JP2007334784A - Image-generating device, image generation method, image-generating program, and recording medium thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem, wherein conventional technologies for printing on a label deform image results in a distorted image, and consequently the content of the image is not accurately expressed to give an artificial image. <P>SOLUTION: An image processing part 24 deforms the shapes of respective images to make them the same shapes as those of respective printing areas so that the images are printed on the respective printing areas, with the respective images being determined to arrange in the respective printing areas by an arrangement determination part 23. At this time, a main image-specifying part 24A specifies a main image part, which becomes a main object, from the overall image, and an image processing part 24B deforms the shapes of the images to make them the same shapes as those of the printing areas, by using a deformation degree which makes the specified main image part fixed and other parts, other than the main image part, to be variable. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image generation apparatus that generates an image to be printed on a label surface of a recording medium, an image generation method, an image generation program, and a recording medium that records the program.

  2. Description of the Related Art Conventionally, there is a technique for printing a title, an image, or the like on a label surface of a recording medium such as a CD-R (CD Recordable) or a DVD-R (DVD Recordable) using a printer. For example, in the technique described in Patent Document 1 below, in order to print an image to be printed on a circular label surface, the image is deformed and printed concentrically.

JP 2005-25283 A

  However, in the technique of printing on the label surface as described in Patent Document 1 above, the image is distorted by deforming the image into concentric circles, and the image content is not accurately expressed and is unnatural. It becomes an image. For example, when a person's face is in the center of the image, the face is deformed into a concentric circle and an uncomfortable face is printed.

  An object of the present invention is to provide an image generation apparatus, an image generation method, and an image generation program that can produce a natural image by accurately expressing the image contents even when the image to be printed is deformed for printing on the label surface. And providing a recording medium in which the program is recorded.

  In order to solve the above-described problem, an image generation apparatus according to the present invention is an image generation apparatus that generates an image to be printed on a label surface of a recording medium, the image acquisition unit that acquires an image, and the acquired An image selection unit that selects an image to be printed from an image; and an image processing unit that converts the image to be printed into an image to be printed on the label surface. A main image specifying unit that specifies a main image part that is a main object from the image, and an image processing unit that transforms a shape other than the main image part into a predetermined shape without changing the shape of the main image part. Prepare.

  According to the image generating apparatus of the present invention, the image to be printed acquired by the image acquisition unit and selected by the image selection unit is converted into an image to be printed on the label surface by the image processing unit. The image processing unit included in the image processing unit transforms the shape other than the main image portion into a predetermined shape while keeping the shape of the main image portion specified by the main image specifying unit. Thereby, the shape of the image part that becomes unnatural when deformed is not deformed, and the other image part can be deformed into an image adapted to the label surface. For this reason, the image to be printed on the label surface converted by the image processing unit is a natural image in which the image content is accurately expressed.

  In the above-described image generating apparatus according to the present invention, the main image portion is at least one of an image at a position close to a central portion of the image to be printed and an image showing the object.

  In the above-described image generating apparatus according to the present invention, the object is a person or an animal, and the image indicating the object is an image including a face area of the object.

  In the image generating apparatus according to the present invention described above, the image processing unit has a plurality of divisions obtained by dividing the shape other than the main image portion into a substantially fan shape when the label surface is circular. Deforms according to one shape of the region.

  In the image generating apparatus according to the present invention described above, the image processing unit reduces the deformation of the image around the main image portion, and gradually deforms as it approaches the end of the image to be printed. Do more.

  The image generation apparatus according to the present invention described above further includes a feature information detection unit that detects feature information of an image included in the image to be printed, and the image selection unit selects the feature when selecting a plurality of images. Images having similar feature information detected by the information detection unit are selected.

  The image generation apparatus according to the present invention described above further includes an arrangement determination unit that determines an arrangement of the image to be printed on the label surface, and the arrangement determination unit is detected by the feature information detection unit. The arrangement on the label surface is determined based on the feature information of the left and right ends of the image.

  In the image generating apparatus according to the present invention described above, an image information output unit that outputs image information for identifying an image acquired by the image acquisition unit, and designation information that is information designated by a user for the output image information A designation information acquisition unit that acquires the image information, and the image selection unit selects an image based on the acquired specification information.

