KR101024384B1 - Method and system for video quality measurement - Google Patents

Abstract

Disclosed are a video quality evaluation method and system. According to an aspect of the present invention, there is provided a video quality evaluation method comprising: generating an encoded video by encoding an original video; Generating a decoded video by decoding the encoded video by a decoding method corresponding to the encoding method; Extracting a matching feature to be used for matching for image quality evaluation from the decoded video; Extracting an image quality evaluation feature to be used for image quality evaluation from the original image; And encoding the encoded video, the matching feature, and the image quality evaluation feature through a network. According to the present invention, matching of the original video and the transmitted video for image quality evaluation can be performed more quickly and accurately.

Video quality evaluation, matching

Description

Method and system for video quality measurement {Method and system for video quality measurement}

The present invention relates to a video quality estimation method and system, and more particularly, to a video quality estimation method and system that can more quickly and accurately match the original image and the transmitted video for image quality evaluation.

In verifying the performance of video codecs and developing new compression techniques, it is very important to evaluate the quality of video. In addition, when multimedia data is transmitted using a communication network such as IPTV, quality deterioration may occur and monitoring of the data is emerging as an important problem.

In general, quality evaluation of a video is subjectively performed by evaluators who evaluate the quality of the video. Such an evaluation method reflects human perception, and there is a problem that a large number of evaluators are required for evaluation and are inefficient in terms of time and cost.

In order to solve this problem, the present applicant has filed an "image quality evaluation apparatus and method" (Registration No. 0525467). The patent evaluates the video quality by using the pixel value difference of the outline region between the source video sequence image and the evaluation target video sequence image, thereby shortening the evaluation time and performing the evaluation in real time.

In a process of encoding and decoding by a codec and a transmission process, an original image may be displaced in space and time (spatial and temporal shift). In particular, during video encoding and transmission of video data through a transmission medium, a movement (Δx), a movement (Δy) on the y axis, and a movement (Δt) on the time axis of the frame may occur. In addition, the same frame may appear repeatedly or some frames may be lost. In particular, when transmitting at a low bit rate, the encoder may reduce the number of frames per second and then encode the same, and thus the same frame may be periodically repeated on the receiving side. In addition, a still frame may occur due to a transmission error.

Spatio-temporal registration refers to precisely matching an image to a location where the deformation is minimized by detecting such deformation, and need to be registered along the time axis as well as spatial registration. . Especially, in the objective image quality evaluation, the quality evaluation result shows a big difference depending on whether or not the image is matched. Since the quality evaluation value is obtained from the difference between the processed image and the original image, matching between the two images is essential.

The technical problem to be achieved by the present invention is to provide a video quality evaluation system and method that can more quickly and accurately match the original image and the transmitted video for image quality evaluation.

In order to solve the above technical problem, according to the present invention, a video transmission apparatus for enabling an image quality evaluation in a video receiving apparatus includes: a first encoder for encoding a moving image to be transmitted to the video receiving apparatus to generate an encoded video; A decoder configured to decode the encoded video by using a decoding method corresponding to an encoding method of the first encoder, to generate a decoded video; A matching feature extracting unit for extracting matching features to be used for matching for image quality evaluation from the decoded video; An image quality evaluation feature extracting unit for extracting an image quality evaluation feature to be used for image quality evaluation from the original image; And a second encoder which encodes the image quality evaluation feature and the matching feature.

The matching feature extracting unit may include: a boundary area detecting unit detecting a boundary area from the decoded video; And a pixel selector for extracting pixel values and position information of the detected pixel of the boundary area as the matching feature.

The matching feature extracting unit may include a random number generating unit generating a random number within a range of pixel position values defined in the decoded video; And a pixel selector configured to extract pixel values and random number generation seed values of pixels selected according to the generated random number as the matching feature.

Alternatively, the matching feature extractor may extract the sum of pixel values or the sum of squares of pixel values in each frame of the decoded video as the matching feature.

