JP2018093426A - Video recovery system, video recovery method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make it possible to extremely improve efficiency of recovery work for a video film.SOLUTION: A splice linear line detection unit 2 detects a picture Pn including a splice linear line of a series of pictures P1 to PN constituting a moving picture. A similarity calculation unit 3 calculates similarity between a detection picture Pn detected by the splice linear line detection unit 2 and each of pictures Pn-1, Pn+1 prior and posterior to the detection picture Pn. A picture recovery unit 4 extracts a partial picture corresponding to part at which the splice linear line has emerged, from a picture having higher similarity to the detection picture Pn of the prior and posterior pictures Pn-1, Pn+1; and, with the extracted partial picture, replaces a corresponding partial picture in the detection picture Pn to erase the splice linear line included in the detection picture Pn. A moving picture generation unit 7 connects the series of pictures P1 to PN from which the splice linear line has been erased by the picture recovery unit 4 to generate a moving picture.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a video restoration system, a video restoration method, and a program.

  In the multi-channel era, older video content is often viewed on large screens and fine displays. Therefore, digitalization of old video content has been performed. In old movie content, a technique for restoring video such as a technique for restoring the color of an aged film and a noise removal called para-erasing are partially automated (for example, see Patent Document 1).

JP 2011-138035 A

  When old video content is displayed on a large screen and a fine display, particularly noticeable scratches such as splice lines and vertical scratches that are displayed momentarily in the image. However, at present, detection and repair of scratches and the like left on the video film are generally still performed visually and manually.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a video restoration system, a video restoration method, and a program capable of improving the restoration work of a video film at each stage.

In order to achieve the above object, a video restoration system according to the first aspect of the present invention includes:
A video repair system that repairs videos,
Among the series of images constituting the moving image, a splice line detection unit that detects an image including a splice line;
A similarity calculation unit for calculating the similarity between the detection image detected by the splice line detection unit and the images before and after the detection image;
A partial image corresponding to a portion where the splice line appears is extracted from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is a portion of the corresponding detected image. An image restoration unit that replaces the image and erases the splice line included in the detected image;
A moving image generating unit that generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration unit;
Is provided.

In this case, the splice straight line detection unit is
From the series of images, specify the image corresponding to the scene change point,
Detect images that contain splice lines from the identified images.
It is good as well.

In addition, the splice straight line detection unit,
Detect images containing splice lines by Hough transform,
It is good as well.

The image restoration unit
Detecting a horizontal shift amount between the detected image and the image having the higher similarity,
The partial image extracted from the image is shifted by the amount of shift detected in the horizontal direction and replaced with the corresponding partial image of the corresponding detected image.
It is good as well.

The image restoration unit
If there is a blank in the image after replacement, the partial image adjacent to the blank is embedded in the blank to repair the image.
It is good as well.

The image restoration unit
Detecting the amount of horizontal deviation between the detected image and the image with the higher similarity using a phase-only correlation method;
It is good as well.

An image smoothing unit that performs smoothing around the partial image restored by the image restoration unit;
It is good as well.

A vertical flaw detection unit that detects an image including a vertical flaw included in a series of images constituting the video;
The image smoothing unit
Smoothing the image of the peripheral area of the vertical flaw detected by the vertical flaw detection unit,
It is good as well.

The video restoration method according to the second aspect of the present invention is:
A video restoration method for repairing a video,
A computer detects a splice line detection step of detecting an image including a splice line among a series of images constituting the moving image;
A degree-of-similarity calculation step in which the computer calculates the degree of similarity between the detection image detected in the splice line detection step and images before and after the detection image;
The computer extracts a partial image corresponding to a portion where the splice line appears from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is associated with the corresponding detection. An image repairing step of replacing a partial image of the image and erasing the splice line contained in the detected image;
A moving image generating step in which a computer generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration step;
including.

The program according to the third aspect of the present invention is:
The computer that repairs the video
A splice line detection unit for detecting an image including a splice line among a series of images constituting the moving image;
A similarity calculation unit for calculating the similarity between the detection image detected by the splice line detection unit and images before and after the detection image;
A partial image corresponding to a portion where the splice line appears is extracted from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is a portion of the corresponding detected image. An image restoration unit that replaces the image and erases the splice line included in the detected image,
A moving image generating unit that generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration unit;
To function as.

