JP2001111804A - Image converter and image conversion method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve a problem of a conventional image converter that has required much time and labor to generate a mask image and a background image by analogizing an image behind an object of interest based on the object of interest of one original image. SOLUTION: The image converter that generates a converted image resulting from changing a view point and a noticed point of a two-dimensional original image is provided with an area setting means that sets an area surrounding area of the object of interest in the original image, a mask image generating means that generates the mask image by setting a white level to pixels in the area surrounding the object of interest of the original image and setting a black level to pixels at the outside of the area surrounding the object of interest, a background image generating means that multiplies a predetermined coefficient (k) less than the unity with values of pixels of the original image within the area surrounding the object of interest to obtain pixels behind the object of interest and uses the pixels at the outside of the area surrounding the object of interest for the pixels of the original image and a converted image generating means that uses the mask image and the background image to generate the converted image resulting from changing the view point and the point of interest of the original image.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image conversion device, an image conversion method, and a recording medium on which an image conversion program is recorded for converting a two-dimensional original image into an image viewed from any viewpoint.

[0002]

2. Description of the Related Art Conventionally, in the field of computer graphics, a perspective drawing method has been used as a method for drawing a figure having a perspective on a two-dimensional plane. In the perspective drawing method, a vanishing point which is the center position of the image is set, and a figure is drawn based on the vanishing point, thereby expressing the perspective while maintaining the perspective.
This is a drawing method for drawing a two-dimensional shape on a two-dimensional plane.

[0003] As a method of synthesizing a perspective view image drawn by a perspective drawing method, a computer is provided with image data of a three-dimensional shape composed of a plurality of surfaces and affixes a perspective view image to each surface. There was a law. The texture mapping method is realized by some three-dimensional computer graphics software.
996).

In the above-described method for converting a perspective view image by the texture mapping method, it is necessary to photograph or draw a texture image to be attached to a surface from the front. However, in general, an image is often photographed or drawn from an oblique viewpoint. Further, due to the limitation of the memory in the computer, the resolution of the texture image is low, and it is difficult to increase the resolution of the image of the perspective view to be recombined.

Therefore, an image conversion method for converting a two-dimensional image into an image viewed from another viewpoint (angle) on a computer without maintaining the resolution of the original image without requiring a frontal image is disclosed in Japanese Patent Laid-Open Publication No. Hei 10 (1998) -107. No. 49704.

The image conversion method disclosed in Japanese Patent Application Laid-Open No. H10-49704 sets a vanishing point and a dead end region of a depth of an original image, and based on the set vanishing point and a dead end region of a depth, a plurality of images are formed. Of the original image based on each element of the structure, set an angle different from the angle of the original image, and convert the image based on the set angle. To generate a converted image having an angle different from that of the original image.

According to the above-described image conversion method, a mask image in which an area corresponding to an object of interest in an original image is whitened and the other area is blackened, and a background image in which an object of interest in the original image is filled with a surrounding pattern or the like. By generating in advance,
The target object in the original image can be arranged in the three-dimensional space.

The mask image is used to extract an image of the object of interest from the original image. For example, pixels on the original image corresponding to black portions of the mask image are ignored, and pixels of the original image corresponding to white portions are extracted. The image extracted by the mask image is pasted on a plate-shaped target object arranged in a three-dimensional space.

The background image is an image that appears from behind the object of interest when the viewpoint (angle) for viewing the three-dimensional space is changed. The image that appears from behind the object of interest is
Since there is no information on the original image, the user has to estimate the image behind the object and process the original image to create a background image in advance.

[0010]

The task of selecting a target object from one original image and creating a mask image and a background image based on the target object takes time and effort. In addition, the task of estimating an image behind the object of interest from one image and creating a background image also requires time and effort.

An object of the present invention is to provide an image conversion apparatus and an image conversion method capable of easily performing image conversion and automatically generating a background image having no uncomfortable feeling with a mask image.

