Canon Kabushiki Kaisha

Toshiba Lifestyle Products & Services Corporation

Yasuhiro Komori

Masayuki Yamada

Toshiaki Fukada

Hung Khei Huang

Tetsuo Kosaka

Yasunori Ohora

Masakazu Matsugu

Sangwon Chae

Yasuo Okutani

Shunta Tate

Makoto Hirota

Kenichiro Nakagawa

Hiroki Yamamoto

Tsuyoshi Yagisawa

Yusuke Mitarai

Teruhiko Ueyama

Mitsuru Otsuka

Akihiro Kushida

Philip Garner

Katsuhiko Kawasaki

Seyed Behzad Sajadi

Yoshinori Ito

Atsushi Nogami

Masahiro Mutsuno

Yuki Saito

Yasuhiro Okuno

Michio Aizawa

Hideo Noro

Masato Aoba

Takashi Aso

Hideo Kuboyama

Akira Ohno

Tomoya Honjo

Takayuki Saruta

Satoshi Nagai

Hiroshi Nishimura

Nobuaki Kuwabara

Hiromi Ikeda

Hironori Sasaki

Tomonori Uchiyama

Mamoru Yoshimoto

According to the present disclosure, a weight parameter of a neural network is divided into a plurality of portions having a certain size and approximation is individually performed on the portions using a weighted sum of the codebook vectors.

Information processing apparatus, information processing method, and program

A minute bubble generator includes a flow path member including a flow path allowing a liquid to pass therethrough; and a colliding part provided in the flow path and generating minute bubbles in the liquid passing through the flow path by locally reducing a cross sectional area of the flow path. The colliding part is formed integrally with the flow path member and is provided closer to an upstream end or a downstream end relative to a lengthwise center of the flow path.

Minute bubble generator, home appliance provided with minute bubble generator, and method of manufacturing minute bubble generator

A result of recognition processing of a convolutional neural network is acquired using recognition object data including information of a recognition object, as an input. A region of interest for the recognition object data and/or an intermediate layer output of the convolutional neural network is set. Detail recognition processing is performed for the recognition object data and/or the intermediate layer output in the region of interest. Integration processing of a result of the detail recognition processing and the intermediate layer output is performed. A result of the integration processing is input as the intermediate layer output to the convolutional neural network. A result of the recognition processing is output.

Information processing apparatus, information processing method, and non-transitory computer-readable storage medium

It is an object of the present invention to provide a user interface which facilitates confirmation of an area in an image and associated data corresponding to the area without requiring user's complicated operations. To achieve the object, an information processing apparatus comprises: an obtaining unit configured to obtain a first image including a plurality of objects, and information related to respective positions of the plurality of objects in the first image; and a determining unit configured to determine a position in case of shifting and displaying a second image indicating the plurality of objects with respect to the first image, based on the obtained positions of the plurality of objects.

Information processing apparatus, information processing method and program

An image processing apparatus comprising: a learning unit configured to perform learning of a discriminator based on an image feature amount in a first image and a class of the first image defined by a first granularity; an evaluation unit configured to evaluate an image feature amount in a second image whose class is known by the discriminator after the learning; and a control unit configured to control the learning unit to, in a case in which the evaluation by the evaluation unit is that a predetermined criterion is not satisfied, perform the learning of the discriminator based on the image feature amount in the first image and a class of the first image defined by a second granularity coarser than the first granularity.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium that perform class identification of an input image using a discriminator that has undergone learning to perform class identification at different granularities

An information processing apparatus includes a learning unit configured to learn a plurality of multi-layer neural networks configured to carry out a plurality of tasks, a generation unit configured to generate a shared layer candidate at a predetermined layer between or among the plurality of multi-layer neural networks, a first relearning unit configured to relearn the plurality of multi-layer neural networks in a structure using the shared layer candidate, and a determination unit configured to determine whether to share the shared layer candidate at the predetermined layer with respect to each of the plurality of tasks based on an evaluation of the relearning.

Information processing apparatus using multi-layer neural network and method therefor

An image processing apparatus includes: an acquisition unit configured to acquire a plurality of images each capturing an identical target and having a different attribute; a derivation unit configured to derive features from the plurality of images, using a first neural network; an integration unit configured to integrate the features derived from the plurality of images; and a generation unit configured to generate a higher quality image than the plurality of images from the feature integrated by the integration unit, using a second neural network.