  According to the present invention, it is possible to automatically detect splice lines and vertical flaws remaining on the video film, and to automatically repair the detected splice lines and vertical flaws by erasing them. Thereby, the restoration work of the video film can be made efficient at each stage.

It is a block diagram which shows the structure of the video restoration system which concerns on embodiment of this invention. It is a figure which shows an example of a splice straight line. It is a figure which shows an example of a vertical crack. It is a figure which shows an example of the switching of a scene. FIG. 5A and FIG. 5B are diagrams showing an example of a flow for detecting a splice line using Hough transform. 6A, 6B, and 6C are histograms of image luminance values used to calculate the similarity between images. FIGS. 7A and 7B are schematic diagrams showing the flow of image restoration. It is a schematic diagram which shows the flow which calculates the deviation | shift amount between images. FIG. 9A and FIG. 9B are schematic diagrams illustrating a flow of restoring an image. FIG. 10A, FIG. 10B, and FIG. 10C are schematic diagrams showing the flow of detection of vertical flaws. It is a block diagram which shows the hardware constitutions of the image restoration system of FIG. It is a flowchart of the operation | movement of the video restoration system which concerns on embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The video restoration system according to the present embodiment is an image processing system that repairs scratches that appear on the screen when an old video film is played.

  As shown in FIG. 1, the data storage unit 10 includes a series of images P1, P2, P3, P4, P5,..., Pn (n is a natural number) constituting moving image data obtained by digitizing an old video film. Is remembered. In the present embodiment, this series of images P1 to Pn is a restoration target. Below, each image P1-Pn is also called shot P1-Pn. In the present embodiment, the scratches to be repaired are mainly splice straight lines and vertical scratches.

  The splice line is a line that appears on the screen so as to extend in the horizontal direction. The splice straight line is mainly generated at a portion where the film is cut and joined when the video is edited. In FIG. 2, a splice line S is included in the image Pn. As shown in FIG. 2, the splice line S is generated mainly at the switching of the scene (scene) of the video content, and the generation location is the upper part or the lower part of the image Pn.

  A vertical flaw is a flaw extending in the vertical direction of the screen and appears at an arbitrary location in each image Pn. In FIG. 3, an example of the vertical scratch I is shown. The vertical scratch I appears at random regardless of the switching of the scene of the video content.

  Returning to FIG. 1, the video restoration system 1 includes a splice line detection unit 2, a similarity calculation unit 3, an image restoration unit 4, a vertical flaw detection unit 5, an image smoothing unit 6, and a moving image generation unit 7. .

  The splice line detection unit 2 detects an image Pn (n = 1 to N) including the splice line S among a series of images P1 to PN constituting the moving image.

  More specifically, as shown in FIG. 4, the splice line detection unit 2 first selects an image Pn corresponding to a scene change point Ck (k is a natural number) from a series of images P1 to PN. Identify. Since the splice line S often appears mainly at the scene change of the video content, in the present embodiment, the splice line detection unit 2 detects the scene change point Ck in advance and narrows it down to the image Pn near the point Ck. Then, the splice line S is detected. The splice line detection unit 2 detects the image Pn including the splice line S from the specified images P1 to PN, that is, the images Pn before and after the scene switching time Ck.

  For the detection of the splice line S, for example, Hough transformation can be used. The Hough transform is one of feature extraction methods used in digital image processing, and is a technique for detecting graphics such as straight lines, circles, and ellipses from an image. For example, as shown in FIG. 5A, the position coordinates of each pixel of the image Pn are (x, y). When there is a splice line S in the image Pn, the relational expression of the splice line S is y = ax + b. By performing the Hough transform, the coefficients a and b of the relational expression of the splice line S can be obtained.

  First, the splice line detection unit 2 detects a pixel point having a large luminance change as a candidate point on the splice line S in the image Pn. In FIG. 5A, (x1, y1), (x2, y2), (x3, y3), (x4, y4),... Are detected as candidate points.

  There are an infinite number of straight lines passing through the candidate points (x1, y1), (x2, y2), (x3, y3), (x4, y4),. The splice line detection unit 2 detects, as the splice line S, the line through which the extracted candidate points pass most.

  Here, FIG. 5B shows a plane having the coefficients a and b of the relational expression of the splice line S as coordinate axes. As shown in FIG. 5 (B), the splice line detection unit 2 has candidate points (x1, y1), (x2, y2), (x3, y3), (x4, y4),.・ Vot for points (a, b) that may pass. The coordinates (a1, b1) having the highest score in this vote are determined as the coefficients a, b of the linear expression of the splice line S.

