right eyes from one two-dimensional image in consideration of the person's cognitive characteristics. The visual difference of these eyes is the parallax, and the parallax is generated using the depth map.

The stability calculator 930 calculates the stability of the three-dimensional image using the depth information and the parallax information. The stability calculator 930 calculates the stability of the three-dimensional image using the range of the parallax, the maximum value of the absolute value of the parallax, There are seven factors such as Average, Spatial Complexity, Depth Position of screen and square of distance, Temporal Complexity, Scene Movement of difference of squared difference. ) Is calculated and a final stability coefficient (CF) value is generated by a linear combination.

10 is a flowchart illustrating a stability analysis method of a stability analysis unit according to an embodiment of the present invention.

First, the stability analysis unit 130 according to the embodiment of the present invention receives depth information per frame for a two-dimensional image through the input unit 110 (S1010).

At this time, the stability analysis unit 130 extracts depth values for each pixel per frame as shown in FIG. 5 from a depth map of the two-dimensional image, and calculates depth values of the extracted pixels by each frame Respectively.

Next, the stability analysis unit 130 generates parallax information through the parallax information generation unit 920 using a depth map for each frame (S1020).

That is, the parallax information generating unit 920 generates parallax information on the visual difference of eyes used when two images considering the visual difference of the left and right eyes are generated from one two-dimensional image.

The stability analyzer 130 then uses the depth information and the parallax information to calculate the range of the parallax through the stability calculator 930, the maximum value Max of the parallax absolute value, the distance between the average value of the parallaxes and the screen Average Factor, Spatial Complexity, Depth Position of Screen and Distance Squares, Temporal Complexity, 7 Factors on Scene Movement of Difference, (S1030).

That is, the stability calculation unit 930 calculates a coefficient value (CF _Range ) with respect to a range of a time difference according to the following equation (5) as the first coefficient value.

Here, the range of the disparity is a value obtained by dividing the value of the disparity (the disparity value) from the screen (Screen) of the depth map for each frame by the value (The disparity value is the largest value of minus (-) when the screen value is 0), and min (the disparity value is the largest value of plus value) that is the most value behind. The larger the range value, the greater the parallax width, which may affect the stability.

Disp (x, y) is a value indicating how much the x and y coordinate values of the original image have moved in the left image, and the gray value of the x and y coordinates of the depth map is 256 (256-depthmap (x, y coordinate gray value)) - The gray value of the screen face] is obtained by subtracting the gray value of the screen face from the 256-depthmap (x, y coordinate gray value) The range of the parallax according to the embodiment of the present invention and the maximum value Max of the parallax according to the embodiment of the present invention, Fig.

In addition, the stability measuring unit 150 calculates the coefficient value CF _Max with respect to the maximum value Max of the absolute value of the parallax according to the following equation (6) as the second coefficient value.

11, the maximum value (MAX) is a value (disp (x, y), that is, minus (-)) values in which the value of disparity is most advanced forward from the screen (screen) ) Value and therefore the absolute value is applied). The larger the value of MAX, the more image is displayed than the screen, which may affect the stability.

In addition, the stability calculator 930 calculates a coefficient _average (CF _average ) about the average value of the parallax and the distance (Average) between the screens as shown in FIG. 12 according to the following equation (7) with the third coefficient value.

Here, disp _display represents the disparity (disp.) Value on the screen, which is zero because there is no difference on the screen.

12 is a view for explaining an average value of parallax and a distance between screens according to an embodiment of the present invention. As shown in FIG. 12, the larger the Average value, the farther from the screen surface, the stability may be affected. Also, if the absolute value is subtracted, if the average value is minus (-) value, there are a lot of areas that are protruding forward than the screen surface, which adversely affects stability. Here, disp _display represents the disparity (disp.) Value on the screen, which is zero because there is no difference on the screen.

In addition, the stability calculator 930 calculates a coefficient value (CF _{SpatialComplexity} ) related to the spatial _complexity as shown in FIG. 13 according to the following equation (8) with the fourth coefficient value.

Here, E (disp (x, y)) represents the disparity (disp.) Value in the Average plane of the (x, y) coordinates, , And as the image is densely dispersed at the average point, the dizziness may be reduced as compared with the same image (the image having a large variance value in the average plane). 13 is a view for explaining the spatial complexity according to an embodiment of the present invention.