  An image generation method according to the present invention is an image generation method for generating an image to be printed on a label surface of a recording medium in order to solve the above-described problem, an image acquisition step for acquiring an image, and the acquired image An image selection step of selecting an image to be printed from the image, and an image processing step of converting the image to be printed into an image to be printed on the label surface, wherein the image processing step includes the image to be printed To a main image specifying step of specifying a main image portion as a main object, and an image processing step of deforming a shape other than the main image portion into a predetermined shape while keeping the shape of the main image portion as it is.

  An image generation program according to the present invention is an image generation program for generating an image to be printed on a label surface of a recording medium in order to solve the above-described problem, an image acquisition function for acquiring an image, and the acquired image An image selection function for selecting an image to be printed from the image, and an image processing function for converting the image to be printed into an image to be printed on the label surface, wherein the image processing function is the image to be printed. A main image specifying function for specifying a main image portion as a main object, and an image processing function for deforming a shape other than the main image portion into a predetermined shape while keeping the shape of the main image portion as it is.

  A recording medium according to the present invention is a computer-readable recording medium in which the image generation program is recorded in order to solve the above-described problem.

(First embodiment)
Hereinafter, an image generation apparatus according to a first embodiment of the present invention will be described with reference to the drawings.

<Configuration of Image Generation Device>
First, the configuration of the image generation apparatus according to the first embodiment will be described.
FIG. 1 is an explanatory diagram illustrating a hardware configuration of the image generation apparatus according to the first embodiment of the present invention. As shown in FIG. 1, the image generation apparatus 1 is a general-purpose computer and includes a CPU 2, a ROM 3, a RAM 4, a hard disk 5 and an input / output I / F (interface) 7, which are connected to each other via a bus 6. ing. A CD-R / RW drive 8 and a DVD-R / RW drive 9 are connected to the image generation apparatus 1 via an input / output I / F 7.

  In the image generation apparatus 1, the CPU 2 reads and executes an image generation program stored in the ROM 3 or the hard disk 5, thereby functioning as each unit shown in FIG. 2 to be described later. Is to be generated. The image generation program executed by the CPU 2 may be stored in the ROM 3 or the hard disk 5 in advance, or the image generation program read by the CD-R / RW drive 8 or the like may be stored in the hard disk 5. Further, a server or the like that supplies the image generation program as data may be accessed via network means such as the Internet, and the data may be downloaded and stored in the hard disk 5.

  FIG. 2 is a block diagram illustrating a functional configuration of the image generation apparatus 1. As illustrated in FIG. 2, the image generation apparatus 1 includes an image acquisition unit 20, a feature information detection unit 21, an image selection unit 22, an arrangement determination unit 23, and an image processing unit 24. The image processing unit 24 includes a main image specifying unit 24A and an image processing unit 24B.

  The image acquisition unit 20 includes a plurality of images such as a person image and a landscape image from a recording medium such as a CD-R or DVD-R set in the CD-R / RW drive 8 or the DVD-R / RW drive 9. Is obtained via the input / output I / F 7. These acquired images are stored in the data area of the hard disk 5. The acquired image is not limited to an image recorded on a recording medium such as a CD-R or a DVD-R, and an image directly acquired from a digital camera, a scanner, or the like via the input / output I / F 7 or an input / output An image recorded in another storage device connected via the I / F 7 may be used.

  For the plurality of images acquired by the image acquisition unit 20, the feature information detection unit 21 detects the feature information of the entire image and the feature information of the left and right ends of the image from each image.

  The image selection unit 22 selects an image to be printed from a plurality of images acquired by the image acquisition unit 20 based on the feature information of the entire image detected by the feature information detection unit 21.

  The arrangement determination unit 23 arranges the image to be printed selected by the image selection unit 22 in each print area on the label surface based on the feature information of the left and right ends of the image detected by the feature information detection unit 21. decide. In this embodiment, in order to print a plurality of images on a circular label surface, the label surface is equally divided into a plurality of substantially fan-shaped print regions.

  The image processing unit 24 transforms the shape of the image into the shape of the print region so that each image whose placement in the print region is determined by the placement determination unit 23 can be printed in each print region. At this time, the shape of the entire image is not simply deformed to the shape of the print area with a fixed deformation degree, but is deformed with the deformation degree being variable depending on the image content and the image position. Specifically, the main image specifying unit 24A specifies the main image part that is the main object from the entire image, and the image processing unit 24B fixes the specified main image part and changes the parts other than the main image part. The shape of the print area is deformed using the degree of deformation.