[0012]

According to a first aspect of the present invention, there is provided an image conversion apparatus for generating a converted image in which a viewpoint is changed based on a two-dimensional original image. A mask image generating means for generating a mask image by whitening pixels in a region surrounding the object of interest in the original image and blackening pixels outside the region surrounding the object of interest, and surrounding the object of interest. Background image generating means for multiplying a value indicating the luminance of a pixel of the original image in the region by a coefficient k less than a predetermined value to generate a background image in which pixels outside the region surrounding the object of interest are pixels of the original image And a converted image generating means for generating a converted image whose viewpoint has been changed using the mask image and the background image.

According to a second aspect of the present invention, in an image conversion method for generating a converted image in which the viewpoint is changed based on a two-dimensional original image, an area setting step of setting an area surrounding an object of interest in the original image And a mask image generating step of generating a mask image by whitening pixels in a region surrounding the object of interest in the original image and blackening pixels outside the region surrounding the object of interest, and A background image generating step of multiplying a value indicating the luminance of the pixel by a predetermined coefficient k less than 1 to generate a background image in which pixels outside an area surrounding the object of interest are pixels of the original image; A conversion image generating step of generating a conversion image in which the viewpoint and the point of interest are changed using the image.

According to a third aspect of the present invention, there is provided a recording medium in which an image conversion program for generating a converted image whose viewpoint is changed based on a two-dimensional original image is recorded. An area setting step of setting a pixel in a region surrounding the object of interest in the original image, and a mask image generating step of generating a mask image by blacking pixels outside the region surrounding the object of interest. A background image generating step of multiplying a value indicating the luminance of a pixel of the original image in the region by a coefficient k less than 1 to generate a background image in which pixels outside the region surrounding the object of interest are pixels of the original image And an image conversion program that includes a conversion image generation step of generating a conversion image in which a viewpoint and a point of interest are changed using the mask image and the background image. That.

[0015]

FIG. 1 is a schematic diagram showing a schematic configuration of an embodiment of an image conversion apparatus according to the present invention. In FIG. 1, an image conversion apparatus includes a central processing unit 101 and a storage device 1.
02. An image reading device 103, an image display device 104, and an input instruction device 105 are connected to the image conversion device.

The central processing unit 101 is connected to the storage device 102, and processes data stored in the storage device 102 according to the processing procedure stored in the storage device 102.

The storage device 102 is a magnetic disk drive, an optical disk drive, or the like.
An area setting processing procedure, a mask image generation processing procedure, a background image generation processing procedure, and a converted image generation processing procedure are stored.
The storage device 102 also stores image data and area information read by the image reading device 103.

The image reading device 103 is an optical disk drive, a scanner, or the like, and reproduces a recording medium on which image data is recorded to read image data, or reads image data from a two-dimensional image using a scanner or the like.

The image display device 103 is, for example, a monitor or the like, and displays read image information and displays each processing step and processing result.

The input instruction device 105 is, for example, a mouse or a keyboard having at least one button. By operating the input instruction device 105, an arrow displayed on the image display device 104 is moved. The central processing unit 101 is notified of the position information, the state of the buttons, and the like.

The processing operation in the image conversion method will be described. FIG. 2 is a flowchart illustrating an image conversion processing procedure of the image conversion apparatus according to the present embodiment. In FIG. 2, the central processing unit 101 reads an original image according to an image reading processing procedure, and causes the image display device 104 to display the read original image (step 201).

The central processing unit 101 sets the region of the object of interest according to the region setting procedure by the user operating the input instruction device 105 (step 20).
2).

The central processing unit 101 generates a mask image necessary for extracting the target object from the original image according to the mask image generation processing procedure (step 203).

The central processing unit 101 generates a background image to be an image behind the object of interest according to the background image generation processing procedure (step 204).

The central processing unit 101 uses the generated mask image and background image to generate a converted image in which the viewpoint and the point of interest have been changed (step 205).

Each processing procedure in the image conversion apparatus of this embodiment will be described. FIG. 3 is a flowchart illustrating an image reading processing procedure of the image conversion apparatus according to the present embodiment. FIG.
When the image data is read from the image reading device 103 (step 301), the central processing unit 101
The image data is stored in the storage device 102 (step 30).
2) Display the read image data on the image display device 104 (step 303).