In addition, the reliability calculation unit 930 calculates a coefficient (CF _{DepthPosition)} on the depth position (Depth Point) as shown in Figure 14 in accordance with the following equation (9) in the fifth coefficient value.

Here, disp _display represents the disparity (disp.) Value on the screen, which is zero because there is no difference on the screen.

That is, the coefficient value (CF _{DepthPosition} ) with respect to the depth position is a variance value of the object distance square from the screen as shown in Fig. FIG. 14 is a diagram for explaining an example of calculating a coefficient value with respect to a depth position according to an embodiment of the present invention.

In addition, the stability calculation unit 930 calculates a coefficient value (CF _Temporal Complexity) related to the temporal complexity according to the following equation (10) as the sixth coefficient value.

Here, disp _i (x, y) represents the (x, y) Time (disp.) Value of the coordinates of the current i-th frame, disp _{i - 1} (x, y) are from the previous i-1 frame, (x (x, y) represents a difference value (diff) between a parallax value of a current i-th frame and a parallax value of a previous i-1 frame, and E (diff (x, y)) represents the difference (diff.) value of the parallaxes on the screen surface.

In addition, the reliability calculation unit 930 calculates a coefficient of the mean (Scene Movement) of the square of the difference between differential (CF _{SceneMovement)} according to the following Equation 11 as the seventh coefficient value.

Here, disp _i (x, y) represents the (x, y) Time (disp.) Value of the coordinates of the current i-th frame, disp _{i - 1} (x, y) are from the previous i-1 frame, (x (x, y) represents the difference (diff) between the time difference of the current i-th frame and the time difference of the previous i-1 frame.

Next, the stability calculator 930 calculates a final stability factor (CF) for one frame by performing linear combination according to the following equation (12) (S1040).

Here, omega 1 to omega 7 represent weight values for seven respective coefficient values.

In this case, the stability analyzer 130 calculates seven coefficient values according to Equation 10 for each frame for all the frames in the same process of calculating the stability coefficient value CF for one frame, for all the frames. The total stability factor is obtained by arranging the seven coefficient values of each frame according to the following equation (13) (Total Compatibility Factor; T _CF ). Calculate a weighting factor (X) value (ω1 to ω7) arranged with the weighting values for. That is, the stability calculation unit 930 determines the weighting coefficient of the linear combination so that the subjective evaluation and the degree of correlation are high through the Least Mean Square method.

Here, X denotes a weight coefficient value composed of a 7x1 matrix, S denotes a matrix vector relating to Nx1 subjective evaluation, and N denotes the number of frames.

Therefore, according to the stability analysis unit 130 according to the embodiment of the present invention, it is possible to confirm how good the stability of the 3D stereoscopic image is.

[ Errors  Detailed Configuration and Operation of Analysis Unit]

FIG. 15 is a schematic block diagram of the error analysis unit according to the embodiment of the present invention.

The error analysis unit 140 receives the original sequence image and the depth map sequence image through the input unit 110 and stores the input depth map sequence image in the depth information storage unit 1510. [

That is, the depth information storage unit 1510 extracts depth values for each pixel per frame as shown in (a) of FIG. 5 from a depth map of the two-dimensional image, The values are stored separately for each frame as in (b).

Next, the parallax information generating unit 1520 generates parallax information using the generated depth map. 3D stereoscopic images generate two images considering the visual difference of left and right eyes from one 2D image considering human cognitive characteristics. The visual difference of these eyes is the parallax, and the parallax is generated using the depth map.

The error calculator 1530 divides the generated depth information for each frame into a background portion and an object portion by using the depth value thereof, , Or generates an error count value for the depth inversion processing the background as an object.

At this time, the error calculator 1530 separates the background and the object by using the depth value of the object in each horizontal line for the depth information that is greater than the depth value of the background.

The error calculator 1530 sets the depth value of the background as a threshold value for each horizontal line in the depth information and regards an object larger than the threshold value per horizontal line as an object You can separate the background and the object.

In addition, the error calculator 1530 detects a depth inversion process for processing an object as a background in the presence of a depth value for a background among the separated object portions, thereby calculating an error count value.

