JPH1083033A - Method for printing moving image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a print excellent in image quality from moving image data. SOLUTION: Each of data of an image to be printed in the moving image and reference images obtained one second before and after the image is fetched in a frame memory 28 in a frame unit. The data of the image and the reference images are subjected to local matching processing by a matching processing part 30 to divide the image into a still area and a moving area. Picture element data at the same position as the image and the reference image with respect to the still area is weighted and averaged by a still area weighting-averaging part 31. Then, the moving area is subjected to smoothing processing by using the image data on the object pciture by a moving area smoothing processing part 32. The processed image data in the still area and the moving area are composited by an image compositing part 33. Thus, random noise in the still area is reduced and blur in the moving area is made inconspicuous.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a moving image printing method for specifying an image to be printed from a moving image and printing based on the data.

[0002]

2. Description of the Related Art Moving images recorded by an 8 mm video camera or a video recorder are printed using a video printer or the like. In this case, by operating the freeze key on the scene to be printed while reproducing and confirming the moving image on the monitor, the image data for one frame of the moving image is loaded into the frame memory. Printing is performed based on image data.

[0003]

However, when one frame of image data is extracted from the moving image data and simply printed based on this image data, the image data obtained by another still camera or the like is used. There is a problem that the image quality becomes insufficient due to the low resolution compared to the data and the influence of noise or the like, and a satisfactory print cannot be created. When extracting one frame of image data from moving image data captured by an 8 mm video camera or the like, the shutter speed is usually set lower than that of an electronic still camera or the like. , And if you print as it is,
There is a problem that blurring of a moving image is conspicuous and image quality is reduced.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and provides a moving image printing method in which the overall image quality is not degraded when a print is created from moving image data. With the goal.

[0005]

According to a first aspect of the present invention, there is provided a method for printing a moving image, comprising: a printing target image in the moving image; and n (n is a natural number) frames before the printing target image. Each data of the reference image after n frames is taken into the memory in frame units, and a local matching process is performed on the image data to be printed and the reference image data,
The print target image is divided into a still area and a moving area, and different image quality improvement processing is performed on the still area and the moving area. Also, in addition to dividing into a still area and a moving area, a face candidate area is extracted from the print target image data,
A region where the moving region and the face candidate region overlap each other is determined as a face region, and different image quality improvement processing is performed on the face region, the moving region excluding the face region, and the still region. Good. Further, the face candidate area extraction processing may be performed based on the print target image data in the moving area. In this case, the calculation load of the face candidate area extraction processing is reduced. In the image quality improvement processing for the still area, it is preferable that pixel data at the same position between the print target image and the reference image be weighted and averaged, and the weighted average value be used as image data. In the image quality improvement processing for the moving area, it is preferable to perform a smoothing processing or an enhancement processing using image data of an image to be printed. The image quality improvement processing for the face area is performed by adjusting the print density and color of the entire image based on the image data in the face area of the image to be printed so as to appropriately finish the density and color of the face area, It is preferable to partially adjust only the face area based on the image data in the face area so that the density and the color are appropriately finished.

According to a ninth aspect, there is provided a moving image printing method,
Each data of the print target image in the moving image and the reference image n frames before or after the print target image is fetched into the memory in frame units, and the position of the reference image data is two-dimensionally stored with respect to the print target image data. Local matching processing is performed on the divided areas obtained by dividing each image into a large number, and the divided area of the reference image at the shifted position where the degree of difference is minimized is associated with the divided area of the image to be printed. Based on this association, the motion vector of the divided area of the reference image with respect to the divided area of the image to be printed is obtained over the entire screen, and it is determined whether the moving image capturing or the zooming image capturing is performed based on the motion vector. A corrected motion vector that cancels the motion of is obtained, and the magnitude of the corrected motion vector is within a predetermined value. If so, the divided area of the print target image corresponding to the divided area of the reference image is determined as a still area, the other areas are determined as moving areas, and each divided area in the print target image is determined as a still area and a moving area. Division,
Different image quality improvement processing is performed for a still area and a moving area.