FIG. 4 is a flowchart showing an area setting processing procedure of the image conversion apparatus of this embodiment. FIG. 5 is a schematic diagram for explaining an area setting processing procedure of the image conversion apparatus according to the present embodiment. In FIG. 4, the user operates the input instruction device 105 to display the image display device 104 as shown in FIG.
5A, the arrow 502 is moved to the upper left of the target object 501 to be stereoscopically displayed, and the button is pressed at that position to set the start point of the area shown in FIG. (Step 401).

When the arrow 502 is moved while holding down the button (hereinafter referred to as "drag"), FIG.
As shown in (1), a rectangular area ending from the start point to the current position is set and displayed on the image display device (step 402).

The user operates the input instruction device 105 to change the rectangular area to the target object 50 as shown in FIG.
1 is completely surrounded (step 403).

Then, after surrounding the object of interest 501 with a rectangular area, the arrow 502 is moved, as shown in FIG.
The number of vertices is increased by selecting the line connecting the vertices and pressing the button, and as shown in FIG.
(Step 4)
04). The region may be set by surrounding the target object 501 using a curve connecting the vertices. Information on this area, such as vertex position information, is stored in the storage device 1.
02 is stored.

The area set by the user is displayed on the image display device 104 so as to overlap the original image (step 40).
5).

FIG. 6 is a flowchart showing a mask image generation processing procedure of the image conversion apparatus of the present embodiment. FIG.
FIG. 3 is a schematic diagram for explaining a mask image of the image conversion device of the present embodiment. In FIG. 6, the central processing unit 101
In the image shown in FIG. 7A, the pixels in the region surrounding the object of interest 701 are turned white with reference to the region information stored in the storage device 102 (step 601).

Here, the whiteness of the pixel in the area surrounding the object of interest 701, the color information of the pixel, or the luminance information of the pixel may be set by the user.

The central processing unit 101 makes the pixels outside the region surrounding the object of interest 701 black, thereby obtaining the pixels shown in FIG.
Is generated and stored in the storage device 102 (step 602).

FIG. 8 is a flowchart showing a background image generation processing procedure in the image conversion apparatus of this embodiment. In FIG. 8, the central processing unit 101 refers to the region information stored in the storage device 102, assigns a pixel in an area surrounding the object of interest 701 to a coefficient k less than 1 which is set in advance, and surrounds the object of interest 701 The value of the pixel on the original image corresponding to the area, that is, the value of the pixel of the object of interest 701 is multiplied to obtain the pixel value of the pixel behind the object of interest (step 801).

Here, a pixel is represented by R, G, and B, and the color of the pixel is determined by the ratio of R, G, and B. The sum of the R, G, and B values is the luminance of the pixel. That is, when the pixel is multiplied by the coefficient k = 1, the pixel value becomes the same as that of the original pixel. For example, the coefficient k = 0.
In the case of 8, since the value of each pixel of R, G, and B is multiplied by 0.8, the pixel has low luminance.

Therefore, when the area surrounding the object of interest 701 is multiplied by a coefficient k of less than 1, the area becomes a dark pixel with low luminance, and as shown in FIG. Image.

In the case of an image with a high luminance of the original image (bright image), a lower value of the coefficient k looks like a shadow of the object of interest, and in the case of an image with a low luminance of the original image (dark image), Even if the value is not lowered, the object looks like a shadow. The value of the coefficient k can be arbitrarily set by the user within a range of less than 1. Alternatively, a background image may be generated by giving light and dark based on color information or luminance information of pixels in a region surrounding the object of interest.

A background image is generated by setting pixels outside the area surrounding the object of interest 701 to the same value as the original image, and stored in the storage device (step 802).

Next, the angle of the two-dimensional original image is changed by using the mask image shown in FIG. 7B and the background image shown in FIG. By converting to an image, a converted image as shown in FIG. 7D is obtained.

