Information processing apparatus and method of controlling the same, and program

Abstract

To express a user's intended impression and generate a poster that achieves a user's intended quality.SOLUTION: An information processing apparatus receives, from a user, a designation of a target impression of a poster to be generated, receives, from the user, a designation of a target quality of the poster to be generated, and generates poster data on the basis of at least the target impression. The information processing apparatus calculates an evaluation value from first information indicating a difference between the target impression and impression of the poster data and second information indicating a difference between the target quality and quality of the poster data, and selects the poster data for which the evaluation value has an evaluation higher than a predetermined evaluation.SELECTED DRAWING: Figure 9

Description

[Technical field]

[0001] The present invention relates to an information processing device, a control method thereof, and a program. [Background technology]

[0002] Conventionally, a method has been proposed for generating a poster by preparing a template that stores information indicating the shape and arrangement of the images, text, graphics, etc. that make up the poster, and then automatically arranging the images, text, graphics, etc. according to the template.

[0003] Patent Document 1 describes generating a poster by selecting templates in ascending order of difference between the impression evaluation value of the template and the impression evaluation value of the image. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6537419 Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, a template is selected in which the difference between the impression evaluation value of the template and the impression evaluation value of the image is small, but no consideration is given to generating a poster that expresses the user's intended impression (hereinafter also referred to as the "target impression").

[0006] There is also a trade-off between bringing the impression of the poster generated closer to the target impression and improving the quality of the poster generated. The quality of a poster refers to the quality of the poster design. For example, a poster can be said to have a high-quality design if it is well-balanced overall, eye-catching, and easy to see and read. On the other hand, if a poster is generated with only consideration given to bringing it closer to the target impression, it may not be possible to achieve the poster quality desired by the user (hereinafter also referred to as the "target quality"), and the poster desired by the user may not be generated.

[0007] For example, let us use Fig. 16 to explain the problem of creating a poster with a strong sense of dynamism. As shown in Fig. 16(a), a poster that uses many expressions to enhance the sense of dynamism, such as tilting objects and using a large number of colors, gives a strong sense of dynamism, but the design is unbalanced and the quality of the poster is reduced. In contrast, as shown in Fig. 16(b), a poster that uses gentler object tilts and fewer colors gives a slightly weaker sense of dynamism compared to Fig. 16(a), but the design is well-balanced and the quality of the poster is improved.

[0008] An object of the present invention is to solve at least one of the problems of the above-mentioned conventional techniques.

[0009] An object of the present invention is to provide a technique for generating poster data that reflects a user's intention regarding the impression and quality of the poster data. [Means for solving the problem]

[0010] In order to achieve the above object, an information processing device according to one aspect of the present invention has the following configuration. An information processing device, A first reception means for receiving from a user a designation of a target impression that the poster to be generated has; A second reception means for receiving from a user a designation of a target quality of the poster to be generated; A generating means for generating poster data based on at least the target impression; an evaluation value calculation means for calculating an evaluation value from first information indicating a difference between the target impression and an impression possessed by the poster data, and second information indicating a difference between the target quality and a quality possessed by the poster data; and a selection means for selecting poster data having an evaluation value higher than a predetermined evaluation value. Effect of the Invention

[0011] According to the present invention, it is possible to generate poster data that satisfies the impression and quality that the user desires.

[0012] Other features and advantages of the present invention will become apparent from the following description taken in conjunction with the accompanying drawings, in which the same reference numerals are used to designate the same or similar features throughout the drawings. [Brief description of the drawings]

[0013] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. [Figure 1] FIG. 1 is a block diagram illustrating a hardware configuration of a poster generation device according to a first embodiment. [Diagram 2] FIG. 2 is a functional block diagram for explaining functions of a poster creation application according to the first embodiment. [Diagram 3] FIG. 2 is a diagram showing an example of a skeleton according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a table of color scheme patterns according to the first embodiment. [Diagram 5] FIG. 4 is a view showing an example of an application start-up screen provided by the poster creation application according to the first embodiment. [Figure 6]FIG. 4 is a diagram showing an example of a poster preview screen displayed by a poster display unit in the first embodiment. [Figure 7] 5 is a flowchart for explaining a poster impression quantification process executed by the poster generation device according to the first embodiment. [Figure 8] 11A and 11B are diagrams for explaining an example of a subjective evaluation method for an impression of a poster. [Figure 9] 1A is a flowchart illustrating a poster generation process performed by a poster generation unit of the poster creation application according to the first embodiment, and FIG. 1B is a flowchart illustrating a condition determination process performed by a skeleton acquisition unit. [Figure 10] 3A to 3C are diagrams for explaining a method in which a skeleton selection unit according to the first embodiment selects a skeleton. [Figure 11] 5A to 5C are diagrams showing examples of a color scheme pattern impression table and a font impression table according to the first embodiment. [Figure 12] FIG. 2 is a functional block diagram for explaining functions of a layout unit according to the first embodiment. [Figure 13] 10 is a flowchart for explaining the layout process of S910 in FIG. 9. [Figure 14] 4A and 4B are diagrams for explaining information input to a layout unit; [Figure 15] 5A to 5C are diagrams for explaining the process of processing by a layout unit. [Figure 16] A diagram explaining the problem. [Figure 17] 1 is a flowchart showing a poster generation process illustrating a process for quantifying poster quality. [Figure 18] 1 is a diagram for explaining an example of a subjective evaluation method for the quality of a poster. [Figure 19] A diagram explaining the difference between impression and quality. [Figure 20] 13 is a flowchart illustrating an evaluation value calculation process in S913. [Figure 21] FIG. 13 is a diagram showing an example of a poster preview screen that displays a poster image generated by a poster display unit according to a modified example of the first embodiment. [Figure 22]FIG. 11 is a functional block diagram for explaining functions of a poster creation application according to a second embodiment. [Diagram 23] 10 is a flowchart for explaining the processing of a poster generation unit of a poster creation application according to a second embodiment. [Figure 24] 10 is a flowchart for explaining a poster data modification process performed by a design modification unit according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, the embodiments of the present invention will be described in detail with reference to the attached drawings. Note that the following embodiments do not limit the invention according to the claims. Although the embodiments describe a number of features, not all of these features are essential to the invention, and the features may be combined in any manner. Furthermore, in the attached drawings, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0015] In the embodiment described below, a method of automatically generating a poster by running an application (hereinafter simply referred to as "app") for creating a poster in a poster generating device will be described as an example. In the following description, "image" includes still images and frame images extracted from videos, unless otherwise specified.

[0016] [Embodiment 1] 1 is a block diagram for explaining a hardware configuration of a poster generation device 100 according to embodiment 1. The poster generation device 100 is an example of an information processing device, such as a personal computer (hereinafter, PC) or a smartphone. In the embodiment, the poster generation device will be explained as having the same hardware configuration as a PC.

[0017] The poster generating device 100 includes a CPU 101, a ROM 102, a RAM 103, a HDD (hard disk drive) 104, a display 105, a keyboard 106, a pointing device 107, and a data communication unit .

[0018] The CPU (Central Processing Unit / Processor) 101 comprehensively controls the poster generating device 100, and for example, loads a program stored in the ROM 102 into the RAM 103 and executes it to realize the operation according to the embodiment. Although FIG. 1 shows one CPU, the device may be configured with multiple CPUs. The ROM 102 is a general-purpose ROM, and for example, stores programs executed by the CPU 101 and various data. The RAM 103 is a general-purpose RAM, and is used, for example, as a working memory for temporarily storing various information when the CPU 101 executes a program. The HDD 104 is a storage medium (storage unit) for storing image files, a database for holding processing results such as image analysis, and skeletons used by a poster creation application. The display 105 is a display unit that displays a user interface (UI) according to the embodiment, and an electronic poster as a layout result of image data (hereinafter also referred to as "image") to the user. The keyboard 106 and the pointing device 107 receive instruction operations from the user. The display 105 may have a touch sensor function. The keyboard 106 is used, for example, when a user inputs the number of double pages of a poster to be created on the UI displayed on the display 105. The pointing device 107 is used, for example, when a user clicks a button on the UI displayed on the display 105. The data communication unit 108 communicates with an external device via a wired or wireless network. For example, the data communication unit 108 transmits data laid out by an automatic layout function to a printer or a server that can communicate with the poster generating device 100. The system bus 109 connects the devices in FIG. 1 described above so that they can communicate with each other. Note that the configuration shown in FIG. 1 is merely an example and is not limited thereto. For example, the poster generating device 100 may not have the display 105 and may display a UI on an external display.

[0019] The poster creation application according to the first embodiment is stored in HDD 104. The poster creation application is started when a user executes an operation such as clicking or double-clicking an application icon displayed on display 105 with pointing device 107.

[0020] FIG. 2 is a functional block diagram illustrating functions of the poster creation application according to the first embodiment.

[0021] The poster creation application has a poster creation condition designation unit 201, a text designation unit 202, an image designation unit 203, a target impression designation unit 204, a poster display unit 205, a poster generation unit 210, a target quality designation unit 220, and a weight designation unit 223. The poster generation unit 210 has an image acquisition unit 211, an image analysis unit 212, a skeleton acquisition unit 213, a skeleton selection unit 214, a color scheme pattern selection unit 215, a font selection unit 216, and a layout unit 217. Furthermore, the poster generation unit 210 has an impression estimation unit 218, a poster selection unit 219, a quality estimation unit 221, and an evaluation value calculation unit 222.

[0022] When the poster creation application is installed in poster generation device 100, a start-up icon is displayed on the top screen (desktop) of the OS (operating system) running on poster generation device 100. Then, the user operates (e.g., double-clicks) the start-up icon displayed on display 105 with pointing device 107. This causes the program of the poster creation application stored in HDD 104 to be loaded into RAM 103 and executed by CPU 101. In this way, the poster creation application is started.

[0023] The poster creation application described above includes program modules corresponding to the components shown in Fig. 2. CPU 101 executes each program module, causing CPU 101 to function as each component shown in Fig. 2. Hereinafter, each component shown in Fig. 2 will be described assuming that each component executes various processes. Fig. 2 also shows a block diagram of software relating to poster generation unit 210 that executes the automatic poster creation function.

[0024] The poster creation condition designation unit 201 designates poster creation conditions to the poster generation unit 210 in response to UI operations using the pointing device 107. In the first embodiment, the poster size, the number of posters to be created, and the purpose category are designated as the poster creation conditions. The poster size may be designated by actual values ​​of width and height, or may be designated by a paper size such as A1 or A2. The purpose category is a category that indicates the purpose for which the poster will be used, such as a restaurant, a school event, or a sale.

[0025] The text designation unit 202 designates character information to be placed on the poster through UI operations using the keyboard 106. The character information to be placed on the poster includes, for example, character strings representing a title, date and time, location, etc. The text designation unit 202 also links each piece of character information so as to be able to determine whether it is a title, date and time, location, or other type of information, and then outputs the information to the skeleton acquisition unit 213 and the layout unit 217.

[0026] The image designation unit 203 designates one or more image data to be placed on a poster, which are stored in the HDD 104. The image data may be designated based on the structure of a file system including the image data, such as a device and a directory, or may be designated by associated information for identifying the image, such as the shooting date and time, or attribute information. The image designation unit 203 outputs the file path of the designated image to the image acquisition unit 211.

[0027] The target impression designation unit 204 designates a target impression of the poster to be created. The target impression is an impression that the poster to be created is ultimately required to maintain. In the first embodiment, the strength indicating the degree of impression to be given to a word expressing an impression is designated by a UI operation using the pointing device 107. Information indicating the target impression designated by the target impression designation unit 204 is shared by the skeleton selection unit 214, the color scheme selection unit 215, the font selection unit 216, and the evaluation value calculation unit 222. Details of impressions will be described later.

