Abstract: Provided are an image processing device, an image processing method and program, and an imaging apparatus capable of assisting in capturing an image in which a character or a character string is laid out at the appropriate position. In order to achieve the above-mentioned object, the image processing device includes a layout determination unit that determines a layout of the character or the character string in an image of the target image in accordance with meaning of the character or the character string; an assist information generation unit that generates imaging assist information for assisting in setting composition during imaging performed by the imaging unit; a synthesis unit that synthesizes the imaging assist information with the target image based on the determined layout; and a display control unit that displays the synthesized image on a display unit.

Abstract: The information processing apparatus includes a space information acquisition unit that acquires space information based on the space sensing information, an object information acquisition unit that acquires object information, a user information acquisition unit that acquires user information based on the user sensing information, an attention level map creation unit that creates an attention level map showing an attention level of the user for each local area of the space, a goodness-of-fit map creation unit that creates a goodness-of-fit map showing a goodness-of-fit of the object for each local area, and a proposing unit that proposes a disposition of the object in the space on the basis of the attention level map and the goodness-of-fit map.

Abstract: To prompt generation of a new motion of a mobile body. The mobile body includes: a blending parameter setting section that sets a blending parameter; a motion generator that is configured to be able to generate a third motion by blending, into a predetermined first motion as a motion of the mobile body, a predetermined second motion as a motion of the mobile body different from the first motion with a reflection degree corresponding to the blending parameter set by the blending parameter setting section; and a motion controller that is configured to be able to reflect the third motion generated by the motion generator to a motion to be actually performed by the mobile body.

Abstract: A data storage unit collects and stores, for each user, data related to a “room-and-image” combination preferred by the user. A generation unit generates information which indicates a “room-and-image” relationship and in which a preference of the user is reflected by using the data collected for each user. In a case where a room image (second image) captured by the user is acquired, an image selection unit selects an image (third image) in which the preference of the user is reflected, from an image group registered in a content DB or an image group registered in a user image DB, based on the acquired second image and the information which indicates the “room-and-image” relationship, and suggests the selected image to the user. Thereby, it is possible to suggest an image which matches with the user's room and in which the preference of the user is reflected, as an image for decorating the user's room.

Abstract: There are provided a font creation apparatus, a font creation method, and a font creation program capable of generating, from small-number character images having a desired-to-be-imitated style, a complete font set for any language having the same style as the character images. A feature amount extraction unit (40) receives a character image (32) of a first font having a desired-to-be-imitated style and extracts a first feature amount of the first font of the character image (32). An estimation unit (42) estimates a transformation parameter between the extracted first feature amount and a second feature amount of a reference second font (34). A feature amount generation unit (44) generates a fourth feature amount of a second font set to be created by transforming a third feature amount of a complete reference font set (36) based on the estimated transformation parameter.

Abstract: There are provided a device with a touch panel display, a control method of a device with a touch panel display, and a program capable of performing desired processing on an object in an image by a simple operation. An object region occupied by an object including at least a portion of a contact region on an image is determined based on a contact region by a pinch-in operation, and in a case where a transition from the pinch-in operation to an operation other than the pinch-in operation is recognized, an action related to the object region on the image displayed on the touch panel display is performed.

Abstract: Efficiency of work for laying out an object extracted from an image on another image is improved, and a burden on a user who performs the work is reduced. In S6, a second image attribute information extraction unit 15 extracts attribute information of a second image. In S7, a layout determination unit 16 determines a combining position of the object in the second image based on object attribute information, object surrounding attribute information, and second image attribute information. In S8, a correction unit 17 corrects at least one of the extracted object or the second image based on the object attribute information, the object surrounding attribute information, and the second image attribute information. In S9, the combining unit 18 creates a composite image obtained by combining the object (corrected object in a case where correction on object is performed) at a combining position of the second image (corrected second image in a case where correction on second image is performed).

Abstract: Provided are an image processing device, an image processing method and program, and an imaging apparatus capable of assisting in capturing an image in which a character or a character string is laid out at the appropriate position. In order to achieve the above-mentioned object, the image processing device includes a layout determination unit that determines a layout of the character or the character string in an image of the target image in accordance with meaning of the character or the character string; an assist information generation unit that generates imaging assist information for assisting in setting composition during imaging performed by the imaging unit; a synthesis unit that synthesizes the imaging assist information with the target image based on the determined layout; and a display control unit that displays the synthesized image on a display unit.

Abstract: Provided are an image processing device, an image processing method and program, and an imaging apparatus for synthesizing an appropriate character or character string with an image. The image processing device comprises: an image acquisition unit that acquires a time-series image group; a character selection unit that selects a character or a character string from the image group; an image selection unit that selects a target image, with which the character or the character string is synthesized, from the image group; a layout determination unit that determines a layout of the character or the character string in an image of the target image; and a synthesis unit that synthesizes the character or the character string with the target image based on the layout. With such a configuration, the above-mentioned object is solved.

Abstract: There are provided an image processing device, an image processing method, a program, and a portable terminal device which more accurately extract a user's region of interest from an image with fewer operations. The object is solved by an image processing device which divides an acquired image into a plurality of regions, selects at least one region from among the plurality of divided regions, analyzes a relationship between the selected region and a region other than the selected region, and outputs a grouping candidate for a region belonging to the same group as the selected region from the analyzed relationship.