In addition, the error calculator 1530 can calculate the error count by detecting the depth inversion that processes the background as an object using information other than depth in the separated background portion. Here, the information other than the depth uses the difference image of the two-dimensional image. When the difference image of the difference image between the previous frame and the current frame of the two-dimensional image is used, if the difference image is smaller than the threshold value, If it is large, it is regarded as an object. Assuming that the movement of the camera is not very dynamic, since the background part has almost no change and only the object part changes, the value of the difference image of the background part is small and the value of the difference image of the object part is relatively large will be. Accordingly, the error calculator 1530 regards the difference image as a depth inversion if the difference image has a value larger than the threshold value in the background portion, and calculates the error coefficient value.

The error calculator 1530 can detect an error using a motion vector with information other than depth. The error motion calculator 1530 sets a global motion vector for each block, A motion vector is calculated and an error coefficient value is calculated by considering the calculated motion vector value as an object when a difference of a predetermined difference with a background motion vector occurs.

16 is a flowchart illustrating an error analysis method of the error analysis unit according to the embodiment of the present invention.

Referring to FIG. 16, the error analysis unit 140 according to the embodiment of the present invention first receives depth information per frame for a two-dimensional image through the input unit 110 as shown in FIG. 5 (S1610).

That is, the error-rate analyzing unit 140 extracts depth values for each pixel per frame as shown in FIG. 5 from a depth map of the two-dimensional image, And stores them in the depth information storage unit 1510. FIG.

Then, the erroneous property analyzing unit 140 uses the depth value through the erroneousness calculating unit 1530 with respect to the depth information for each frame, as shown in FIG. 17, (S1620). < / RTI > 17 is a view illustrating an example of dividing a two-dimensional image into a background and an object using a depth value according to an embodiment of the present invention. FIG. 18 shows an example in which an object part and a background part are separated using a depth value for a manual conversion image and an automatic conversion image.

That is, the error calculator 1530 separates the background and the object by using the depth value of the object in each horizontal line for the depth information of the two-dimensional image larger than the depth value of the background.

In addition, the error calculator 1530 sets a threshold value for each horizontal line in the depth information and regards the depth value for the background and the object for each horizontal line as an object larger than the threshold value You can separate the background and the object.

If the value of the difference image is smaller than the threshold value by using difference information between the previous image (frame) and the current image (frame) as shown in Fig. 19 with information other than the depth, the error calculator 1530 If the threshold is greater than the threshold, it is regarded as an object, and the background can be treated as an object or the object can be detected as a background. 19 is a diagram illustrating an example of using a difference image between a previous frame and a current frame of a two-dimensional image according to an embodiment of the present invention.

In step S1630, the error analysis unit 140 detects an inverse of the depth of the object processed by the background or processed by the object through the error calculator 1530, and calculates an error coefficient value.

That is, as the depth value for the background among the separated object parts exists, the error calculator 1530 detects the depth inversion (the inner part of the red circle) in which the object is processed as the background as shown in FIG. 20, The coefficient value is calculated. FIG. 20 is a diagram illustrating an example of calculating an error count value by detecting a depth inversion in which an object is processed as a background in accordance with an embodiment of the present invention.

In addition, the error analysis unit 140 can detect an error in which the background is processed as an object by using the difference image as the information other than the depth in the separated background part. That is, if the camera movement is not very dynamic, the error analyzing unit 140 has almost no change in the background portion and only changes the image of the object portion, so that the difference image of the background portion is small and the value of the object portion As shown in FIG. 21, if there is a portion where the difference of the difference image is larger than the threshold value in the background portion (black portion), the error is regarded as the depth inversion and the error is detected. FIG. 21 is a diagram illustrating an example of detecting an error by considering a depth inversion according to a value of a difference image in a background portion according to an exemplary embodiment of the present invention, which is greater than a threshold value.

The error analyzing unit 140 detects an error using a motion vector with information other than the depth. The error analyzing unit 140 sets a global motion vector in a unit of a block, And detects an error when the calculated motion vector is regarded as an object when a difference between the calculated motion vector and a motion vector of the background occurs.

Then, the error analysis unit 140 displays the error detection on the screen or stores it in a storage unit or the like (S1640).

Therefore, according to the error analysis unit 140 according to the embodiment of the present invention, the quality of the 3D stereoscopic image can be confirmed by objectively evaluating the quality of the erroneousness, which is one factor of the quality of the 3D stereoscopic image have.