[0028] The target quality designation unit 220 designates a target quality of the poster to be created. The target quality is the quality that the poster to be created is ultimately required to achieve. In the first embodiment, the strength indicating the level of quality to be achieved is designated by a UI operation using the pointing device 107. Here, the quality may be expressed as a comprehensive evaluation value of a design that combines images, graphics, characters, fonts, etc. that make up the design. Information indicating the target quality designated by the target quality designation unit 220 is shared with the evaluation value calculation unit 222. Details of the quality will be described later.

[0029] Next, the configuration of poster generator 210 will be described in detail.

[0030] The image acquisition unit 211 acquires one or more image data designated by the image designation unit 203 from the HDD 104, and outputs the acquired image data to the image analysis unit 212. Also, the image acquisition unit 211 outputs the number of acquired images to the skeleton acquisition unit 213. The images stored in the HDD 104 include still images and frame images cut out from a video. The still images and frame images are acquired from an imaging device such as a digital camera or a smart device. The imaging device may be provided in the poster generating device 100 or an external device. If the imaging device is an external device, the images are acquired via the data communication unit 108. As another example, the still images may be illustration images created by image editing software or CG images created by CG production software. The still images and cut-out images may be images acquired from a network or a server via the data communication unit 108. Examples of images acquired from a network or a server include social networking service images (hereinafter referred to as "SNS images"). The program executed by the CPU 101 analyzes data attached to each image to determine the source of storage. For example, the SNS image may be acquired from the SNS via the application, and the acquisition destination may be managed within the application. Note that the image is not limited to the above-mentioned images, and may be other types of images.

[0031] The image analysis unit 212 executes an analysis process of the image data acquired from the image acquisition unit 211 by a method described later, and acquires information indicating an image feature amount described later. Specifically, the image analysis unit 212 executes an object recognition process described later, and acquires information indicating an image feature amount of the image data. The image analysis unit 212 also links the acquired information indicating the image feature amount to the image data, and outputs the image data to the layout unit 217.

[0032] The skeleton acquisition unit 213 acquires, from the HDD 104, one or more skeletons that meet the conditions specified by the poster creation condition specification unit 201, the text specification unit 202, and the image acquisition unit 211. In the first embodiment, a skeleton is layout information that indicates the arrangement of character strings, images, figures, and the like to be arranged on a poster.

[0033] FIG. 3 is a diagram illustrating an example of a skeleton according to the first embodiment.

[0034] 3(a), three graphic objects 302, 303, and 304, one image object 305, and four text objects 306, 307, 308, and 309, which are objects on which text is to be placed, are arranged on a skeleton 301. Each object is recorded with metadata required for generating a poster, in addition to the position, size, and angle indicating where it is to be placed.

[0035] FIG. 3B is a diagram showing an example of metadata. For example, character objects 306 to 309 hold, as metadata attributes, information about the type of character information to be arranged. In FIG. 3A, character object 306 represents a title, character object 307 represents a subtitle, and character objects 307 and 308 represent main text. Furthermore, character objects 306 to 309 hold, as metadata attributes, information about the alignment position of characters. For example, in a character object with a left-justified attribute, a character string is arranged so that the left end of an input character string is aligned with the left end of the character object, and in a character object with a center attribute, a character string is arranged so that the center of an input character string is aligned with the center of the character object.

[0036] Moreover, the graphic objects 302 to 304 hold color scheme numbers (color scheme IDs) indicating the shape and color scheme pattern of the graphic as metadata attributes. In FIG. 3(a), the attributes of the graphic objects 302 and 303 are rectangles, and the attribute of the graphic object 304 is an ellipse. Also, it is assumed that the graphic object 302 is assigned color scheme number 1 (color_no=1), and the graphic objects 303 and 304 are assigned color scheme number 2. Here, the color scheme number is information to be referred to when coloring, which will be described later, and indicates that different colors are assigned to different color scheme numbers. Note that the types of objects and metadata are not limited to the above. For example, there may be a map object for arranging a map, or a barcode object for arranging a QR code (registered trademark) or a barcode. Furthermore, there may be metadata indicating the width between lines or the width between characters as metadata for a character object. The metadata may include the purpose of the skeleton, and may be used to control whether or not the skeleton can be used depending on the purpose. The skeleton may be stored in the HDD 104 in, for example, a CSV format, or in a DB format such as SQL. The skeleton acquisition unit 213 outputs one or more skeletons acquired from the HDD 104 to the skeleton selection unit 214 .

[0037] A skeleton selection unit 214 selects one or more skeletons that match the target impression specified by the target impression specification unit 204 from among the skeletons acquired from the skeleton acquisition unit 213, and outputs them to a layout unit 217. Since the layout of the entire poster is determined by the skeleton, by preparing various types of skeletons in advance, it is possible to increase the variety of posters after generation.

[0038] The color scheme selection unit 215 obtains from the HDD 104 one or more color schemes that match the desired impression specified by the desired impression specification unit 204, and outputs them to the layout unit 217. A color scheme is a combination of colors to be used in a poster.

[0039] FIG. 4 is a diagram showing an example of a color scheme table according to the first embodiment. In the first embodiment, the color scheme is expressed as a combination of four colors (color 1 to color 4). The color scheme ID column in FIG. 4 is an ID for uniquely identifying the color scheme. The columns Color 1 to Color 4 express the colors in RGB order, with each RGB color value ranging from 0 to 255 (R, G, B=(0 to 255, 0 to 255, 0 to 255)). Note that, although the first embodiment uses a color scheme consisting of a combination of four colors, it may be possible to use a different number of colors, or a mixture of multiple colors.

[0040] The font selection unit 216 selects one or more font patterns that match the desired impression specified by the desired impression specification unit 204, obtains them from the HDD 104, and outputs them to the layout unit 217. A font pattern is a combination of at least one of a title font, a subtitle font, and a body font.

[0041] The layout unit 217 generates one or more poster data pieces equal to or greater than the specified number of posters to be created, by laying out various data for each of the one or more skeletons obtained from the skeleton selection unit 214. The layout unit 217 arranges the text obtained from the text designation unit 202 and the image data obtained from the image analysis unit 212 for each skeleton, applies a color pattern obtained from the color pattern selection unit 215, and applies a font pattern obtained from the font selection unit 216. The layout unit 217 outputs the one or more poster data pieces thus generated to the impression estimation unit 218.

[0042] The impression estimation unit 218 estimates an impression of each piece of poster data among the multiple poster data acquired from the layout unit 217, and links the estimated impression (estimated impression) to each piece of poster data. Then, the impression estimation unit 218 outputs the one or multiple pieces of poster data linked with the estimated impression to the evaluation value calculation unit 222.

[0043] The quality estimation unit 221 estimates the quality of each piece of poster data among the multiple poster data acquired from the layout unit 217, and links the estimated quality (estimated quality) to each piece of poster data. Then, the quality estimation unit 221 outputs the one or multiple pieces of poster data linked with the estimated quality to the evaluation value calculation unit 222.

[0044] The evaluation value calculation unit 222 compares the target impression specified by the target impression designation unit 204 with the estimated impressions linked to the multiple poster data acquired from the impression estimation unit 218, and calculates an impression evaluation value. The evaluation value calculation unit 222 also compares the target quality specified by the target quality designation unit 220 with the estimated quality linked to the multiple poster data acquired from the quality estimation unit 221, and calculates a quality evaluation value. Then, the evaluation value calculation unit 222 calculates an overall evaluation value for selecting poster data from the impression evaluation value and the quality evaluation value. The evaluation value calculation unit 222 outputs the overall evaluation value calculated in this manner to the poster selection unit 219.

[0045] The poster selection unit 219 selects the poster data associated with the smallest overall evaluation value, i.e., the highest evaluation value, from among the overall evaluation values ​​acquired from the evaluation value calculation unit 222. The selection result is stored in the HDD 104. The poster selection unit 219 outputs the selected poster data to the poster display unit 205. The poster display unit 205 outputs a poster image to be displayed on the display 105 according to the poster data acquired from the poster selection unit 219. The poster image is, for example, bitmap data. The poster display unit 205 displays the poster image on the display 105.

[0046] The poster creation application may also be provided with a function (not shown) that enables the user to edit the layout, color, shape, etc. of images, text, and graphics through additional operations after the generated result is displayed on the poster display unit 205, and to further change the design to the user's desired design.

[0047] Furthermore, if the device is equipped with a function for printing the poster data stored in HDD 104 using a printer according to conditions specified in poster creation condition specification section 201, the user can obtain a printed copy of the poster he or she has created.

[0048] FIG. 5 is a diagram showing an example of an application start screen 501 provided by the poster creation application according to the first embodiment.

[0049] An application start-up screen 501 is displayed on the display 105. A user sets the creation conditions, text, and image of a poster, which will be described later, via the application start-up screen 501. The poster creation condition designation unit 201, the image designation unit 203, and the text designation unit 202 acquire the settings from the user via this UI screen.

[0050] A title box 502, a subtitle box 503, and a text box 504 accept the specification of text information to be arranged on the poster. In the first embodiment, three types of text information are accepted, but this is not limited to this. For example, additional text information such as location and date and time may be accepted. Also, it is not necessary to specify all the items, and some boxes may be left blank.

[0051] Image designation area 505 is an area for displaying an image to be placed on a poster. Image 506 represents a thumbnail of the designated image. Add image button 507 is a button for adding an image to be placed on a poster. When the user presses add image button 507, image designation unit 203 displays a dialog screen for selecting a file saved in HDD 104 and accepts the user's selection of an image file. Then, a thumbnail of the selected image is added to image designation area 505.

[0052] The impression sliders 508 to 511 are objects for setting factors of the target impression of the poster to be created. For example, the slider 508 is a slider for setting factors of the target impression related to luxury, and the target impression is set such that the more the slider is slid to the right, the more luxurious the poster becomes, and the more the slider is slid to the left, the less luxurious (cheaper) the poster becomes. In addition, by combining factors of the target impression set by each slider, a target impression is set that reflects not only factors of the target impression set by one slider, but also factors of the target impression set by other sliders. For example, it is assumed that a user operation is performed on the screen of the poster generation application, and the impression slider 508 is set to the right of the center of the slider, and the impression slider 511 is set to the left of the center of the slider. In this case, a poster with an elegant impression, such as a high sense of luxury and a low sense of solidity, is generated. In addition, for example, it is assumed that the impression slider 508 is set to the right of the center of the slider, and the impression slider 511 is set to the right of the center of the slider, by a user operation. In this case, a poster with a gorgeous impression, such as a high sense of luxury and dignity, is generated. In this way, by combining the factors of the target impression indicated by the multiple impression sliders, even if the common target impression factor of "luxury" is set, it is possible to set target impressions with different directions, such as a "refined" target impression and a "gorgeous" target impression. In other words, the target impression is composed and determined by multiple factors indicating impressions, but it may also be determined by one factor indicating impressions.

[0053] In the first embodiment, the state where the slider is set to the leftmost position is set to -2, and the state where it is set to the rightmost position is set to +2, and correction is made to an integer value between -2 and +2. These numerical values ​​indicate that the impression is low (-2), slightly low (-1), neutral (0), slightly high (+1), and high (+2). The purpose of correcting to -2 to +2 is to match the scale with the estimated impression and facilitate distance calculation, which will be described later, but this is not limiting and normalization may also be made using values ​​between 0 and 1.