  Returning to FIG. 1, the similarity calculation unit 3 calculates the similarity between the detection image Pn detected by the splice line detection unit 2 and the images Pn−1 and Pn + 1 before and after the detection image Pn. Here, for the detected image Pn and the images Pn-1 and Pn + 1 before and after it, the similarity between the detected image Pn and the previous image Pn-1 and the similarity between the detected image Pn and the subsequent image Pn + 1 are calculated. Is done.

  The similarity of each image Pn is calculated based on the correlation degree of the histogram of the luminance value of each image Pn. For example, as shown in FIGS. 6A, 6B, and 6C, the similarity calculation unit 3 obtains histograms of luminance values of images Pn, Pn−1, and Pn + 1. Further, the similarity calculation unit 3 obtains the correlation between the luminance value histogram of the image Pn and the luminance value histogram of the image Pn−1, and calculates the correlation between the luminance value histogram of the image Pn and the luminance value histogram of the image Pn + 1. Ask. One of the images Pn + 1 and Pn−1 having a high correlation value in the luminance value histogram is an image having a high similarity.

  Returning to FIG. 1, as shown in FIG. 7A, the image restoration unit 4 selects an image P ′ having a higher degree of similarity among the previous and subsequent images Pn−1 and Pn + 1. Further, as shown in FIG. 7B, the image restoration unit 4 extracts a partial image PI ′ corresponding to the portion where the splice line S appears from the image P ′ having the higher similarity. Further, the image restoration unit 4 replaces the extracted partial image PI ′ with the corresponding partial image PI of the detected image Pn, and deletes the splice line S included in the detected image Pn.

  Note that the splice line S appears in an area near the upper end or near the lower end of each image Pn, and the generated area generally appears in a certain range from the upper end or the lower end. Therefore, the partial images PI and PI ′ can be a fixed-size image region at the upper end or the lower end of each image Pn. For this reason, it is only necessary to detect whether the position of the splice line S appears on the upper side or the lower side of the image.

  Further, as shown in FIG. 8, the image restoration unit 4 detects the amount of horizontal deviation between the detected image Pn and the image P ′ having a higher similarity. Then, the image restoration unit 4 shifts the partial image PI ′ extracted from the image P ′ by the amount of displacement detected in the horizontal direction and replaces it with the corresponding partial image PI of the detected image Pn. In the present embodiment, a phase only correlation method (POC) is used to detect the shift amount. The phase only correlation method is a method of estimating how much the two images are deviated, that is, the shift amount of the image using the phase image of each image. This method focuses on the phases of two images, correlates those phases, and measures the “similarity” between the images.

  In the phase only correlation method, the image restoration unit 4 first performs Fourier transform on the image Pn and the image P ′, respectively, as shown in FIG. 8 to obtain respective spectral components Fa and Fb. Then, the image restoration unit 4 normalizes the spectral components Fa and Fb by dividing them by the amplitude spectrum, and obtains the phase limited image Fab by performing inverse Fourier transform. In the phase only image Fab, points are formed at the position coordinates (Δx, Δy). The position coordinates (Δx, Δy) of this point indicate the amount of deviation between the image Pn and the image P ′ in the x-axis direction and the y-axis direction.

  The image restoration unit 4 shifts the partial image PI ′ by Δx in the x-axis direction and embeds it in the image Pn. In this case, a blank portion Q is generated as shown in FIG. When there is a blank portion Q in the replaced image Pn ′, the image restoration unit 4 embeds a partial image RI adjacent to the blank portion Q of the image P ′ in the blank portion Q as shown in FIG. Then repair the image. FIG. 9A shows a case where Δx is positive, but Δx may be negative and the partial image PI ′ may be shifted leftward.

  Returning to FIG. 1, the vertical flaw detection unit 5 detects a vertical flaw I included in the series of images P <b> 1 to PN. Specifically, as shown in FIG. 10A, the vertical flaw detection unit 5 detects a change in luminance of pixels in the horizontal direction in each image Pn, and detects an edge portion where the luminance changes rapidly. A portion where the edge portions are connected in the vertical direction is detected as a vertical flaw I.