  FIG. 7 is an explanatory diagram illustrating an example in which an image to be printed is printed on a label surface. As shown in the figure, here, four images G1 to G4 are selected as images to be printed, and the label surface R of the CD-R is divided into four substantially fan-shaped print regions R1 to R4. Divided equally. Each of these images G1 to G4 is printed in the print areas R1 to R4 after the rectangular image is transformed into a substantially fan-shaped image.

<Image generation operation>
Next, an operation for generating an image in the image generation apparatus 1 will be described.
FIG. 3 is a flowchart showing an operation for generating an image.

  First, in step S110 shown in FIG. 3, the image acquisition unit 20 acquires a plurality of images that are candidates for printing on a label surface such as a CD-R or DVD-R. These images include various images such as a person image and a landscape image, and each image data is for each color of R (red), G (green), and B (blue) for each pixel. This is multi-gradation value data represented by 8 bits.

  In step S120, the feature information detection unit 21 detects the feature information of the image included in each of the plurality of images acquired in step S110. Here, the feature information to be detected includes information indicating the presence / absence of image blurring, camera shake, etc., information on the face image pattern of a person included in the image, information for determining the similarity of the entire image, And information for determining the similarity between the left and right ends. Details of this process will be described later.

  In step S130, the image selection unit 22 selects a plurality of images to be printed from the plurality of images acquired in step S110. Here, the selection of the image is performed in order to determine the information detected in step S120 indicating the presence / absence of image blurring, camera shake, and the like, the information on the face image pattern of the person included in the image, and the similarity of the entire image. Based on information. Details of this process will be described later.

  In step S140, the arrangement determining unit 23 determines the arrangement of each of the plurality of images to be printed selected in step S130 in each print area on the label surface. The arrangement of each image in each print area is such that when the images are arranged in the print area, the images at the adjacent end portions are as similar as possible. Here, the determination as to whether or not the edge image is a similar image is made by determining the feature information detected in step S120, specifically the similarity between the left and right ends of the image detected in step S240 shown in FIG. Based on the information to do.

  In the example shown in FIG. 7, four images G1 to G4 are selected as images to be printed, and the images G1, G2, G3, and G4 are printed in the print areas R3, R4, R1, and R2 on the label surface R, respectively. Has been placed. In addition, the image regions 11 to 14 are provided in the image region at the left end of the images G1 to G4, and the image regions r1 to r4 are provided in the image region at the right end. Here, as shown in the figure, the image areas l3 and r4, l4 and r1, l1 and r2, and l2 and r3 at the adjacent edges on the label surface R are similar to each other.

  In step S150, the image processing unit 24 deforms the shape of the image to be printed so as to match the shape of the print area on the label surface. Here, the main image portion that is the main object is identified from the entire image, and the shape of the main image portion is not deformed, and the shape other than the main image portion is transformed into the shape of each print area on the label surface. To do. At this time, changing the shape other than the main image portion reduces the degree of deformation around the main image portion, and increases the degree of deformation as it approaches the end of the entire image. Details of this process will be described later.

  The image acquisition process and the image acquisition function of the present invention correspond to step S110. The image selection process and the image selection function of the present invention correspond to the above step S130. The image processing step and the image processing function of the present invention correspond to step S150.

<Detecting image feature information>
Next, a description will be given of processing for detecting feature information of each of a plurality of acquired images.
FIG. 4 is a flowchart showing an operation for detecting feature information of an image. When the processing proceeds to the above-described processing for detecting the feature information of the image in step S120 shown in FIG. 3, the processing in step S210 shown in FIG. 4 is started.

  First, in step S210, information indicating the presence / absence of image blurring and camera shake is detected as feature information from the acquired image. In this embodiment, the method for detecting image blur and camera shake determines the amount of edge in the image data, and determines the presence or absence of blur and camera shake based on the size of the edge amount. Image data with a large edge amount is a sharp image with a clear outline, and is determined to be an image without blurring and camera shake. On the other hand, image data with a small edge amount is an image with an unclear outline, It is determined that the image has camera shake or the like. Specifically, if the edge amount is greater than or equal to a predetermined threshold, it is determined that there is no blur and camera shake, and if it is less than the predetermined threshold, it is determined that there is blur and camera shake. Note that the method of detecting blurring, camera shake, and the like is not limited to this method, and may be detected using other methods such as detection based on the brightness characteristics of image data.