[0054] The impression radio button 512 is a button that can control whether to enable or disable the setting of each target impression. The user can set whether to enable or disable the setting of each target impression by pressing the impression radio button 512 to set it to an on or off state. For example, when the impression radio button 512 is set to an off state, the impression corresponding to the button is excluded from the impression control. For example, a user who wants to create a calm poster with low dynamism but has no particular designation for other impressions can generate a poster specialized in low dynamism by setting the impression radio buttons 512 other than dynamism to an off state. Note that FIG. 5 shows a state in which luxury and familiarity are set to on, and dynamism and solidity are set to off. This enables highly flexible control, such as using all target impressions for poster generation, or using only some target impressions for poster generation. Note that when each slider is set to the leftmost position, the same as when each target impression is not set (for example, when the slider 508 is set to the leftmost position, the luxury is 0), the impression radio button 512 may be omitted. In this case, when the user wishes to invalidate the setting of the target impression, the user can invalidate the setting of the target impression by setting the slider to the leftmost position.

[0055] The quality slider 518 is an object for setting a target quality to be achieved in the poster to be created. For example, the slider 518 is set such that the poster achieves higher quality as it is slid to the right, and lower quality as it is slid to the left. In the first embodiment, the slider 518 is corrected to an integer value of +1 to +5, with +1 being the state where the slider 518 is set to the leftmost position, and +5 being the state where the slider 518 is set to the rightmost position. These numerical values ​​indicate that the quality is low, +2 is slightly low, +3 is neither, +4 is slightly high, and +5 is high. The purpose of correcting to +1 to +5 is to match the scale with the estimated quality to facilitate distance calculation, which will be described later, and is not limited to this, and normalization may be performed using values ​​of 0 to 1. The quality radio button 519 is a button that can control whether the setting of the target quality is enabled or disabled. The user can set whether the setting of the target quality is enabled or disabled by pressing the quality radio button 519 to set it to an on or off state. For example, when the quality radio button 519 is turned off, the quality is excluded from the control. For example, a user who does not care about the quality and wants to emphasize the expression of the target impression can generate a poster specialized in expressing the target impression by turning off the quality radio button 519. Note that the quality radio button 519 may not be present in the case where the quality slider 518 is set to the leftmost position and the result is the same as when the target quality is not set. In this case, when the user wishes to disable the setting of the target quality, the slider 518 can be set to the leftmost position to disable the setting of the target quality. The quality slider 518 and the quality radio button 519 may not be present in the configuration. In this case, the target quality is set to a predetermined value. As described later, since the quality is a user-independent evaluation axis in which the higher the quality, the more likely it is to be accepted, it is also possible to configure the target quality to be specified internally.

[0056] The weight slider 520 is an object for setting a weight indicating the degree of balance between the target impression specified by the impression sliders 508 to 511 and the target quality specified by the quality slider 518. For example, the more the weight slider 520 is slid to the left, the more the target impression is emphasized, and the more the weight slider 520 is slid to the right, the more the poster generation is controlled. When the weight slider 520 is located in the middle, the poster generation is controlled by emphasizing the target impression and the target quality at a ratio of 1:1. In the first embodiment, the weight slider 520 is corrected to a decimal value between 0.0 and 1.0, with the state in which the weight slider 520 is set to the leftmost position being 0.0 and the state in which the weight slider 520 is set to the rightmost position being 1.0. For example, these values ​​(weight information) are values ​​indicating that 0.0 emphasizes only the target impression, 0.5 emphasizes equally the target impression and the target quality, and 1.0 emphasizes only the target quality.

[0057] Size list box 513 is a list box for setting the size of the poster to be created. A list of poster sizes that can be created is displayed and can be selected by the user clicking the pointing device 107. Number to create box 514 allows the number of posters to be created to be set. Category list box 515 allows the purpose category of the poster to be created to be set. Reset button 516 is a button for resetting each setting information on application start screen 501.

[0058] When the user presses the OK button 517, the poster creation condition designation unit 201, the text designation unit 202, the image designation unit 203, the target impression designation unit 204, the target quality designation unit 220, and the weight designation unit 223 output the contents set on the application start screen 501 to the poster generation unit 210. At that time, the poster creation condition designation unit 201 acquires the size of the poster to be created from the size list box 513, the number of posters to be created from the number of creations box 514, and the purpose category of the poster to be created from the category list box 515. The text designation unit 202 acquires character information to be placed on the poster from the title box 502, the subtitle box 503, and the main text box 504. The image designation unit 203 acquires the image file path to be placed on the poster from the image designation area 505. The target impression designation unit 204 acquires the target impression of the poster to be created from the impression sliders 508 to 511 and the impression radio button 512. The target quality designation unit 220 acquires the target quality of the poster to be created from the quality slider 518 and the quality radio button 519. The weight designation unit 223 acquires the weight that emphasizes the target impression and the target quality from the weight slider 520. The poster creation condition designation unit 201, the text designation unit 202, the image designation unit 203, the target impression designation unit 204, the target quality designation unit 220, and the weight designation unit 223 may process the value set in the application start screen 501. For example, the text designation unit 202 may remove unnecessary blank characters at the beginning or end from the input character information. The target impression designation unit 204 may correct the value of the target impression designated by the impression sliders 508 to 511. The target quality designation unit 220 may correct the value of the target quality designated by the quality slider 518. The weight designation unit 223 may correct the value of the weight designated by the weight slider 520.

[0059] Fig. 6 is a diagram showing an example of a poster preview screen 601 displayed by the poster display unit 205 in embodiment 1. When the OK button 517 on the application start-up screen 501 in Fig. 5 is pressed and the generation of a poster image is completed, the screen transitions to this poster preview screen 601.

[0060] Poster image 602 is a poster image output by poster display unit 205. Since poster generation unit 210 generates the number of posters specified by poster creation condition specification unit 201 or more, the generated posters are displayed as a list as poster images 602 on poster preview screen 601. When a user clicks on a poster image in this list with pointing device 107, that poster image becomes selected. Edit button 603 allows the selected poster image to be edited via a UI that provides an editing function (not shown). Print button 604 allows the selected poster image to be printed via a printer control UI (not shown).

[0061] <Quantifying the impression of posters> Here, a method of quantifying the impression of a poster image, which is a pre-processing required for the poster generation process and is required for executing the impression estimation process described later in S911 of Fig. 9(a), will be described. The process of quantifying the impression of a poster is performed by a vendor developing a poster creation application at the development stage of the poster creation application. The process of quantifying the impression of a poster image may be performed by the poster generation device 100, or may be performed by an information processing device different from the poster generation device 100. When the process is performed by an information processing device different from the poster generation device 100, the process is executed by the CPU of that information processing device.

[0062] In the process of quantifying the impression of a poster, the impression that a person has of various posters is quantified. At the same time, a correspondence between the poster image and the impression of the poster is derived. This makes it possible to estimate the impression of the poster from the generated poster image. If the impression can be estimated, it becomes possible to control the impression of the poster by correcting the poster image, or to search for a poster image that has a certain target impression. The poster impression quantification process is executed, for example, in the poster generation device 100, by running an impression learning application for learning the impression of the poster image in advance before the poster generation process.

[0063] Fig. 7 is a flowchart for explaining the poster impression quantification process executed by the poster generation device 100 according to the first embodiment. The process shown in the flowchart in Fig. 7 is realized, for example, by the CPU 101 expanding a program stored in the HDD 104 into the RAM 103 and executing it. Hereinafter, the poster impression quantification process according to the first embodiment will be explained with reference to Fig. 7. The process in Fig. 7 is executed. Note that the symbol "S" in the explanation of each process indicates a step in the flowchart (the same applies hereinafter in this specification).

[0064] In S701, the CPU 101 executes acquisition of a subjective evaluation of an impression of a poster.

[0065] FIG. 8 is a diagram for explaining an example of a subjective evaluation method for an impression of a poster.

[0066] Here, a poster is presented to a subject, and the CPU 101 obtains a subjective evaluation of the impression of the poster based on the subject's response. In this case, a measurement method such as the Semantic Differential (SD) method or the Likert scale method can be used. FIG. 8 shows an example of the results of a questionnaire using the SD method. Here, an example of a questionnaire is shown in which adjective pairs (light and dark, light and shade, etc.) expressing impressions are presented to a plurality of evaluators, and subjective evaluation results are scored for the adjective pairs that are recalled from the target poster. After obtaining subjective evaluation results from a plurality of subjects for a plurality of posters, the CPU 101 calculates an average value of the responses to each adjective pair, and sets the average value as a representative score value for the corresponding adjective pair. Note that the subjective evaluation method of the impression may be other than the SD method, as long as words expressing impressions and corresponding scores are determined.

[0067] Next, the process proceeds to S702, and the CPU 101 executes factor analysis of the subjective evaluation results acquired in S701. If the subjective evaluation results are used as is, the number of adjective pairs will be the number of dimensions, which will complicate control, so it is desirable to reduce the number of dimensions to an efficient number using an analysis method such as factor analysis. In the first embodiment, the description will be given assuming that the dimensions are reduced to four factors by factor analysis. Naturally, this number varies depending on the selection of adjective pairs in the subjective evaluation. In addition, the output of the factor analysis is assumed to be standardized. That is, each factor is scaled so that the average is 0 and the variance is 1 in the poster used in the analysis. As a result, the impressions of -2, -1, 0, +1, and +2 specified by the target impression specification unit 204 can be directly associated with -2σ, -1σ, the average value, +1σ, and +2σ in each impression, which makes it easier to calculate the distance between the target impression and the estimated impression, which will be described later. In the first embodiment, the four factors are shown in FIG. 5 as luxury, familiarity, dynamism, and solidity. However, these are names given for convenience in order to convey impressions to the user through the user interface, and each factor is composed of multiple adjective pairs that influence each other.

[0068] Next, the process proceeds to S703, and the CPU 101 associates the poster image with the impression. Although it is possible to quantify the poster that has been subjectively evaluated by the above-mentioned method, it is necessary to estimate the impression of the poster to be created without subjective evaluation. The association between the poster image and the impression can be realized by learning a model that estimates the impression from the poster image, for example, using a deep learning method using a Convolution Neural Network (CNN) or a machine learning method using a decision tree. In the first embodiment, the impression learning means inputs the poster image and outputs four factors, and performs supervised deep learning using CNN. That is, a deep learning model is created by learning the subjectively evaluated poster image and the corresponding impression as the correct answer, and an impression is estimated by inputting an unknown poster image to the learning model.

[0069] Next, the process proceeds to S704, and the CPU 101 stores in the HDD 104 the model configuration and learned parameters of the deep learning model for impression estimation created in S703.

[0070] The deep learning model created above is stored in, for example, HDD 104, and the impression estimation unit 218 loads the deep learning model of impression estimation stored in HDD 104 in RAM 103 and executes it. The impression estimation unit 218 images the poster data acquired from the layout unit 217, and estimates the impression of the poster by operating the deep learning model loaded in RAM 103 with the CPU 101 or a GPU (not shown). Although the deep learning method is used in the first embodiment, the present invention is not limited to this. For example, when using a machine learning method such as a decision tree, a machine learning model that extracts feature amounts such as the average brightness value and edge amount of the poster image by image analysis and estimates the impression based on the feature amounts may be created.

[0071] <Quantifying poster quality> Here, a method of quantifying the quality of a poster will be described, which is a pre-processing required for the poster generation process in order to execute the quality estimation process described later in S912 of Fig. 9(a). The process of quantifying the quality of a poster is performed by a vendor or the like who develops the poster creation application at the development stage of the poster creation application. The process of quantifying the quality of a poster may be executed by the poster generation device 100, or may be executed by an information processing device different from the poster generation device 100. When the process is executed by an information processing device different from the poster generation device 100, it is executed by the CPU 101 of that information processing device.