Meanwhile, a program for executing the method for analyzing the quality of three-dimensional stereoscopic image according to the embodiment of the present invention can be recorded on a computer-readable medium such as a CD or a USB medium.

According to the embodiment of the present invention, by using the depth information (depth map) generated when converting a two-dimensional image into a three-dimensional image, the degree of a three-dimensional effect as to how good the three- And the seven factors that affect the stability of the 3D stereoscopic image are displayed to show how severe the visual fatigue is, and there is no error in processing the depth information by the object as the background or the background as the object Dimensional stereoscopic image quality analyzing apparatus and method capable of performing an objective quality evaluation on the 3D stereoscopic image.

Thus, those skilled in the art will appreciate that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the embodiments described above are to be considered in all respects only as illustrative and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

The present invention uses a depth map generated when a two-dimensional image is converted into a three-dimensional image, and displays the degree of a three-dimensional effect as to how good the three-dimensional image has a three- Objective quality evaluation to determine how severe the visual fatigue is, or whether there is an error processing the object with the depth information or processing the background as the object, by obtaining the seven factor that affects the stability of the stereoscopic image Dimensional stereoscopic image quality analysis apparatus and method, which can perform the three-dimensional stereoscopic image.

100: apparatus for analyzing quality of three-dimensional stereoscopic image 110:
120: three-dimensional analysis unit 130: stability analysis unit
140: Error Analysis Unit 150: Analysis Result Unit
160: Output section

Claims (27)

An input unit for inputting an original sequence image and a depth map sequence image for a two-dimensional image;
Extracts depth values for each pixel for each frame from the depth information of the two-dimensional image, and generates a depth information histogram representing a depth map distribution map according to a depth gray value for each depth value per extracted frame A three-dimensional analysis unit for generating a three-dimensional (DF) value by analyzing the similarity of the depth information histogram and the uniformity histogram using a Batarya coefficient;
The parallax information is generated using the depth information of the two-dimensional image, and the parallax information is generated by using the depth information and the parallax information to calculate the parallax range, the maximum value of the parallax absolute value, The seven coefficients on the Scale Movement of the squares of the average of the disparity, the Spatial Complexity of the screen, the Depth Position of the screen and the square of the distance, the temporal complexity, A stability analyzer for obtaining a final stability factor (CF) value by linear combination;
An error analysis unit that detects an error of processing a background as an object or an error of processing an object as a background by using depth information of the 2D image or using information other than the depth information;
When converting the 2D image into a 3D stereoscopic image, the total evaluation score is calculated by giving weights and constants to the values of the stereoscopic sense, stability, and error of the sequence images for each sequence image. An analysis result unit having a total evaluation score and providing the list according to a ranking; And
Coefficient values for stereoscopic feeling, stability, and error are output on the screen as numerical values and graphs for each sequence image, and a list according to the total evaluation score and the ranking of each total evaluation score for each sequence image is output on the screen. An output unit;
Dimensional stereoscopic image. The method of claim 1,
Wherein the analysis result section outputs a total evaluation score (QM) by calculating a linear combination of the three-dimensional sensation and the stability with respect to the total evaluation score according to the following equation (1) Stereoscopic image quality analyzer.
[Equation 1]

Here, QM represents the overall total evaluation score of the 3D image, DF represents the 3D value of the 3D image, CF represents the stability coefficient of the 3D image,

Represents a weight coefficient,

Denotes a cost. 3. The method of claim 2,
Wherein the analysis result section determines a logarithmic function of the histogram stereo value and a parallax product according to the following equation (2) for the stereoscopic value DF.
&Quot; (2) "

The method of claim 1,
The histogram analyzer may include: a histogram generator for generating a depth information histogram representing a depth map distribution map corresponding to a depth gray value with respect to depth information per frame; And a stereo value calculating unit for calculating a stereo value DF using the Battacharyya coefficient based on the similarity of the depth map histogram and the uniform distribution histogram. Dimensional stereoscopic image. 5. The method of claim 4,
The histogram generation unit converts the depth values of each pixel per frame into deep gray values of 0 to 255 values and generates a depth information histogram representing a distribution of depth gray values for each pixel in one frame Dimensional stereoscopic image. 5. The method of claim 4,
The stereoscopic value calculator normalizes the frequency of the depth map histogram by the number of pixels and normalizes the i-th value of the depth information histogram (x [i]) using the following mathematical expression And the i-th value of the depth information histogram is calculated by dividing the i-th value of the depth information histogram by the entire pixel value according to Equation (4).
&Quot; (4) "

