JP2010097449A - Image composition device, image composition method and image composition program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To obtain an image of a natural face without incongruity when processing an optional person's face to a face resembling a face of another person. <P>SOLUTION: When an image composition mode is set in a digital camera provided with the image composition mode, a CPU 6 is made to perform processing of setting a composition ratio of a first image and a second image according to a request of a user, and processing of composing the first image and the second image at the set composition ratio to generate a composition image, and the generated composition image is made to be displayed on a display 13. When composing the second image to the first image to generate the composition image, such a characteristic that the user intends as a characteristic of the first image is secured in the composition image. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image composition apparatus, an image composition method, and an image composition program that generate a new face image from two different face images, for example.

Conventionally, there is a service in which two face photographs are combined to create another face photograph and provided to the user (see Non-Patent Document 1). According to this service, the user can see and enjoy a composite image of his / her face and a celebrity's face. This uses a computer graphics technique called morphing (hereinafter referred to as morphing composition processing) used in movies and the like, and is a face image during transformation from one face image to the other face image. Is used to generate a face having an intermediate feature between the two faces. By using such a technique, it is possible to easily obtain a face obtained by synthesizing one's face with the face of a favorite celebrity or entertainer.
Morph Thing homepage, [online], Internet <URL: http://www.morphthing.com/>

  However, if the above technique is used, an image obtained by processing an arbitrary person's face into a face resembling the face of another person can be easily obtained. If they are significantly different, the newly generated composite image often becomes, for example, a face image that does not have much of the original facial features against the user's intention. For this reason, there is a problem that it is extremely inconvenient when it is desired to process the face of an arbitrary person into a face similar to the face of another person.

  The present invention has been made in view of such conventional problems, and when a face of an arbitrary person is processed into a face similar to the face of another person, an image of a natural face without a sense of incongruity is easily obtained. An object of the present invention is to provide an image composition apparatus, an image composition method, and an image composition program used for realizing them.

  In order to solve the above-described problem, in the image composition device according to the first aspect of the present invention, composition ratio setting means for setting a composition ratio between the first image and the second image according to a user's request; The image processing apparatus further includes image combining means for generating a combined image by combining the first image and the second image at the combining ratio set by the combining ratio setting means.

  In the image composition device according to the second aspect of the present invention, the first image is a first face image, and the second image is a second face image, and the image The synthesizing means generates a third face image as a synthesized image.

  Further, in the image composition device according to the invention of claim 3, the image composition apparatus further comprises a part setting means for setting a part for synthesizing the second image for the first image according to a user's request, The image synthesizing unit, when generating the synthesized image, sets the combination ratio between the first image and the part set by the part setting unit and the corresponding part of the second image corresponding to the part. The synthesis is performed at a synthesis ratio set by the means.

  In the image composition device according to the invention described in claim 4, the part setting means sets a plurality of parts for compositing the second image for the first image in response to a user's request. The composition ratio setting means sets the composition ratio of the first image and the second image for each part set by the part setting means in response to a user request. When the composite image is generated, the combination of the plurality of parts that are the first image and set by the part setting unit and the plurality of corresponding parts of the second image that correspond to the plurality of parts. The composition is characterized by combining at a composition ratio set for each part by the ratio setting means.

  In the image composition device according to the fifth aspect of the present invention, among the image storage means storing a plurality of predetermined images and the plurality of images stored in the image storage means, the first A similar image extracting unit that extracts a similar image similar to the first image as the second image, and the image synthesizing unit includes the first image and the first image at a synthesis ratio set by the synthesis ratio setting unit. The synthesized image is generated by synthesizing the similar image extracted as the second image by the similar image extracting means.

  According to a sixth aspect of the present invention, there is provided an image synthesizing apparatus comprising: an imaging unit that captures an image of a subject; and a storage unit that records an image of the subject imaged by the imaging unit. The first image and the second image based on the image recorded in the storage unit are synthesized to generate a synthesized image.

  The image composition method according to claim 7 is an image composition method for generating a composite image by combining the first image and the second image, the first image and the second image. A step of setting a composite ratio of the first image and the second image according to a user request, and a step of generating a composite image by combining the first image and the second image at the set composite ratio. It is characterized by.