[0072] In the process of quantifying the poster quality, the quality that people have for various posters is quantified. At the same time, a correspondence between the poster image and the poster quality is derived. This makes it possible to estimate the poster quality from the generated poster image. If the poster quality can be estimated, it becomes possible to control the quality of the poster by correcting the poster image, or to find a poster image having a certain target quality. The process of quantifying the poster quality is executed, for example, by running a quality learning application for learning the quality of the poster image in advance in the poster generation device 100 before the poster generation process.

[0073] Fig. 17 is a flowchart for explaining the poster quality quantification process according to embodiment 1. The flowchart shown in Fig. 17 is realized, for example, by CPU 101 loading a program stored in HDD 104 into RAM 103 and executing it. Hereinafter, the poster quality quantification process will be described with reference to Fig. 17.

[0074] In S1701, the CPU 101 acquires a subjective evaluation of the quality of a poster.

[0075] FIG. 18 is a diagram for explaining an example of a subjective evaluation method for the quality of a poster.

[0076] The CPU 101 presents a poster to a subject and obtains a subjective evaluation of the quality of the poster from the subject. In this case, a measurement method such as the Semantic Differential (SD) method or the Likert scale method can be used. FIG. 18 shows an example of a questionnaire using the Likert scale method, in which evaluation items that affect the quality are presented to a plurality of evaluators and each evaluation item of the target poster is scored. After obtaining subjective evaluation results from a plurality of subjects for a plurality of posters, the CPU 101 calculates an average value of the answers to each evaluation item, and sets the average value as a representative score value for the corresponding evaluation item. Note that the subjective evaluation method of quality may be other than the Likert scale method, as long as the items for evaluating quality and the corresponding scores are determined.

[0077] Next, the process proceeds to S1702, and the CPU 101 executes a principal component analysis of the subjective evaluation results acquired in S1701. If the subjective evaluation results are used as is, the number of evaluation items will be dimensional, and control will become complicated, so it is desirable to reduce the number of dimensions to an efficient number using an analysis method such as principal component analysis. In the first embodiment, a description will be given assuming that a plurality of evaluation items are summarized into one principal component by the principal component analysis, and the quality is evaluated comprehensively. In addition, the output of the principal component analysis is normalized. That is, the summarized principal component is scaled to, for example, a minimum of 1 and a maximum of 5 in the poster used in the analysis. As a result, the quality of +1, +2, +3, +4, and +5 specified by the target quality specification unit 220 can be directly corresponding to +1, +2, +3, +4, and +5 in the quality, which makes it easier to calculate the distance between the target quality and the estimated quality, which will be described later.

[0078] Next, the process proceeds to S1703, and the CPU 101 associates the poster image with the quality. Although it is possible to quantify the poster that has been subjectively evaluated by the above-mentioned method, it is necessary to estimate the quality of posters to be created without subjective evaluation. The association between the poster image and the quality can be realized by learning a model that estimates the quality from the poster image, for example, using a deep learning method using a Convolution Neural Network (CNN) or a machine learning method using a decision tree. In the first embodiment, the quality learning means inputs a poster image and outputs one evaluation value, and performs supervised deep learning using CNN. That is, a deep learning model is created by learning the subjectively evaluated poster image and the corresponding quality as the correct answer, and the quality is estimated by inputting an unknown poster image into the learning model.

[0079] The process then proceeds to 1704, in which the CPU 101 stores in the HDD 104 the model configuration and learned parameters of the deep learning model for quality estimation created in S1703.

[0080] The quality estimation unit 221 loads the deep learning model for quality estimation stored in the HDD 104 in the RAM 103 and executes it. The quality estimation unit 221 converts the poster data acquired from the layout unit 217 into an image, and estimates the quality of the poster by running the deep learning model loaded in the RAM 103 on the CPU 101 or the GPU 109. Although the deep learning method is used in the first embodiment, the present invention is not limited to this. For example, when using a machine learning method such as a decision tree, feature amounts such as a blank space ratio and a pure color ratio of a poster image may be extracted by image analysis, and a machine learning model that estimates the quality based on the feature amounts may be created.

[0081] Also, instead of a poster image, feature values ​​may be extracted from poster data before rendering, and a machine learning model may be created that estimates quality based on the feature values. For example, to estimate the balance of a design, the center of gravity position and margin ratio may be calculated. Note that the rendering process is a process of converting poster data into image data.

[0082] When creating a machine learning model that estimates quality based on features, it is desirable to use features that affect the quality of the poster. For example, the quality of a poster is affected by factors such as the balance, attention, and visibility of the design. Features related to balance include the center of gravity and the margin ratio. If the center of gravity of a poster is far from the center, the design will look silly. The center of gravity is calculated by converting the poster into a luminance image and calculating the center of gravity. If the margin of a poster is small, the design will be cramped because too much information is packed in. The margin ratio is calculated by extracting the edges of the poster image, performing a certain expansion process, and then calculating the ratio of pixels whose pixel value remains 0 to all pixels. Features related to attention include the jump ratio of font size and the distribution of object placement. The jump ratio is the ratio of the size of large elements to the size of small elements, and a high jump ratio makes the important information more noticeable. The jump ratio of font size is calculated by calculating the ratio of the maximum character size in the poster data to the average value of all character sizes. In a poster, if all elements such as photos and text are arranged in a vertical line in the center with small variance, the design will be orderly, static, and unobtrusive. Layout variance can be calculated by calculating the variance of the positions of each object in the poster data. Features related to visibility include the pure color ratio and the type of font for the main text. Pure colors are colors with high brightness and dark, and it is said that if pure colors are used frequently in a poster, it will flicker, be difficult to read, and put strain on the eyes. The pure color ratio can be calculated by converting the poster image to the HSV color space and calculating the ratio of pixels with a saturation S and brightness V of a certain level or higher to all pixels. For the main text of a poster, which contains detailed information, it is recommended to use fonts such as Gothic and Mincho, which place more importance on readability than on prominence. The type of font for the main text can be calculated by determining whether the font assigned to the text object specified as "main text" in the poster data is Gothic or Mincho. Note that the types of features that affect quality and the calculation method are not limited to these.

[0083] <The difference between impression and quality> Learning of both impression and quality involves analyzing the subjective evaluation results and learning the relationship between the poster and the analysis results using a machine learning model. However, the two processes are different in nature, as explained in Figure 19.

[0084] FIG. 19 is a diagram explaining the difference between impression and quality. Impression and quality have different characteristics, and as shown in FIG. 19(a), impression is a concept expressed by direction and intensity. For example, an intensity of +2 in the direction of dynamism means that a strong sense of dynamism is felt, and an intensity of -2 in the direction of dynamism means that a strong impression of calmness, which is the opposite of dynamism, is felt. There are no fixed indicators for the direction and intensity of impressions to aim for, and the impression that the user intends is the correct answer for that user. In other words, impression is an evaluation axis that depends on the user.

[0085] In contrast, as shown in FIG. 19(b), quality is a concept expressed by the quality of a design. For example, a poster with a sophisticated design such as that created by a professional designer can be said to be of high quality, while a poster with an unbalanced design and no eye-catching elements can be said to be of low quality. Since a high quality is acceptable to any user, the concept of quality itself is an evaluation axis independent of the user. However, since the degree of quality to be tolerated is user-dependent, in the first embodiment, the acceptable range of quality can be specified by the quality slider 520 shown in FIG. 5. In this way, the impression is a user-independent evaluation axis expressed by direction and intensity, while the quality is a user-dependent evaluation axis expressed by good or bad, and the characteristics of the two are different.

[0086] Furthermore, there is a difference in the positioning of impression and quality, and therefore also in the methods of analyzing the subjective evaluation results. As shown in Figure 19(c), impression is a common factor that affects various emotions. For example, if a poster has an impression of luxury, it evokes emotions such as "elegant," "stylish," and "mature." In other words, the impression of luxury becomes the common factor, and emotions such as "elegant," "stylish," and "mature" become observed variables. Therefore, when quantifying impressions, evaluations of adjectives expressing various emotions are obtained by subjective evaluation, and the impression, which is the common factor, is found by factor analysis.

[0087] On the other hand, as shown in Figure 19(d), quality is a principal component that comprehensively represents various evaluation items. For example, if a poster has a design that is "balanced," "attractive," and "easy to see and read," the overall "quality" of the poster can be said to be high. In other words, evaluation items such as "balanced," "attractive," and "easy to see and read" are observed variables, and the "quality" that integrates them is the principal component. Therefore, when quantifying quality, evaluations for various evaluation items are obtained by subjective evaluation, and quality, which is the principal component, is obtained by principal component analysis. In this way, impression is a common factor common to various emotions obtained by factor analysis, and quality is a principal component that integrates various evaluation items obtained by principal component analysis, and the positioning of the two is different. Therefore, impression and quality are concepts with different characteristics, and therefore need to be used as different control axes.

[0088] <Poster generation process> Fig. 9(a) is a flowchart for explaining a poster generation process by the poster generation unit 210 of the poster creation application according to the first embodiment. As described above, the flowchart shown in Fig. 9(a) is started when the user sets various setting items on the poster creation application and presses the OK button. The process shown in this flowchart is realized, for example, by the CPU 101 expanding a program stored in the HDD 104 into the RAM 103 and executing it. In the first embodiment, the CPU 101 functions by executing the poster creation application, so the components shown in Fig. 2 will be described as executing the process shown in this flowchart.

[0089] In S901, the CPU 101 displays the application start screen 501 on the display 105. The user inputs each setting through the UI screen of the application start screen 501 using the keyboard 106 or the pointing device 107. Next, the process proceeds to S902, where the poster creation condition designation unit 201, the text designation unit 202, the image designation unit 203, and the target impression designation unit 204 acquire the corresponding settings from the application start screen 501. Then, the process proceeds to S903, where the skeleton selection unit 214, the color scheme pattern selection unit 215, and the font selection unit 216 respectively determine the number of skeletons, the number of color scheme patterns, and the number of fonts to be selected according to the number of posters to be created designated by the poster creation condition designation unit 201. In the first embodiment, the layout unit 217 generates poster data of (number of skeletons) x (number of color scheme patterns) x (number of fonts) by a method to be described later. At this time, the number of skeletons, the number of color scheme patterns, and the number of fonts to be selected are determined so that the number of posters to be created exceeds the number of posters to be created. In the first embodiment, the number of skeletons, the number of color patterns, and the number of fonts are each determined according to the following formula (1).

[0090] Number of selections = | 3 √{(number of creations)×2}| … formula (1) Here, the symbol "|x|" indicates a ceiling function, and is expressed as an integer value by rounding up the decimal point of x. For example, if the number of creations is 6, the number of selections is 3, the number of poster data generated by the layout unit 217 will be 27, and the poster selection unit 219 will select 6 poster data from among them. This allows the poster selection unit 219 to select posters whose overall impression is closest to the target impression from among the poster data generated in excess of the number of creations.

[0091] Next, the process proceeds to S904, where the image acquisition unit 211 acquires image data. Specifically, the image acquisition unit 211 reads out the image file in the HDD 104, which is specified by the image specification unit 203, into the RAM 103.