  In step S220, information on the face image pattern of the person included in the acquired image is detected as feature information. This face image pattern is for extracting an image that includes the face of the same person from a plurality of images that include a person image, and is detected when the image does not include a person image. Not.

  In step S230, information for determining the similarity of the entire image is detected as feature information from the acquired image. Here, a histogram pattern of hue, brightness, and saturation of the entire image is generated as information for determining the similarity of the entire image.

  In step S240, information for determining the degree of similarity is detected as feature information from the acquired image by limiting to both left and right ends of the image. Here, a histogram pattern of hue, brightness, and saturation at the left and right ends of the image is generated as information for determining the similarity between the left and right ends of the image. In the present embodiment, the left and right ends of the image are regions that occupy an area of 10% of the entire image from the both ends of the image to the inside.

  In step S250, it is determined whether or not the above processing has been completed for all acquired images. If not completed, the process returns to step S210 to process the next image. On the other hand, when the processing is completed, the processing returns to the flowchart shown in FIG.

<Select an image to be printed>
Next, processing for selecting an image to be printed from a plurality of acquired images will be described. FIG. 5 is a flowchart showing an operation for selecting an image to be printed. When the process proceeds to the process of selecting an image to be printed in step S130 shown in FIG. 3, the process of step S310 shown in FIG. 5 is started.

  First, in step S310, based on the information indicating the presence / absence of blur and camera shake detected in step S210 shown in FIG. 4, an appropriate image free of blur and camera shake from a plurality of images acquired in step S110 shown in FIG. Select. That is, an image in which defocusing or camera shake has occurred is excluded from the images to be printed.

In step S320, it is determined whether or not a person image is included in the appropriate image selected in step S310. If at least one person image is included, the process proceeds to step S340, and processing for the person image is performed. On the other hand, if no person image is included, the process advances to step S330 to perform processing for a landscape image or the like that does not include a person image.
Here, whether or not a person image is included in the image is determined based on the information on the face image pattern of the person detected in step S220 shown in FIG.

In step S330, images having the same overall image are selected from the above-described appropriate images by the number of print areas on the label surface, and the images having the similar overall image are selected as images to be printed. The processing returns to the flowchart shown in FIG.
Here, the determination of whether or not the entire image is similar is made based on information for determining the similarity of the entire image detected in step S230 shown in FIG. Specifically, the histogram patterns of hue, brightness, and saturation of the entire image of each image are compared, and when the difference is less than a predetermined threshold, it is determined that the images are similar.

In step S340, an image including the same person is selected from the appropriate images. Then, among the images including the same selected person, the image of the person included in the largest number of images is set as the important person image.
Here, whether or not they are the same person is determined by comparing the face image patterns included in each image based on the face image pattern information of the person detected in step S220 shown in FIG. When it is less than the predetermined threshold, it is determined that they are the same person.
Here, the image of the person included in the largest number of images is the important person image. However, the present invention is not limited to this. For example, among the persons included in each image, the person having the largest face area is selected. The image may be an important person image.

In step S350, the number of important person images selected in step S340 is compared with the number of print areas on the label surface. If the number of important person images is smaller than the number of print areas, that is, if all of the print areas on the label surface are not filled with only the important person images, the process advances to step S360 to further select the insufficient images from the appropriate images.
On the other hand, if the number of important person images is larger than the number of print areas, that is, if there are too many person images that cannot be assigned to the print area, the process proceeds to step S370 to narrow down the important person images.
On the other hand, when the number of important person images is equal to the number of print areas, that is, when all the important person images can be assigned to all the print areas, these important person images are shown in FIG. 3 as images to be printed. Returning to the flowchart processing.

In step S360, in order to add a deficient image, an image whose entire image is similar to the important person image is selected from the appropriate images, and these important person images and the image and the entire image are similar to each other. 3 is returned to the process of the flowchart shown in FIG. 3 as an image to be printed.
Here, the determination as to whether or not the entire image is similar is made based on the information for determining the similarity of the entire image detected in step S230 shown in FIG. 4 as in step S330.

In step S370, in order to set the number of important person images to the number of print areas, the important person images that are similar to each other are narrowed down, and these narrowed images are displayed as images to be printed in the flowchart shown in FIG. Return to processing.
Here, the determination as to whether or not the entire image is similar is made based on the information for determining the similarity of the entire image detected in step S230 shown in FIG. 4 as in step S330.