Alternatively, the matching feature extracting unit may generate a random number within a range of pixel position values defined in the decoded video, and may include a sum of pixel values or sums of squares of pixel values of pixels selected according to the generated random number. The seed value for random number generation may be extracted as the matching feature.

Alternatively, the matching feature extractor may select pixels belonging to an arbitrary area within the frame of the decoded video and extract the matching feature by using pixel values of the selected pixels. In this case, an average of pixel values of the selected pixels, a sum of pixel values, or a sum of squares of pixel values may be extracted as the matching feature.

Alternatively, the matching feature extracting unit may extract the matching feature by using a difference in pixel values at each pixel between adjacent frames of the decoded video. In this case, the sum of the difference of pixel values in each pixel between the adjacent frames may be extracted as the matching feature.

In order to solve the above technical problem, the video quality evaluation system according to the present invention generates an encoded video by encoding an original video, and decodes the encoded video by a decoding method corresponding to the encoding method. After generating, extracting and encoding matching features to be used for matching from the decoded video, encoding and extracting the quality evaluation features to be used for image quality evaluation from the original image, and encoding the image quality evaluation. A video transmission device for transmitting a video feature and the encoded matching feature through a network; And a video receiving apparatus for matching the video received from the video transmitting apparatus through the network using the matching feature and performing image quality evaluation on the matched video using the quality evaluation feature. It is done.

In order to solve the above technical problem, the video quality evaluation system according to the present invention generates a coded video by encoding a moving picture in a video transmission apparatus, and decodes the coded video by decoding the decoding method corresponding to the coding method. After the video is generated, the video received through the network is matched using the matching feature extracted for matching for quality evaluation from the decoded video, and the quality evaluation is performed using the quality evaluation feature for the matched video. Characterized in that it comprises a video receiving device to perform.

According to an aspect of the present invention, there is provided a video quality evaluation method comprising: (a) generating an encoded video by encoding a moving image; (b) generating a decoded video by decoding the encoded video by a decoding method corresponding to the encoding method in step (a); (c) extracting matching features to be used for matching for image quality evaluation from the decoded video; (d) extracting an image quality evaluation feature to be used for image quality evaluation from the original image; And (e) encoding the encoded video, the matching feature, and the image quality evaluation feature and transmitting the encoded video over a network.

Here, in step (c), a boundary region may be detected from the decoded video, and pixel values and position information of pixels of the detected boundary region may be extracted as the matching feature.

Alternatively, the step (c) may generate a random number within a range of pixel position values defined in the decoded video, and match the pixel value and the random number generation seed value of the pixels selected according to the generated random number. Can be extracted as a feature.

Alternatively, in the step (c), the sum of the pixel values or the sum of the squares of the pixel values in each frame of the decoded video may be extracted as the matching feature.

Alternatively, the step (c) may generate a random number within a range of pixel position values defined in the decoded video, and add the sum of the pixel values of the pixels selected according to the generated random number or the sum of the squares of the pixel values. The seed value for random number generation may be extracted as the matching feature.

Alternatively, step (c) may select pixels belonging to an arbitrary region within the frame of the decoded video, and extract the matching feature using pixel values of the selected pixels. In this case, an average of pixel values of the selected pixels, a sum of pixel values, or a sum of squares of pixel values may be extracted as the matching feature.

Alternatively, in the step (c), the matching feature may be extracted by using a difference of pixel values in each pixel between adjacent frames of the decoded video. At this time. The sum of differences of pixel values in each pixel between the adjacent frames may be extracted as the matching feature.

In order to solve the above technical problem, the video quality estimation method according to the present invention comprises: (a) generating a video encoded by encoding a moving image in a video transmission apparatus and decoding the encoded video by a decoding method corresponding to the encoding method. Generating a decoded video and matching the video received through the network using the matching feature extracted for matching for image quality evaluation from the decoded video; And (b) performing image quality evaluation on the matched video using the image quality evaluation feature.