[0092] Next, the process proceeds to S905, where the image analysis unit 212 executes an analysis process on the image data acquired in S904, and acquires information indicating a feature amount. Examples of the information indicating the feature amount include meta information stored in the image, and information indicating an image feature amount that can be acquired by analyzing the image. These pieces of information are used in an object recognition process, which is an analysis process. Note that, in the first embodiment, an object recognition process is executed as the analysis process, but this is not limited thereto, and other analysis processes may be executed. Furthermore, the process of S905 may be omitted. Details of the process performed by the image analysis unit 212 in S905 will be described below.

[0093] The image analysis unit 212 executes object recognition processing on the image acquired in S904. Here, a known method can be used for the object recognition processing. In the first embodiment, an object is recognized by a classifier created by Deep Learning. The classifier outputs the likelihood of a pixel constituting an image being a pixel constituting each object as 0 to 1, and recognizes that an object exceeding a certain threshold is present in the image. By recognizing the object image, the image analysis unit 212 can acquire the type and position of an object such as a face, a pet such as a dog or a cat, a flower, food, a building, an ornament, and a landmark.

[0094] Next, the process proceeds to S906, where skeleton acquisition unit 213 acquires skeletons that meet the various set conditions. In the first embodiment, it is assumed that skeletons are described in one file per skeleton and stored in HDD 104. Skeleton acquisition unit 213 sequentially reads skeleton files from HDD 104 to RAM 103, leaves skeletons that meet the set conditions on RAM 103, and deletes skeletons that do not meet the conditions from RAM 103.

[0095] FIG. 9B is a flowchart illustrating a condition determination process for the skeleton acquisition unit 213 according to the first embodiment to select a skeleton that meets the set conditions.

[0096] In S921, skeleton acquisition unit 213 determines whether the skeleton size matches the poster size specified by poster creation condition specification unit 201 for the skeleton read into RAM 103. Note that although it is confirmed that the sizes match here, it is also sufficient that the aspect ratios match. In this case, skeleton acquisition unit 213 acquires a skeleton that matches the poster size specified by poster creation condition specification unit 201 by enlarging or reducing the coordinate system of the read skeleton.

[0097] Next, the process proceeds to S922, where skeleton acquisition unit 213 determines whether the purpose category specified by poster creation condition specification unit 201 matches the skeleton category. For skeletons used only for specific purposes, the purpose category is written in the skeleton file, and the skeleton is not acquired unless the relevant purpose category is selected. This is to prevent a skeleton designed specifically for a specific purpose, such as a graphic pattern that evokes a school or a pattern of sporting goods, from being used in other purpose categories. Note that if a purpose category has not been set on application startup screen 501, S922 is skipped.

[0098] Next, the process proceeds to S923, where the skeleton acquisition unit 213 determines whether the number of image objects of the loaded skeleton matches the number of images acquired by the image acquisition unit 211. Next, the process proceeds to S924, where the skeleton acquisition unit 213 determines whether the character objects of the loaded skeleton match the character information specified by the text designation unit 202. More specifically, the skeleton acquisition unit 213 determines whether the type of character information specified by the text designation unit 202 is in the skeleton. For example, assume that character strings are designated in the title box 502 and the body box 504 on the application startup screen 501, and a blank is designated in the subtitle box 503. In this case, all character objects in the skeleton are searched, and if both a character object with "title" set as the type of character information in metadata and a character object with "body" designated are found, the skeleton acquisition unit 213 is deemed to be suitable, and otherwise is deemed to be unsuitable.

[0099] As described above, skeleton acquisition unit 213 stores in RAM 103 a skeleton whose skeleton size, purpose category, number of image objects, and type of text object all match the set conditions. In the first embodiment, skeleton acquisition unit 213 judges all skeleton files on HDD 104, but the present invention is not limited to this. For example, the poster creation application may store in HDD 104 a database that associates file paths of skeleton files with search conditions (skeleton size, number of image objects, and type of text object). In this case, skeleton acquisition unit 213 can quickly acquire skeleton files by reading only matching skeleton files from HDD 104 to RAM 103 as a result of searching the database.

[0100] Next, the process proceeds to S907, where the skeleton selection unit 214 selects a skeleton that matches the target impression designated by the target impression designation unit 204 from among the skeletons acquired in S906.

[0101] Fig. 10 is a diagram for explaining a method in which the skeleton selection unit 214 according to the first embodiment selects a skeleton. Fig. 10(a) shows an example of a skeleton impression table linking skeletons with impressions. The skeleton name column in Fig. 10(a) lists the skeleton file names, and the columns for luxury, familiarity, dynamism, and solidity show numbers (numeric values) indicating the degree to which each skeleton affects each impression. These numerical values ​​indicate that, for that impression, -2 is low, -1 is slightly low, 0 is neither, +1 is slightly high, and +2 is high, respectively.

[0102] First, the skeleton selection unit 214 calculates the distance between the target impression acquired from the target impression designation unit 204 and the impression of each skeleton shown in the skeleton impression table of FIG. 10(a). For example, if the target impression is "luxury +1, familiarity -1, dynamism -2, solidity +2", the distance calculated by the skeleton selection unit 214 is as shown in FIG. 10(b). Note that in the first embodiment, the Euclidean distance is used as the distance (hereinafter, the simple distance is referred to as the Euclidean distance). The smaller the value indicated by the Euclidean distance, the closer the target impression and the impression of the skeleton are. Next, the skeleton selection unit 214 selects the top N skeletons with the smallest distance values ​​in FIG. 10(b). In the first embodiment, the skeleton selection unit 214 selects the top two skeletons. That is, the skeleton selection unit 214 selects skeleton 1 and skeleton 4.

[0103] Here, N may be set to a fixed value, or may be variable depending on the conditions specified by the poster creation condition specification unit 201. For example, when the number of posters to be created is specified as 6 in the number of posters to be created box 514 on the application start screen 501, the poster generation unit 210 generates six posters. The layout unit 217 described later generates a poster by combining skeletons, color patterns, and fonts selected by the skeleton selection unit 214, color pattern selection unit 215, and font selection unit 216. Therefore, for example, by selecting two skeletons, two color patterns, and two fonts, 2×2×2=8 posters can be generated, so that the condition of the number of posters to be created of 6 can be satisfied. In this way, the number N of skeletons to be selected may be determined depending on the conditions specified by the poster creation condition specification unit 201.

[0104] Also, the value range of each impression in the skeleton impression table in FIG. 10(a) does not need to be the same as the value range of the impression specified by the target impression designation unit 204. In the first embodiment, the value range of the impression specified by the target impression designation unit 204 is -2 to +2, but the value range of the impression in the skeleton impression table may be different from this. In that case, the value range of the skeleton impression table is scaled to match the value range of the target impression, and then the distance calculation is performed. Also, the distance calculated by the skeleton selection unit 214 is not limited to the Euclidean distance, and it is sufficient if the distance between vectors can be calculated, such as Manhattan distance or cosine similarity. Also, impressions for which the target impression is set to off by the impression radio button 512 are excluded from the distance calculation.

[0105] The skeleton impression table is created in advance by fixing, for example, the color scheme, font, and the image and character data to be arranged on the skeleton, generating a poster image based on each skeleton, and estimating the impression, and is stored in the HDD 104. That is, the impression of each poster image, which uses the same character color and image, but has a different arrangement of characters and images, is estimated, and the relative characteristics with other skeletons are tabulated. In this case, it is desirable to cancel the impression due to the color scheme pattern, image, etc. used, by standardizing the entire estimated impression, or averaging the impressions of multiple poster images generated from one skeleton using multiple color scheme patterns and images. This makes it possible to tabulate the influence of the arrangement on the impression, such as the impression of a skeleton with a small image being determined by elements such as graphics and characters regardless of the image, or the impression of a more dynamic image or character being tilted.

[0106] FIG. 10(c) shows an example of a skeleton corresponding to skeleton 1 to skeleton 4 in FIG. 10(a). For example, skeleton 1 has image objects and character objects regularly arranged and the image area is small, so it has a low sense of dynamism. Skeleton 2 has circular graphic objects and image objects, so it has a high sense of familiarity and a low sense of solidity. Skeleton 3 has a high sense of dynamism by arranging image objects large and arranging inclined graphic objects overlapping image objects. Skeleton 4 has an image arranged over the entire skeleton and a minimum number of character objects, so it has a high sense of solidity and a low sense of dynamism. In this way, when a poster image includes characters or images, poster images with different target impressions are generated depending on the arrangement method of the characters or images. Note that the method of creating the skeleton impression table is not limited to this, and may be estimated from the characteristics of the arrangement information itself, such as the area and coordinates of the image and title character string, or may be adjusted manually. The skeleton impression table is stored in the HDD 104, and the skeleton selection unit 214 reads the skeleton impression table from the HDD 104 into the RAM 103 for reference.

[0107] Next, the process proceeds to S908, where color scheme selection unit 215 selects a color scheme that matches the desired impression specified by desired impression specification unit 204. In a similar manner to S906, color scheme selection unit 215 refers to the impression table corresponding to the color scheme and selects a color scheme according to the desired impression.

[0108] FIG. 11(a) shows an example of a color scheme impression table that links color scheme patterns with impressions. The color scheme selection unit 215 calculates the distance value between the impression indicated by the columns of luxury to stateliness in FIG. 11(a) and the target impression, and selects the top N color scheme patterns with the smallest distance values. In the first embodiment, the top two color scheme patterns are selected. Note that, like the skeleton impression table, the color scheme impression table can tabulate the impression tendency of color scheme patterns by fixing the skeleton, font, and image other than the color scheme pattern, and then creating and estimating the impression of a poster with a different color scheme pattern.

[0109] Next, the process proceeds to S909, where the font selection unit 216 selects a font combination that matches the desired impression specified by the desired impression designation unit 204. The font selection unit 216 refers to the impression table corresponding to the fonts in the same manner as in S906, and selects a font according to the desired impression.

[0110] Fig. 11(b) shows an example of a font impression table that links fonts with impressions. The font selection unit 216 calculates the distance value between the impression indicated by the columns of luxury to dignity in Fig. 11(b) and the target impression, and selects the top N fonts with the smallest distance values. Note that, like the skeleton impression table, the font impression table can tabulate the tendency of font impressions by fixing the skeleton, color scheme, and image other than the font, and then creating and estimating the impression of a poster with a different font.

[0111] Next, the process proceeds to S910, where the layout unit 217 sets character information, images, color schemes, and fonts for the skeletons selected by the skeleton selection unit 214, and generates a poster.

[0112] Next, S910 and the processing of the layout unit 217 will be described in detail with reference to FIGS.

[0113] FIG. 12 is a functional block diagram for explaining the function of the layout unit 217 according to the first embodiment.

[0114] The layout unit 217 includes a color allocation unit 1201 , an image arrangement unit 1202 , an image correction unit 1203 , a font setting unit 1204 , a text arrangement unit 1205 , and a text decoration unit 1206 .

[0115] Fig. 13 is a flowchart for explaining the layout process of S910 in Fig. 9. The process shown in this flowchart is realized, for example, by CPU 101 expanding a program stored in HDD 104 into RAM 103 and executing it. In the first embodiment, the CPU 101 functions by executing the poster creation application, so the components shown in Fig. 12 will be described as executing the process shown in this flowchart.

[0116] 14 is a diagram for explaining the information input to the layout unit 217, and Fig. 14(a) shows a table summarizing the character information specified in the text specification unit 202 and the image specified in the image specification unit 203. Fig. 14(b) shows an example of a table showing the color scheme obtained from the color scheme selection unit 215, and Fig. 14(c) shows an example of a table showing the fonts obtained from the font selection unit 216. Furthermore, Fig. 15 is a diagram for explaining the process of processing by the layout unit 217.

[0117] First, the layout process of S910 will be described in detail with reference to FIG.