Image processing apparatus and method for generating high quality image

In the present disclosure, an image parameter of an input image is changed, features is extracted from each of a plurality of generated images, a category of each region is determined based on the features in each image, and the results are integrated.

Image recognition apparatus, image recognition method, and program

To appropriately superimpose and display a virtual object on an image of a real space, an information processing apparatus according to exemplary embodiment of the present invention determines the display position of the virtual object based on information indicating an allowable degree of superimposition of a virtual object on each real object in the image of the real space, and a distance from a real object for which a virtual object is to be displayed in association with the real object.

Information processing apparatus, information processing method, information processing system, and storage medium

Determination of locations of multiple rectangular areas within a composite projection area formed on a projection surface by a projector array of multiple projectors. A location of a maximum rectangular area is determined within the composite projection area. Available regions comprise regions unoccupied by previously-located rectangular areas. The maximum rectangular area is removed from the available regions. The following are iteratively repeated: determining a location of a next maximum rectangular area and removing the next maximum rectangular area from the available regions, until a stopping condition is met. A list of determined locations for rectangular areas within the composite projection area is provided after the stopping condition has been met.

Identifying multiple rectangular areas in a multi projector system

A centralization point in a projection area is designated. The projection area is on a projection surface onto which images are projected by a projector array, which includes a plurality of projectors. A first image is projected in a first maximum area rectangle at a first aspect ratio of the first image, and the first image is projected into the projection area centered at the centralization point. A second image is projected in a second maximum area rectangle at a second aspect ratio of the second image, and the second image is projected into the projection area centered at the centralization point.

Projector array for multiple images

A projector array includes a plurality of projectors, which together project images into a projection area on a projection surface. Aspect ratios are normalized for all of multiple images designated for display. The normalized aspect ratios are aligned at a common central point. An aspect ratio of a minimum rectangular shape is determined that will encompass all of the aligned aspect ratios. A maximum rectangular projection area is determined within the projection area having the same aspect ratio as the minimum rectangular shape. The center of the maximum rectangular area is designated as a centralization point. Each of all of the multiple images is sequentially projected into the projection area. Each image is scaled for display at its aspect ratio and is displayed centered at the centralization point.

Determining a rectangular area with a given aspect ratio within a global boundary formed by multiple projectors. An iterated process is repeated at moved locations along the global boundary, until a stopping condition is met. According to the iterated process, a point at a location of the global boundary is selected, a minimum rectangle with the given aspect ratio is grown from identified directions, and the largest rectangle encountered is delivered when the stopping condition has been met. For each such direction, the minimum rectangle is grown in the direction from the selected point until it intersects with a boundary, the grown rectangle is grown in another direction responsive to a determination that the grown rectangle can grow in another direction. The largest rectangle encountered previously is replaced, responsive to a comparison which indicates that the grown rectangle is larger than the largest rectangle encountered previously.

Identifying a rectangular area in a multi-projector system

Control of a multiprojector system having multiple projectors arranged in a projector array. It is determined whether the projector array is positioned to form one object or two or more objects. A first keystone correction mode is selected if it is determined that the projector array is positioned to form one object. A second keystone correction mode is selected if it is determined that the projector array is positioned to form two or more objects. In the first keystone correction mode, a homography transformation for each of the projectors is derived so as to accommodate keystone correction of all projectors in the projector array involved in the projection of the single object. In the second keystone correction mode, a homography transformation for each of the projectors is derived so as to accommodate keystone correction of all projectors involved in the projection of each object.

Automatic mode switching between single and multiple projectors

Keystone correction for a projector. An uncorrected graphic is displayed on a display unit utilizing pixels. The uncorrected graphic is projected from the display unit onto a projection screen to form an uncorrected image. An orientation of the uncorrected image relative to the projection screen is captured. The uncorrected graphic is transformed into a pre-distorted graphic for projection from the display unit onto the projection screen so as to form a corrected image with an orientation more aligned with the projection screen than the orientation of the uncorrected image and such that the pre-distorted graphic utilizes more pixels in the display unit than a second pre-distorted graphic, wherein if formed, would be formed by transforming the uncorrected graphic such that the second pre-distorted graphic forms a second corrected image with a maximum rectangular area inside the uncorrected image when projected from the display unit onto the projection screen.

Growing community of inventors

Kawasaki, Japan

Yasuhiro Komori