According to the present invention described above, it is possible to more quickly and accurately match the original video and the transmitted video for image quality evaluation.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, and redundant description will be omitted. In addition, in the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

In general, space-time matching requires a lot of operations, and when the original image is encoded, all pixel values are converted to cause a matching error in space-time. In order to solve such a problem, the present invention decodes compressed video data (encoded video) at the transmitting side, extracts a matching feature to be used for matching for image quality evaluation from the decoded video data, and then at the receiving side, the matching feature. Space-time matching is performed using.

1 illustrates a configuration of a video quality evaluation system according to an embodiment of the present invention. The moving picture quality evaluation system according to the present embodiment is a moving picture transmitting device 100 which is a main body for transmitting a moving picture, and a moving picture which is a client receiving a moving picture transmitted by the moving picture transmitting device 100 via a predetermined network 10. It includes a receiver 200. At this time, the network 10 includes both wireless and wired communication networks. In addition, the video receiving apparatus 200 may be a user's mobile communication terminal. Hereinafter, a moving picture to be transmitted is referred to as a 'moving picture', a moving picture encoding the moving picture is referred to as 'compressed moving picture data', and a decoded compressed moving picture data at the receiving device is referred to as a 'receiving picture.' An error may occur in the compressed video data during the transmission process. In this case, the received video may include deterioration due to a transmission error. In the present invention, a frame unit is assumed and described. However, in the case of an interlaced signal, it may be applied in a field unit.

The video transmission apparatus 100 generates compressed video data by encoding an original video, and decodes the compressed video data by a decoding method corresponding to an encoding method to generate a decoded video, and then evaluates the image quality from the decoded video. Matching feature data is generated by extracting and encoding matching features to be used for matching, and image quality evaluation data is generated by extracting and encoding quality evaluation features to be used for image quality evaluation from the original image, and compressed video data and matching features. Data and image quality evaluation data are transmitted via the network 10. At this time, the information on the space-time position of the matching feature and the space-time position of the feature for image quality evaluation must also be transmitted. This can easily be done using a frame or field index. For example, a matching feature and an image quality evaluation feature may be extracted from one frame or field, and then encoded and transmitted together to inform a receiver that they have been extracted from the same frame or field.

The video receiving apparatus 200 decodes the compressed video data, the image quality evaluation data, and the matching feature data received through the network 10, respectively, and uses the matching feature obtained by decoding the matched feature data in time and space. After matching, the image quality evaluation of the received video is performed using the image quality evaluation feature obtained as a result of decoding the image quality evaluation data. In this case, the image quality evaluation method may use boundary area pixels as described in Korean Patent No. 0525467. That is, a predetermined number of pixels are selected in the boundary region for image quality evaluation, and the pixel values and position information are encoded and transmitted to the receiving side. The receiving side can decode this to obtain the sum of the squared errors with the received video pixels corresponding to the pixel of the boundary region, divide it by the total number of pixels of the boundary region to obtain the mean squared error per pixel, and use it to calculate the image quality index.

2 shows a configuration of a video transmission apparatus according to an embodiment of the present invention.

Referring to FIG. 2, the video transmission apparatus 100 according to the present embodiment encodes a moving image input from an image input unit 110 and an image input unit 110 for inputting a moving image (source video). Image quality from the video decoded by the first encoder 120 to output the decoded data, and a decoder 130 to decode the compressed video data using a decoding method corresponding to the encoding method of the first encoder 120. Matching feature extraction unit 140 for extracting matching features to be used for matching for evaluation, picture quality evaluation feature extraction unit 150 for extracting features for picture quality evaluation to be used for picture quality evaluation from a moving image, matching feature A second encoding unit 160 which encodes the matching features from the extraction unit 140 and the quality evaluation features from the image quality evaluation feature extraction unit 150, respectively, and outputs the matching feature data and the image quality evaluation data, and compression. It comprises a communication unit 170 for transmitting the video data and the matching feature data and image quality evaluation data over a network (10). Here, the second encoder 160 internally encodes an encoding unit for encoding a matching feature from the matching feature extraction unit 140 and an image quality evaluation feature from the image quality evaluation feature extraction unit 150. It can be configured separately.