[0118] In S1301, the layout unit 217 lists all combinations of skeletons acquired from the skeleton selection unit 214, color patterns acquired from the color pattern selection unit 215, and fonts acquired from the font selection unit 216. The layout unit 217 generates poster data for each combination in order by the following layout process. For example, if the number of skeletons acquired from the skeleton selection unit 214 is 3, the number of color patterns acquired from the color pattern selection unit 215 is 2, and the number of fonts acquired from the font selection unit 216 is 2, the layout unit 217 generates 3×2×2=12 poster data. Next, in S1301, the layout unit 217 selects one combination from the listed combinations, and executes the processes of S1302 to S1307 for the selected combination.

[0119] Next, the process proceeds to S1302, where the coloration assignment unit 1201 assigns the coloration pattern acquired from the coloration pattern selection unit 215 to the skeleton acquired from the skeleton selection unit 214. Fig. 15(a) shows an example of a skeleton. In the first embodiment, an example will be described in which the coloration pattern with the coloration ID "1" in Fig. 14(b) is assigned to the skeleton 1501 in Fig. 15(a).

[0120] A skeleton 1501 in FIG. 15(a) is composed of two graphic objects 1502 and 1503, one image object 1504, and three character objects 1505, 1506, and 1507. First, the color allocation unit 1201 performs color allocation on the graphic objects 1502 and 1503. Specifically, based on the color number, which is metadata described in the graphic object, the color allocation unit 1201 allocates a corresponding color from a color scheme pattern. Next, the color allocation unit 1201 allocates, for example, the last color from the color scheme pattern to a character object whose metadata is type and whose attribute is "title" among the character objects. That is, in the first embodiment, the color 4 is allocated to the character arranged in the character object 1505. Next, for the character arranged in a character object whose metadata is type and whose attribute is other than "title" among the character objects, the character color is set based on the brightness of the background of the character object. In the first embodiment, if the brightness of the background of the character object is equal to or lower than a threshold value, the character color is set to white, and otherwise, the character color is set to black. 15B is a diagram showing the state of a skeleton 1508 after the above color allocation process has been performed. The color allocation unit 1201 outputs the skeleton data after color allocation to the image arrangement unit 1202.

[0121] Next, the process proceeds to S1303, where the image arrangement unit 1202 arranges the image data acquired from the image analysis unit 212 on the skeleton data acquired from the color allocation unit 1201 based on the associated analysis information. In the first embodiment, the image arrangement unit 1202 allocates the image data 1401 to the image object 1504 in the skeleton. Furthermore, when the aspect ratios of the image object 1504 and the image data 1401 are different, the image arrangement unit 1202 performs trimming so that the aspect ratio of the image data 1401 matches the aspect ratio of the image object 1504. More specifically, based on the position of the object obtained by the image analysis unit 212 analyzing the image data 1401, trimming is performed so that the object area reduced by trimming is minimized. Note that the trimming method is not limited to this, and other trimming methods may be used, such as trimming the center of the image or devising a composition so that the face position is in a triangular composition. The image arrangement unit 1202 outputs the skeleton data to which the images have been assigned to the image correction unit 1203 .

[0122] Next, the process proceeds to S1304, where the image correction unit 1203 obtains skeleton data to which images have been assigned from the image arrangement unit 1202, and performs correction on the image arranged on the skeleton. In the first embodiment, if the resolution of the image is insufficient, upsampling processing is performed using super-resolution processing. First, the image correction unit 1203 determines whether the image arranged on the skeleton meets a certain resolution. For example, assume that an image of 1600px x 1200px is assigned to an area of ​​200mm x 150mm on the skeleton. In this case, the print resolution of the image can be calculated using Equation 2.

[0123] (1600) / (200÷25.4)≒203(dpi) …Equation (2) Next, the image correction unit 1203 increases the resolution by super-resolution processing if it is determined that the print resolution of the image is less than the threshold. On the other hand, if it is determined that the print resolution of the image is equal to or greater than the threshold and has sufficient resolution, no image correction is performed. In the first embodiment, the super-resolution processing is performed if the print resolution of the image is less than 300 dpi.

[0124] Next, the process proceeds to S1305, where the font setting unit 1204 sets the font acquired from the font selection unit 216 to the skeleton data after image correction acquired from the image correction unit 1203. FIG. 14C shows an example of a combination of fonts selected by the font selection unit 216. In the first embodiment, an example of font assignment will be described in which the font ID "2" in FIG. 14C is assigned to the skeleton data after image correction. In the first embodiment, fonts are set to the character objects 1505, 1506, and 1507 of the skeleton 1508. Note that in posters, a font that is easy to see is often set for the title from the viewpoint of eye-catchingness, and a font that is easy to read from the viewpoint of visibility is often set for the other characters. Therefore, in the first embodiment, the font selection unit 216 selects two types of fonts, a title font and a body font. The font setting unit 1204 sets the title font to the character object 1505 whose attribute is "title", and sets the body font to the other character objects 1506 and 1507. The font setting unit 1204 outputs the skeleton data with the font set to the text layout unit 1205. In the first embodiment, the font selection unit 216 selects two types of fonts, but this is not limiting, and for example, only the title font may be selected. In this case, the font setting unit 1204 uses a font corresponding to the title font as the body font. That is, if the title is a Gothic font, a typical Gothic font with high readability is selected for the rest, and if the title is a Mincho font, a typical Mincho font is selected for the rest, and so on. Naturally, the title font and the body font may be the same. Also, different fonts may be used depending on the degree of prominence, such as using a title font for the character objects of the title and subtitle and a body font for the other character objects, or using a title font for a certain font size or larger.

[0125] Next, the process proceeds to S1306, where the text placement unit 1205 places the text specified by the text designation unit 202 in the skeleton data with the font set, obtained from the font setting unit 1204. In the first embodiment, each piece of text shown in FIG. 14(a) is assigned by referring to the metadata attributes of the skeleton character objects. That is, "Big Summer Thank You Sale", whose attribute is the title, is assigned to character object 1505, and "Blow away the midsummer heat", whose attribute is the subtitle, is assigned to character object 1506. Since no body text has been set in FIG. 14(a), nothing is assigned to character object 1507.

[0126] 15C shows a skeleton 1509, which is an example of skeleton data after processing by the text layout unit 1205. The text layout unit 1205 outputs the skeleton data after the text layout to the text decoration unit 1206.

[0127] Next, the process proceeds to S1307, where the text decoration unit 1206 adds decoration to the character objects in the skeleton with text layout obtained from the text layout unit 1205. In the first embodiment, if the color difference between the title character and its background area is equal to or less than a threshold, a process of adding a border to the title character is performed. This improves the readability of the title. The text decoration unit 1206 outputs the skeleton data with decoration, i.e., the poster data with all layout completed, to the impression estimation unit 218.

[0128] Finally, the process proceeds to S1308, where the layout unit 217 determines whether all poster data has been generated. If the layout unit 217 determines that poster data has been generated for all combinations of skeletons, color patterns, and fonts, the process ends this layout process and transitions to S911 in Fig. 9. On the other hand, if it determines that all poster data has not been generated, the process returns to S1301 and generates poster data for combinations that have not yet been generated. This concludes the explanation of S910. Returning to Fig. 9.

[0129] In S911, the impression estimation unit 218 executes a rendering process for each poster data acquired from the layout unit 217, and links the estimated impression obtained by estimating the impression of the rendered poster image to the poster data. The rendering process is a process of converting poster data into image data. For example, even if the color scheme is the same, the layout will change if the skeleton is different, and therefore which color is actually used and to what extent. Therefore, since it is necessary to evaluate not only the tendency of the individual impressions of the color scheme pattern and skeleton but also the impression of the final poster, this process is executed at this timing. This makes it possible to evaluate not only the impression of the individual elements of the poster, such as the color scheme and layout, but also the impression of the final poster laid out including images and characters.

[0130] Next, the process proceeds to S912, where the quality estimation unit 221 executes a rendering process for each poster data acquired from the layout unit 217, estimates the quality of the rendered poster image, and associates the estimated quality obtained with the poster data. Note that, when a feature amount calculated from the poster data is used as an input as the quality learning means, the quality of the poster is estimated after calculating the same feature amount from the poster data.

[0131] Next, the process proceeds to S913, and the evaluation value calculation unit 222 calculates an evaluation value that serves as an index for selecting a poster, from the poster data acquired from the impression estimation unit 218 and the quality estimation unit 221, and the weighting acquired from the weighting designation unit 223.

[0132] FIG. 20 is a flowchart illustrating the evaluation value calculation process in S913.

[0133] In S2001, the evaluation value calculation unit 222 compares the target impression specified by the target impression specification unit 204 with each estimated impression linked to a plurality of poster data acquired from the impression estimation unit 218, and calculates an impression evaluation value. In the first embodiment, the evaluation value calculation unit 222 calculates the distance between the target impression and the estimated impression of the poster as the impression evaluation value. Note that in the first embodiment, the Euclidean distance is used as the distance. The smaller the value indicated by the Euclidean distance, the closer the target impression and the estimated impression are. Also, the distance calculated by the evaluation value calculation unit 222 is not limited to the Euclidean distance, and any distance between vectors can be calculated, such as Manhattan distance or cosine similarity.

[0134] Next, the process proceeds to S2002, where the evaluation value calculation unit 222 compares the target quality specified by the target quality specification unit 220 with the estimated quality associated with the multiple poster data acquired from the quality estimation unit 221, and calculates a quality evaluation value. In the first embodiment, the evaluation value calculation unit 222 calculates the quality evaluation value according to the following formula (3).

[0135] Quality evaluation value = MAX (target quality - estimated quality, 0) ... formula (3) Here, MAX(·) is a function that outputs the larger numerical value. For example, if the target quality is 4 and the estimated quality is 3, the quality evaluation value is 1. If the target quality is 4 and the estimated quality is 5, the quality evaluation value is 0. In other words, if the estimated quality of the generated poster does not reach the target quality, the quality evaluation value is the difference, and if it has been achieved, the quality evaluation value is 0. Note that the method of calculating the quality evaluation value by evaluation value calculation unit 222 is not limited to equation (3), and any method may be used as long as it is possible to calculate the degree of achievement of the target quality.

[0136] Next, the process proceeds to S2003, where the evaluation value calculation unit 222 calculates a comprehensive evaluation value for selecting poster data from the impression evaluation value calculated in S2001, the quality evaluation value calculated in S2002, and the weighting obtained from the weighting specification unit 223. In the first embodiment, the evaluation value calculation unit 222 calculates the comprehensive evaluation value according to the following formula (4).

[0137] Overall evaluation value = (1 - weight) x impression evaluation value + weight x quality evaluation value ... formula (4) The method of calculating the overall evaluation value by the evaluation value calculation unit 222 is not limited to formula (4). For example, formula (4) may be applied after applying a nonlinear function to the quality evaluation value to make the influence of the quality evaluation value more extreme. The evaluation value calculation unit 222 links each calculated evaluation value with poster data and outputs it to the poster selection unit 219. This concludes the explanation of S913. Return to FIG. 9.