  Returning to FIG. 1, the image smoothing unit 6 smooths the peripheral region of the partial image PI of the image Pn restored by the image restoration unit 4 or the periphery of the vertical scratch I of the image Pn detected by the vertical scratch detection unit 5. Smooth the area. A median filter is used for smoothing the image. The median filter performs a filter process in which the sizes of the peripheral luminance values are arranged in order, and the median (median value) is replaced with the pixel of interest.

  By using this median filter, the image smoothing unit 6 can remove noise included in the image Pn. For example, as shown in FIG. 10B, it is assumed that the luminance value of the surrounding pixels is 10, 15, 41, 30, 34, 60, 180, 130 for the target pixel having a pixel value of 100. When the luminance values of these nine pixels are rearranged in order, they become 10, 15, 30, 34, 41, 60, 100, 130, and 180, respectively. In this case, the image smoothing unit 6 sets the value of the center target pixel to an intermediate value of 41. This is a smoothing process using a median filter.

  As shown in FIG. 10C, the image smoothing unit 6 applies a median filter to the region IA around the vertical scratch I. Thereby, the vertical scratch I is erased. The image smoothing unit 6 applies a median filter to the periphery of the boundary between the image Pn and the partial image PI ′ shown in FIG. 9B.

  Returning to FIG. 1, the moving image generating unit 7 connects the series of images P <b> 1 to PN from which the splice line S and the vertical flaw I are deleted to generate a moving image.

  FIG. 11 shows a hardware configuration of the video restoration system 1 of FIG. As shown in FIG. 11, the video restoration system 1 includes a control unit 31, a main storage unit 32, an external storage unit 33, an operation unit 34, and a display unit 35. The main storage unit 32, the external storage unit 33, the operation unit 34, and the display unit 35 are all connected to the control unit 31 through the internal bus 30.

  The control unit 31 includes a CPU (Central Processing Unit) and the like. The CPU executes the program 39 stored in the external storage unit 33, thereby realizing each component of the video restoration system 1 shown in FIG.

  The main storage unit 32 is composed of a RAM (Random-Access Memory) or the like. The main storage unit 32 is loaded with a program 39 stored in the external storage unit 33. In addition, the main storage unit 32 is used as a work area (temporary data storage area) of the control unit 31.

  The external storage unit 33 includes a nonvolatile memory such as a flash memory, a hard disk, a DVD-RAM (Digital Versatile Disc Random-Access Memory), and a DVD-RW (Digital Versatile Disc ReWritable). In the external storage unit 33, a program 39 to be executed by the control unit 31 is stored in advance. Further, the external storage unit 33 supplies data used when executing the program 39 to the control unit 31 in accordance with an instruction from the control unit 31, and stores the data supplied from the control unit 31.

  The operation unit 34 includes a pointing device such as a keyboard and a mouse, and an interface device that connects the keyboard and the pointing device to the internal bus 30. Information regarding the content operated by the operator is input to the control unit 31 via the operation unit 34.

  The display unit 35 includes a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), an organic EL (ElectroLuminescence), or the like. When the operator inputs operation information, an operation screen is displayed on the display unit 35.

  Note that, by executing the program 39 of the control unit 31, the splice line detection unit 2, the similarity calculation unit 3, the image restoration unit 4, the vertical flaw detection unit 5, and the image smoothing in the configuration of the video restoration system 1 shown in FIG. The unit 6 and the moving image generation unit 7 correspond to the control unit 31 and the main storage unit 32, and the data storage unit 10 corresponds to the external storage unit 33.

  Next, the operation of the video restoration system 1 will be described.

  First, processing related to the repair of the splice line S will be described. As shown in FIG. 12, first, the splice line detection unit 2 detects a scene switching time Ck of the video content (step S1). As a result, as shown in FIG. 4, the scene change point Ck of the video content is detected.

  Subsequently, the splice line detection unit 2 performs Hough conversion on the splice line S included in the image Pn at the scene switching time Ck of the video content as shown in FIGS. 5 (A) and 5 (B). It detects (step S2; splice straight line detection process).

  Subsequently, the splice line detection unit 2 determines whether or not there is a splice line S (step S3). When there is no splice line S (step S3; No), the video restoration system 1 ends the process related to the splice line S. On the other hand, when there is a splice line S (step S3; Yes), the similarity calculation unit 3 performs the image Pn and the front and back of the image Pn as shown in FIGS. 6 (A), 6 (B), and 6 (C). The similarity between the images Pn−1 and Pn + 1 is compared, and an image with high similarity is selected (step S4; similarity calculation step).

