Patents by Inventor Masaharu Sakamoto

Masaharu Sakamoto has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11120305
    Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.
    Type: Grant
    Filed: July 10, 2019
    Date of Patent: September 14, 2021
    Assignee: International Business Machines Corporation
    Inventors: Takuya Goto, Hiroki Nakano, Masaharu Sakamoto
  • Patent number: 11074479
    Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.
    Type: Grant
    Filed: March 28, 2019
    Date of Patent: July 27, 2021
    Assignee: International Business Machines Corporation
    Inventors: Takuya Goto, Hiroki Nakano, Masaharu Sakamoto
  • Publication number: 20210216895
    Abstract: A determination is made of an explanatory variable with respect to an objective variable. A subset of data from data to be analyzed is created, in response to setting the objective variable to be analyzed to perform analysis. Association analysis is applied to analysis results, in response to a number of analysis runs exceeding a predetermined number. An association rule is derived for the explanatory variable from a result of the association analysis. An explanatory variable having a relevance value greater than a threshold value with the objective variable in the data to be analyzed is selected. The selected explanatory variable is scored as an input using the association rule to determine whether the explanatory variable is to be added or removed.
    Type: Application
    Filed: January 14, 2020
    Publication date: July 15, 2021
    Inventors: Hiromi KOBAYASHI, Masaharu SAKAMOTO, Yasue MAKINO, Hirokazu KOBAYASHI
  • Publication number: 20210142119
    Abstract: Image classification using a generated mask image is performed by generating a mask image that extracts a target area from an input image, extracting an image feature map of the input image by inputting the input image in a first neural network including at least one image feature extracting layer, masking the image feature map by using the mask image, and classifying the input image by inputting the masked image feature map to a second neural network including at least one classification layer.
    Type: Application
    Filed: January 14, 2021
    Publication date: May 13, 2021
    Inventors: Hiroki Nakano, Takuya Goto, Masaharu Sakamoto
  • Patent number: 10936912
    Abstract: Image classification using a generated mask image is performed by generating a mask image that extracts a target area from an input image, extracting an image feature map of the input image by inputting the input image in a first neural network including at least one image feature extracting layer, masking the image feature map by using the mask image, and classifying the input image by inputting the masked image feature map to a second neural network including at least one classification layer.
    Type: Grant
    Filed: November 1, 2018
    Date of Patent: March 2, 2021
    Assignee: International Business Machines Corporation
    Inventors: Hiroki Nakano, Takuya Goto, Masaharu Sakamoto
  • Patent number: 10915810
    Abstract: A cascading convolutional neural network (CCNN) comprising a plurality of convolutional neural networks (CNNs) that are trained by weighting training data based on loss values of each training datum between CNNs of the CCN. The CCNN can receiving an input image from plurality of images, classify the input image using the CCNN, and present a classification of the input image.
    Type: Grant
    Filed: November 12, 2019
    Date of Patent: February 9, 2021
    Assignee: International Business Machines Corporation
    Inventors: Taro Sekiyama, Masaharu Sakamoto, Hiroki Nakano, Kun Zhao
  • Patent number: 10834060
    Abstract: A method, a computing system and a computer program product are provided. A link for use by a user to access a file is created. Content of the file is encrypted using a common key. The common key is encrypted using a public key of the user and is registered in the link. Access rights regarding the file are set for the user and registered in the link. The link includes information for use by the user to access the file when the access rights indicate that the user is authorized to access the file.
    Type: Grant
    Filed: November 9, 2018
    Date of Patent: November 10, 2020
    Assignee: International Business Machines Corporation
    Inventors: Junichi Kato, Takayuki Kushida, Tomoko Murayama, Masaharu Sakamoto, Kazuto Yamafuji
  • Publication number: 20200311483
    Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.
    Type: Application
    Filed: July 10, 2019
    Publication date: October 1, 2020
    Inventors: Takuya Goto, Hiroki Nakano, Masaharu Sakamoto
  • Publication number: 20200311479
    Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.
    Type: Application
    Filed: March 28, 2019
    Publication date: October 1, 2020
    Inventors: Takuya Goto, Hiroki Nakano, Masaharu Sakamoto
  • Patent number: 10713783
    Abstract: Neural network classification may be performed by inputting a training data set into each of a plurality of first neural networks, the training data set including a plurality of samples, obtaining a plurality of output value sets from the plurality of first neural networks, each output value set including a plurality of output values corresponding to one of the plurality of samples, each output value being output from a corresponding first neural network in response to the inputting of one of the samples of the training data set, inputting the plurality of output value sets into a second neural network, and training the second neural network to output an expected result corresponding to each sample in response to the inputting of a corresponding output value set.
    Type: Grant
    Filed: June 1, 2017
    Date of Patent: July 14, 2020
    Assignee: International Business Machines Corporation
    Inventors: Hiroki Nakano, Masaharu Sakamoto
  • Patent number: 10691845
    Abstract: A method for using data driven shrinkage compensation to fabricate an object using an additive manufacturing process includes predicting one or more dimensional changes in one or more directional strands disposed between facets of one or more respective predetermined facet pairs as a result of the fabrication of an object using an additive manufacturing process based on a shape shrinkage model. The object is modeled from a file and includes one or more dimensions calculated from the one or more directional strands. The method further includes correcting coordinate data of at least one facet of the one or more predetermined facet pairs to compensate for the one or more predicted dimensional changes in the one or more directional strands.