[0138] In S914, the poster selection unit 219 selects a poster to be output to the display 105 (presented to the user) from the poster data acquired from the evaluation value calculation unit 222 and the overall evaluation value associated with the poster data. In the first embodiment, the poster selection unit 219 selects posters in ascending order of overall evaluation value, i.e., in descending order of evaluation, for the number of posters to be created specified by the poster creation condition specification unit 201. Note that the method of selecting a poster is not limited to this. For example, as a selection method that emphasizes the degree of agreement between the target impression and the estimated impression, posters having an impression evaluation value of a predetermined threshold or less, i.e., a high evaluation of a predetermined height or more, are set as selection candidate posters. Then, from among them, posters may be selected in descending order of overall evaluation value, i.e., in descending order of evaluation, for the number of posters to be created. Also, as a selection method that emphasizes the degree of achievement of the target quality, posters having a quality evaluation value of a predetermined threshold or less, i.e., a quality evaluation value of a predetermined height or more, are set as selection candidate posters. Then, from among them ... may be selected in descending order of overall evaluation value, i.e., in descending order of evaluation, for the number of posters to be created. Furthermore, in order to enable these poster selection methods to be explicitly specified, a list box for specifying a selection method (not shown) may be provided on the application start-up screen 501, and the selection method specified in the box may be executed.

[0139] In addition, in each selection method, if the number of posters selected by the poster selection unit 219 is less than the number of posters to be created specified by the poster creation condition specification unit 201, the poster selection unit 219 may select the shortage from posters other than the selection candidate posters in ascending order of overall evaluation value, i.e., in descending order of overall evaluation. Alternatively, a notice of shortage may be displayed on the poster preview screen 601. Alternatively, the poster selection unit 219 may select the shortage posters and display them on the preview screen 601 so that posters whose impression evaluation value or quality evaluation value is equal to or less than the threshold, i.e., whose impression evaluation or quality evaluation is higher than the threshold, and posters whose impression evaluation or quality evaluation is equal to or more than the threshold, i.e., whose impression evaluation or quality evaluation is lower than the threshold, can be distinguished. Also, for example, if the selected posters are insufficient, the process may return to S903 and the number of skeletons, color scheme patterns, and fonts to be selected may be increased.

[0140] The process then proceeds to S915, where the poster display unit 205 renders the poster data selected by the poster selection unit 219, and outputs the poster image to the display 105. That is, the preview screen 601 in FIG.

[0141] The above is an explanation of the flow of the poster generation process in which a poster is generated by the user specifying a target impression and a target quality.

[0142] As described above, according to the first embodiment, by controlling the balance between the target impression and the target quality, it is possible to generate a poster that reflects the user's intention regarding the impression and quality as much as possible under the generation conditions. Specifically, in the first embodiment, each element constituting the poster, such as a skeleton, a color scheme pattern, and a font, is combined based on the target impression to generate a plurality of variations of poster candidates according to the target impression. Furthermore, by estimating the impression of the entire poster and evaluating the distance from the target impression, it is evaluated whether not only the individual elements but also the overall impression conforms to the user's intention. Furthermore, by estimating the quality of the poster and evaluating the difference from the target quality, it is evaluated whether the quality meets the user's intention. Then, by selecting a poster taking into account both the impression evaluation and the quality evaluation, it is possible to generate a poster that expresses the impression desired by the user and achieves the quality desired by the user. More specifically, for example, in the first embodiment, it is assumed that the target impression on the application startup screen 501 is set to luxury -1, familiarity +1, dynamism and solidity are each set to off, and the target quality is set to +3.6. At that time, for example, a poster image 602 on a preview screen 601 is generated with an estimated impression close to the target impression and an estimated quality that achieves the target quality, such as luxury -1.2, familiarity +0.9, dynamism +0.2, solidity -1.3, and quality +3.8. Furthermore, according to the first embodiment, it is possible to control so that posters of low quality such as those shown in Fig. 16(a) are not proposed to the user.

[0143] In the above embodiment 1, the evaluation value is the difference (distance) from the target impression or the difference (distance) from the target quality, so that the evaluation value is determined to be high when it is smaller than a threshold value. However, the present invention is not limited to this, and the smaller the difference (distance), the larger the evaluation value is, so that the evaluation value may be determined to be high when it is larger than a threshold value.

[0144] <Modification of the first embodiment> In the first embodiment, the preview screen 601 is displayed in order to output the generated poster image to the display 105, but the estimated impression and estimated quality of the poster may also be displayed together.

[0145] 21 is a diagram showing an example of a poster preview screen that displays a poster image generated by the poster display unit 205 according to a modified example of the first embodiment on the display 105. When the OK button 517 on the application start-up screen 501 is pressed and the poster generation is completed, the screen displayed on the display 105 transitions to a poster preview screen 2100. The components with the same numbers as those in FIG. 6 perform the same processes as those described above in the first embodiment, and therefore will not be described here.

[0146] The estimated value display area 2102 is an area that displays the estimated impression of the poster output by the impression estimation unit 218 and the estimated quality of the poster output by the quality estimation unit 221. In a modified example of the first embodiment, the impression estimation unit 218 links the estimated impression estimated in S911 to the poster data, and the quality estimation unit 221 links the estimated quality estimated in S912 to the poster data. This allows the poster display unit 205 to refer to the estimated impression and estimated quality linked to the poster data, and allows the estimated values ​​to be displayed in the estimated value display area 2102. Note that the estimated value display area 2102 may display only some of the estimated values ​​of the impressions and qualities that can be set on the application startup screen 501. For example, the estimated values ​​may be displayed only for items for which the impression radio button 512 or the quality radio button 519 is turned on.

[0147] As described above, according to the modification of the first embodiment, the user can check to what extent the intended impression and quality are reflected in the generated poster. Therefore, the user can use this information to select a poster to edit or print, or to provide feedback such as reviewing the settings on the application start-up screen 501.

[0148] [Embodiment 2] In the above-mentioned embodiment 1, an example was described in which the impression and quality of a poster are evaluated based on a target impression and a target quality, and a poster that reflects the user's intention is generated and selected. In contrast, in embodiment 2, an embodiment is described in which poster data is modified to improve quality when the poster's quality evaluation value does not reach a predetermined threshold. This increases the number of posters that better reflect the user's intention, allowing the user to select a desired poster from a wider variety of candidates.

[0149] Fig. 22 is a functional block diagram for explaining the functions of a poster creation application according to embodiment 2. In the configuration of the block diagram shown in Fig. 22, a design modification unit 2201 is added. Note that components with the same numbers as those in Fig. 2 perform the same processes as those explained in Fig. 2 of embodiment 1, and therefore their explanation will be omitted here.

[0150] The design modification unit 2201 acquires poster data associated with a quality evaluation value from the evaluation value calculation unit 222. If the quality evaluation value associated with the poster data is greater than a predetermined threshold, the design modification unit 2201 modifies the poster data. Then, the design modification unit 2201 outputs the modified poster data to the layout unit 217.

[0151] Fig. 23 is a flowchart for explaining the processing of the poster generation unit 210 of the poster creation application according to the embodiment 2. In this flowchart, the processing steps denoted by the same numbers as those in the flowchart of Fig. 9 are similar to those explained in the embodiment 1, and therefore the explanation thereof will be omitted here.

[0152] In S2301, the design modification unit 2201 determines whether or not the quality evaluation value associated with the poster data acquired from the evaluation value calculation unit 222 is greater than a predetermined threshold value. In the second embodiment, it determines whether or not the quality evaluation value is greater than 0, that is, whether or not the estimated quality has reached the target quality. If it is determined that the quality evaluation value associated with the poster data is greater than 0, the process transitions to S2302. If it is determined that the quality evaluation value associated with the poster data is 0 or less, the process transitions to S914, and the poster data is not modified.

[0153] In S2302, the design modification unit 2201 modifies the poster data to improve the quality of the poster.

[0154] FIG. 24 is a flowchart for explaining the poster data modification process performed by the design modification unit 2201 according to the second embodiment.

[0155] In S2401, the design modification unit 2201 increases the character size of the title to improve the jump rate of the font size. As described above, the jump rate is the ratio of the size of a large element to that of a small element, and a high jump rate results in a design in which important information stands out more. By increasing the character size of the title, which is important character information, and increasing the jump rate, the title stands out and the quality of the poster is improved in terms of visibility. First, the jump rate of the title is calculated by calculating the ratio between the character size of a character object whose attribute is "title" and the average character size of all character objects. Then, if the obtained jump rate is less than a predetermined threshold, the character size of the title is increased until the jump rate reaches the predetermined threshold. In the second embodiment, if the character size of the title is less than twice the average character size of all character sizes, the character size of the title is increased.

[0156] Next, the process proceeds to S2402, where the design modification unit 2201 aligns the character objects. In poster design, aligning the positions of the character objects improves readability and reduces discomfort caused by minute positional deviations, thereby improving the quality of the poster. First, the character objects having the same character position attribute are grouped by referring to the character position attribute of each character object. Then, if there is a combination of character objects whose difference in position is equal to or less than a predetermined threshold among multiple character objects belonging to the same group, the positions of the character objects are aligned. At this time, for a group whose character position attribute is left-justified, the position of the other character object is aligned to the character object whose position is further to the left. For a group whose character position attribute is centered, the positions of both objects are aligned to the center of the positions of both objects. For a group whose character position attribute is right-justified, the position of the other character object is aligned to the character object whose position is further to the right. In the second embodiment, the positions are aligned when the difference in position of the character objects is 2 mm or less.

[0157] Next, the process proceeds to S2403, where the design modification unit 2201 modifies the pure colors contained in the color scheme pattern. A pure color is a color with the highest saturation among all hues. In poster design, it is desirable to avoid using pure colors because pure colors are hard to see and cause eye flickering, thus reducing the quality of the poster. In the second embodiment, if the color scheme pattern of the poster data contains a color with a saturation of 95% or more in the HSV color space, the saturation of the color is changed to 95%. In addition, the design modification unit 2201 modifies the pure black or pure white contained in the color scheme pattern. Pure black is a pure black color with all RGB values ​​of 0, and pure white is a pure white color with all RGB values ​​of 255. In poster design, it is desirable to avoid using pure black and pure white because pure black is a very strong color that does not blend in with the design, and pure white gives a cheap impression. In the second embodiment, if the color scheme pattern of the poster data includes a color with a brightness of 5 or less in the L*a*b* color space, the brightness of that color is changed to 5. Also, if the color scheme pattern of the poster data includes a color with a brightness of 95 or more in the L*a*b* color space, the brightness of that color is changed to 95.

[0158] Next, the process proceeds to S2404, and the design modification unit 2201 changes the text color of the title. The text color of the title is assigned color 4 of the color scheme pattern in S1302 of FIG. 13, but depending on the color of the graphic object or image object arranged in the background of the text object, the visibility of the title may be reduced, and the quality of the poster may be reduced. Therefore, if the visibility of the title is low, the text color of the title is changed to improve the visibility of the title and improve the quality of the poster. First, it is determined whether the difference between the brightness of the text color of a text object whose attribute is "title" and the brightness of the background area of ​​the text object is less than a threshold value. In the second embodiment, the threshold value is set to 30. Then, for a text object whose brightness difference is less than the threshold value, if the brightness of the background of the text object is equal to or less than the threshold value, the text color is set to white, and otherwise the text color is set to black. In the second embodiment, the threshold value is set to 50.

[0159] This concludes the description of the design modification process in S2302. By this process in S2302, the components of the poster, such as the layout, color scheme, and font, are modified. Return to FIG.

[0160] In S910 to S913 following S2302, the above-mentioned process is executed again, and the overall evaluation value is calculated and linked for the poster data after design modification. Then, the process proceeds to S914, and the poster selection unit 219 selects a poster to be output to the display 105 (presented to the user) from the poster data acquired from the evaluation value calculation unit 222 and the overall evaluation value linked to the poster data. In the second embodiment, first, the overall evaluation value linked to the poster data whose design has been modified in S2302 is compared with the overall evaluation value linked to the poster data before the design modification. Then, the poster data linked to the larger overall evaluation value, that is, the poster data linked to the worse evaluation, is excluded from the selection candidates. Thereafter, as in the first embodiment, in S914, the poster selection unit 219 selects posters in ascending order of overall evaluation value, the number of posters to be created specified by the poster creation condition specification unit 201.

