-
公开(公告)号：US20190251471A1
公开(公告)日：2019-08-15
申请号：US16308328
申请日：2016-11-01
Applicant: HITACHI, LTD.
Inventor： Kenichi MORITA , Yuki WATANABE , Atsushi HIROIKE , Yoshitaka MURATA , Tsutomu IMADA
IPC: G06N20/00 , G06F16/55 , G06F16/583
CPC classification number: G06N20/00 , G06F16/55 , G06F16/583 , G06T7/00
Abstract: An object is to provide a machine learning device that can reliably and promptly improve image classification accuracy. A machine learning device of the present invention includes: an image database that stores a plurality of images and image features of these images; and a processor that is connected to this image database and that performs machine learning using the plurality of images and the image features stored in the image database, and the processor preferentially selects a predetermined number of images that are images other than images used in past machine learning and that have the low similarities to the images used in the past machine learning, as images used for machine learning from among the images stored in the image database, and performs new machine learning using the selected images.
-
公开(公告)号：US20190147292A1
公开(公告)日：2019-05-16
申请号：US16171710
申请日：2018-10-26
Applicant: Hitachi, Ltd.
Inventor： Yuki WATANABE , Kenichi MORITA , Tomokazu MURAKAMI , Atsushi HIROIKE , Quan KONG
Abstract: An image retrieving apparatus includes a pose estimating unit which recognizes pose information of a retrieval target including a plurality of feature points from an input image, a features extracting unit which extracts features from the pose information and the input image, an image database which accumulates the features in association with the input image, a query generating unit which generates a retrieval query from pose information specified by a user, and an image retrieving unit which retrieves images including similar poses according to the retrieval query from the image database.
-
3.发明申请公开(公告)号：US20200380168A1
公开(公告)日：2020-12-03
申请号：US16879224
申请日：2020-05-20
Applicant: Hitachi, Ltd.
Inventor： Martin KLINKIGT , Mohit CHHABRA , Atsushi HIROIKE , Tomokazu MURAKAMI
Abstract: In a case of receiving an access request to a target image, an image access management device can provide an appropriate access right holder with an appropriate range of information by determining a browsing level with respect to the target image according to an access authority or purpose included in the access request to the target image, by an access management unit, by generating a final image that corresponds to the access authority by processing the feature vector according to the browsing level, and providing the generated final image as a response to the access request, by an image generation unit.
-
公开(公告)号：US20180060356A1
公开(公告)日：2018-03-01
申请号：US15556994
申请日：2015-03-13
Applicant: Hitachi, Ltd.
Inventor： Yuki WATANABE , Atsushi HIROIKE , Kenichi YONEJI , Nobuo NUKAGA , Naoto AKIRA , Tomoaki YOSHINAGA
IPC: G06F17/30
CPC classification number: G06F16/5838 , G06F16/24578
Abstract: An image search device searching an image from an image database storing a recorded image, one or more types of feature values, and propagation information that indicates a link between a same type of the feature values of the recorded image, the device acquires a first image and the one or more types of feature values of the first image, records the first image and the feature values in the image database, calculates a propagation intensity indicating similarity or sameness between the types of feature values of the recorded image and the types of feature values of the first image, and includes in the propagation information a link between the types of feature values of the first image and the types of feature values of the recorded image for which the propagation intensity between the types of feature values of the recorded image and the types of feature values of the first image is at a maximum value.
-
5.发明申请公开(公告)号：US20160343147A1
公开(公告)日：2016-11-24
申请号：US15114585
申请日：2015-01-14
Applicant: HITACHI, LTD.
Inventor： Nobuo NUKAGA , Daisuke MATSUBARA , Yuki WATANABE , Kenichi YONEJI , Tomoaki YOSHINAGA , Atsushi HIROIKE
CPC classification number: G06T7/2033 , G06F17/30 , G06F17/30784 , G06F17/30823 , G06K9/4671 , G06K9/6201 , G06T1/0007 , G06T7/246
Abstract: An image search system comprising an video taking unit that takes a video, a search unit that contains a processor and a storage unit and searches for an image contained in the video, an input unit that receives information that is input to the search unit, and a display unit that displays information that is output from the search unit. The storage unit holds information indicating the shapes of trajectories that represent the travel paths of a plurality of moving objects extracted from the video. When information indicating the shape of a trajectory is input from the input unit, the search unit searches the plurality of moving-object trajectories held in the storage unit for trajectories that are similar to the input trajectory shape, and if such a trajectory is found, the search unit displays, on the display unit, images of the moving objects that have traveled along the found trajectories.
Abstract translation: 一种图像搜索系统，包括：视频采集单元，包含处理器的搜索单元和存储单元，并且搜索包含在视频中的图像;输入单元，其接收输入到搜索单元的信息;以及 显示单元，显示从搜索单元输出的信息。 存储单元保存指示表示从视频中提取的多个移动对象的行进路径的轨迹的形状的信息。 当从输入单元输入指示轨迹的形状的信息时，搜索单元搜索保存在存储单元中的多个运动对象轨迹中的与输入轨迹形状类似的轨迹，并且如果找到这样的轨迹， 搜索单元在显示单元上显示沿着找到的轨迹行进的移动物体的图像。
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20160005171A1
公开(公告)日：2016-01-07
申请号：US14769976
申请日：2013-02-27
Applicant: HITACHI, LTD.