  In the image composition program according to the invention described in claim 8, the first image and the first image are stored in a computer included in an image composition apparatus that synthesizes the first image and the second image to generate a composite image. A procedure for setting a composite ratio with the second image according to a user's request and a procedure for generating a composite image by combining the first image and the second image at the set composite ratio are executed. It is characterized by being.

  According to the present invention, when a face of an arbitrary person is processed into a face similar to the face of another person, it is possible to easily obtain a natural face image without a sense of incongruity.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing an outline of an electronic circuit configuration of a digital camera having a function as an image composition apparatus of the present invention.

  In FIG. 1, the digital camera has a camera module 1 for capturing image data of a photographed subject. The camera module 1 includes an imaging optical system block 2, an image sensor 3, an ISP (lmage Signa1 Processor) 4, and an optical system drive control unit 5. The imaging optical system block 2 includes a zoom motor and a focusing motor for driving a lens group constituting an imaging lens (not shown), an aperture, and a mechanical shutter, which are driven by an optical system drive control unit 5 in accordance with a command from the CPU 6. Controlled.

  The image sensor 3 is a CCD, CMOS sensor, or the like, and photoelectrically converts and A / D-converts the optical image of the subject formed by the imaging lens, and outputs the digital data to the ISP 4. The output of the image sensor 3 is an output according to the color filter array (Bayer array in this embodiment) on the light receiving surface. The ISP 4 performs color adjustment and data format conversion (conversion from Bayer data to Y, Cb, Cr data) on the input digital data.

  Output signals (Y, Cr, and Cb data) from the camera module 1 (ISP 4) are transferred by the DMA 7 to the work memory 8 constituted by a DRAM or the like. The data transferred to the work memory 8 is converted into RGB format image data by the image processing unit 9 and then transferred to the VRAM 11 via the display control unit 12.

  Further, the image processing unit 9 compresses each data of Y, Cr, Cb in the work memory 8 according to a command of the CPU 6 and converts it into image data of a predetermined file format such as JPEG. The converted image data is stored in the flash memory 10, read out as necessary, decompressed by the image processing unit 9, and expanded in the work memory 8.

  The display control unit 12 generates display data based on the image data stored in the VRAM 11 and outputs the display data to the display unit 13 including a liquid crystal monitor or the like, and causes the display unit 13 to display an image. For example, an image sequentially captured by the camera module 1 at a predetermined frame rate in the shooting standby state is displayed on the display unit 13 as a through image. Further, a recorded image based on the image data read from the flash memory 10 and expanded is displayed on the display unit 13. Further, the image data may be combined with various OSD (On Screen Display) data such as a menu screen used for various operation settings of the digital camera, as necessary, or a display composed of only the menu screen. Data is generated and output to the display unit 13.

  The key input unit 14 includes a power key, a mode setting key, a shutter button, a menu key, a control key including a cursor key, and a SET key, which are not shown, and outputs a status signal indicating the operation state of each key to the CPU 6. The mode setting key is a key for setting a basic operation mode of the digital camera to a shooting mode or a playback mode for displaying a recorded image. In addition, the control key is a key having a structure capable of performing a direction instructing operation and confirming operation in the up / down / left / right directions generally used in a digital camera. This is used for selecting an item, selecting a setting value of the selected item, determining setting contents, and the like.

  The USB control unit 15 controls communication of image data between a personal computer or the like connected to the USB connection terminal unit 16 via a USB cable and the digital camera.

  FIG. 2 is a conceptual diagram showing a memory space of the flash memory 10. The flash memory 10 has a program data storage area 10a, a setting data storage area 10b, a face image data storage area 10c, and a photographed image data storage area 10d as shown in the figure.

  The program data storage area 10a stores an operation program for the CPU 6 and various data (AE control program AE data, etc.) accompanying the operation program. The setting data storage area 10b stores the OSD data described above and various setting data related to the operation contents of the digital camera, such as data set by the user and automatically set data. Has been. The photographed image data storage area 10d stores photographed image data compressed by the image processing unit 9 and converted into image data of a predetermined file format.

  The face image data storage area 10c stores face image data of a person registered in advance by the user. In the present embodiment, the flash memory 10 implements the image storage means of the present invention.

  The CPU 6 controls the operation of each part of the digital camera in accordance with the status signal from the key input unit 14 and the operation program. For example, shooting operations when the shutter button is pressed, recording of image data, playback / display of recorded images, display control of various function setting screens according to operations of menu keys, cursor keys, and SET keys, and setting contents Make changes.

