Abstract: An image recognition system includes sensors and a server. Each of the sensors includes a processing unit to perform (i) first image recognition on time-series images chronologically captured, (ii) a first estimation as to whether a predetermined event has occurred by a target of the images, and (iii) generation of transmission data based on the first estimation that the predetermined event occurred. The transmission data may include a feature map of a multilayered neural network or image portions, which include the imaged target respectively clipped from the time-series images. The server may obtain the transmission data and perform second image recognition with greater accuracy than that of the sensors, to perform a second estimation as to whether the predetermined event has occurred.

Abstract: An image recognition system includes a plurality of sensor devices and a server device. Bach of the plurality of sensor devices includes a first image recognition unit and a transmission data generation unit. The first image recognition unit performs an image recognition process on time-series images captured in chronological order, and estimates whether a predetermined event has occurred in an imaging target captured in the time-series images. On condition that the first image recognition unit has made the estimation that the predetermined event has occurred in the imaging target, the transmission data generation unit generates, as transmission data to be transmitted to the server device, first time-series images obtained by partial images including the image of the imaging target being cut out from respective images included in the time-series images. The server device includes a second image recognition unit.

Abstract: An ultrasound image processing apparatus includes a structural object extracting unit, an abnormal candidate spot detecting unit and a cine information generating unit. The structural object extracting unit extracts a structural object in an ultrasound image of each frame from ultrasound image data of a plurality of continuous frames. The abnormal candidate spot detecting unit detects an abnormal candidate spot in the extracted structural object. The cine information generating unit generates cine information where the detected abnormal candidate spot is made to be associated with a frame in which the abnormal candidate spot is detected.

Abstract: An ultrasound image processing apparatus includes a structural object extracting unit, an abnormal candidate spot detecting unit and a cine information generating unit. The structural object extracting unit extracts a structural object in an ultrasound image of each frame from ultrasound image data of a plurality of continuous frames. The abnormal candidate spot detecting unit detects an abnormal candidate spot in the extracted structural object. The cine information generating unit generates cine information where the detected abnormal candidate spot is made to be associated with a frame in which the abnormal candidate spot is detected.

Abstract: An image region extraction device for extracting a target region on the basis of a designated region with high precision. An image region extraction device (100) extracts a target region from an image on the basis of a designated region and is provided with: a spatial change learning unit (180) for acquiring, for each section of the image, a pixel value changing pattern which is a characteristic of the spatial changes in a pixel value component, and a distance changing pattern which is a characteristic of the spatial changes in a distance component extending from a reference position to a photographic object; and a region dividing unit (210) for extracting a target region on the basis of the similarities between the pixel value changing pattern and the distance changing pattern among the designated region and each section of the image.

Abstract: Disclosed is an information processing apparatus including virtual object management section (104) that manages virtual object management information of the information processing apparatus thereof on a virtual object disposed in an augmented real space shared by a group to which this information processing apparatus belongs. Communication section (107) receives virtual object management information of another information processing apparatus from this other information processing apparatus belonging to another group, the information regarding a virtual object disposed in an augmented real space shared in the other group. Reference point setting section (103) sets a common reference point based on the virtual object management information of the information processing apparatus and the virtual object management information of the other information processing apparatus, the common reference point being commonly used by the other group and the group to which the information processing apparatus belongs.

Abstract: An image region extraction device for extracting a target region on the basis of a designated region with high precision. An image region extraction device (100) extracts a target region from an image on the basis of a designated region and is provided with: a spatial change learning unit (180) for acquiring, for each section of the image, a pixel value changing pattern which is a characteristic of the spatial changes in a pixel value component, and a distance changing pattern which is a characteristic of the spatial changes in a distance component extending from a reference position to a photographic object; and a region dividing unit (210) for extracting a target region on the basis of the similarities between the pixel value changing pattern and the distance changing pattern among the designated region and each section of the image.

Abstract: A feature amount calculation apparatus calculates a feature amount of a target object from image data, and is provided with: a feature value calculator that calculates an edge direction and edge magnitude as input image data pixel-unit feature values; a feature amount calculator that has an edge direction group calculator that calculates a group of edge directions, and a correlation value calculator that takes all pixels or predetermined pixels among a plurality of pixels used in feature value calculation as pixels subject to correlation value calculation and calculates an edge magnitude correlation value between the pixels subject to correlation value calculation for each feature value; and a histogram creator that counts feature amounts in a histogram for each correlation value, and creates a histogram as a feature vector.