The method of claim 1,
The stability analysis unit may include: a depth information storage unit for extracting depth values for each pixel per frame from a depth map of the 2D image, and storing the extracted depth values for each pixel for each frame; A parallax information generation unit generating parallax information using the generated depth map; A stability calculator for calculating seven coefficient values using the depth information and the parallax information and generating a final stability factor CF by linear combination;
Dimensional stereoscopic image by using the three-dimensional image. The method of claim 7, wherein
Wherein the stability calculator calculates the final stability coefficient (CF) for one frame by linear combination of the seven coefficient values according to the following equation (12): < EMI ID = Device.
&Quot; (12) "

Here, omega 1 to omega 7 represent weight values for seven respective coefficient values. The method of claim 8,
The stability calculation unit calculates seven coefficient values according to Equation 10 for each frame for all the frames in the same process of calculating the stability coefficient value CF for one frame. The total stability factor is obtained by arranging the branch coefficient values as the number of frames according to Equation 13 (Total Compatibility Factor; T _CF ). And a weight coefficient (X) value (ω1 to ω7) arranged as the values of the 3D stereoscopic image.
&Quot; (13) "

&Quot; (14) "

Here, X represents a weighting coefficient value consisting of a 7x1 matrix, S represents a matrix vector for Nx1 subjective evaluation, and N represents the number of frames. The method of claim 1,
The error analysis unit extracts depth values for each pixel per frame from a depth map of the 2D image, and stores the depth information for each frame by dividing the depth values for each pixel. ; A parallax information generation unit generating parallax information using the generated depth map; And generating error coefficient values for depth reversal of processing an object as a background or processing a background as an object by using a depth value for each frame for the 2D image or using information other than the depth information. An error calculation unit;
Dimensional stereoscopic image by using the three-dimensional image. 11. The method of claim 10,
The error calculating unit divides the depth information per frame into a background part and an object part using a depth value, and processes the background as an object using information other than depth in the separated background part. Detecting depth reversal to calculate the error coefficient value of the three-dimensional stereoscopic image analysis device. 11. The method of claim 10,
The error image calculation unit uses the difference image between the previous frame and the current frame of the 2D image as information other than the depth to regard the background as a value when the difference image is smaller than a threshold value and to regard the object as an object when the difference value is larger than the threshold value. 3D stereoscopic image quality analysis device, characterized in that for calculating an error coefficient value. 11. The method of claim 10,
The error calculator may detect an error using a motion vector using information other than the depth. The error calculation unit may set a global motion vector in a block unit, and set the motion vector in a block unit. And calculating an error coefficient value when the calculated motion vector value differs from the background motion vector by a predetermined amount, and calculates an error coefficient value. (a) inputting an original sequence image and a depth map sequence image for a two-dimensional image;
(b) extracting depth values for each pixel per each frame from depth information of the two-dimensional image, and extracting depth information indicating a depth map distribution according to a depth gray value with respect to depth values per extracted frame Generating a histogram, generating a stereoscopic (DF) value by analyzing the similarity between the depth information histogram and the uniform histogram using Battaria's coefficient;
(c) generating parallax information using the depth information of the two-dimensional image, and generating parallax information by using the depth information and the parallax information to calculate a parallax range, a maximum value of a parallax absolute value, The average of the distance between the screen and the screen, the spatial complexity, the depth value of the screen and the square of the distance, the temporal complexity, and the mean of the squared difference Generating a final stability coefficient (CF) value by linear combination by obtaining seven coefficient values;
(d) detecting an error of processing a background as an object or an error of processing an object as a background using depth information of the 2D image or information other than the depth information; And
(e) calculate the total evaluation score by giving weights and constants to the values of the three-dimensional, stability, and error coefficients for each sequence image of the 2D image, or rank the total evaluation score for each sequence image Providing as a list according to (Ranking);
Dimensional stereoscopic image. 15. The method of claim 14,
Wherein the step (e) calculates a linear combination of the three-dimensional sensation and the stability with respect to the total evaluation score according to the following equation (1), and outputs the total evaluation score QM A method for quality analysis of 3D stereoscopic images.
[Equation 1]