  When the face registration mode, which is a lower mode of the playback mode, is set by the user, the CPU 6 uses a desired image from the recorded image recorded in the flash memory 10 (the photographed image data storage area 10d). Then, an image showing a person is selected, and the face area of an arbitrary person is selected from the selected image using image recognition techniques such as binarization, contour extraction, pattern matching, etc. Detection is performed using a known face detection technique such as recognizing a part where the nose or mouth is present, and the detected face area is cut out and the image data is stored in the flash memory 10 (face image data storage area 10c). . Further, in the face registration mode, in response to a user request, image data of a face portion sent from a personal computer or the like via a USB cable is also stored in the flash memory 10 (face image data storage area 10c).

  In addition, when an image composition mode provided as a lower mode of the reproduction mode is set by the user, the CPU 6 executes processing described later to perform a composition ratio setting unit, an image composition unit, a part setting unit, It functions as a similar image extraction means. Note that the image composition mode is provided in advance for the purpose of processing a face of an arbitrary person into a face similar to the face of another person, and more specifically, two different faces. This is a mode for generating a composite image (the third face image in the present invention) by combining the images by a predetermined method.

  Next, the processing of the CPU 6 when the image composition mode is set in the digital camera having the above configuration will be described with reference to the flowchart of FIG.

  When the image composition mode is set, the CPU 6 first causes the user to set a unit (composition unit) for composing a face image (step S1). In the present embodiment, two types, “face unit” and “part unit”, can be set as the composition unit. In such processing, a predetermined selection screen is displayed and the user selects one of the composition units. . Further, a list of photographed image thumbnails recorded in the flash memory 10 is displayed on the display unit 13 to allow the user to select a desired image (step S2). However, at this time, the user is allowed to select an image obtained by copying the face of an arbitrary person from the front. Such an image is the first image in the present invention, and in the following description, the image selected here is referred to as an original image.

  Next, the CPU 6 selects the face image most similar to the person's face in the original image (hereinafter referred to as a similar model image) from the face image data stored in the flash memory 10 (face image data storage area 10c). Data, that is, three second images of the present invention are extracted (step S3). In this process, first, after detecting a face area (face part) using a known face detection technique in the same manner as the registration of the face image described above from the original image, for example, a plurality of faces of the face area are detected. For each feature item (face outline, positional relationship between eyes, nose and mouth, etc.), all the stored face image data is matched, the degree of similarity is examined, and each of the plurality of feature items is checked. In accordance with a predetermined ranking criterion based on the similarity, all the stored face image data are ranked in descending order of similarity, and the face images with the first to third ranks are extracted as similar model images.

  Subsequently, after determining the composition unit initially selected by the user (step S4), the CPU 6 performs the following processing described later according to the determination result.

  First, a process when “face unit” is selected as a synthesis unit by the user will be described. When “face unit” is selected, the CPU 6 changes the target similar model images in order, and individually synthesizes each similar model image into the original image at a three-step synthesis ratio. A composite image is generated for each ratio, and the generated composite image data is temporarily stored in the work memory 8 (step S5). The above three-stage synthesis ratios are ratios for synthesizing the similar model image with the original image, differ by 4% from each other, and are 4%, 8%, and 12% at the beginning of the operation. Further, the synthesis of the original image and the similar model image is based on the morphing synthesis process described above.

  Here, FIG. 5 shows an outline of a basic synthesis method for an original image and a similar model image. First, a feature point (black circle in the figure) for specifying the region of the main part A such as the face outline, eyes, nose and mouth is set in the original image f, and a mesh Ms is generated based on the feature point. Similarly, feature points (black circles in the figure) that correspond to each feature point of the original image f and that specify the main part B such as the face outline, eyes, nose, mouth, etc., are displayed on the similar model image g to be synthesized. Set and generate a mesh Mt based on the feature points.

  Next, an intermediate mesh Mi is generated between the mesh Ms and the mesh Mt by linearly interpolate. Next, using the mesh Ms and the intermediate mesh Mi, each point of the image Ls of each mesh in the original image f is warped (transformed) to generate a first mesh image (image1), and the mesh Mt And the intermediate mesh Mi, each point of the image Lg of each mesh in the similar model image g is warped (transformed) to generate a second image (image2). Thereafter, the pixel values (luminance, color difference) of the first mesh image (image1) and the second image (image2) are cross-dissolved, or sparse intermediate pixels are A morphing composite image (image3) is generated by linearly interpolating.