[0007]

The data of the print target image in the moving image and the reference image n frames before or n frames after the print target image are loaded into the frame memory in frame units. Local matching processing is performed on the print target image data and the reference image data. If the image data to be printed matches the reference image data by this local matching process, it is determined that the image is a still area. If they do not match, it is determined to be a moving area. Different image quality improvement processing is performed on the still area and the moving area.

[0008] After dividing into a still area and a moving area, a face candidate area is extracted. The face candidate area is a face candidate area when, for example, pixels having a color and density that specify the flesh color of a person are extracted from the print target image data and these extracted pixels are gathered in a certain area. Alternatively, the face candidate region may be specified by detecting the shape of the internal structure of the face such as the contour of the face, the head, the human body, the eyes, the mouth, and the eyebrows. Then, an area where the moving area and the face candidate area overlap with each other is determined as a face area. Discrimination processing between a stationary area and a moving area,
The face candidate area extraction processing may be performed in parallel or sequentially. When processing is performed sequentially, the face candidate area is extracted based on the print target image data of the moving area, so that the extraction processing target area is limited to the moving area, so that the face area can be efficiently extracted.

Different image quality improvement processing is performed on the face area, the moving area excluding the face area, and the still area. As image quality improvement processing, weighted averaging of pixel data at the same position of the print target image and the reference image is performed in the still area, thereby removing random noise. In addition, the moving area is subjected to a smoothing process using image data of an image to be printed, and blurring an image in the moving area makes blurring of a person or the like inconspicuous. For example, an emphasis process is performed on the face area. Further, the print density and color of the entire image or only the face area are adjusted so that the density and color of the face area are appropriately finished based on the image data in the face area of the print target image.

Further, local matching processing is performed while the positions of the print target image data and the reference image data are shifted two-dimensionally. Then, the block at the shift position where the degree of difference is minimized is associated, and a motion vector is obtained over the entire screen by this association. Based on this motion vector, it is determined whether the camera is moving or zooming. And, based on the result of this
A corrected motion vector for canceling the motion of the entire screen is obtained based on the behavior of the camera. If the magnitude of the corrected motion vector is within a predetermined value, it is determined that the area is a stationary area, and the remaining area is a moving area. Different image quality improvement processing is performed on the still area and the moving area.

[0011]

FIG. 1 is a functional block diagram of a video printer embodying the present invention. The video printer 10 includes an image input unit 11, an image processing unit 12, and a print unit 13.

An image output from, for example, an 8 mm video camera 14 is input to the image input unit 11. Image input unit 11 is Y
/ C separation circuit 16 and a decoder 17. Y /
The C separation circuit 16 separates the NTSC signal from the video camera 14 into a luminance signal (Y) and a chrominance signal (C). The decoder 17 converts the luminance signal (Y) and the chrominance signal (C) into three primary color signals of red (R), green (G), and blue (B).
The signal is sent to the / D converter 18 and the selector 19. The video output is not limited to that of the 8 mm video camera 14, but may be output from a video tape recorder, a television, a personal computer, or the like. The video output is not limited to the NTSC signal, but may be an R, G, B digital signal or the like.

The selector 19 is set on the terminal (a) side in the normal reproduction mode, and is set on the terminal (b) side in the freeze mode. When the selector 19 is set to the terminal (a) side, the image data is
0 is sent to the color monitor 22, and the image being reproduced is displayed on the color monitor 22. By observing the image on the color monitor 22, the image to be printed is specified.
This specification is performed by pressing the freeze button of the keyboard 25. The keyboard 25 is connected to the system controller 26, and various commands are input from the keyboard 25. The system controller 26 is composed of a well-known microcomputer, and controls each part in sequence. A liquid crystal display 27 is connected to the system controller 26 to display various modes and commands. Note that instead of using the liquid crystal display 27, the color monitor 22 is used.
In addition, various modes, commands, and the like may be displayed.

The three-color image data from the decoder 17 is A /
The image is digitized by the D converter 18, and the display image is sent to the frame memory 28 in real time by the system controller 26 while the image is being reproduced. Frame memory 28
Is composed of a print target frame memory and two reference frame memories, and each frame memory stores image data for each of R, G, and B colors.
The reference frame memory stores images one second before and one second after the image to be printed.
The time interval is not limited to seconds before or after one second, and the sampling interval of the reference image from the keyboard 25 can be set as appropriate. This sampling interval may be specified by the number of frames in addition to being specified by time.