    Type: Grant
    Filed: October 30, 2019
    Date of Patent: June 23, 2020
    Assignee: International Business Machines Corporation
    Inventor: Masaharu Sakamoto
  • Patent number: 10685011
    Abstract: The present invention may be a method, a computer system, and a computer program product. An embodiment of the present invention provides a method for judging data consistency in a database. In one embodiment, the method comprises the following: generating a property of data obtained from a first database; associating the property with an attribute of a data model to generate a data property definition; judging whether data obtained from a second database satisfies the data property definition or not; and outputting a result of the judgment. In another embodiment, the method comprises the following: generating a property of data obtained from a database; associating the property with an attribute of a data model to generate a data property definition; judging whether data which is stored in the database satisfies the data property definition or not; and outputting a result of the judgment.
    Type: Grant
    Filed: February 2, 2017
    Date of Patent: June 16, 2020
    Assignee: International Business Machines Corporation
    Inventors: Junichi Kato, Takayuki Kushida, Tomoko Murayama, Masaharu Sakamoto, Kazuto Yamafuji
  • Patent number: 10671674
    Abstract: The present invention may be a method, a computer system, and a computer program product. An embodiment of the present invention provides a method for finding a problem in procedures described in a guide document for install and configuration of software. The method comprises calculating, using a dynamic programming matching, a distance between an install-and-configuration log generated by executing the install and configuration of the software according to the guide document at a user-side computer and a log template generated by executing the install and configuration of the software according to the guide document at an administrator-side computer, and finding a problem in the procedures, using the distance.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: June 2, 2020
    Assignee: International Business Machines Corporation
    Inventors: Junichi Kato, Takayuki Kushida, Tomoko Murayama, Masaharu Sakamoto, Kazuto Yamafuji
  • Publication number: 20200143204
    Abstract: Image classification using a generated mask image is performed by generating a mask image that extracts a target area from an input image, extracting an image feature map of the input image by inputting the input image in a first neural network including at least one image feature extracting layer, masking the image feature map by using the mask image, and classifying the input image by inputting the masked image feature map to a second neural network including at least one classification layer.
    Type: Application
    Filed: November 1, 2018
    Publication date: May 7, 2020
    Inventors: Hiroki Nakano, Takuya Goto, Masaharu Sakamoto
  • Publication number: 20200110994
    Abstract: Methods and systems are provided for training a neural network with augmented data. A dataset comprising a plurality of classes is obtained for training a neural network. Prior to initiation of training, the dataset may be augmented by performing affine transformations of the data in the dataset, wherein the amount of augmentation is determined by a data augmentation variable. The neural network is trained with the augmented dataset. A training loss and a difference of class accuracy for each class is determined. The data augmentation variable is updated based on the total loss and class accuracy for each class. The dataset is augmented by performing affine transformations of the data in the dataset according to the updated data augmentation variable, and the neural network is trained with the augmented dataset.
    Type: Application
    Filed: October 4, 2018
    Publication date: April 9, 2020
    Inventors: Takuya Goto, Masaharu Sakamoto, Hiroki Nakano
  • Publication number: 20200097800
    Abstract: A cascading convolutional neural network (CCNN) comprising a plurality of convolutional neural networks (CNNs) that are trained by weighting training data based on loss values of each training datum between CNNs of the CCN. The CCNN can receiving an input image from plurality of images, classify the input image using the CCNN, and present a classification of the input image.
    Type: Application
    Filed: November 12, 2019
    Publication date: March 26, 2020
    Inventors: Taro Sekiyama, Masaharu Sakamoto, Hiroki Nakano, Kun Zhao
  • Patent number: 10599977
    Abstract: A method includes: training a first neural network using a first training dataset; inputting each test data of a first test dataset to the first neural network; calculating output data of the first neural network for each test data of the first test dataset; composing a second training dataset of training data from the first test dataset that causes the first neural network to output data within a first range; and training a second neural network using the second training dataset.
    Type: Grant
    Filed: August 23, 2016
    Date of Patent: March 24, 2020
    Assignee: International Business Machines Corporation
    Inventors: Hiroki Nakano, Masaharu Sakamoto
  • Patent number: D886258
    Type: Grant
    Filed: November 5, 2018
    Date of Patent: June 2, 2020
    Assignee: IRIS OHYAMA INC.
    Inventor: Masaharu Sakamoto
  • Patent number: D886269
    Type: Grant
    Filed: October 18, 2018
    Date of Patent: June 2, 2020
    Assignee: IRIS OHYAMA INC.
    Inventor: Masaharu Sakamoto
  • Patent number: D907759
    Type: Grant
    Filed: April 1, 2019
    Date of Patent: January 12, 2021
    Assignee: IRIS OHYAMA INC.
    Inventor: Masaharu Sakamoto