  In step S5, when the above-described intermediate mesh Mi is generated, the arrangement is determined according to the above-described synthesis ratio. For example, if the composition ratio is 90%, that is, “original image: similar model image” = 1: 9, by generating an intermediate mesh Mi that internally divides the mesh Ms and the mesh Mt into 1: 9, a predetermined value is obtained. Each of the composite images (morphing composite images) having the composite ratio is generated.

  After that, after generating the composite image with the composite ratio of three stages for each similar model image as described above, the CPU 6 displays them on the display unit 13 together with the original image and the similar model image (step S6). .

  FIG. 6 is a diagram conveniently showing an example of the display screen G1 of the display unit 13 in that case. In step S6, the CPU 6 displays the original image 201 on the upper left side of the display screen G1, and displays three types of similar model images 202a to 202c in a vertical arrangement in close proximity to the right side of the display screen G1. Between the original image 201 and the first similar model image 202a in the upper right of the screen, a composite image generated based on both images, and the composition ratio of the first similar model image 202a at the time of composition is Three different types of composite images 203a to 203c are displayed side by side, and similarly, there are three types of composite images 203a to 203c corresponding to the second similar model image 202b, and a third similar image thereunder. Three-stage composite images 203a to 203c corresponding to the model image 202c are displayed side by side.

  In addition, a composite ratio (n%) of the similar model images 202a to 202c corresponding to the composite images 203a to 203c with respect to the original image 201 is displayed. Further, a scroll bar 301 for scrolling the respective composite images 203a to 203c is displayed on the lower side of the display screen G1.

  Thereafter, the CPU 6 sequentially detects the presence / absence of a scroll instruction, a recording candidate selection instruction, and a composite image recording instruction by the user. Here, the scroll instruction is, for example, a direction instruction in the right direction or the left direction by the scroll bar 301 in a state where the scroll bar 301 is selected by operating the control key. It is a direction instruction operation and a determination operation.

  When a scroll instruction from the user is detected while the display screen G1 is being displayed (YES in step S7), the above-described three-stage composition ratio is changed step by step so as to increase or decrease (step S8). ), Returning to step S5, changing the composite ratio of each of the similar model images 202a to 202c with respect to the original image 201 to the composite ratio after the change, generating new composite images 203a to 203c (step S6), and displaying them It is displayed on the screen G1.

  For example, when a scroll instruction is given, if composite images with composite ratios of 8%, 12%, and 16% are displayed as composite images 203a to 203c corresponding to the similar model images 202a to 202c, these are displayed. The composite image is changed to three types of composite images with a composite ratio of 12%, 16%, and 20%, or three composite images with composite ratios of 4%, 8%, and 12%.

  If the scroll instruction cannot be detected (NO in step S7), a composite image of recording candidates is continuously set according to the user instruction (step S9). That is, a mark indicating a selection state (a circle in the example in the figure) corresponding to a predetermined key operation is displayed so as to be superimposed on any of the composite images 203a to 203c corresponding to the similar model images 202a to 202c. Is moved according to a direction instruction operation using a control key, and the mark is fixedly displayed according to a determination operation.

  If a recording instruction by the user is detected at any point during the repetition of the processing from step S5 described above (YES in step S10), it is selected at that point (set as a recording candidate) 1 Alternatively, a plurality of composite images are recorded in the captured image data storage area 10d of the flash memory 10 (step S11).

  On the other hand, if “partial unit” is selected as the synthesis unit by the user in step S4 described above, the CPU 6 proceeds to the process shown in FIG. In this case, first, the user selects one or a plurality of facial parts to be synthesized from a plurality of predetermined parts by a scheduled key operation, and the composition ratio (0% for each part) ˜100%) is set (step S12). It should be noted that the selectable parts in the present embodiment are five parts: contour, eyes, eyebrows, nose, and lips (see FIG. 7).

  Next, the original image and each similar model image are combined based on the morphing combining process described above, with the combination ratio for each of the selected one or a plurality of parts being set. Specifically, when the intermediate mesh Mi (see FIG. 5) corresponding to the selected part is generated, the composition ratio set for the part is 90%, that is, “original image: similar model image” = 1: 9. If there is, an intermediate mesh Mi that internally divides the mesh Ms of the original image f and the mesh Mt of the similar model image g into 1: 9 is generated, while the intermediate mesh Mi corresponding to the unselected part is generated as the original image. A process of setting the mesh Ms of f is performed, and the same number of synthesized images as the similar model images are generated. The generated composite image data is temporarily stored in the work memory 8 (step S13).