[0161] As described above, according to the second embodiment, if the quality evaluation value of a poster does not reach a predetermined threshold, the poster data is modified to improve the quality of the poster. Although the quality of the poster is improved by modifying the design, the impression it conveys may change, so the impression and quality are evaluated again to select a poster with a higher evaluation. This increases the number of posters that better reflect the user's intentions, allowing the user to select a desired poster from a wider variety of candidates.

[0162] <Modification of the second embodiment> In the second embodiment, the poster data is retouched in S2302 to improve the quality of the poster. However, each design retouching process may be switched on or off based on the target impression.

[0163] The difference in data flow between the second embodiment and this modification will be described with reference to FIG.

[0164] In this modified example, the evaluation value calculation unit 222 links the desired impression received from the desired impression designation unit 204 to the poster data to be output to the design modification unit 2201 .

[0165] The difference between the poster data correction process in the second embodiment and this modified example will be described with reference to FIG.

[0166] In S2401, the design modification unit 2201 improves the jump rate of the title only when the value of the sense of dynamism is equal to or greater than a threshold value or the value of the sense of luxury is equal to or less than a threshold value among the target impressions linked to the poster data. This is because there are cases where the jump rate is intentionally lowered when a calm or luxurious impression is desired. In this modified example, the modification to improve the jump rate of the title is performed only when the target sense of dynamism is equal to or greater than 0 and the sense of luxury is equal to or less than 0.

[0167] In addition, in S2403, the design modification unit 2201 changes the pure color only when the value of the sense of dynamism is equal to or less than a threshold value among the target impressions linked to the poster data. This is because there are cases where pure colors are used intentionally when a dynamic or energetic impression is desired. In this modified example, the pure color is changed only when the target sense of dynamism is equal to or less than 0. In addition, the design modification unit 2201 changes the pure black color only when the value of the sense of luxury is equal to or less than a threshold value or the value of the sense of weight is equal to or less than a threshold value among the target impressions linked to the poster data. This is because there are cases where pure black is used intentionally when a luxurious or weighty impression is desired. In this modified example, the pure black color is changed only when the target sense of luxury is equal to or less than 0 and the sense of weight is equal to or less than 0. In addition, the design modification unit 2201 changes the pure white color only when the value of the sense of luxury is equal to or more than a threshold value among the target impressions linked to the poster data. This is because there are cases where pure white is used intentionally when a cheap impression is desired. In this modified example, the pure white color is changed only when the target sense of luxury is equal to or more than 0.

[0168] As described above, according to the modification of the second embodiment, it is possible to improve the quality of poster data while taking into account the target impression.

[0169] (Other embodiments) The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0170] This specification and drawings disclose the following information processing device, its control method, and program.

[0171] [Item 1] An information processing device, A first reception means for receiving from a user a designation of a target impression that the poster to be generated has; A second reception means for receiving from a user a designation of a target quality of the poster to be generated; A generating means for generating poster data based on at least the target impression; an evaluation value calculation means for calculating an evaluation value from first information indicating a difference between the target impression and an impression possessed by the poster data, and second information indicating a difference between the target quality and a quality possessed by the poster data; a selection means for selecting poster data having an evaluation value higher than a predetermined evaluation value; An information processing device comprising:

[0172] [Item 2] The information processing device described in item 1, characterized in that the evaluation value calculation means uses the second information when the quality of the poster data does not reach the target quality, and calculates the evaluation value by setting the second information to 0 when the quality of the poster data reaches the target quality.

[0173] [Item 3] 3. The information processing device according to item 1 or 2, wherein the difference is represented by a Euclidean distance.

[0174] [Item 4] 4. The information processing device according to any one of items 1 to 3, wherein the generating means generates the poster data by arranging at least one of an image, a text, and a figure to be used in the poster according to layout information.

[0175] [Item 5] The information processing device according to any one of items 1 to 4, characterized in that the first reception means and the second reception means display a screen for receiving the designation from a user and receive the designation of the target impression and the target quality via the screen.

[0176] [Item 6] the screen displays sliders as objects for designating the target impression and the target quality; 6. The information processing device according to item 5, wherein the first receiving means and the second receiving means receive designation of the target impression and the target quality in response to an operation of the slider by the user.

[0177] [Item 7] The information processing device according to any one of items 1 to 6, characterized in that the quality of the poster is expressed by a numerical value calculated from at least one evaluation item among the design balance, eye-catchingness, and visibility of the poster.

[0178] [Item 8] a third reception means for receiving weight information indicating weights of the target impression and the target quality, The information processing device described in any one of items 1 to 7, characterized in that the evaluation value calculation means calculates the evaluation value based on information indicating a difference between the target impression and the impression possessed by the poster data, information indicating a difference between the target quality and the quality possessed by the poster data, and the weighting information.

[0179] [Item 9] The information processing device according to any one of items 1 to 8, further characterized in that, when a plurality of poster data are generated, the selection means selects from the plurality of poster data, poster data having an evaluation value higher than a predetermined evaluation, the number of poster data being based on the number of posters created specified by a user, or a number greater than the number of posters selected.

[0180] [Item 10] 10. The information processing device according to any one of items 1 to 9, further comprising a display means for displaying a poster image based on the poster data selected by the selection means.

[0181] [Item 11] 11. The information processing device according to item 9 or 10, wherein the selection means selects the poster data having an evaluation value higher than a predetermined evaluation in descending order of the evaluation.

[0182] [Item 12] 11. The information processing device according to item 10, wherein the display means displays the impression and quality of the poster image.

[0183] [Item 13] The information processing device according to any one of items 1 to 12, characterized in that the generation means regenerates poster data different from the poster data when information indicating a difference between the target quality and the quality of the poster data generated by the generation means is greater than a predetermined threshold value.

[0184] [Item 14] The information processing device described in item 13, characterized in that, in the re-generation, the generation means generates poster data different from the poster data by changing at least one of the layout, color scheme, and font in the poster data.

[0185] [Item 15] 15. The information processing device according to item 13 or 14, wherein the generating means determines whether or not to change a layout or a color scheme in the poster data based on the target impression.

[0186] [Item 16] A control method for controlling an information processing device, comprising: a first reception step in which a first reception means of the information processing device receives, from a user, a designation of a target impression that a poster to be generated has; a second reception step in which a second reception means of the information processing device receives, from a user, a designation of a target quality of the poster to be generated; a generation step in which a generation means of the information processing device generates poster data based on at least the target impression; an evaluation value calculation step in which an evaluation value calculation means of the information processing device calculates an evaluation value from first information indicating a difference between the target impression and the impression possessed by the poster data and second information indicating a difference between the target quality and a quality possessed by the poster data; a selection step in which a selection means of the information processing device selects poster data having an evaluation value higher than a predetermined evaluation; An information processing device comprising:

[0187] [Item 17] 16. A program for causing a computer to function as each of the means of the information processing device according to any one of items 1 to 15.

[0188] The present invention is not limited to the above-described embodiments, and various modifications and variations can be made without departing from the spirit and scope of the present invention. Therefore, the following claims are appended to apprise the public of the scope of the present invention. [Explanation of symbols]

[0189] 100... poster generating device, 105... display, 106... keyboard, 210... poster generating unit, 201... poster creation condition designation unit, 204... target impression designation unit, 213... skeleton acquisition unit, 215... color scheme pattern selection unit, 217... layout unit, 218... impression estimation unit, 220... target quality designation unit, 221... quality estimation unit, 222... evaluation value calculation unit, 223... weight designation unit

Claims

1. An information processing device, a first receiving means for receiving from a user a designation of a target impression that the poster to be generated has; A second reception means for receiving from a user a designation of a target quality of the poster to be generated; A generating means for generating poster data based on at least the target impression; an evaluation value calculation means for calculating an evaluation value from first information indicating a difference between the target impression and an impression possessed by the poster data, and second information indicating a difference between the target quality and a quality possessed by the poster data; a selection means for selecting poster data having an evaluation value higher than a predetermined evaluation value; An information processing device comprising:

2. The information processing device according to claim 1, characterized in that the evaluation value calculation means calculates the evaluation value by using the second information when the quality of the poster data does not reach the target quality, and by setting the second information to 0 when the quality of the poster data reaches the target quality.

3. 2. The information processing apparatus according to claim 1, wherein the difference is represented by a Euclidean distance.

4. 2. The information processing apparatus according to claim 1, wherein said generating means generates said poster data by arranging at least one of an image, a text, and a graphic to be used in said poster in accordance with layout information.

5. 2 . The information processing apparatus according to claim 1 , wherein the first reception means and the second reception means display a screen for receiving the designation from a user, and receive the designation of the target impression and the target quality via the screen.

6. the screen displays sliders as objects for designating the target impression and the target quality; 6. The information processing apparatus according to claim 5, wherein the first receiving means and the second receiving means receive the designation of the target impression and the target quality in response to an operation of the slider by the user.

7. 2. The information processing device according to claim 1, wherein the quality of the poster is expressed by a numerical value calculated from at least one evaluation item among the balance, eye-catchingness, and visibility of the design of the poster.

8. a third reception means for receiving weight information indicating weights of the target impression and the target quality, The information processing device according to claim 1, characterized in that the evaluation value calculation means calculates the evaluation value based on information indicating a difference between the target impression and the impression possessed by the poster data, information indicating a difference between the target quality and the quality possessed by the poster data, and the weighting information.

9. The information processing device according to claim 1, further characterized in that, when a plurality of poster data are generated, the selection means selects from the plurality of poster data, poster data having an evaluation value higher than a predetermined evaluation, the number of poster data being based on the number of posters to be created specified by a user, or a number greater than the number of posters to be created.

10. 10. The information processing apparatus according to claim 1, further comprising display means for displaying a poster image based on the poster data selected by said selection means.

11. 10. The information processing apparatus according to claim 9, wherein the selection means selects the poster data having an evaluation value higher than a predetermined evaluation in descending order of the evaluation.

12. 11. The information processing apparatus according to claim 10, wherein said display means displays the impression and quality of said poster image.

13. The information processing device according to claim 1, characterized in that the generation means regenerates poster data different from the poster data when information indicating a difference between the target quality and a quality of the poster data generated by the generation means is greater than a predetermined threshold value.

14. 14. The information processing apparatus according to claim 13, wherein the generating means generates poster data different from the original poster data by changing at least one of a layout, a color scheme, and a font in the poster data in the regeneration.

15. 14. The information processing apparatus according to claim 13, wherein said generating means determines whether or not to change a layout or a color scheme in said poster data based on said target impression.

16. A control method for controlling an information processing device, comprising: a first reception step in which a first reception means of the information processing device receives, from a user, a designation of a target impression that a poster to be generated has; a second reception step in which a second reception means of the information processing device receives, from a user, a designation of a target quality of the poster to be generated; a generation step in which a generation means of the information processing device generates poster data based on at least the target impression; an evaluation value calculation step in which an evaluation value calculation means of the information processing device calculates an evaluation value from first information indicating a difference between the target impression and the impression possessed by the poster data and second information indicating a difference between the target quality and a quality possessed by the poster data; a selection step in which a selection means of the information processing device selects poster data having an evaluation value higher than a predetermined evaluation; An information processing device comprising:

17. A program for causing a computer to function as each of the means of the information processing apparatus according to claim 1.

Images