The image data of the print target image and the reference image specified by the freeze button are stored in the frame memory 2.
8 is written. When the display of the freeze image is selected by operating the keyboard 25, the selector 19 is set to the terminal (b) side, and the data of the print target image written through the D / A converter 29 and the encoder 20 is converted into color data. It is sent to the monitor 22. As a result, the image to be printed is displayed on the color monitor 22. After the print target image is confirmed on the color monitor 22 and a print start signal is input from the keyboard 25, the system controller 26 transmits the image data of the print target image and the reference image from the frame memory 28 to the image processing unit 12. Send to

In the image processing section 12, first, the matching processing section 30 performs a local matching process between the image to be printed and the reference image. This local matching process divides the print target image and the reference image into m × m divided areas, and for each of these divided areas, calculates the absolute value of the pixel difference between the print target image and the reference image for each pixel. A sum of values is obtained, and when this value is within a predetermined threshold, this block is determined as a still area, and when it deviates from the predetermined threshold, this block is determined as a moving area. Note that, in addition to the sum of absolute values, a sum of squares of differences between pixels may be used. The image data of the still area is sent to the still area weighted averaging unit 31. The image data of the moving region excluding the still region is sent to the moving region smoothing processing unit 32. The image processing unit 1
In step 2, other well-known processes such as gamma correction, matto-criss correction, character illustration synthesis, enlargement / reduction, and trimming are performed.

The still area weighted averaging unit 31 calculates a weighted average value from pixel data at the same position in the image to be printed and the reference image, and sends this to the image synthesizing unit 33. The weighted average value is obtained by weighting the image data on the image to be printed, and the weighting coefficient is changed by the system controller 26 according to the interval between the reference images to be collected and the type of the input image. When calculating the weighted average value, pixels having a value that is a predetermined value away from the pixel value of the image to be printed are excluded to prevent a part of a different subject from entering. Further, instead of the pixel value of the image to be printed, a pixel having a value that is a predetermined value away from this value may be excluded based on the obtained weighted average value.

The moving area smoothing section 32 uses the image data of the image to be printed, divides the moving area into k × k blocks, and performs a smoothing process on each block. This smoothed image data is sent to the image synthesizing unit 33. By this smoothing process, a process of blurring the image in the moving area can be performed. Therefore, when an image moves due to the movement of the subject in the moving area, the flow of the image can be made inconspicuous, and the overall print quality can be improved.

The image synthesizing section 33 synthesizes the image data of the static area from the static area weighted averaging section 31 and the image data of the moving area from the moving area smoothing processing section 32. One frame of image data obtained by the image synthesis is written into the print frame memory 35.

The printing section 13 includes a printing frame memory 35 and a printer 36. The printer 36 reads out image data from the print frame memory 35, modulates a light beam based on the read out image data, and scans and exposes yellow, magenta, and cyan photosensitive layers of a silver halide photographic color photosensitive material (color paper). I do. Instead of modulating the light beam, mirrors (micromirrors) of extremely small size are arranged in a line or a matrix,
Scanning exposure may be performed using a micromirror device that deflects incident light by controlling the tilt angle of each micromirror. Further, a liquid crystal panel or a CRT may be used. As is well known, when a negative / positive color paper is used, image data is subjected to positive / negative conversion. This positive / negative conversion may be performed by the image processing unit 12 in addition to the printing unit 13. The image data may be read from the print frame memory 35 and displayed on the color monitor 22 in a simulated manner.

Next, the operation of the above embodiment will be described with reference to FIG. First, by operating the freeze button, a reference image which is an image to be printed and an image one second before and one second after this is stored in the frame memory 28.

Next, the matching processing section 30 of the image processing section 12 determines a moving area and a still area based on the print target image data and the reference image data in the frame memory 28. Then, based on the determination result, the image data in the still area of the print target image and the image data in the still area of the reference image are converted into the still area weighted average unit 31.
Where it is weighted and averaged. Further, based on the determination result in the matching processing unit 30, the image data in the moving area of the image to be printed is converted into the moving area smoothing processing unit 32.
, Where it is subjected to a smoothing process.