  In the example shown in FIG. 7, four images G1 to G4 are selected as images to be printed. Here, the same person is included in the images G1 and G2, and these images G1 and G2 are important person images. The images G3 and G4 are selected as images whose entire image is similar to the images G1 and G2.

<Deform the shape of the image>
Next, a process for changing the shape of the image to be printed so as to match the shape of the print area of the label surface will be described.
FIG. 6 is a flowchart showing an operation for changing the shape of an image to be printed. When the process proceeds to the process of deforming the shape of the image in step S150 shown in FIG. 3, the process of step S410 shown in FIG. 6 is started.

  First, in step S410, it is determined whether a person image is included in the image to be printed. If a person image is included, the process proceeds to the next step S420, and image deformation processing for the person image is performed. On the other hand, if a person image is not included, the process proceeds to step S440, and image deformation processing is performed on a landscape image or the like that does not include a person image.

  In step S420, the main image specifying unit 24A specifies an image region whose shape is not deformed when the shape of the image is deformed as a main image portion. Here, the main image portion is an image portion including a person's face area, and includes, for example, the whole body portion, upper body portion, face portion, and the like of the person.

  In step S430, in order to change the shape of the image to the shape of the print area on the label surface, the shape of the main image portion specified in step S420 is not changed, and only the other image portions are changed in shape. Derive and set a vector. At this time, the derived movement vector is a movement vector in which the change in the shape of the periphery of the main image portion is reduced and the change in the shape is increased stepwise as it approaches the end of the entire image.

  In step S440, in order to transform the shape of the image into the shape of the print area on the label surface, a movement vector that is uniformly deformed with a fixed deformation degree is derived and set.

  In step S450, warping is performed based on the movement vector set in step S430 or S440, thereby transforming the image to be printed into the shape of the print area on the label surface.

  In step S460, it is determined whether or not the above processing has been completed for all images to be printed. If not completed, the process returns to step S410 to process the next image. On the other hand, when the processing is completed, the processing returns to the flowchart shown in FIG.

  In the example shown in FIG. 7, people are included in the images G1 and G2, and the whole body of these people is specified as the main image portion. When a rectangular image is changed to a substantially fan shape, only the background image is transformed into a substantially fan shape without changing the shape of these persons. Since the images G3 and G4 are images that do not include a person, the entire image is uniformly transformed into a substantially fan shape.

  The main image specifying step and the main image specifying function of the present invention correspond to step S420 described above. The image processing step and the image processing function of the present invention correspond to the above steps S430, S440, and S450.

  As described above, in the image generation apparatus 1 according to the present embodiment, from the acquired image, information indicating the presence / absence of defocusing and hand shaking of the image, information on the face image pattern of the person included in the image, and the similarity of the entire image Information for determining the degree is detected as image feature information, and an image to be printed is selected based on the feature information. Accordingly, it is possible to obtain an appropriate image in which no blur or camera shake occurs in the image to be printed. In addition, the images printed in the print areas R1 to R4 on the label surface R can be edited into an image group centered on the same person, and even if the image does not include the person, the entire image is displayed. It is possible to make images similar to each other naturally.

  Further, a main image portion that is a main object is specified from the entire image, and the shape of the main image portion is not deformed, and the shapes other than the main image portion are deformed into the shapes of the printing regions R1 to R4. . As a result, the rectangular images G1 to G4 to be printed are transformed into the substantially fan shape of the print regions R1 to R4 while maintaining the shape of the main image portion, so that the entire image of the person to be the main image portion And the shape of the face image can be appropriately expressed without unnatural deformation.

  Further, when each of the images to be printed is arranged in the print regions R1 to R4, based on the information for determining the similarity between the left and right ends of the image detected from the acquired image, the edge of the adjacent image Make the parts as similar as possible. As a result, in the print regions R1 to R4, it is possible to prevent a feeling of incongruity and lack of unity caused by a large difference between images in adjacent portions between the images.

(Second Embodiment)
Hereinafter, an image generation apparatus according to a second embodiment of the present invention will be described with reference to the drawings.

<Configuration of Image Generation Device>
First, the configuration of the image generation apparatus according to the second embodiment of the present invention will be described.
FIG. 8 is an explanatory diagram illustrating a hardware configuration of the image generation apparatus according to the second embodiment. As shown in FIG. 8, in the hardware configuration of the image generation apparatus 10 according to the second embodiment, in addition to the hardware configuration of the image generation apparatus 1 according to the first embodiment shown in FIG. The scanner 11 and the printer 12 are connected via the terminal.