The image input unit 110 may be an input device that receives a video from an external device or a predetermined storage device in which an image is stored in advance. In addition, the original video may be provided by being encoded by the content provider.

It is also possible to use a special coding technique because no error should occur in the transmission of the image quality evaluation data used for image quality evaluation and the matched characteristic data used for matching. In addition, it is desirable to avoid an error occurring simultaneously in the encoded compressed video data, the matched feature data and the image quality evaluation data. Therefore, the compressed video data, the matched feature data and the image quality evaluation data are preferably transmitted using different channels. For example, compressed video data, matching feature data, and image quality evaluation data may be transmitted using different packets, or may be transmitted with a time difference.

3 shows a configuration of a video receiving apparatus according to an embodiment of the present invention.

Referring to FIG. 3, the video receiving apparatus 200 according to the present embodiment may include a first decoder 210 for decoding compressed video data received through a network, and matched feature data and image quality evaluation data received through a network. A second decoding unit 220 decoding each, a matching unit 230 matching the received video in space-time using the matching feature decoded by the second decoding unit 220, and a received video matched in space-time And a picture quality evaluator 240 which performs picture quality evaluation by using the picture quality evaluation feature decoded by the decoder 220. The second decoder 220 may be divided into a decoder that decodes the matched feature data internally and a decoder that decodes the image quality evaluation data.

In one embodiment, the matching feature extractor 140 may select a plurality of pixels in the frame and extract pixel values and position information of the selected pixels as the matching feature. In this case, the matching in space-time performed by the matching unit 230 may be modeled as follows.

O (t + Δt, x + Δx, y + Δy) = I (t, x, y)

I (t, x, y) is the pixel value at the pixel at the (x, y) point of the t-th frame of the original image, and O (t, x, y) is the (x, y) of the t-th frame of the received video. The pixel value in the pixel at the point, Δx represents the movement on the spatial coordinate x-axis, Δy represents the movement on the spatial coordinate y-axis, and Δt represents the movement on the time axis. Where x is the horizontal axis of the frame and y is the vertical axis. In space-time matching, the values of Δx, Δy, and Δt that change Δx, Δy, and Δt within given limits and minimize the following mean square error are obtained as the result of the match in space-time (movement in the x, y, t axis). Can be.

Where N is the number of matching pixels and j is the index of each selected pixel.

Figure 4 is a configuration showing an embodiment of the matching feature extraction unit 140. The matching feature extractor 140 according to the present exemplary embodiment includes a boundary region detector 410 that detects a boundary region from a video from the decoder 130, and pixel values and position information of pixels of the detected boundary region. And a boundary area pixel selector 420 to be extracted.

The matching feature extractor 140 according to the present exemplary embodiment extracts pixel values and position information of a plurality of pixels in a frame. In addition, the feature extraction unit 150 for image quality evaluation can also extract pixel values and position information of pixels to be used for image quality evaluation from the boundary region of the original image. It may have the same configuration and operation. However, the technique of selecting the image quality evaluation feature to be used for the image quality evaluation by the feature extraction unit 150 for image quality evaluation may be applied in various ways in addition to the present embodiment.

5A is a diagram illustrating an example of detecting a boundary region from a moving image.

In the present embodiment, an edge detection algorithm is applied to a video to detect a boundary area. As an edge detection algorithm, one of the conventionally proposed algorithms may be used. For example, a gradient operator may be used.

The boundary area detector 410 generates a vertical gradient image and a horizontal gradient image by using a vertical gradient operator and a horizontal gradient operator, respectively. An absolute value is calculated on the generated vertical and horizontal gradient images to generate vertical and horizontal gradient images. A threshold area is generated by applying a threshold operation to the vertical and horizontal gradient images to extract a pixel value having a predetermined value or more. Since a method of extracting the boundary region pixel by detecting the boundary region is described in detail in Korean Patent No. 0525467, a detailed description thereof will be omitted.