  Subsequently, the similarity calculation unit 3 determines whether or not there is a deviation from an image with high similarity (step S5). When there is no deviation from the image having high similarity (step S5; No), the image restoration unit 4 performs splicing in the image Pn as shown in FIGS. 7A, 7B, and 7C. Image restoration is performed by replacing the partial image PI in which the straight line S exists with the corresponding partial image PI ′ of the image P ′ having high similarity (step S6; image restoration process).

  On the other hand, when there is a deviation from the image P ′ having high similarity (step S5; Yes), the image restoration unit 4 calculates the shift amount Δx using the phase limit estimation method as shown in FIG. (Step S7). Subsequently, as shown in FIG. 9A, the image restoration unit 4 shifts by the shift amount Δx and replaces the partial image PI ′ of the image P ′ with the partial image PI of the image Pn (step S8). Subsequently, as shown in FIG. 9B, the image restoration unit 4 embeds the adjacent partial image RI of the image P ′ in the blank portion Q of the image Pn, and performs image filling (step S9). This is because the adjacent partial image RI is most approximated as the blank portion Q.

  Subsequently, the image smoothing unit 6 smoothes the repaired image using a median filter (step S10). Subsequently, the moving image generating unit 7 generates a moving image including the image repaired so far (step S14; moving image generating step).

  Next, processing related to repairing vertical scratches will be described. First, the vertical flaw detection unit 5 detects a vertical flaw (step S12). Subsequently, the vertical flaw detection unit 5 determines whether or not there is a vertical flaw I as shown in FIG. 10A (step S13). When there is no vertical flaw I (step S13; No), the moving image generating unit 7 generates a moving image (step S14; moving image generating step), and ends the process. On the other hand, when there is a vertical flaw I (step S13; Yes), the image smoothing unit 6 smoothes a portion having a vertical flaw (step S10). Thereafter, the moving image generating unit 7 generates a moving image with the image from which the vertical scratch has been removed (step S14; moving image generating step).

  As described in detail above, according to the present embodiment, the splice line S and the vertical flaw I remaining in the moving image of the video film can be automatically detected and automatically repaired. Thereby, the restoration work of the video film can be made efficient at each stage.

  In the embodiment described above, the scene switching time Ck of the video content is detected, and the splice line S is detected for the image at the time Ck. In this way, since the image Pn for detecting the splice line S can be narrowed down, the time required for detection can be shortened. However, the present invention is not limited to this. The splice line S may be detected for all images Pn.

  In the above embodiment, the horizontal shift amount of the preceding and following images Pn based on the motion of the object in the moving image is detected, and the partial image PI ′ is displaced and replaced according to the shift amount Δx. Thereby, it is possible to restore the image without deviation.

  Then, in the blank portion Q generated by replacing the partial image PI ′ by shifting, as shown in FIGS. 9A and 9B, a partial image RI adjacent to the portion is embedded. Thereby, natural image restoration without a sense of incongruity becomes possible.

  In addition, according to the above-described embodiment, since the periphery of the replacement portion of the partial image PI ′ is smoothed as described above, it is possible to perform image restoration without discomfort while replacing a part of the image Pn. .

  Further, according to the above-described embodiment, the vertical flaw I generated on the screen when reproduced on an old video film is detected, and the vertical flaw I is automatically corrected. Thereby, the restoration work of the video film can be made efficient at each stage.

  In the above embodiment, the Hough transform is used for detecting the splice line S, the phase-only correlation method is used for motion detection (shift amount detection) of the partial image, and the median filter or the like is used for image smoothing. The present invention is not limited to this. If these methods are other methods and the splice line S can be detected, the motion of the partial image (shift amount detection), and the smoothing of the image can be applied, the method can be applied.

  In addition, the hardware configuration and software configuration of the video restoration system 1 are merely examples, and can be arbitrarily changed and modified.

  The central part that performs processing of the video restoration system 1 including the control unit 31, the main storage unit 32, the external storage unit 33, the operation unit 34, the display unit 35, the internal bus 30, and the like is independent of the dedicated system. It can be realized using a normal computer system. For example, a computer program for executing the above operation is stored in a computer-readable recording medium (flexible disk, CD-ROM, DVD-ROM, etc.) and distributed, and the computer program is installed in the computer. Thus, the video restoration system 1 that executes the above-described processing may be configured. Further, the video restoration system 1 may be configured by storing the computer program in a storage device included in a server device on a communication network such as the Internet and downloading the computer program from a normal computer system.

