JP3984704B2 - Image processing apparatus and method - Google Patents

Description

なお、上記式（３）において、「^」はべき乗を表し、たとえば「Ｘ^2」はＸの２乗を表す。この結果△Ｅ0〜△Ｅp-1のＰ個の評価結果が選られる。
【００２６】
ステップＳ２０６ではＰ回の評価関数の結果から、その値の最も小さくなる素材画像を選択し、第二の画像の対応するタイル位置（すなわち，（Ｘ−ｐｏｓ，Ｙ−ｐｏｓ）で指定されるタイル）に貼り込むタイルとする。
【００２７】
ステップＳ２０７では第一の画像のすべてのタイルについて上述の処理が行われたかどうかを判断し、未処理のタイルがあれば、ステップＳ２０４に戻り，上記処理を繰り返す。一方、すべてのタイルについて処理が終わっていれば、ステップＳ２０８に進む。
【００２８】
ステップＳ２０８では、キーボード１０４から操作者により入力されるα値を読み出す。ただしαの値は０以上１以下として説明する。ステップＳ２０９では第一の画像、第二の画像、αを用いて、第三の画像を合成し、これを最終的なモザイク画像とする。
【００２９】
αを用いた画像の合成方法の一例としては、第一の画像のα倍と第二の画像の（１−α）倍を加えることが挙げられる。すなわち、第一の画像と第二の画像の同じ位置の画素値をそれぞれ、（Ｒ１，Ｇ１，Ｂ１）、（Ｒ２，Ｇ２，Ｂ２）とすると、合成の結果得られる第三の画像の同じ位置の画素値（Ｒ３，Ｇ３，Ｂ３）は、以下の式（４）によって求まる。
【００３０】
Ｒ３＝α×Ｒ１＋（１−α）Ｒ２
Ｇ３＝α×Ｇ１＋（１−α）Ｇ２
Ｂ３＝α×Ｂ１＋（１−α）Ｂ２
となる。
【００３１】
以上説明したように、本実施形態によれば、モザイク画像構成方法により作成された第二の画像の個々のタイルが、第一の画像の色・テクスチャとあまりにも異なるものとなるような場合でも、設定された率で第１の画像が反映されるので、全体として第一の画像をよく摸した画像を得ることが可能となる。従って、少ない素材画像数で良好なモザイク画像を得ることができる。
【００３２】
［第２の実施形態］
次に本発明の第２の実施形態について説明する。なお、以下では、第１の実施形態と第２の実施形態の相違点について説明する。
【００３３】
図３は第２の実施形態によるモザイク画像生成の手順を説明するフローチャートである。第１の実施形態と同様にステップＳ２０１〜Ｓ２０９を実行し、その結果として、第一の画像と第二の合成画像である第三の画像を得る。次に、ステップＳ３１０では第三の画像をディスプレイ装置に表示する。そして、ステップＳ３１１では、α値の変更入力が可能なインターフェースを表示し、操作者によってα値の変更入力が行われたかどうかを判定する。ここでα値が変更された場合はステップＳ２０８に戻り、変更後のαを用いて第３の画像生成を行う。
【００３４】
図４は、α値の変更を行うためのユーザインターフェース例を示す図である。図４に示されるようなユーザインターフェースがディスプレイ装置１０５に表示される。図４において、４０１は第一の画像、４０２は第３の画像をそれぞれ表示する表示部、４０３は処理の開始を指示するスタートボタン、４０４はα値を変更するスライダーである。なお、さらに第二の画像を表示するようにしても良い。第二の画像も表示するようにすれば、αの値を操作者が設定する際の参照となる。
【００３５】
スタートボタン４０３を押す以前は、４０１に第一の画像が表示されている。スタートボタン４０３を押すと、フローチャートのステップＳ２０１から処理を開始する。そして、ステップＳ２０９を終了すると表示部４０２に第三の画像が表示される。つづいて、スライダー４０４をマウスにより操作する。スライダー４０４は最左端でα＝０、最右端でα＝１となり、その間は均等にわけられている。
【００３６】
スライダー４０４が最左端では、α＝０であるから、式（４）において、
Ｒ３＝α×Ｒ１＋（１−α）Ｒ２＝Ｒ２