5B is a diagram illustrating an example of selecting a predetermined number of pixels from the detected boundary region.

The boundary area pixel selector 420 selects a boundary area pixel from the detected boundary area, but performs the data within a limit allowed by a given bit rate. This corresponds to both the matching feature and the image quality evaluation feature. There are several ways to select pixels in the boundary area. For example, a gradient image is obtained by applying a gradient operator to a frame, and the video pixels corresponding to the pixel values are sequentially selected based on the pixel value of the gradient image. Can be. If ten boundary region pixels are selected per frame, first, ten pixels having the highest pixel value of the frame gradient image are searched, and video pixels corresponding thereto are selected as the boundary region pixels. As another example, there is a method of randomly extracting from video pixels corresponding to a pixel whose pixel value of the gradient image is greater than or equal to a threshold. For example, a random selection may be made among video pixels corresponding to pixels corresponding to the top 10% based on the size of the pixel value of the gradient image. In addition, pixels existing at the same position as the pixel selected in the previous frame may be excluded from the selection. In general, the border area pixels may be selected to maintain a certain number of possible frames. A method for obtaining a gradient image and a method for extracting boundary region pixels are described in detail in Korean Patent No. 0525467.

FIG. 5C illustrates an example in which the matching unit 230 matches the received video in space-time using boundary area pixels. In order to find the decoded video frame corresponding to one frame of the received video, the frame of the decoded video is searched within the given time axis range using the matching feature. In this case, since the information on the decoded video frame exists only several boundary region pixels of the matched feature data, the difference between the frames is calculated using only the received video frame pixels corresponding to the decoded video frame boundary region pixels. That is, the mean square error of the decoded video p th frame and the received video q th frame may be calculated as follows.

Where E _{DEC_p} (i) is a boundary pixel of the decoded video pth frame, E _{PVS_q_DEC_p} (i) is a pixel corresponding to the boundary area pixel of the video p-th frame decoded in the qth frame, and N _{DEC _p} is decoded. The number of pixels in the boundary region of the p-th frame of the video.

6 is a diagram illustrating another example of the matching feature extractor 140. The matching feature extractor 140 according to the present embodiment randomly selects a plurality of pixels within a frame and selects the selected pixels. Extract with matching features. To this end, the matching feature extractor 140 according to the present embodiment selects a random number generator 610 that generates a random number within a range of pixel position values defined in the decoded video data, and selects a pixel according to the generated random number. And a pixel selector 620 for extracting pixel values of the selected pixels. In this case, the same random number generating unit may be provided on the receiving side, and a seed value for generating random numbers may be transmitted from the video transmitting apparatus 100 to the video receiving apparatus 200 as a matching feature. The video receiving apparatus 200 may generate a random number based on the seed value to determine the position of the extracted pixel.

In one embodiment, especially for time axis matching, the matching feature extractor 140 may extract the sum of the pixel values or the sum of the squares of the pixel values in each frame as the matching feature. That is, for each frame of the decoded video, the sum sumx of the pixel values and the sum sumxx of the squares of the pixel values are calculated as in the following equation.

FIG. 7 illustrates a configuration of a matching feature extractor 140 according to an exemplary embodiment, and includes a sum of squares of pixel values and a pixel sum calculator 710 that calculates a sum of pixel values for each frame of a decoded video. And a pixel sum sum calculating unit 720 for calculating. In the present exemplary embodiment, the matching feature extractor 140 may include only one of the pixel sum calculator 710 and the pixel sum calculator 720.

In general, in the case of different frames, the sum of pixel values and the sum of squares of the pixel values have different values. Therefore, sumx or sumxx may be transmitted to the receiver along with the frame index, and the receiver may change Δt within a given limit and obtain a Δt value in which the sumx or sumxx coincides or minimizes the difference as a result of matching in time. In addition, a function indicating a characteristic of a frame may be calculated using pixel values, and the matching may be performed on a time axis by comparing the difference for each frame.

