公开(公告)号：US20150269437A1

公开(公告)日：2015-09-24

申请号：US14661360

申请日：2015-03-18

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Masayuki MARUYAMA ,  Osamu YAMAGUCHI ,  Mayumi YUASA ,  Tatsuo KOZAKAYA ,  Tomokazu KAWAHARA ,  Quoc Viet PHAM

IPC: G06K9/00 ,  G06K9/46

CPC classification number: G06K9/00624 ,  G06K9/2063 ,  G06K2009/3225

Abstract: An image processing method includes: retaining marker information including markers, each of the markers having a type which is shape, pattern or color; acquiring images in which at least one of the markers is caught; referring the marker information to detect the type and a position of the marker caught in the image; and dividing the image into a plurality of divided areas on the basis of the positions of one or more markers in the image, the plurality of divided areas having no common area and each including at least one type of the marker.

Abstract translation: 图像处理方法包括：保留包括标记的标记信息，每个标记具有形状，图案或颜色的类型; 获取其中至少一个标记被捕获的图像; 参考标记信息以检测捕获在图像中的标记的类型和位置; 并且基于图像中的一个或多个标记的位置将图像划分成多个分割区域，所述多个分割区域不具有公共区域，并且每个划分区域包括至少一种类型的标记。

公开(公告)号：US20210125067A1

公开(公告)日：2021-04-29

申请号：US17082738

申请日：2020-10-28

Applicant: Kabushiki Kaisha Toshiba ,  Toshiba Digital Solutions Corporation

Inventor： Yukio KAMATANI ,  Hidemasa ITOU ,  Katsuyuki HANAI ,  Mayumi YUASA ,  Meiteki SO

IPC: G06N3/08 ,  G06K9/62 ,  G06F17/18

Abstract: An information processing device includes a definer, a determiner, and a reinforcement learner. The definer is configured to associate a node and an edge with attributes and to define a convolution function associated with a model representing data of a graph structure representing a system structure on the basis of data regarding the graph structure. The evaluator is configured to input a state of the system into the model. The evaluator is configured to obtain, for each time step, a policy function as a probability distribution of a structural change and a state value function for reinforcement learning for a system of one or more structurally changed models which have been changed with assumable structural changes from the model for each time step. The evaluator is configured to evaluate the structural changes in the system on the basis of the policy function. The reinforcement learner is configured to perform reinforcement learning by using a reward value as a cost generated when the structural change is applied to the system, the state value function, and the model, to optimize the structural change in the system.

公开(公告)号：US20160117839A1

公开(公告)日：2016-04-28

申请号：US14977280

申请日：2015-12-21

Applicant: Kabushiki Kaisha Toshiba

Inventor： Tomokazu KAWAHARA ,  Tatsuo KOZAKAYA ,  Osamu YAMAGUCHI ,  Mayumi YUASA ,  Tomoki WATANABE ,  Mayu OKUMURA ,  Viet quob PHAM

IPC: G06T7/20 ,  G06K9/00 ,  G06T7/00

CPC classification number: G06K9/00335 ,  G06K9/00348 ,  G06T7/231 ,  G06T7/248 ,  G06T7/337 ,  G06T7/38 ,  G06T2207/30196 ,  G06T2207/30241 ,  H04N7/18

Abstract: According to an embodiment, an image output device includes an extractor, a search unit, an associate unit, and a controller. The extractor is configured to extract a first parameter that varies in accordance with a movement of an object from at least one first image of the object, and extract a second parameter that varies in accordance with a movement of the object from each second image of the object. The search unit is configured to search for a second parameter similar to the first parameter. The associate unit is configured to associate the first image from which the first parameter is extracted with the second image from which the second parameter that is retrieved with respect to the first parameter is extracted. The controller is configured to instruct an output unit to output an image based on the first and second images that are associated to each other.

Abstract translation: 根据实施例，图像输出装置包括提取器，搜索单元，关联单元和控制器。 提取器被配置为提取根据对象从对象的至少一个第一图像的移动而变化的第一参数，并且提取根据对象从每个对象的每个第二图像的移动而变化的第二参数 目的。 搜索单元被配置为搜索类似于第一参数的第二参数。 关联单元被配置为将从其提取第一参数的第一图像与从其提取关于第一参数检索的第二参数的第二图像相关联。 控制器被配置为指示输出单元基于彼此相关联的第一和第二图像来输出图像。

公开(公告)号：US20170116745A1

公开(公告)日：2017-04-27

申请号：US15261573

申请日：2016-09-09

Applicant: Kabushiki Kaisha Toshiba

Inventor： Mayumi YUASA ,  Ryuzo OKADA

IPC: G06T7/00 ,  G06T7/60 ,  G06T5/00 ,  G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00255 ,  G06K9/00899 ,  G06K9/6201 ,  G06K9/6289 ,  G06T5/001 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/20076 ,  G06T2207/30201

Abstract: A detector in embodiments includes a processor. The processor acquires an image including a face of a person. The processor acquirer depth information of the face in the image from a distance measuring module. The processor sets a deficient area indicating an area where the depth information fails to be acquired. The processor detects the face area from the image. The processor acquires a reference image generated based on a probability set to the deficient area in the image, and calculates a degree of similarity between the face area where the deficient area is set and the reference image. The processor determines whether the image is impersonation based on the degree of similarity.

公开(公告)号：US20160088261A1

公开(公告)日：2016-03-24

申请号：US14858116

申请日：2015-09-18

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Tatsuo KOZAKAYA ,  Mayumi YUASA ,  Osamu YAMAGUCHI ,  Masayuki MARUYAMA ,  Tomokazu KAWAHARA ,  Quoc Viet PHAM

IPC: H04N7/18 ,  G06K9/00 ,  G06K9/62

CPC classification number: H04N7/181 ,  G06K9/00255 ,  G06K9/22 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30196 ,  G06T2207/30201 ,  G06T2207/30232 ,  H04N5/23219 ,  H04N5/247

Abstract: According to one embodiment, a system includes a portable device, a plurality of second image capturing units, an extraction unit, a calculation unit, and a specifying unit. The portable device includes a first image capturing unit that captures a first image of a person, and a sending unit that sends the first image. The plurality of second image capturing units captures second images. The extraction unit extracts a first feature of the first image and a second feature of each of the second images. The calculation unit calculates a similarity based on the first feature and the second feature of the each of the second images. If the similarity for a second image is larger than a predetermined threshold, the specifying unit specifies a second image capturing unit that has captured the second image, among the plurality of second image capturing units.

Abstract translation: 根据一个实施例，系统包括便携式设备，多个第二图像捕获单元，提取单元，计算单元和指定单元。 便携式装置包括拍摄人物的第一图像的第一图像拍摄单元和发送第一图像的发送单元。 多个第二图像捕获单元捕获第二图像。 提取单元提取第一图像的第一特征和每个第二图像的第二特征。 计算单元基于第一图像和第二图像的第二特征来计算相似度。 如果第二图像的相似度大于预定阈值，则指定单元指定在多个第二图像拍摄单元中捕获了第二图像的第二图像拍摄单元。