Inventor： Yuki WATANABE , Atsushi HIROIKE
CPC classification number: G06K9/00281 , G06K9/00268 , G06K9/00677 , G06T7/248 , G06T2207/10016 , G06T2207/20224
Abstract: An image analysis device according to the present invention includes a storage unit storing an image and information of a detected object included in the image, an input unit receiving a target image serving as a target in which an object is detected, a similar image search unit searching for a similar image having a feature quantity similar to a feature quantity extracted from the target image and the information of the object included in the similar image from the storage unit, a parameter deciding unit deciding a parameter used in a detection process performed on the target image based on the information of the object included in the similar image, a detecting unit detecting an object from the target image according to the decided parameter, a registering unit accumulating the target image in the storage unit, and a data output unit outputting the information of the detected object.
Abstract translation: 根据本发明的图像分析装置包括存储图像的存储单元和包括在图像中的检测对象的信息，接收用作检测对象的目标的目标图像的输入单元，类似图像搜索单元 从存储单元中搜索具有与从目标图像提取的特征量相似的特征量的特征量和包含在类似图像中的对象的信息的类似图像，参数确定单元，确定在对该图像执行的检测处理中使用的参数 基于所述相似图像中包含的对象的信息的目标图像，检测单元根据所确定的参数从所述目标图像检测对象;存储单元，将所述目标图像累积在所述存储单元中;以及数据输出单元， 检测到的物体的信息。
-
7.发明公开公开(公告)号：US20240212228A1
公开(公告)日：2024-06-27
申请号：US18503440
申请日：2023-11-07
Applicant: Hitachi, Ltd.
Inventor： Yuki WATANABE , Ryosuke MIKI , Atsushi HIROIKE , Soichiro OKAZAKI , Koichiro ITO , Hiroto NAGAYOSHI
IPC: G06T11/00 , G06F16/532 , G06F16/583 , G06V10/44
CPC classification number: G06T11/00 , G06F16/532 , G06F16/583 , G06V10/44 , G06V2201/07
Abstract: Provided is an image generating and retrieving apparatus that enables a user to easily find a desired image from a large number of image generation results. A similarity is calculated from a text feature amount and an image feature amount, a similar image similar to a retrieval target is retrieved from an image text database using the similarity, and an image generation process held in the image text database is visualized.
-
公开(公告)号：US20230005268A1
公开(公告)日：2023-01-05
申请号：US17784472
申请日：2020-10-10
Applicant: Hitachi, Ltd.
Inventor： Masato TAMURA , Tomoaki YOSHINAGA , Atsushi HIROIKE , Hiromu NAKAMAE , Yuta YANASHIMA
Abstract: An object of the invention is to configure an object search device capable of expressing information on shapes and irregularities as features only by images, in a search for an object that is characteristic in shape or irregularity, and performing an accurate search.
The object search device includes: an image feature extraction unit that is configured with a first neural network, and is configured to input an image to extract an image feature; a three-dimensional data feature extraction unit that is configured with a second neural network, and is configured to input three-dimensional data to extract a three-dimensional data feature; a learning unit that is configured to extract an image feature and a three-dimensional data feature from an image and three-dimensional data of an object obtained from a same individual, respectively, and update an image feature extraction parameter so as to reduce a difference between the image feature and the three-dimensional data feature; and a search unit that is configured to extract image features of a query image and a gallery image of the object by the image feature extraction unit using the updated image feature extraction parameter, and calculate a similarity between the image features of both images to search for the object.-
公开(公告)号：US20200327380A1
公开(公告)日：2020-10-15
申请号：US16838256
申请日：2020-04-02
Applicant: HITACHI, LTD.
Inventor： Shun FUKUDA , Martin KLINKIGT , Atsushi HIROIKE , Toshiaki TARUI
Abstract: A connection relationship between an object feature extraction unit and a plurality of task-specific identification units is changed based on connection information stored in a connection switch according to a type of a task.
-
10.发明申请公开(公告)号：US20180373737A1
公开(公告)日：2018-12-27
申请号：US16062308
申请日：2015-12-17
Applicant: HITACHI, LTD.
Inventor： Yuki WATANABE , Kenichi MORITA , Atsushi HIROIKE
Abstract: An image processing device includes a processor, a storage unit coupled to the processor and storing an image database, and a display unit coupled to the processor. The processor obtains arrangement information of a first object on the display unit when the processor accepts an input of the first object via the display unit. The processor obtains first co-occurrence information using the first object and the arrangement information of the first object. The first co-occurrence information indicates a correlation relationship with the first object based on the image database. The processor outputs a candidate for a second object based on the first co-occurrence information to the display unit.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.013 seconds)