The sum of the pixel values or the sum of the squares of the pixel values may be calculated for all the pixels of each frame of the decoded video, and a random number of pixels may be arbitrarily selected and then the sum of the pixel values or the pixel values of the selected pixels. You can also sum the squares. As illustrated in FIG. 8, the matching feature extractor 140 according to the present embodiment may include a random number generator 810 for generating a random number within a range of pixel position values defined in the decoded video and a random number generated. And a pixel sum calculator 820 for calculating a sum of pixel values with respect to the pixels selected according to the selected pixel, and a pixel square sum calculator 820 for calculating a sum of squares of pixel values. In the present exemplary embodiment, the matching feature extractor 140 may include only one of the pixel sum calculator 810 and the pixel sum calculator 820. In this case, the same random number generating unit may be provided on the receiving side, and a seed value for generating random numbers may be transmitted from the video transmitting apparatus 100 to the video receiving apparatus 200 as a matching feature. The video receiving apparatus 200 may generate a random number based on the seed value to determine the position of the extracted pixel.

In one embodiment, the matching feature extractor 140 may select pixels belonging to an arbitrary area within the frame of the decoded video data and extract the matching feature using pixel values of the selected pixels. For example, as illustrated in FIG. 9, a block having a specific pattern is defined in each frame, and an average of pixel values, sum of pixel values, or sum of squares of pixel values of pixels included in the block is calculated. It can be used as matching feature with area information.

In an embodiment, when the time axis matching is also aimed at, the matching feature extractor 140 may calculate a pixel value difference in each pixel between adjacent frames to extract the matching feature. For example, the sum FD _j of the pixel value difference from the (j-1) th frame, which is the previous frame, is calculated for the _j th frame and used as a matching feature.

는 j 번째 프레임에서의 화소값을,

는 (j-1) 번째 프레임에서의 화소값을 나타낸다. 이러한 실시예에 따른 정합용 특징추출부(140)는 도 10에 도시된 바와 같이, 복호화부(130)로부터 입력되는 복호화된 동영상을 한 프레임만큼 지연시켜 출력하는 버퍼(1010)와, 복호화부(130)로부터 입력되는 복호화된 동영상의 프레임과 버퍼(1010)로부터의 동영상의 프레임에 대하여 화소값의 차이의 합을 계산하는 프레임 차이 계산부(1020)를 포함하여 이루어진다.here,

Is the pixel value in the j th frame,

Denotes a pixel value in the (j-1) th frame. As shown in FIG. 10, the matching feature extractor 140 according to the present embodiment includes a buffer 1010 for delaying and outputting a decoded video input from the decoder 130 by one frame, and a decoder ( And a frame difference calculator 1020 that calculates a sum of difference of pixel values with respect to the frame of the decoded video inputted from 130 and the frame of the video from the buffer 1010.

The matching feature extracting unit 140 may be implemented by combining the components of the matching feature extracting unit 140 according to the above-described embodiments. For example, by combining the configuration shown in FIG. 4 with the configuration shown in FIG. 7, the matching feature extractor 140 sums or sums the pixel values of each frame together with the pixel value and position information of the boundary area pixel. The sum of squares of values may be extracted as a matching feature.

Meanwhile, the above-described embodiments of the present invention can be written as a program that can be executed in a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. The computer-readable recording medium may be a magnetic storage medium (for example, a ROM, a floppy disk, a hard disk, etc.), an optical reading medium (for example, a CD-ROM, DVD, etc.) and a carrier wave (for example, the Internet). Storage medium).

So far I looked at the center of the preferred embodiment for the present invention. Those skilled in the art will appreciate that the present invention can be implemented in a modified form without departing from the essential features of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the scope will be construed as being included in the present invention.

1 illustrates a configuration of a video quality evaluation system according to an embodiment of the present invention.