Ｇ３＝α×Ｇ１＋（１−α）Ｇ２＝Ｇ２
Ｂ３＝α×Ｂ１＋（１−α）Ｂ２＝Ｂ２
となり、第三の画換は第二の画像と等しくなる。
【００３７】
また、スライダー４０４が最右端では、α＝１であるから、式（４）において、
Ｒ３＝α×Ｒ１＋（１−α）Ｒ２＝Ｒ１
Ｇ３＝α×Ｇ１十（１−α）Ｇ２＝Ｇ１
Ｂ３＝α×Ｂ１＋（１−α）Ｂ２＝Ｂ１
となり、第三の画像は第一の画像と等しくなる。
【００３８】
αの値が０と１の間では、第三の画像は第一の画像と第二の画像が混ぜ合わされた画像となる。
【００３９】
以上説明したように、第二の実施形態によれば、マウス等の入力装置を用いて対話的にαの値を制御する構成を付加したことにより、ユーザが、容易に、好みの度合いで第一の画像と第二の画像を混ぜることが可能になる。
【００４０】
なお、本発明は、複数の機器（例えばホストコンピュータ，インタフェイス機器，リーダ，プリンタなど）から構成されるシステムに適用しても、一つの機器からなる装置（例えば、複写機，ファクシミリ装置など）に適用してもよい。
【００４１】
また、本発明の目的は、前述した実施形態の機能を実現するソフトウェアのプログラムコードを記録した記憶媒体を、システムあるいは装置に供給し、そのシステムあるいは装置のコンピュータ（またはＣＰＵやＭＰＵ）が記憶媒体に格納されたプログラムコードを読出し実行することによっても、達成されることは言うまでもない。
【００４２】
この場合、記憶媒体から読出されたプログラムコード自体が前述した実施形態の機能を実現することになり、そのプログラムコードを記憶した記憶媒体は本発明を構成することになる。
【００４３】
プログラムコードを供給するための記憶媒体としては、例えば、フロッピディスク，ハードディスク，光ディスク，光磁気ディスク，ＣＤ−ＲＯＭ，ＣＤ−Ｒ，磁気テープ，不揮発性のメモリカード，ＲＯＭなどを用いることができる。
【００４４】
また、コンピュータが読出したプログラムコードを実行することにより、前述した実施形態の機能が実現されるだけでなく、そのプログラムコードの指示に基づき、コンピュータ上で稼働しているＯＳ（オペレーティングシステム）などが実際の処理の一部または全部を行い、その処理によって前述した実施形態の機能が実現される場合も含まれることは言うまでもない。
【００４５】
さらに、記憶媒体から読出されたプログラムコードが、コンピュータに挿入された機能拡張ボードやコンピュータに接続された機能拡張ユニットに備わるメモリに書込まれた後、そのプログラムコードの指示に基づき、その機能拡張ボードや機能拡張ユニットに備わるＣＰＵなどが実際の処理の一部または全部を行い、その処理によって前述した実施形態の機能が実現される場合も含まれることは言うまでもない。
【００４６】
【発明の効果】
以上説明したように、本発明によれば、小数の素材画像で多様な元画像を適切に反映したモザイク画像を生成することが可能となる。
【００４７】
【図面の簡単な説明】
【図１】本発明の一実施形態に係る、モザイク画像生成方法を実現するハードウェア構成図である。
【図２】第１の実施形態によるモザイク画像のせいせい手順を示すフローチャートである。
【図３】第２の実施形態によるモザイク画像生成の手順を説明するフローチャートである。
【図４】α値の変更を行うためのユーザインターフェース例を示す図である。
【図５】モザイク手法において用いられる画像（第一の画像、第二の画像、素材画像）の関係を示す概念図である。
【図６】モザイク手法における第一の画像及び第二の画像の分割方法を示す図である。[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing method and apparatus, and more particularly to an image processing method and apparatus suitable for forming a mosaic image.