Here, QM represents the overall total evaluation score of the 3D image, DF represents the 3D value of the 3D image, CF represents the stability coefficient of the 3D image,

Represents a weight coefficient,

Denotes a cost. The method of claim 15,
Wherein the step (e) comprises: determining a logarithmic function of a histogram stereogram and a parallax product according to the following equation (2) for the stereoscopic value DF.
&Quot; (2) "

15. The method of claim 14,
Wherein the step (b) comprises: (a) generating a depth information histogram representing a depth map distribution map corresponding to a depth gray value for each depth information per frame; And a step (b) of calculating a stereoscopic value DF using the Battacharyya coefficient using the similarity between the depth map histogram and the uniform distribution histogram. A method for analyzing the quality of 3D images. The method of claim 17,
The step (a) converts a depth value of each pixel per frame into a depth gray value of 0 to 255, and a depth information histogram showing a distribution of depth gray values for each pixel in one frame Dimensional stereoscopic image by using the three-dimensional image. The method of claim 17,
The step (b) normalizes the frequency of the depth map histogram by the number of pixels and normalizes the i-th value of the depth information histogram (x [i]). Wherein the i-th value of the depth information histogram is calculated by dividing the i-th value of the depth information histogram by the total pixel value according to Equation (4).
&Quot; (4) "

15. The method of claim 14,
In the step (c), the depth values of each pixel per frame are extracted from the depth map of the 2D image, and the depth values of the extracted pixels are divided and stored for each frame. process; (B) generating parallax information using the generated depth map; And (c) generating seven final factor values by linear combination using the depth information and the time difference information.
Dimensional stereoscopic image, the method comprising the steps of: 21. The method of claim 20,
(C) calculating a final stability coefficient (CF) for one frame by performing linear combination of the seven coefficient values according to the following equation (12): < EMI ID = Quality analysis method of.
&Quot; (12) "

Here, omega 1 to omega 7 represent weight values for seven respective coefficient values. 22. The method of claim 21,
Step (c) is the same process of calculating the stability coefficient value CF for one frame, and calculates seven coefficient values according to Equation 10 for each frame for every frame, and calculates each frame for every frame. The total stability factor (T _CF ) is arranged by arranging the seven coefficient values of N as the number of frames according to the following equation (13), and the weights for the seven coefficient values for each frame according to the following equation (14). A quality analysis method for a 3D stereoscopic image, comprising calculating a weighting coefficient (X) value arranged from (ω) values (ω1 to ω7).
&Quot; (13) "

&Quot; (14) "

Here, X represents a weighting coefficient value consisting of a 7x1 matrix, S represents a matrix vector for Nx1 subjective evaluation, and N represents the number of frames. 15. The method of claim 14,
In the step (d), the depth values of each pixel per frame are extracted from the depth map of the 2D image, and the depth values of each extracted pixel are divided and stored for each frame. process; (B) generating parallax information using the generated depth map; And generating error coefficient values for depth reversal of processing an object as a background or processing a background as an object by using a depth value for each frame for the 2D image or using information other than the depth information. (C) process of doing;
Dimensional stereoscopic image, the method comprising the steps of: 24. The method of claim 23,
In the step (c), the depth information for each frame is divided into a background part and an object part using a depth value, and the background is converted into an object using information other than depth in the separated background part. A quality analysis method for a 3D stereoscopic image, characterized by detecting a depth reversal to be processed and calculating an error coefficient value. 24. The method of claim 23,
In the step (c), the difference between the previous frame and the current frame of the 2D image is different from the depth. The method of claim 3, wherein the error coefficient value is calculated. 24. The method of claim 23,
In the step (c), an error may be detected using a motion vector with information other than the depth, and a motion vector of a background is set in units of blocks, and the motion vectors are units of blocks. And calculating an error coefficient value when the calculated motion vector value differs from the background motion vector by a predetermined amount as an object, and calculates an error coefficient value. A computer readable medium having recorded thereon a program for executing the quality analysis method of the three-dimensional stereoscopic image according to claim 14.

Images