  FIG. 9 is a block diagram illustrating a functional configuration of the image generation apparatus according to the second embodiment. As illustrated in FIG. 9, the image generation apparatus 10 includes an image acquisition unit 50, a feature information detection unit 51, an image information output unit 52, a designation information acquisition unit 53, an image selection unit 54, an arrangement determination unit 55, and an image processing unit 56. Consists of. The image processing unit 56 includes a main image specifying unit 56A and an image processing unit 56B.

  Similar to the image acquisition unit 20 illustrated in FIG. 2, the image acquisition unit 50 acquires a plurality of images via the input / output I / F 7 and stores the acquired images in the data area of the hard disk 5.

  Similar to the feature information detection unit 21 shown in FIG. 2, the feature information detection unit 51 detects the feature information of the entire image from each of the plurality of images acquired by the image acquisition unit 50. At this time, unlike the feature information detection unit 21 shown in FIG. 2, the feature information detection unit 51 does not detect feature information at both the left and right ends of the image.

  The image information output unit 52 prints on the printer 12 an image selection entry sheet for the user to enter. The image acquired by the image acquisition unit 50 is printed on the entry sheet in the form of a thumbnail image. The user designates an image to be printed and an arrangement in each print area on the label surface by referring to the printed thumbnail image and filling in an entry sheet.

  FIG. 11 is a diagram showing an example of an image selection entry sheet. As shown in FIG. 11, eight thumbnail images that are candidates for printing on the label surface are printed on the upper half of the entry sheet S. These thumbnail images are images acquired by the image acquisition unit 50. Further, four check boxes are provided at the bottom of each thumbnail image, and numbers 1 to 4 are printed behind each check box. Further, a schematic diagram of the label surface of the CD-R is drawn on the lower half of the entry sheet S, and this label surface is equally divided into four substantially fan-shaped print areas. 1 to 4 are printed for identification.

  When the user selects an image to be printed on the label surface, the thumbnail image printed on the upper half of the entry sheet S is referred to and one of the four check boxes at the bottom of the thumbnail image to be selected is selected. Fill in the check mark. At this time, since the numbers behind the respective check boxes correspond to the identification areas 1 to 4 of the print area of the label surface in the lower half of the entry sheet S, the user enters a check mark in the check box. By doing so, it is possible to designate the arrangement of the image in each print area on the label surface.

  The designation information acquisition unit 53 reads the information entered by the user on the image selection form using the scanner 11 as designation information. This designation information includes information on an image selected as a printing target and an arrangement position of the image on the label surface.

  The image selection unit 54 selects an image to be printed from a plurality of images acquired by the image acquisition unit 50 based on the specification information acquired by the specification information acquisition unit 53.

  Based on the designation information acquired by the designation information acquisition unit 53, the arrangement determination unit 55 determines the arrangement of the image to be printed selected by the image selection unit 54 in each print area on the label surface.

  Similar to the image processing unit 24 shown in FIG. 2, the image processing unit 56 prints each label surface for each image whose arrangement is specified by the arrangement determining unit 55 by the main image specifying unit 56A and the image processing unit 56B. The shape of the image is changed to the shape of the print area so that the area can be printed.

<Image generation operation>
Next, an operation for generating an image in the image generation apparatus 10 will be described.
FIG. 10 is a flowchart illustrating an operation of generating an image in the image generation apparatus according to the second embodiment.

  First, in step S510 shown in FIG. 10, the image acquisition unit 50 acquires a plurality of images that are candidates for printing on a label surface such as a CD-R or DVD-R. These images are the same as the images acquired in step S110 shown in FIG.

  In step S520, the feature information detection unit 51 detects feature information included in each of the plurality of images acquired in step S510. The image feature information detected here includes information indicating the presence / absence of blurring of the image and camera shake, and information on the face image pattern of the person included in the image. Note that the method for detecting these feature information is the same as that in step S120 shown in FIG. 3, but here, unlike step S120, information for determining the similarity of the entire image, and both left and right ends of the image Information for judging the degree of similarity is not detected. That is, the similarity information of the entire image for selecting an image and the similarity information of the left and right end portions of the image for determining the arrangement in each print area on the label surface are not necessary.