Next, in the image synthesizing section 33, the still area image data from the still area weighted averaging section 31 and the moving area image data from the moving area smoothing processing section 32 are image-synthesized. The data is written to the print frame memory 35 of the print unit 13. Then, printing is performed by the printer 36 on the basis of the image-combined data. Therefore, in the present embodiment, since a weighted average value is calculated between frames for a still region, random noise can be reduced. In addition, since the blurring correction is performed on the moving area by performing the smoothing process, when the subject is blurred, it can be made inconspicuous. Note that instead of smoothing and blurring the moving area, USM
(Unsharp mask correction) may be performed to sharpen the image.

In the above-described embodiment, the processing is performed on the assumption that there is no movement of the video camera during shooting and no zooming shooting. However, in addition to this, shooting by moving the video camera (camera shooting) or zooming is performed. When photographing is performed, the following motion compensation processing is performed to perform printing processing. This motion compensation processing is performed when the ratio of the still area to the entire screen in the above embodiment is small, for example, 10% or less.

In this motion compensation processing, as shown in FIG. 3, the print target image and the reference image are divided into m × m divided areas, and the position of each divided area of the reference image is shifted two-dimensionally. A local matching process is performed with each divided area of the image to be printed. Then, the divided area of the reference image at the shift position where the degree of difference is minimized is associated with the divided area of the print target image, and by this association, the motion vector of the divided area of the reference image with respect to the divided area of the print target image over the entire screen. Ask. Based on this motion vector, it is determined whether the shooting is moving or zooming.

If the directions of the motion vectors are entirely the same, it is determined that the image to be printed is a camera moving shooting scene. Note that a moving subject often shows a motion vector different from the above-mentioned motion vector. However, since the movement of this subject is small in proportion to the entire screen, this can be ignored. In the case of this camera moving shooting scene, the reference image is shifted by the motion vector, and the still area and the moving area are determined in the same manner as in the above embodiment based on the reference image at the shifted position and the print target image. Then, different processing is performed on the stationary area and the moving area.

If the directions of the motion vectors are not entirely the same, it is determined whether or not the scene is a zoom photographing scene. First, an average vector is obtained for the motion vectors of the entire screen. Then, a corrected motion vector is calculated by subtracting the average vector from the motion vector of each divided area. If the directions of the corrected motion vectors are arranged radially from the center as a whole, it is determined that the image is captured while zooming the camera. Also,
In this case, the size of the average vector obtained by averaging the corrected motion vectors becomes a value close to “0” over the entire screen.
By also referring to this, it is possible to increase the accuracy of determining whether or not zooming shooting is performed.

Based on the determination result, a corrected motion vector in which the motion of the entire screen of the reference image is canceled is obtained. If the magnitude of the corrected motion vector is within a predetermined value, a set of divided areas of the print target image corresponding to the divided area of the reference image is determined as a still area. For this still area, a weighted average value is calculated between frames as in the above embodiment. The calculation of the weighted average value between the frames is performed by the divided areas associated with each other based on the motion compensation result in the preceding and succeeding frames. Also, a set of other divided areas excluding the stationary area is determined as a moving area. The smoothing process is performed on this moving region in the same manner as in the above embodiment.

When determining the motion of a scene, in addition to dividing the entire screen into a large number of divided areas and obtaining motion vectors of these divided areas, a limited number of the peripheral parts of the screen are limited to the peripheral parts of the screen. The screen may be divided into a plurality of divided areas, and the motion of the scene may be determined for the periphery of the screen. In this case, since the calculation target area is narrower than in the case of the entire screen, the calculation processing can be performed efficiently. Then, based on the result of the motion determination by the peripheral part of the screen, a motion vector is estimated for each divided area of the central part divided into the same size as the peripheral part, and based on this, various processes are performed in the same manner as in the above embodiment. . In addition, after judging the camera moving shooting and the zooming shooting, the inter-frame smoothing process is performed in the camera moving shooting, and the intra-frame smoothing process is performed in the zooming shooting, and the process branches to a different process according to the determination result. In this case, image processing suitable for the movement of the scene can be performed.