[0002]
[Prior art]
Mosaic is widely known as “a combination of small pieces of stone, glass, marble, etc. of various colors, designed on floors, walls, etc. and designed” (Sanseido, contemporary Japanese dictionary) . Using this technique, it is possible to combine a large number of photographic images into a design or a single photographic image.
[0003]
By applying such a mosaic technique to image data processing, it may be possible to replace the original image with a plurality of material images to form a mosaic image. That is, by preparing a plurality of types of material images smaller than the original image, and selecting and arranging them according to the contents of the original image, a mosaic image composed of a plurality of material images can be obtained. .
[0004]
[Problems to be solved by the invention]
However, in the above-described mosaic method, it is assumed that the number of material images is a sufficiently large number so as to have the types of colors and textures that are generally required for constructing a mosaic image. However, in practice, it is difficult to prepare an enormous amount of images as image files in advance, and a large amount of memory is required, resulting in an increase in cost and not so practical. This results in the use of a small number of material images that are insufficient for practicing the mosaic method, and the individual material images that make up the mosaic image may be too different from the color and texture of the original image. There was a problem that the image quality as a mosaic image deteriorated.
[0005]
In addition, even the first target image may not satisfy the image quality of the second image sufficiently.
[0006]
The present invention has been made in view of the above problems, and an object thereof is to provide an image processing method and apparatus capable of generating a mosaic image that appropriately reflects various original images with a small number of material images. To do.
[0007]
[Means for Solving the Problems]
In order to achieve the above object, an image processing apparatus according to an aspect of the present invention includes, for example, the following configuration. That is,
Dividing means for dividing the image into a plurality of partial images;
For each of the partial images obtained by the dividing means, a selection means for selecting one of a plurality of material images prepared in advance based on the feature amount of the partial image;
Combining means for combining the material image selected by the selecting means and the partial image;
Generating means for generating an image by replacing the synthesized image obtained by the synthesizing means with the partial image.
[0008]
An image processing method according to another aspect of the present invention for achieving the above object includes the following steps, for example. That is,
An image processing method by an image processing apparatus,
Dividing means, a dividing step of dividing an image into a plurality of partial images,
A selection step in which the selection means selects one of a plurality of material images prepared in advance based on the feature amount of the partial image for each of the partial images obtained by the dividing step;
A synthesizing unit that synthesizes the material image selected in the selection step and the partial image;
And a generating unit that generates an image by replacing the composite image obtained in the combining step with the partial image.
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.
[0010]
[First Embodiment]
FIG. 1 is a hardware configuration diagram for realizing a mosaic image generating method according to an embodiment of the present invention. In FIG. 1, 101 is a CPU, 102 is a memory, 103 is a hard disk, 104 is a keyboard and mouse (hereinafter referred to as a keyboard 104), 105 is a display, 106 is a network interface, 107 is a DVD-ROM drive, 108 is a scanner, 109 Is a video capture card, 110 is a database connected via a network, and 111 is a bus.
[0011]
The CPU 101 executes the control program stored in the memory 102 to control the above components. The memory 102 stores an execution module of software that realizes the processing procedure described later with reference to the flowchart of FIG. Further, the image data read from the hard disk 103 is stored, and the generated mosaic image is stored.
[0012]
The keyboard 104 is for inputting a user's intention through the user interface. The display 105 displays a first image, a second image, a material image, and the like. Note that the image is input from the database 110 via the network, the image recorded on the CD-ROM by the CD-ROM 107, or the image from the scanner 108. Needless to say, a DVD-ROM or the like may be used as an image input device.
[0013]
It is also possible to use a DVD-ROM drive to capture video recorded on a DVD-ROM.
[0014]
FIG. 5 is a conceptual diagram showing the relationship between images (first image (original image), second image (mosaic image), material image) used in the mosaic technique. In FIG. 5, a first image 2001 is image data representing a design or image that is a base when an image is constructed using a mosaic technique. The second image 2002 is an image configured using a plurality of small images by a mosaic method. That is, the second image 2002 is divided into M × N, and is configured by a combination of material images obtained by arranging M × N material images in each divided region.