  In step S530, the image information output unit 52 prints on the printer 12 an image selection entry sheet S shown in FIG. The image obtained in step S510 is printed on the entry sheet S in the form of a thumbnail image. However, based on the information on the presence / absence of defocus and camera shake detected in step S520, only proper images without defocus and camera shake are displayed. Print. That is, an image in which out-of-focus or camera shake is generated is not printed on the entry sheet S.

  In step S 540, the designation information acquisition unit 53 waits until the scanner 11 reads the image selection entry sheet S filled in by the user. When the entry sheet S is read by the scanner 11, based on the read image data of the entry sheet S, the check mark in the check box entered by the user is recognized and acquired as the designation information.

  In step S550, the image selection unit 54 and the layout determination unit 55 determine the image to be printed and the layout of these images in each print area on the label surface based on the designation information acquired in step S540.

  In step S560, the image processing unit 56 deforms the shape of the image to be printed to match the shape of the print area on the label surface. Here, the main image portion that is the main object is identified from the entire image, the shape of the main image portion is not deformed, and the shape other than the main image portion is transformed into the shape of each print area on the label surface. To do. At this time, changing the shape other than the main image portion reduces the degree of deformation around the main image portion, and increases the degree of deformation as it approaches the end of the entire image. Note that the method of changing the shape of these images is the same as that in step S150 shown in FIG.

  As described above, in the image generating apparatus 10 according to the present embodiment, the acquired image is printed on the image selection entry sheet S in the form of thumbnail images, and the entry sheet S on which the user refers and inputs these thumbnail images. Is acquired by the scanner 11 as designated information. Then, based on the designation information, the image to be printed and the arrangement of these images in each print area on the label surface are determined. Thus, the user can select a desired image and designate the arrangement on the label surface with reference to the thumbnail image printed on the entry sheet S. Therefore, the user can select his / her favorite image on the label surface. You can edit freely in the print area.

  In addition, you may change embodiment of this invention as follows.

  (Modification 1) In the above-described embodiment, an image of a person is specified as a main image portion, the shape of the main image portion is not deformed, and the shape other than the main image portion is changed to the shape of each print area on the label surface. It is deformed. However, the main image portion to be specified is not limited to this. For example, only when a person image is included in the predetermined region in the center, the predetermined region may be set as the main image portion. A predetermined area in the center may be used as a main image portion regardless of the presence or absence of a human image. Thereby, generally, since a main target object is often located at the center of the image, it is possible to cope with a general image more appropriately.

(Modification 2) In the above-described embodiment, information on the face image pattern of a person included in the acquired image is detected as feature information, and an image containing the most same person is printed based on the feature information. This is selected as a target image, and this person's image is specified as the main image portion.
However, the image is not limited to a person image, and instead of a person image, an animal such as a dog or a cat, a plant such as a flower, or a structure such as a building or a vehicle may be used. For example, in the case of an image of a dog, information on the face image pattern of the dog is detected as feature information, and based on this feature information, an image containing the most same dog is selected as an image to be printed, The dog image may be specified as the main image portion. Thereby, it can apply not only to a person's image but to other various images.

  In addition, the entire image is divided into a plurality of image areas, feature information regarding edge pixels and brightness is detected from each image area, and the degree of importance of the image area is determined based on the feature information to obtain the highest degree of importance. A high image area may be specified as the main image portion. Thereby, even when the object is not clear and the image pattern cannot be detected, the image area determined as the main image portion can be specified.

  (Modification 3) In the above-described embodiment, the image acquisition units 20 and 50 acquire a plurality of images, and the image selection unit 22 and the designation information acquisition unit 53 select a plurality of images to be printed. However, the present invention is not limited to acquisition of a plurality of images and selection of a plurality of images. A plurality of images may be acquired to select one image to be printed, or one image may be acquired. Then, the image may be selected. As a result, even when only one image is printed on the print area of the label surface, the main image portion that is the main object is identified from the image, thereby deforming the shape of the main image portion unnaturally. Can be expressed properly.

  (Modification 4) In the above-described embodiment, when determining the arrangement in the print areas on the label surface, the images at the edges adjacent to each other in the print areas are made as similar as possible to each other. This prevents an uncomfortable feeling in the image of the adjacent part. Here, when the images are processed in the image processing unit 24B and the image processing unit 56B, the images at the end portions may be combined with the images at the adjacent end portions, or both images may be processed. The edge image may be processed into a blurred image. As a result, it can be expected that the adjacent portions of the images are connected in a natural manner without a sense of incongruity.