Next, as shown in FIG. 4 and FIG. 5, the face area of the person is extracted by combining the determination result of the still area and the moving area with the face area extraction algorithm of the still image person. An embodiment in which printing is performed with emphasis on the image data of the face area will be described. In a moving image, it is probable that the person's still state lasts for a predetermined time or more. Therefore, there is a high possibility that the person is included in the moving area. Also,
In the face image algorithm of a person for a still image, an area having a color and density specifying the skin color of a person is determined as a face image, so that even a subject other than a person such as a wall or the ground has the same color and density as the skin color. In the case of, there is a possibility that the face image of the person is erroneously determined. Therefore, by adding a condition that is a human face candidate area and a moving area in the human face area extraction algorithm, the possibility of a human face area is further increased, and the face area extraction performance can be improved. it can.
In addition, instead of the face candidate area, the face candidate area may be specified by detecting the shape of the face internal structure such as the contour of the face, the head, the human body, the eyes, the mouth, and the eyebrows. Furthermore, a face region extraction algorithm based on the color and density specifying a person's skin color and a face region extraction algorithm based on shape detection such as the outline of a face may be used together.

FIG. 4 is a flowchart showing this processing procedure. First, image data of an image to be printed and a reference image is fetched from moving image data. Based on the captured image data, a moving area and a still area are determined in the same manner as in FIG. A weighted average value is calculated for the stationary region in the same manner as in the stationary region weighted averaging unit 31 in FIG.

In parallel with the determination of the moving area and the still area, a face candidate area extracting process is performed based on the image data of the frame to be printed, and a face candidate area is extracted. And by ANDing the face candidate area and the moving area,
The face area is determined, and other areas are determined as non-face areas. The smoothing process is performed on the non-face region based on the image data of the image to be printed, similarly to the moving region smoothing processing unit 32 illustrated in FIG. Also, for the face area,
An emphasis process is performed. Instead of this emphasizing process, data conversion may be performed so that the density and color of the face area become the density and skin color specified in advance. Next, print processing is performed after the image data of the still area, the non-face area, and the face area are combined.

FIG. 5 shows an example of the image data in FIG. 4, wherein (B) shows the image to be printed, (A) shows the reference image one second before the image to be printed, and (C) shows the image to be printed. It shows a reference image one second after the image. When you press the freeze button and import image data,
The image to be printed (B), the reference image (A) one second before this, and the reference image (C) one second after this are stored in the frame memory 2.
8.

(D) shows the extraction result of the still area SA,
(E) shows the extraction result of the moving area MA, which is extracted by the local matching processing by the matching processing unit 30 with respect to the print target image (B) and the reference images (A) and (C). is there.

(F) shows the result of extraction processing of the face candidate area FCA based on the image to be printed. In this example, two subjects having flesh color exist in the background in addition to the human image. I understand. By taking the AND of the extraction result (F) of the face candidate area FCA and the extraction result (E) of the moving area MA, the extraction result (G) of the face area FA and the extraction result of the other non-face moving area MNFA ( H). Therefore, the print target frame is changed to the static area SA.
And a non-face moving area MNFA and a face area FA. By performing optimal image processing on each of the still area SA, the non-face moving area MNFA, and the face area FA obtained in this manner, a print with a good finish can be obtained as a whole.

For example, by applying an emphasis process to the image data of the face area FA, a clearer image can be obtained. In addition, other moving regions MN
For the FA and the still area SA, the same print processing as in the above embodiment can improve the overall print quality. Further, by performing printing so that the density and color of the face area of the person become appropriate, the main subject can be properly finished, and a high-quality print can be created.

In the above embodiment, the determination of the still area SA and the moving area MA and the determination of the face area FA and the non-face area NFA are executed in parallel, and the face candidate area FCA obtained by the face extraction processing is executed. The face area FA and the non-face area MNFA are determined by ANDing the moving area MA with the moving area MA. In addition, as shown in FIG. After the determination, the face area extraction processing may be performed on the moving area MA to determine the face area FA and the non-face moving area MNFA.