In FIG. 7 (c), when the angle is gradually changed, an image behind the object of interest appears. However, the image behind the object of interest looks like a shadow of the object of interest, and a natural image without discomfort. Images can be easily obtained.

In the mask image generation processing procedure and the background image generation processing procedure, processing may be performed using a smoothing filter so that the boundary between the mask image and the background image is inconspicuous.

[0043]

According to the present invention, it is possible to easily generate a mask image and a background image from a single original image, and to generate a natural background image that is uncomfortable.

[Brief description of the drawings]

FIG. 1 is a schematic diagram illustrating a schematic configuration of an embodiment of an image conversion apparatus according to the present invention.

FIG. 2 is a flowchart illustrating an image conversion processing procedure of the image conversion apparatus according to the embodiment.

FIG. 3 is a flowchart illustrating an image reading process performed by the image conversion apparatus according to the embodiment.

FIG. 4 is a flowchart illustrating an area setting processing procedure of the image conversion apparatus according to the embodiment.

FIG. 5 is a schematic diagram for explaining an area setting processing procedure of the image conversion apparatus according to the embodiment.

FIG. 6 is a flowchart illustrating a mask image generation processing procedure of the image conversion apparatus according to the present embodiment.

FIG. 7 is a schematic diagram for explaining a mask image of the image conversion apparatus according to the present embodiment.

FIG. 8 is a flowchart illustrating a background image generation processing procedure in the image conversion apparatus according to the present embodiment.

[Explanation of symbols]

101: central processing unit, 102: storage device, 1
03: image reading device, 104: image display device,
105: pointing device, 501: target object, 502: arrow, 701: target object.

Continued on front page F-term (reference) 5B050 AA09 BA06 BA09 BA12 BA15 CA07 EA03 EA13 EA15 EA19 EA23 EA30 FA02 FA16 5B057 CA01 CA08 CA12 CA16 CB01 CB08 CB12 CB16 CC03 CD11 CE05 CE11 5C023 AA16 BA11 CA03 A08 A02 A06 A04 A04 5L096 AA02 AA06 BA08 CA24 DA01 GA10 MA03

Claims (3)

[Claims] 1. An image conversion apparatus for generating a converted image viewed from an arbitrary viewpoint based on a two-dimensional original image, wherein: an area setting means for setting an area surrounding an object of interest in the original image; Mask image generating means for generating a mask image by whitening pixels in the region surrounding the object of interest and blacking pixels outside the region surrounding the object of interest, and individual pixels of an original image in the region surrounding the object of interest Background image generating means for multiplying a value indicating the luminance of the target image by a predetermined coefficient k less than 1 to generate a background image in which pixels outside an area surrounding the object of interest are pixels of the original image; and the mask image An image conversion apparatus comprising: a conversion image generation unit configured to generate a conversion image whose viewpoint has been changed using the background image and the background image. 2. An image conversion method for generating a converted image viewed from an arbitrary viewpoint based on a two-dimensional original image, wherein: an area setting step of setting an area surrounding an object of interest in the original image; A mask image generating step of generating a mask image by whitening pixels in an area surrounding the object of interest and blacking pixels outside the area surrounding the object of interest, and generating individual pixels of an original image in the area surrounding the object of interest. A background image generating step of multiplying a value indicating luminance by a coefficient k less than a predetermined value of 1 to generate a background image in which pixels outside an area surrounding the object of interest are pixels of an original image; and A conversion image generation step of generating a conversion image whose viewpoint has been changed using a background image. 3. An area setting step for setting an area surrounding an object of interest in the original image on a recording medium in which an image conversion program for generating a converted image viewed from an arbitrary viewpoint based on a two-dimensional original image is recorded. A mask image generating step of generating a mask image by whitening pixels in a region surrounding the object of interest in the original image and blackening pixels outside the region surrounding the object of interest, and A background image generating step of multiplying a value indicating the luminance of each pixel of the original image by a predetermined coefficient k less than 1 to generate a background image in which pixels outside the region surrounding the object of interest are pixels of the original image And a conversion image generation step of generating a conversion image in which a viewpoint is changed using the mask image and the background image. .