[0015]
A material image 2003 is an image used to configure the second image 2002. The number P of material images is generally large enough to prepare the types of colors and textures necessary for constructing the second image. Here, in order to simplify the description, the size of P material images is the same size as the tile, that is, p × q (pixels) as described below, but this does not necessarily need to match, , P sheets need not all be the same size. However, when material images having different sizes are included, it is necessary to convert the size of the material image to the tile size when pasting the material image on the corresponding tile portion.
[0016]
Next, a method for constructing a mosaic image will be described with reference to FIGS. FIG. 2 is a flowchart showing a mosaic image generation procedure according to the first embodiment. FIG. 6 is a diagram showing a method for dividing the first image and the second image in the mosaic method.
[0017]
First, in step S201, the first image (original image) is divided into M × N tiles as shown in FIG. As a result of the division, as shown in FIG. 6, the first image has M × N rectangular tiles TL (0,0), TL (1,0), TL (2,0)... TL (2,4 ), TL (3, 4). In FIG. 6, X and Y are the numbers of pixels in the horizontal direction and the vertical direction of the first image 2001, respectively. p and q are the numbers of pixels in the horizontal and vertical directions of each tile. Therefore, the relationship X = p × M, Y = q × N is established. Here, for the sake of simplicity, it is assumed that the tiles are all equal in size, but this is not necessary.
[0018]
In step S202, an evaluation target value is calculated for each of M × N tiles divided in step S201. In order to construct a mosaic image, it is necessary that the tile obtained by dividing the first image and the material image pasted with the tile are similar under a certain evaluation criterion. That is, a variable (hereinafter referred to as a feature value) is calculated from an image by a predetermined method, and a value obtained from an image of each tile (hereinafter referred to as an evaluation target value) and a value obtained from a material image (hereinafter referred to as an evaluated value). ). Then, the tile image is replaced with a material image having a close value.
[0019]
Here, the evaluation target value is a feature amount calculated for each tile image obtained by dividing the first image by a certain method. For example, the average luminance value of R, G, B can be used as this feature amount. In this case, the evaluation target values (Rd-av, Gd-av, Bd-av) are calculated by the following equation (1). Needless to say, as the evaluation target value, for example, another feature amount such as an average density value of each image may be used.
[0020]
Rd-av = (1 / (p × q)) × ΣRi
Gd-av = (1 / (p × q)) × ΣGi
Bd-av = (1 / (p × q)) × ΣBi (1)
Here, i represents all the pixels in the tile.
[0021]
In step S203, an evaluated value is calculated for P material images. The evaluated value is obtained for each material image, which is the same as the feature amount used in step S202. Therefore, when the average luminance values of R, G, and B are used as feature amounts, the evaluated values (Rs-av, Gs-av, Bs-av) are obtained by the following equation (2).
[0022]
Rs-av = (1 / p × q)) × ΣRi
Gs-av = (1 / p × q)) × ΣGi
Bs-av = (1 / p × q)) × ΣBi (2)
Here, i represents all the pixels in the material image.
[0023]
In step S204, one tile to be processed is selected from the M × N tiles. Here, the tile is specified using counters X-Pos (0 ≦ X-Pos ≦ M−1) and Y-Pos (0 ≦ Y-Pos ≦ N−1) indicating the position of the tile. As an example, when processing from the upper left to the right edge of the image and processing sequentially from the lower end, first, both X-Pos and Y-Pos are initialized to 0, and in the repetition of steps S2104 to S2107 (X-pos, Y-pos ) = (0,0), (1,0) ... (3,0), (0,1), ... (3,1), ... (0,4), ... (3,4) Change the value.
[0024]
In step S205, the evaluation target values (Rd-av, Gd-av, Bd-av) of the tiles to be processed and the evaluated values (Rs-av, Gs-av, Bs-av) of the P material images are obtained. Is evaluated by the evaluation function f (). As an example of the evaluation function f (), the mean square of the difference between the evaluation target value and the evaluated value can be mentioned. That is, the evaluation value is obtained by the following formula (3).