  Thereafter, the CPU 6 causes the display unit 13 to display the composite image generated for each similar model image together with the original image and the similar model image (step S14). FIG. 7 is a diagram conveniently showing an example of the display screen G2 of the display unit 13 in that case. In step S14, the CPU 6 displays the original image 201 in the upper center of the display screen G2, and displays the display screen. Three types of similar model images 202a to 202c are displayed in a vertical arrangement in the right side of G2. And between the original image 201 and the 1st similar model image 202a of the screen upper right, it is the synthesized image produced | generated based on both images, Comprising: One or several specific site | parts are synthesize | combined by the specific ratio. The synthesized image 203 is displayed, and similarly, the synthesized image 203 synthesized with the second similar model image 202b is synthesized below it, and further synthesized with the third similar model image 202c below it. Each of the composite images 203 is displayed.

  Further, as shown in the drawing, on the left side of the display screen G2, selectable facial parts (contour, eyes, eyebrows, nose, lips), a part selected at that time, and a part are set. Displays the composition ratio. In this embodiment, whether or not each part is selected is indicated by a so-called radio button 401, and the composition ratio is displayed at the position of the slider 402.

  Thereafter, the CPU 6 sequentially detects whether the user has changed the synthesis site or whether the synthesis ratio has been changed, a recording candidate selection instruction, and a composite image recording instruction. Here, the change of the synthesis part is an instruction to change the on / off state of the radio button 401 in a state where an arbitrary part is selected, for example, by operating a control key, and the change of the synthesis ratio is a state where an arbitrary part is selected. The direction selection instruction is a direction instruction operation and a determination operation by a control key.

  When a change in the synthesis site or a change in the synthesis ratio is detected during display of the display screen G2 (YES in step S15), the process returns to step S13 described above, and a new synthesized image is generated according to the changed setting contents. Then, the generated composite image data is temporarily stored in the work memory 8 and displayed in the display screen G2.

  If a change in the synthesis site or a change in the synthesis ratio cannot be detected (NO in step S15), a composite image of a recording candidate is continuously set according to the user's instruction (step S16). In other words, a mark indicating a selected state according to a predetermined key operation (a circle in the example in the figure) is displayed so as to be superimposed on one of the composite images 203 corresponding to each of the similar model images 202a to 202c. The mark is moved according to the direction instruction operation using the control key, and the mark is fixedly displayed according to the determination operation.

  If a user's recording instruction is detected at any point in time while repeating the above-described steps S13 to S16 (YES in step S17), the process proceeds to step S11 in FIG. One or a plurality of composite images (set as recording candidates) are recorded in the captured image data storage area 10 d of the flash memory 10. This completes one process in the image composition mode.

  As described above, in the digital camera of the present embodiment, by using the image composition mode, an image obtained by processing an arbitrary person's face into a face similar to the face of another person can be easily obtained. In addition, in this case, if the user selects “face unit” as the synthesis unit, the synthesis ratio between the original image and the similar model image can be adjusted to a desired ratio. The facial features of the original person can be ensured in the face image to the extent intended by the user. As a result, when an arbitrary person's face is processed into a face similar to the face of another person, an image of a natural face without a sense of incongruity can be obtained.

  Further, in the present embodiment, when the user first designates an original image, a similar model image that is an image of a face most similar to a human face in the original image among the face images stored in the flash memory 10. Therefore, when an arbitrary person's face is processed into a face similar to the face of another person, a natural face image without a sense of incongruity can be easily obtained.

  Further, if the user selects “part unit” as the synthesis unit, the original image and the similar model image can be synthesized only for necessary parts with each part of the face as a unit. Therefore, it is possible to generate a face image reflecting the user's detailed intention as a face image after synthesis (after processing). Furthermore, since the composition ratio can be designated for each part at that time, it is possible to generate a face image reflecting a finer intention of the user.

