Canon Kabushiki Kaisha

Q.p. Corporation

Masahiro Ariizumi

Tsewei Chen

Noriyasu Hashiguchi

Hiroshi Tojo

Masami Kato

Hideaki Kobayashi

Yasuhiko Shigematsu

Hajime Matsuda

Nobuhisa Sakabe

Mitsuru Takamiya

There is provided with a data processing apparatus that carries out a computation corresponding to a neural network containing a plurality of layers. A processing unit includes a plurality of processors that, through pipeline processing, sequentially calculate data of each of blocks, each block corresponding to a part of a feature plane in one layer. A control unit determines a calculation order for the data of the blocks on the basis of structure information of the neural network, and sends a command that controls the calculation order to the plurality of processors.

Data processing apparatus and control method

An apparatus includes a first holding unit and a second holding unit configured to hold first-type data and second-type data, respectively, a first operation unit configured to execute a first product-sum operation based on the first-type data, a branch unit configured to output an operation result of the first product-sum operation in parallel, a sampling unit configured to sample the operation result and to output a sampling result, and a second operation unit configured to execute a second product-sum operation based on the second-type data and the sampling result.

Apparatus and method using neural network

An image processing apparatus comprising, a first processing unit configured to process a first image stored in a first memory and output a first processing result in a first size, a conversion unit configured to, if the first size matches a second size, output the first processing result, and if the first size is different from the second size, convert the first processing result into the second size and output a result of the conversion, and a second processing unit configured to process the first processing result outputted from the conversion unit and a second image of the second size stored in a second memory, and to store a second processing result in the second memory in the second size.

Image processing apparatus, method of controlling image processing apparatus, and non-transitory computer-readable storage medium

There is provided with an image processing apparatus. An obtaining unit obtains a video with consecutive frame images. A dividing unit divides a frame image of interest into a plurality of divided regions by reference to information of divided regions previously stored in a storage unit. A determining unit determines whether or not a moving object is included in a divided region of interest in the frame image of interest. An updating unit switches whether or not to update information of the divided region of interest stored in the storage unit with information of the divided region of interest of the frame image of interest, according to whether or not a moving object is included in the divided region of interest in the frame image of interest.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

Plural block images are generated by dividing an input image into blocks each of which has a predetermined size. Clustering of pixels contained in the plural block images is performed based on a representative point associated with each of those block images to apply region segmentation to those block images. The representative point is a part of plural representative points disposed in the input image. The clustering in a target block image of the region segmentation is performed by referring to a representative point in the target block image, a representative point of a processed block image, and a representative point of an unprocessed block image. The processed and unprocessed block images are adjacent to the target block image.

Image processing apparatus and image processing method

In the container-packed, oil-in-water type emulsified food product in accordance with the present invention, an oil-in-water type emulsified food comprises edible oils and fats, vinegar and egg yolk, and is packed and sealed in a container with an oxygen barrier property and has a dissolved oxygen concentration immediately after manufacturing is 0.8 to 8.1% O. This container-packed, oil-in-water type emulsified food product demonstrates excellent flavor balance and small degradation of quality caused by oxidation during storage.

Growing community of inventors

Tokyo, Japan

Masahiro Ariizumi