Patents by Inventor Akira Kudo
Akira Kudo 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).
-
Publication number: 20240005498Abstract: By using a learning model having a structure of a generative adversarial network including a first generator configured using a first convolutional neural network that receives an input of a medical image of a first domain and that outputs a first generated image of a second domain, and a first discriminator configured using a second convolutional neural network that receives an input of data including first image data, which is the first generated image or a medical image of the second domain included in a training dataset and coordinate information of a human body coordinate system corresponding to each position of a plurality of unit elements configuring the first image data, and that discriminates authenticity of the input image, a computer acquires a plurality of pieces of training data including the medical image of the first domain and the medical image of the second domain; and performs training processing.Type: ApplicationFiled: July 24, 2023Publication date: January 4, 2024Applicant: FUJIFILM CorporationInventor: Akira KUDO
-
Publication number: 20230368442Abstract: A method of generating a trained model uses a first generator configured using a three-dimensional convolutional neural network that receives an input of a three-dimensional image of a first domain and that outputs a three-dimensional generated image of a second domain different from the first domain, and a first discriminator configured using a two-dimensional convolutional neural network that receives an input of a two-dimensional image indicating a cross section image in a first slice plane direction cut out from the three-dimensional generated image of the second domain and that discriminates authenticity of the input two-dimensional image. The method includes performing, by a computer, training the first generator and the first discriminator in an adversarial manner based on training data including a three-dimensional image captured under a first imaging condition and a three-dimensional image captured under a second imaging condition different from the first imaging condition.Type: ApplicationFiled: July 24, 2023Publication date: November 16, 2023Applicant: FUJIFILM CorporationInventor: Akira KUDO
-
Publication number: 20230328224Abstract: A vehicular device of an embodiment includes a control unit that executes processing related to displaying on a meter display, an video processing unit that generates a video to be displayed, a video output unit that outputs the generated video, a ROM that stores a telltale image that is a basis of the video to be generated and a CRC master as an error detection code that has been calculated from the telltale image, a CRC calculation unit that calculates the error detection code, and a video error detection unit that detects an error in the video output to the meter display by comparing an HW-CRC, which is an error detection code calculated from the video output from the video output unit, with the CRC master stored in the ROM.Type: ApplicationFiled: June 16, 2023Publication date: October 12, 2023Inventors: Akira KUDO, Takahiro TSUDUKI
-
Publication number: 20230306605Abstract: A processor is configured to acquire an original image and a mask image in which masks are applied to one or more regions respectively representing one or more objects including a target object in the original image, derive a pseudo mask image by processing the mask in the mask image, and derive a pseudo image that has a region based on a mask included in the pseudo mask image and has the same representation format as the original image, based on the original image and the pseudo mask image.Type: ApplicationFiled: February 17, 2023Publication date: September 28, 2023Applicant: FUJIFILM CorporationInventors: Saeko SASUGA, Yoshiro Kitamura, Akira Kudo
-
Publication number: 20230214664Abstract: A processor inputs a first training image having a first feature to a generator, which is a generative model and generates a training virtual image having a second feature. The processor derives a plurality of types of conversion training images with different observation conditions by performing a plurality of types of observation condition conversion processing on a second training image. The processor derives a plurality of types of conversion training virtual images with the different observation conditions by performing the plurality of types of observation condition conversion processing on the training virtual image. The processor trains the generative model using evaluation results regarding the plurality of types of conversion training images and the plurality of types of conversion training virtual images.Type: ApplicationFiled: March 15, 2023Publication date: July 6, 2023Applicant: FUJIFILM CorporationInventor: Akira KUDO
-
Publication number: 20220198734Abstract: An image generation device derives, for a subject including a specific structure, a subject model representing the subject by deriving each feature amount of the target image having the at least one representation format and combining the feature amounts based on the target image. A latent variable derivation unit derives a latent variable obtained by dimensionally compressing a feature of the subject model according to the target information based on the target information and the subject model. A virtual image derivation unit outputs a virtual image having the representation format represented by the target information based on the target information, the subject model, and the latent variable.Type: ApplicationFiled: March 11, 2022Publication date: June 23, 2022Applicant: FUJIFILM CorporationInventors: Akira KUDO, Yoshiro KITAMURA
-