Abstract: There are provided a device with a touch panel display, a control method of a device with a touch panel display, and a program capable of performing desired processing on an object in an image by a simple operation. An object region occupied by an object including at least a portion of a contact region on an image is determined based on a contact region by a pinch-in operation, and in a case where a transition from the pinch-in operation to an operation other than the pinch-in operation is recognized, an action related to the object region on the image displayed on the touch panel display is performed.

Abstract: There are provided a font creation apparatus, a font creation method, and a font creation program capable of generating, from small-number character images having a desired-to-be-imitated style, a complete font set for any language having the same style as the character images. A feature amount extraction unit (40) receives a character image (32) of a first font having a desired-to-be-imitated style and extracts a first feature amount of the first font of the character image (32). An estimation unit (42) estimates a transformation parameter between the extracted first feature amount and a second feature amount of a reference second font (34). A feature amount generation unit (44) generates a fourth feature amount of a second font set to be created by transforming a third feature amount of a complete reference font set (36) based on the estimated transformation parameter.

Abstract: The information processing apparatus includes a space information acquisition unit that acquires space information based on the space sensing information, an object information acquisition unit that acquires object information, a user information acquisition unit that acquires user information based on the user sensing information, an attention level map creation unit that creates an attention level map showing an attention level of the user for each local area of the space, a goodness-of-fit map creation unit that creates a goodness-of-fit map showing a goodness-of-fit of the object for each local area, and a proposing unit that proposes a disposition of the object in the space on the basis of the attention level map and the goodness-of-fit map.

Abstract: Even in a case where an object (OBJ2) of a movable article is placed in a virtual initial room space corresponding to an original position of the movable article in a room image, a position of a product object (IT) is not hindered. Therefore, coordinates (x2, y2, z2) corresponding to the original position of the object (OBJ2) of movable article in the room image are decided to be the placement of the object (OBJ2). On the other hand, in a case where an object (OBJ1) of a movable article is placed in a virtual initial room space corresponding to an original position of the movable article in a room image, a position of a product object (IT) is hindered (that is, the images of the objects overlap each other). Therefore, the coordinates of the object (OBJ1) of the movable article are not provided, and an elimination state is decided to be the placement of the object (OBJ1).

Abstract: A data storage unit collects and stores, for each user, data related to a “room-and-image” combination preferred by the user. A generation unit generates information which indicates a “room-and-image” relationship and in which a preference of the user is reflected by using the data collected for each user. In a case where a room image (second image) captured by the user is acquired, an image selection unit selects an image (third image) in which the preference of the user is reflected, from an image group registered in a content DB or an image group registered in a user image DB, based on the acquired second image and the information which indicates the “room-and-image” relationship, and suggests the selected image to the user. Thereby, it is possible to suggest an image which matches with the user's room and in which the preference of the user is reflected, as an image for decorating the user's room.

Abstract: An endoscope system includes an identification unit that identifies the type of an image obtained by image capturing of a photographic subject, a recognition unit that performs a recognition process of recognizing the photographic subject by using the image, and a notification unit that gives a notification of whether the recognition process functions for the image of a specific type identified by the identification unit. The identification unit identifies the type of the image by determining an operation mode, the model of an endoscope used in image capturing of the photographic subject, or whether or not a drug is administered to the photographic subject.

Abstract: A medical image obtained by imaging of an observation target is acquired. A region of interest including a target of interest is detected from the medical image. A detection result of the region of interest is displayed on a monitor using a display style that differs depending on at least a detection position of the region of interest.

Abstract: Efficiency of work for laying out an object extracted from an image on another image is improved, and a burden on a user who performs the work is reduced. In S6, a second image attribute information extraction unit 15 extracts attribute information of a second image. In S7, a layout determination unit 16 determines a combining position of the object in the second image based on object attribute information, object surrounding attribute information, and second image attribute information. In S8, a correction unit 17 corrects at least one of the extracted object or the second image based on the object attribute information, the object surrounding attribute information, and the second image attribute information. In S9, the combining unit 18 creates a composite image obtained by combining the object (corrected object in a case where correction on object is performed) at a combining position of the second image (corrected second image in a case where correction on second image is performed).

Abstract: There is provided a learning apparatus, a method, and a program that can prevent overlearning and improve generalization performance while suppressing deterioration of convergence performance in learning. A learning apparatus includes a learning unit that performs learning of a neural network composed of a plurality of layers and including a plurality of skip connections in which an output from a first layer to a second layer which is a layer next to the first layer is branched to skip the second layer and is connected to an input of a third layer located downstream of the second layer, a connection invalidating unit that invalidates at least one of the skip connections in a case where the learning is performed, and a learning control unit that changes the skip connection to be invalidated by the connection invalidating unit and causes the learning unit to perform the learning.

Abstract: An image registration device includes: an image acquisition unit that acquires a plurality of images; a divided region setting unit that sets divided regions by dividing each registration processing target of the plurality of images; a pixel value conversion method determination unit that determines, for each set of divided regions set at the same position of the respective registration processing targets, a pixel value conversion method for each divided region based on a pixel value of each divided region of the set; a pixel value conversion unit that performs pixel value conversion within each divided region of the set of divided regions using the determined pixel value conversion method for each divided region; and a registration processing unit that performs registration processing on the plurality of images subjected to pixel value conversion.