[0025]

In the above formula (3), “^” represents a power, for example, “X ^ 2” represents the square of X. As a result, P evaluation results of ΔE0 to ΔEp-1 are selected.
[0026]
In step S206, the material image having the smallest value is selected from the results of the P evaluation functions, and the tile specified by the corresponding tile position (ie, (X-pos, Y-pos)) of the second image. ) Tiles to be pasted on.
[0027]
In step S207, it is determined whether or not the above processing has been performed for all tiles of the first image. If there is an unprocessed tile, the processing returns to step S204 and the above processing is repeated. On the other hand, if all tiles have been processed, the process proceeds to step S208.
[0028]
In step S208, the α value input by the operator is read from the keyboard 104. However, the value of α will be described as 0 or more and 1 or less. In step S209, the third image is synthesized using the first image, the second image, and α, and this is used as the final mosaic image.
[0029]
An example of an image composition method using α is to add α times the first image and (1−α) times the second image. That is, if the pixel values at the same position of the first image and the second image are (R1, G1, B1) and (R2, G2, B2), respectively, the same position of the third image obtained as a result of the synthesis The pixel values (R3, G3, B3) are obtained by the following equation (4).
[0030]
R3 = α × R1 + (1-α) R2
G3 = α × G1 + (1-α) G2
B3 = α × B1 + (1-α) B2
It becomes.
[0031]
As described above, according to the present embodiment, even when the individual tiles of the second image created by the mosaic image construction method are too different from the colors and textures of the first image. Since the first image is reflected at the set rate, it is possible to obtain an image in which the first image is well-defined as a whole. Therefore, a good mosaic image can be obtained with a small number of material images.
[0032]
[Second Embodiment]
Next, a second embodiment of the present invention will be described. In the following, differences between the first embodiment and the second embodiment will be described.
[0033]
FIG. 3 is a flowchart for explaining a procedure for generating a mosaic image according to the second embodiment. Steps S201 to S209 are executed in the same manner as in the first embodiment, and as a result, a first image and a third image that is a second composite image are obtained. In step S310, the third image is displayed on the display device. In step S311, an interface through which an α value can be changed is displayed, and it is determined whether or not the α value has been changed by the operator. If the α value is changed, the process returns to step S208, and the third image is generated using the changed α.
[0034]
FIG. 4 is a diagram illustrating an example of a user interface for changing the α value. A user interface as shown in FIG. 4 is displayed on the display device 105. In FIG. 4, 401 is a display unit for displaying a first image, 402 is a display unit for displaying a third image, 403 is a start button for instructing start of processing, and 404 is a slider for changing an α value. Further, a second image may be displayed. If the second image is also displayed, it becomes a reference when the operator sets the value of α.
[0035]
Before the start button 403 is pressed, the first image is displayed at 401. When the start button 403 is pressed, the process starts from step S201 in the flowchart. When step S209 is completed, the third image is displayed on the display unit 402. Subsequently, the slider 404 is operated with the mouse. The slider 404 has α = 0 at the leftmost end and α = 1 at the rightmost end, and the interval is equally divided.
[0036]
Since α = 0 at the leftmost position of the slider 404, in the equation (4),
R3 = α × R1 + (1-α) R2 = R2
G3 = α × G1 + (1−α) G2 = G2
B3 = α × B1 + (1-α) B2 = B2
Thus, the third change is equal to the second image.
[0037]
In addition, since α = 1 at the right end of the slider 404, in the equation (4),
R3 = α × R1 + (1-α) R2 = R1
G3 = α × G1 + (1-α) G2 = G1
B3 = α × B1 + (1−α) B2 = B1
And the third image is equal to the first image.
[0038]
When the value of α is between 0 and 1, the third image is an image obtained by mixing the first image and the second image.
[0039]
As described above, according to the second embodiment, by adding a configuration that interactively controls the value of α using an input device such as a mouse, the user can easily set It is possible to mix one image with a second image.