  When the functions of the video restoration system 1 are realized by sharing of an OS (operating system) and an application program, or by cooperation between the OS and the application program, only the application program portion is stored in a recording medium or a storage device. Also good.

  It is also possible to superimpose a computer program on a carrier wave and distribute it via a communication network. For example, a computer program may be posted on a bulletin board (BBS, Bulletin Board System) on a communication network, and the computer program distributed via the network. The computer program may be started and executed in the same manner as other application programs under the control of the OS, so that the above-described processing may be executed.

  Various embodiments and modifications can be made to the present invention without departing from the broad spirit and scope of the present invention. The above-described embodiments are for explaining the present invention and do not limit the scope of the present invention. In other words, the scope of the present invention is shown not by the embodiments but by the claims. Various modifications within the scope of the claims and within the scope of the equivalent invention are considered to be within the scope of the present invention.

  The present invention can be applied to the restoration of film moving images.

  1 image restoration system, 2 splice line detection unit, 3 similarity calculation unit, 4 image restoration unit, 5 vertical flaw detection unit, 6 image smoothing unit, 7 moving image generation unit, 10 data storage unit, 30 internal bus, 31 control Part, 32 main storage part, 33 external storage part, 34 operation part, 35 display part, 39 program

Claims (10)

A video repair system that repairs videos,
Among the series of images constituting the moving image, a splice line detection unit that detects an image including a splice line;
A similarity calculation unit for calculating the similarity between the detection image detected by the splice line detection unit and the images before and after the detection image;
A partial image corresponding to a portion where the splice line appears is extracted from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is a portion of the corresponding detected image. An image restoration unit that replaces the image and erases the splice line included in the detected image;
A moving image generating unit that generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration unit;
Video restoration system with The splice straight line detector is
From the series of images, specify the image corresponding to the scene change point,
Detect images that contain splice lines from the identified images.
The video restoration system according to claim 1. The splice straight line detector is
Detect images containing splice lines by Hough transform,
The video restoration system according to claim 2. The image restoration unit
Detecting a horizontal shift amount between the detected image and the image having the higher similarity,
The partial image extracted from the image is shifted by the amount of shift detected in the horizontal direction and replaced with the corresponding partial image of the corresponding detected image.
The video restoration system according to any one of claims 1 to 3, wherein The image restoration unit
If there is a blank in the image after replacement, the partial image adjacent to the blank is embedded in the blank to repair the image.
The video restoration system according to claim 4. The image restoration unit
Detecting the amount of horizontal deviation between the detected image and the image with the higher similarity using a phase-only correlation method;
The image restoration system according to claim 4 or 5. An image smoothing unit that performs smoothing around the partial image restored by the image restoration unit;
The video restoration system according to any one of claims 1 to 6. A vertical flaw detection unit that detects an image including a vertical flaw included in a series of images constituting the video;
The image smoothing unit
Smoothing the image of the peripheral part of the vertical flaw detected by the vertical flaw detection unit,
The video restoration system according to claim 7. A video restoration method for repairing a video,
A computer detects a splice line detection step of detecting an image including a splice line among a series of images constituting the moving image;
A degree-of-similarity calculation step in which the computer calculates the degree of similarity between the detection image detected in the splice line detection step and images before and after the detection image;
The computer extracts a partial image corresponding to a portion where the splice line appears from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is associated with the corresponding detection. An image repairing step of replacing a partial image of the image and erasing the splice line contained in the detected image;
A moving image generating step in which a computer generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration step;
Video restoration method including The computer that repairs the video
A splice line detection unit for detecting an image including a splice line among a series of images constituting the moving image;
A similarity calculation unit for calculating the similarity between the detection image detected by the splice line detection unit and images before and after the detection image;
A partial image corresponding to a portion where the splice line appears is extracted from an image having a higher similarity to the detected image among the preceding and succeeding images, and the extracted partial image is a portion of the corresponding detected image. An image restoration unit that replaces the image and erases the splice line included in the detected image,
A moving image generating unit that generates a moving image by connecting a series of images from which the splice line has been deleted in the image restoration unit;
Program to function as.

Images