Explanatory drawing which shows the hardware constitutions of an image generation apparatus. The block diagram which shows the function structure of an image generation apparatus. 6 is a flowchart illustrating an operation for generating an image. 6 is a flowchart showing an operation for detecting feature information of an image. 6 is a flowchart showing an operation for selecting an image to be printed. 6 is a flowchart illustrating an operation for changing the shape of an image to be printed. Explanatory drawing which shows the example by which the image used as printing object was printed on the label surface. Explanatory drawing which shows the hardware constitutions of the image generation apparatus which concerns on 2nd Embodiment. The block diagram which shows the function structure of the image generation apparatus which concerns on 2nd Embodiment. 9 is a flowchart illustrating an operation for generating an image in the image generation apparatus according to the second embodiment. The figure which shows the example of the entry paper for image selection.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1,10 ... Image generation apparatus, 2 ... CPU, 3 ... ROM, 4 ... RAM, 5 ... Hard disk, 6 ... Bus, 7 ... Input / output I / F, 8 ... CD-R / RW drive, 9 ... DVD-R / RW drive, 11 ... scanner, 12 ... printer, 20, 50 ... image acquisition unit, 21, 51 ... feature information detection unit, 22 ... image selection unit, 23 ... arrangement determination unit, 24, 56 ... image processing unit, 24A , 56A ... main image specifying unit, 24B, 56B ... image processing unit, 52 ... image information output unit, 53 ... designated information acquisition unit.

Claims (11)

An image generation device for generating an image to be printed on a label surface of a recording medium,
An image acquisition unit for acquiring images;
An image selection unit for selecting an image to be printed from the acquired images;
An image processing unit that converts the image to be printed into an image to be printed on the label surface;
The image processing unit
A main image specifying unit for specifying a main image portion as a main object from the image to be printed;
An image generation apparatus comprising: an image processing unit that deforms a shape other than the main image portion into a predetermined shape while maintaining the shape of the main image portion.   The image generating apparatus according to claim 1, wherein the main image portion is at least one of an image at a position close to a central portion of the image to be printed and an image showing the object.   The image generation apparatus according to claim 2, wherein the object is a person or an animal, and the image indicating the object is an image including a face area of the object.   When the label surface is circular, the image processing unit deforms a shape other than the main image portion according to one shape of a plurality of divided regions obtained by dividing the label surface into a substantially fan shape. The image generation apparatus according to claim 1, wherein the image generation apparatus is an image generation apparatus.   The image processing unit reduces deformation of an image around the main image portion and increases deformation step by step as approaching an end of the image to be printed. 5. The image generating device according to any one of 4 above. A feature information detecting unit for detecting feature information of an image included in the image to be printed;
The said image selection part selects the image with which the feature information detected by the said feature information detection part is similar, when selecting a several image, The one of Claims 1-5 characterized by the above-mentioned. Image generation device. An arrangement determining unit that determines an arrangement of the image to be printed on the label surface;
The said arrangement | positioning determination part determines the arrangement | positioning in the said label surface based on the characteristic information of the right-and-left both ends of the image used as the printing object detected by the said characteristic information detection part. Image generation device. An image information output unit for outputting image information for identifying an image acquired by the image acquisition unit;
A specified information acquisition unit that acquires specified information that is information specified by the user for the output image information;
The image generation apparatus according to claim 1, wherein the image selection unit selects an image based on the acquired designation information. An image generation method for generating an image to be printed on a label surface of a recording medium,
An image acquisition process for acquiring images;
An image selection step of selecting an image to be printed from the acquired image;
An image processing step of converting the image to be printed into an image to be printed on the label surface,
The image processing step includes
A main image specifying step for specifying a main image portion as a main object from the image to be printed;
And an image processing step of deforming a shape other than the main image portion into a predetermined shape while keeping the shape of the main image portion as it is. An image generation program for generating an image to be printed on a label surface of a recording medium,
An image acquisition function for acquiring images;
An image selection function for selecting an image to be printed from the acquired images;
An image processing function for converting the image to be printed into an image to be printed on the label surface;
The image processing function is:
A main image specifying function for specifying a main image portion as a main object from the image to be printed;
An image generation program comprising: an image processing function for transforming a shape other than the main image portion into a predetermined shape while keeping the shape of the main image portion as it is. A computer-readable recording medium on which the image generation program according to claim 10 is recorded.

Images