[0040]
Note that the present invention can be applied to a system composed of a plurality of devices (for example, a host computer, interface device, reader, printer, etc.), or a device (for example, a copier, a facsimile device, etc.) composed of a single device. You may apply to.
[0041]
Another object of the present invention is to supply a storage medium storing software program codes for implementing the functions of the above-described embodiments to a system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the storage medium. Needless to say, this can also be achieved by reading and executing the program code stored in the.
[0042]
In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention.
[0043]
As a storage medium for supplying the program code, for example, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.
[0044]
Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) operating on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.
[0045]
Further, after the program code read from the storage medium is written into a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that the CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing.
[0046]
【The invention's effect】
As described above, according to the present invention, it is possible to generate a mosaic image that appropriately reflects various original images with a small number of material images.
[0047]
[Brief description of the drawings]
FIG. 1 is a hardware configuration diagram for realizing a mosaic image generating method according to an embodiment of the present invention.
FIG. 2 is a flowchart showing a procedure for culling a mosaic image according to the first embodiment.
FIG. 3 is a flowchart for explaining a procedure for generating a mosaic image according to a second embodiment;
FIG. 4 is a diagram illustrating an example of a user interface for changing an α value.
FIG. 5 is a conceptual diagram illustrating a relationship between images (first image, second image, and material image) used in the mosaic method.
FIG. 6 is a diagram illustrating a method of dividing a first image and a second image in a mosaic method.

Claims (13)

Dividing means for dividing the image into a plurality of partial images;
For each of the partial images obtained by the dividing means, a selection means for selecting one of a plurality of material images prepared in advance based on the feature amount of the partial image;
Combining means for combining the material image selected by the selecting means and the partial image;
An image processing apparatus comprising: generating means for generating an image by replacing the synthesized image obtained by the synthesizing means with the partial image. The image processing apparatus according to claim 1, wherein the selection unit uses a luminance value of each color component as a feature amount of the partial image. The image processing apparatus according to claim 1, wherein the selection unit selects a material image having a feature amount closest to a feature amount of the partial image from the plurality of material images. The image processing according to claim 1, wherein the synthesizing unit synthesizes the material image selected by the selection unit and the partial image at a synthesis ratio determined in accordance with a preset coefficient. apparatus. The synthesizing means sets the value obtained by multiplying the pixel value of the material image selected by the selection means by α and the pixel value of the partial image as 1-α when the coefficient is in a range of 0 to 1. The image processing apparatus according to claim 4, wherein a value obtained by adding the value multiplied by α is a pixel value of the composite image. The image processing apparatus according to claim 4, further comprising a user interface that allows an operator to set the coefficient. An image processing method by an image processing apparatus,
Dividing means, a dividing step of dividing an image into a plurality of partial images,
A selection step in which the selection means selects one of a plurality of material images prepared in advance based on the feature amount of the partial image for each of the partial images obtained by the dividing step;
A synthesizing unit that synthesizes the material image selected in the selection step and the partial image;
The image processing method of generating means, characterized in that the synthesized image obtained by the synthesis step and a generation step of generating an image by replacing the partial image. The image processing method according to claim 7, wherein in the selection step , a luminance value of each color component is used as a feature amount of the partial image. The image processing method according to claim 7 or 8, wherein, in the selection step , a material image having a feature amount closest to a feature amount of the partial image is selected from the plurality of material images. Wherein in the synthesizing step, the synthesis ratio determined according to a preset coefficients, image according to claim 7, wherein the synthesis of selected material image and in the selection step and the partial image Processing method. In the synthesizing step , when the coefficient is α in the range of 0 to 1, the value obtained by multiplying the pixel value of the material image selected in the selection step by α and the pixel value of the partial image are set to 1 The image processing method according to claim 10, wherein a value obtained by adding the value multiplied by −α is used as a pixel value of the composite image. The control means further comprises a control step of controlling a user interface that allows the coefficient to be set by an operator and providing the coefficient set via the user interface to the synthesis step. The image processing method according to 10 or 11. A computer-readable storage medium storing a program for causing a computer to function as the image processing apparatus according to any one of claims 1 to 6.

Images