  In the present embodiment, the above-described image composition mode is provided in advance for the purpose of processing an arbitrary person's face into a face similar to the face of another person. In the mode, when an original image is designated, a similar model image is automatically extracted as an image to be combined with the original image, and the original image and the similar model image are combined to generate a new image. When the image compositing mode is to be used for a wide range of purposes, the image to be composited with the original image can be a registered person's face image or other recorded images (photographs of the person's face). You may make it make a user select manually from (image).

  Further, the image to be combined with the original image does not necessarily have to be taken by the own device, and any image can be used as long as it is an image stored in the flash memory 10. For example, if an image of the face of a favorite celebrity or entertainer is stored in advance, it is possible to confirm the face when all or part of his / her face is cosmetically shaped to resemble a celebrity or the like. Further, if the first face image taken at the first age and the second face image taken at the second age are stored for the same person, the first age can be stored. A face at an arbitrary age up to the second age can be confirmed in a pseudo manner. Furthermore, for example, a large number of face images are registered (stored) as face images, “part unit” is selected as a synthesis unit, and only a specific part is synthesized, and then the synthesized image is identified again as an original image. If the operation of combining only the parts is repeated, a natural montage image without a sense of incongruity can be obtained.

  Furthermore, although the case where the two images to be combined are human face images has been described in the present embodiment, the present invention is not limited to this, and the present invention is also applicable to a case of combining images other than human face images. be able to. For example, one or both images may be the face of an animal such as a pet, and the present invention can also be applied to a case where a new image is synthesized with any other image as a target.

  Although the case where the present invention is applied to a digital camera has been described here, the present invention is also applicable to an arbitrary image composition device such as a personal computer as long as the device has a function of combining two different images. be able to.

1 is a block diagram of a digital camera according to the present invention. It is a conceptual diagram which shows the memory space of flash memory. It is the flowchart which showed the processing content of CPU when the image composition mode is set. It is a flowchart following FIG. It is a schematic explanatory drawing which shows the synthetic | combination method of an original image and a similar model image. It is the figure which showed an example of the display screen containing a synthesized image when "the face unit" is selected as a synthetic | combination unit. It is the figure which showed an example of the display screen containing a synthetic image when "partial unit" is selected as a synthetic | combination unit.

Explanation of symbols

1 Camera module 3 Image sensor 6 CPU
7 DMA
8 Work memory 9 Image processing unit 10 Flash memory 14 Key input unit

Claims (7)

A composition ratio setting means for setting a composition ratio of the first image and the second image according to a user's request;
An image composition apparatus comprising: an image composition unit configured to compose the first image and the second image at a composition ratio set by the composition ratio setting unit to generate a composite image. The first image is a first face image and the second image is a second face image;
The image synthesizing apparatus according to claim 1, wherein the image synthesizing unit generates a third face image as a synthesized image. A site setting means for setting a site for synthesizing the second image for the first image according to a user's request;
The image synthesizing unit, when generating the synthesized image, combines the part of the first image that is set by the part setting unit and the corresponding part of the second image corresponding to the part. The image synthesizing apparatus according to claim 1, wherein the images are synthesized at a synthesis ratio set by a setting unit. The part setting means sets a plurality of parts for combining the second image with respect to the first image according to a user's request,
The composition ratio setting means sets a composition ratio of the first image and the second image for each part set by the part setting means in response to a user's request. In generating a composite image, the plurality of parts that are the first image and set by the part setting unit and the corresponding parts of the second image that correspond to the plurality of parts are combined with each other. The image synthesizing apparatus according to claim 3, wherein the composition is performed at a composition ratio set for each part by the setting unit. Image storage means for storing a plurality of predetermined images;
A similar image extracting means for extracting, as the second image, a similar image similar to the first image among the plurality of images stored in the image storage means,
The image synthesizing unit synthesizes the first image and the similar image extracted as the second image by the similar image extracting unit by the synthesis ratio set by the synthesis ratio setting unit, and generates a synthesized image. The image synthesizing apparatus according to claim 1, wherein the image synthesizing apparatus is generated. An image composition method for compositing a first image and a second image to generate a composite image,
Setting a composite ratio of the first image and the second image according to a user's request;
And a step of synthesizing the first image and the second image at a set composition ratio to generate a composite image. A computer included in an image composition device that composes a first image and a second image to generate a composite image,
A procedure for setting a composite ratio of the first image and the second image according to a user's request;
An image synthesizing program comprising: executing a procedure of synthesizing the first image and the second image at a set synthesis ratio to generate a synthesized image.

Images