2 shows a configuration of a video transmission apparatus according to an embodiment of the present invention.

3 shows a configuration of a video receiving apparatus according to an embodiment of the present invention.

Figure 4 is a configuration showing an embodiment of the matching feature extraction unit 140.

5A is a diagram illustrating an example of detecting a boundary region from a moving image.

5B illustrates an example of selecting a boundary area pixel from the detected boundary area.

FIG. 5C illustrates an example in which the matching unit 230 matches the received video in space-time using boundary area pixels.

6 is a view illustrating another embodiment of the matching feature extraction unit 140.

7 is a configuration illustrating another embodiment of the matching feature extraction unit 140.

8 is a configuration illustrating another embodiment of the matching feature extraction unit 140.

9 shows an example of how a block having a specific pattern is defined in each frame.

10 is a configuration illustrating another embodiment of the matching feature extraction unit 140.

Claims (23)

In the video transmission device to enable the image quality evaluation in the video reception device, A first encoder configured to generate an encoded video by encoding an original video to be transmitted to the video receiving apparatus; A decoder configured to decode the encoded video by using a decoding method corresponding to an encoding method of the first encoder, to generate a decoded video; A matching feature to be used for matching for image quality evaluation from the decoded video, wherein the matching feature includes at least some pixel values or an operation value of the at least some pixel values in the decoded video; Matching feature extraction unit; Image quality evaluation feature to be used for image quality evaluation from the original image, wherein the image quality evaluation feature includes at least some pixel values in the original image or an operation value of the at least some pixel values. Feature extraction unit; And And a second encoder which encodes the image quality evaluation feature and the matching feature. The method of claim 1, The matching feature extraction unit, A boundary region detector for detecting a boundary region from the decoded video; And And a pixel selector for extracting pixel values and position information of the detected boundary region pixels as the matching feature. The method of claim 1, The matching feature extraction unit, A random number generator generating a random number within a range of pixel position values defined in the decoded video; And And a pixel selector configured to extract pixel values and random number generation seed values of pixels selected according to the generated random number as the matching feature. The method of claim 1, The matching feature extraction unit, And a sum of pixel values or sums of squares of pixel values in each frame of the decoded video as the matching feature. The method of claim 1, The matching feature extracting unit generates a random number within a range of pixel position values defined in the decoded video, and generates a sum of pixel values or sums of squares of pixel values and a random number of pixels selected according to the generated random number. And a seed value for extraction as the matching feature. The method of claim 1, And the matching feature extracting unit selects pixels belonging to an arbitrary area within the frame of the decoded video and extracts the matching feature using pixel values of the selected pixels. The method of claim 6, And the matching feature extracting unit extracts an average of pixel values of the selected pixels, a sum of pixel values, or a sum of squares of pixel values as the matching feature. The method of claim 1, And the matching feature extracting unit extracts the matching feature by using a difference in pixel values at each pixel between adjacent frames of the decoded video. The method of claim 8, And the matching feature extraction unit extracts a sum of differences of pixel values in each pixel between the adjacent frames as the matching feature. In the video quality evaluation system, Encodes an original video to generate an encoded video, decodes the encoded video by a decoding method corresponding to the encoding method, generates a decoded video, and then uses it for matching for image quality evaluation from the decoded video Extract and encode a feature, wherein the matching feature includes at least some pixel values in the decoded video or an operation value of the at least some pixel values, and evaluates an image to be used for image quality evaluation from the original image. Extract and encode a feature, wherein the feature for image quality evaluation includes at least some pixel values in the original image or an operation value of the at least some pixel values, and encodes the coded image quality characteristic and the coded match. A video transmission device for transmitting a feature for transmission over a network; And And a video receiving apparatus for matching the video received from the video transmitting apparatus through the network using the matching feature and performing image quality evaluation on the matched video using the quality evaluation feature. Video quality rating system. In the video quality evaluation system, After generating the encoded video by encoding the moving image in the video transmission apparatus and decoding the encoded video by the decoding method corresponding to the