Abstract: The picture quality of captured images can be improved with the degradation of clearness of image-captured object boundaries suppressed. An image processing apparatus (100) comprises: an image/distance acquiring unit (200) that acquires corresponding pixel pairs between left-eye and right-eye images, its depth information and its matching scores; a weight information calculating unit (300) that determines, for each of the pixel pairs, a weight of each of the pixels in a certain area including, as pixels of interest, the pixel pair on the basis of the depth information and the matching scores; and a pixel value superimposing unit (400) that applies, for each of the pixel pairs, the weight to the pixel values in the aforementioned certain area, thereby performing a smoothing process in at least one of the two images and that superimposes the two images using the values obtained by the smoothing process.

Abstract: Disclosed is an information processing apparatus including virtual object management section (104) that manages virtual object management information of the information processing apparatus thereof on a virtual object disposed in an augmented real space shared by a group to which this information processing apparatus belongs. Communication section (107) receives virtual object management information of another information processing apparatus from this other information processing apparatus belonging to another group, the information regarding a virtual object disposed in an augmented real space shared in the other group. Reference point setting section (103) sets a common reference point based on the virtual object management information of the information processing apparatus and the virtual object management information of the other information processing apparatus, the common reference point being commonly used by the other group and the group to which the information processing apparatus belongs.

Abstract: The picture quality of captured images can be improved with the degradation of clearness of image-captured object boundaries suppressed. An image processing apparatus (100) comprises: an image/distance acquiring unit (200) that acquires corresponding pixel pairs between left-eye and right-eye images, its depth information and its matching scores; a weight information calculating unit (300) that determines, for each of the pixel pairs, a weight of each of the pixels in a certain area including, as pixels of interest, the pixel pair on the basis of the depth information and the matching scores; and a pixel value superimposing unit (400) that applies, for each of the pixel pairs, the weight to the pixel values in the aforementioned certain area, thereby performing a smoothing process in at least one of the two images and that superimposes the two images using the values obtained by the smoothing process.

Abstract: A feature amount calculation apparatus is provided that enables an outline of an object such as a silhouette line of a person, and an important feature due to object outline and surrounding image changes, to be extracted by reducing the influence of background noise.

Abstract: There is provided an image processing apparatus for performing a stable attention condition determination, regardless of the shape and surrounding environment of an object of interest and regardless that the object is unknown or known. The image processing apparatus comprises a direction detector, a displacement detector, and an attention condition determiner. The direction detector detects, from a certain image including a person image, the direction information in two body regions of a person represented by the person image. The displacement detector calculates, from the two direction information, a displacement ratio that is the ratio between the two direction displacements. The attention condition determiner determines, according to a first and a second displacement ratio, how much the person pays attention to a certain object.

Abstract: There is provided an image processing apparatus for performing a stable attention condition determination, regardless of the shape and surrounding environment of an object of interest and regardless that the object is unknown or known. The image processing apparatus comprises a direction detector, a displacement detector, and an attention condition determiner. The direction detector detects, from a certain image including a person image, the direction information in two body regions of a person represented by the person image. The displacement detector calculates, from the two direction information, a displacement ratio that is the ratio between the two direction displacements. The attention condition determiner determines, according to a first and a second displacement ratio, how much the person pays attention to a certain object.

Abstract: The present invention enables estimation of desired parameters with less computation cost and with high precision by inputting first training vectors generated from observation patterns and second training vectors generated from estimation targets in order to learn the correlation between observation patterns as inputs and patterns of the estimation targets such that desired outputs are assumed from the inputs, calculating the auto-correlation information of the two training vectors, and cross-correlation information of an average vector, the first training vectors and second training vectors, and using the information, obtaining probable expectation values based on the Bayes theory of the estimation targets with respect to an input pattern.

Abstract: The present invention enables estimation of desired parameters with less computation cost and with high precision by inputting first training vectors generated from observation patterns and second training vectors generated from estimation targets in order to learn the correlation between observation patterns as inputs and patterns of the estimation targets such that desired outputs are assumed from the inputs, calculating the auto-correlation information of the two training vectors, and cross-correlation information of an average vector, the first training vectors and second training vectors, and using the information, obtaining probable expectation values based on the Bayes theory of the estimation targets with respect to an input pattern.