Further, a well-known pixel complementing process may be performed on the image data to artificially increase the resolution. As a method of determining a pixel value to be complemented, there is a method of taking a weighted average according to a spatial distance from original image data.
In this case, the closer the pixel, the larger the weighting coefficient. This pixel complementing process may be performed before or after the still / moving region determination process.

The frames before and after the image to be printed need not be continuous frames, but may be frames captured at regular intervals. Alternatively, by detecting motion between frames,
A frame captured when there is a motion in the scene may be used. Further, in the above embodiment, for example, an image one second before and one second after the print target image is used as a reference image, but this reference image is used as one image before or after the print target image. Is also good.

In the above embodiment, a weighted average value of pixel data is obtained for a still region, and this value is used as image data of the still region. Although blurring of a person or the like is not noticeable, the content of image processing and its control parameters may be set in accordance with each area.

In the above embodiment, the present invention is applied to a silver halide printer for printing on color paper by scanning exposure.
In addition, various color printers such as a color thermal printer and an ink jet printer may be used.

In the above embodiment, a motion vector is obtained from image data between frames, and shooting while the camera is moving and zooming shooting are detected from the motion vector. In this case, the operation state of the zooming switch may be detected, and this may be stored together with the image data as photographing information. Similarly, a sensor for detecting the movement of the camera may be provided, and the movement of the camera may be detected during shooting, and may be stored together with the image data.

[0043]

According to the present invention, an image to be printed in a moving image and n (n is a natural number) the image to be printed
The data of the reference image before or after the frame is fetched into the memory in frame units, and local matching processing is performed on the print target image data and the reference image data, and the print target image is converted into a still region and a moving region. Therefore, different image quality improvement processes can be performed for the still area and the moving area according to each area. Can be raised.

Further, the image to be printed is divided into a still area and a moving area, a face candidate area is extracted from the printing object image data, and an area where the moving area and the face candidate area overlap is determined as a face area. Since the image to be printed can be divided into a face area, a moving area excluding the face area, and a still area, different image quality improvement processing suitable for each of these areas can be performed. The overall image quality can be further improved. In addition, a face candidate area is extracted from the print target image data for the moving area, and the print target image is divided into a face area, a non-face moving area, and a still area, so that the moving area narrowed down to some extent Since face candidate extraction is performed, face candidate extraction processing can be easily performed.

In the still area, the pixel data at the same position of the image to be printed and the reference image are weighted and averaged, and the weighted average value is used as image data, so that random noise can be reduced. . Also, by performing a smoothing process on the moving area using the image data of the image to be printed, the moving area can be blurred,
Blur in the moving area can be made inconspicuous. In addition, the image can be sharpened by performing an emphasis process on the moving area using the image data to be printed. In particular, in the case of an image with little motion, image quality can be improved as compared with blurring by the smoothing process.

Further, by adjusting the print density and color of the entire image so that the density and color of the face area are properly finished based on the image data in the face area of the image to be printed,
The finish is weighted for the face area, and the print quality can be improved. Also, based on image data in the face area of the image to be printed, only the face area may be partially and appropriately finished in density and color. Can be raised.

The local matching processing is performed while the positions of the image data to be printed and the reference image data are shifted two-dimensionally, and the block at the shifted position that minimizes the difference is associated with the image data. Since motion vectors are obtained over the whole, and it is determined whether the camera is moving or zooming based on the motion vectors, these motions can be canceled based on the determination result. Therefore, even if you move the camera and shoot or zoom shooting,
The image data of the reference image can be used. Moreover,
Since the image data of the reference image uses values obtained by canceling these motions based on the motion vector, it is possible to determine the moving area and the still area of the print target image even when the behavior of the camera changes during shooting. . Therefore, by performing different image quality improvement processing for each area based on the determination result, it is possible to improve the image quality of an image to be printed in photographing while the camera is moving or in zooming photographing.

[Brief description of the drawings]

FIG. 1 is a functional block diagram illustrating a video printer embodying the present invention.

FIG. 2 is a flowchart showing a processing procedure in the video printer.

FIG. 3 is a flowchart showing a processing procedure of another embodiment in which a camera moving shooting scene and a zooming shooting scene are automatically determined and a still area and a moving area are determined in accordance with each scene.