encoding method, the video is transmitted to match the image quality evaluation. Match the video received through the network using the extracted matching feature, wherein the matching feature includes at least some pixel values or an operation value of the at least some pixel values in the decoded video. An image receiving apparatus for performing an image quality evaluation using an image quality evaluation feature, wherein the image quality evaluation feature includes at least some pixel values in the original image or an operation value of the at least some pixel values. Video quality evaluation system comprising a. In the video quality evaluation method, (a) encoding an original video to generate an encoded video; (b) generating a decoded video by decoding the encoded video by a decoding method corresponding to the encoding method in step (a); (c) a matching feature to be used for matching from the decoded video for image quality evaluation, wherein the matching feature includes at least some pixel values or an operation value of the at least some pixel values in the decoded video. Extracting the; (d) extracting an image quality feature to be used for image quality evaluation from the original image, wherein the image quality feature includes at least some pixel values in the original image or an operation value of the at least some pixel values. step; And and (e) encoding the encoded video, the matching feature, and the quality evaluation feature and transmitting the encoded video over a network. The method of claim 12, In the step (c), the boundary region is detected from the decoded video, and the pixel value and position information of the pixel of the detected boundary region are extracted as the matching feature. The method of claim 12, In the step (c), the random number is generated within a range of pixel position values defined in the decoded video, and the pixel value and the random number generation seed value of the pixels selected according to the generated random number are matched. Video quality evaluation method characterized in that the extraction. The method of claim 12, In the step (c), the sum of pixel values or sum of squares of pixel values in each frame of the decoded video is extracted as the matching feature. The method of claim 12, In the step (c), the random number is generated within a range of pixel position values defined in the decoded video, and the sum of pixel values or sums of squares of pixel values and random numbers of pixels selected according to the generated random number is generated. And a seed value for extraction as the matching feature. The method of claim 12, In the step (c), the video quality evaluation method of selecting a pixel belonging to an arbitrary region in the frame of the decoded video and extracting the matching feature using the pixel values of the selected pixels. The method of claim 17, In the step (c), the average of pixel values of the selected pixels, a sum of pixel values, or a sum of squares of pixel values are extracted as the matching feature. The method of claim 12, In the step (c), the matching feature is extracted using the difference in pixel values in each pixel between adjacent frames of the decoded video. The method of claim 19, In the step (c), the sum of the difference of pixel values in each pixel between the adjacent frames is extracted as the matching feature. In the video quality evaluation method, (a) the video transmission apparatus generates an encoded video by encoding the original video, decodes the encoded video by a decoding method corresponding to the encoding method, generates a decoded video, and then evaluates the image quality from the decoded video. Match the video received through the network using a matching feature extracted for matching, wherein the matching feature includes at least some pixel values in the decoded video or an operation value of the at least some pixel values. Making; And (b) image quality evaluation of the matched video using the quality evaluation feature, wherein the quality evaluation feature includes at least some pixel values in the original image or an operation value of the at least some pixel values. Video quality evaluation method comprising the step of performing. In the video receiving apparatus for receiving a video transmitted from the video transmitting apparatus, A first decoder to decode a received video according to a decoding method corresponding to a first encoding method in the video transmitting apparatus; Feature for image quality evaluation received according to a decoding scheme corresponding to a second encoding scheme in the video transmission apparatus—The image quality evaluation feature may include at least some pixel values or the at least some pixel values in the original image input to the video transmission apparatus. A second decoder to decode an operation value of the pixel values of? And An image quality evaluation unit configured to perform image quality evaluation on the video decoded by the first decoder by using the image quality evaluation feature decoded by the second decoder; Video receiving apparatus comprising a. The method of claim 22, Matching to match the video decoded by the first decoding unit using a matching feature, wherein the matching feature includes at least some pixel values in the decoded video or an operation value of the at least some pixel values. It further comprises; And the image quality evaluation unit performs image quality evaluation on the matched video using the image quality evaluation feature.

Images