FIG. 4 is a flowchart illustrating a processing procedure of another embodiment in which a still area / moving area determination process and a face region determination process are performed in parallel.

FIG. 5 shows an example of moving image data and an example of a still area, a non-face moving area, and a face area extracted from the image data, wherein (A) and (C) are reference images, and (B) is a reference image. An image to be printed, (D) is a result of extracting a still region, (E) is a result of extracting a moving region, (F) is a result of extracting a face candidate region, (G) is a result of extracting a face region, and (H) is a non-extracted result. It is a result of extracting a face motion area.

FIG. 6 is a flowchart illustrating a processing procedure of another embodiment for determining a face area after determining a still area / moving area.

[Explanation of symbols]

 Reference Signs List 10 video printer 11 image input unit 12 image processing unit 13 printing unit 14 video camera 28, 35 frame memory 30 matching processing unit 31 still area weighted averaging unit 32 moving area smoothing processing unit 33 image synthesizing unit SA still area MA moving area FCA Face candidate area MNFA Non-face moving area FA Face area

Claims (9)

[Claims] 1. A print target image in a moving image and data of a reference image which is n (n is a natural number) frames before or after the print target image are fetched into a memory in frame units, and the print target image data and reference data are stored. It performs local matching processing on image data, divides the print target image into a still area and a moving area, and performs different image quality improvement processing on the still area and the moving area. Printing method. 2. A print target image in a moving image and data of a reference image n (n is a natural number) frames before or after the print target image are fetched into a memory in frame units, and are referred to as print target image data. Performing local matching processing on the image data to divide each part in the print target image into a still region and a moving region; extracting a face candidate region from the print target image data; A region where the image overlaps with the image is determined as a face region, and different image quality improvement processes are performed on the face region, the moving region excluding the face region, and the still region. . 3. A print target image in a moving image and data of a reference image n (n is a natural number) frames before or after the print target image are fetched into a memory in frame units, and the print target image data and reference data are stored. Performing a local matching process on the image data to divide the print target image into a still region and a moving region, extracting a face candidate region from the print target image data for the moving region, A moving image printing method characterized by performing different image quality improvement processing on a moving region excluding a face region and a still region. 4. The method for printing a moving image according to claim 1, wherein the image quality improvement processing for the still area includes a weighted average of pixel data at the same position between the print target image and the reference image. A moving image printing method characterized in that the weighted average value is used as image data. 5. The method of printing a moving image according to claim 1, wherein the image quality improvement processing for the moving area is performed by using image data of an image to be printed. How to print moving images. 6. The moving image printing method according to claim 2, wherein the image quality improvement processing for the face area is performed by using image data of an image to be printed. How to print an image. 7. The method of printing a moving image according to claim 2, wherein the image quality improvement processing for the face area is performed based on image data in the face area of the print target image. A print method of a moving image, wherein the print density and color of the entire image are adjusted so as to properly finish the image. 8. The method of printing a moving image according to claim 2, wherein the image quality improvement processing for the face area is performed by partially removing only the face area based on image data in the face area of the print target image. And a method for printing a moving image, wherein the density and the color are adjusted so as to be properly finished. 9. A print target image in a moving image and data of a reference image n (n is a natural number) frames before or after the print target image are fetched into a memory in frame units. While the position of the reference image data is two-dimensionally shifted, a local matching process is performed on the divided areas obtained by dividing each image into a large number of pieces, and the divided areas of the reference image at the shifted positions at which the degree of difference is minimized Is associated with the divided area of the image to be printed,
By this association, the motion vector of the divided area of the reference image with respect to the divided area of the image to be printed is obtained over the entire screen, and it is determined whether the moving image capturing or the zooming image capturing is performed based on the motion vector. A corrected motion vector in which the motion is canceled is obtained. If the size of the corrected motion vector is within a predetermined value, the divided area of the print target image corresponding to the divided area of the reference image is determined as a still area, and the other areas are determined. A method of printing a moving image, comprising determining each divided area in a print target image into a still region and a moving region, and performing different image quality improvement processing on the still region and the moving region.