Publication number: 20220139062Abstract: An extraction model is constituted of an encoder that extracts a feature amount of a first image of a first representation format to derive a feature map of the first image, a first decoder that derives a second virtual image of a second representation format different from the representation format of the first image on the basis of the feature map, a first discriminator that discriminates a representation format of an input image and whether the input image is a real image or a virtual image, and outputs a first discrimination result, a second decoder that extracts a region of interest of the first image on the basis of the feature map, and a second discriminator that discriminates whether an extraction result of the region of interest by the second decoder is an extraction result of a first image with ground-truth mask or an extraction result of a first image without ground-truth mask, and outputs a second discrimination result.Type: ApplicationFiled: January 19, 2022Publication date: May 5, 2022Applicant: FUJIFILM CorporationInventors: Akira KUDO, Yoshiro KITAMURA
-
Publication number: 20210374483Abstract: Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.Type: ApplicationFiled: August 12, 2021Publication date: December 2, 2021Applicant: FUJIFILM CorporationInventors: Akira KUDO, Yoshiro KITAMURA
-
Publication number: 20210374911Abstract: Provided are a learning method and a learning system of a generative model, a program, a learned model, and a super resolution image generating device that can handle input data of any size and can suppress the amount of calculation at the time of image generation. A learning method according to an embodiment of the present disclosure is a learning method for performing machine learning of a generative model that estimates, from a first image, a second image including higher resolution image information than the first image, the method comprising using a generative adversarial network including a generator which is the generative model and a discriminator which is an identification model that identifies whether provided data is data of a correct image for learning or data derived from an output from the generator and implementing a self-attention mechanism only in a network of the discriminator among the generator and the discriminator.Type: ApplicationFiled: August 12, 2021Publication date: December 2, 2021Applicant: FUJIFILM CorporationInventors: Akira KUDO, Yoshiro KITAMURA
-
Patent number: 10833318Abstract: In an aspect, an electrode for an electrochemical cell comprises: a structure having a nano- or micro-architected three-dimensional geometry; said structure comprising one or more active carbon allotrope materials; wherein said structure is characterized by an average density less than or equal to 2.3 g cm?3 and an average specific strength (strength-to-density ratio) greater than or equal to 0.004 GPa g?1 cm3. Also disclosed herein are methods for making an electrode for an electrochemical cell, and methods for making an electrochemical cell.Type: GrantFiled: October 3, 2018Date of Patent: November 10, 2020Assignee: California Institute of TechnologyInventors: Julia R. Greer, Andrey Vyatskikh, John S. Thorne, Akira Kudo, Kai Narita, Michael A. Citrin, Xuan Zhang
-
Publication number: 20190103600Abstract: In an aspect, an electrode for an electrochemical cell comprises: a structure having a nano- or micro-architected three-dimensional geometry; said structure comprising one or more active carbon allotrope materials; wherein said structure is characterized by an average density less than or equal to 2.3 g cm?3 and an average specific strength (strength-to-density ratio) greater than or equal to 0.004 GPa g?1 cm3. Also disclosed herein are methods for making an electrode for an electrochemical cell, and methods for making an electrochemical cell.Type: ApplicationFiled: October 3, 2018Publication date: April 4, 2019Inventors: Julia R. GREER, Andrey VYATSKIKH, John S. THORNE, Akira KUDO, Kai NARITA, Michael A. CITRIN, Xuan ZHANG
-
Patent number: 9784964Abstract: An image pickup unit for endoscope is configured such that a first lens frame and a second lens frame are fitted to each other with a first fitting area and bonded and fixed to each other with a first adhesive at a first frame fixing portion, the second lens frame and a holding frame are fitted to each other with a second fitting area and bonded and fixed to each other with a second adhesive at a second frame fixing portion, the first lens frame, the second lens frame, and the fixing frame are bonded and fixed together with the second adhesive, the second fitting area is larger than the first fitting area, and the second adhesive has a glass transition temperature lower than a glass transition temperature of the first adhesive.Type: GrantFiled: December 1, 2016Date of Patent: October 10, 2017Assignee: OLYMPUS CORPORATIONInventor: Akira Kudo
-
Publication number: 20170082848Abstract: An image pickup unit for endoscope is configured such that a first lens frame and a second lens frame are fitted to each other with a first fitting area and bonded and fixed to each other with a first adhesive at a first frame fixing portion, the second lens frame and a holding frame are fitted to each other with a second fitting area and bonded and fixed to each other with a second adhesive at a second frame fixing portion, the first lens frame, the second lens frame, and the fixing frame are bonded and fixed together with the second adhesive, the second fitting area is larger than the first fitting area, and the second adhesive has a glass transition temperature lower than a glass transition temperature of the first adhesive.Type: ApplicationFiled: December 1, 2016Publication date: March 23, 2017Applicant: OLYMPUS CORPORATIONInventor: Akira KUDO
-
Patent number: 8801255Abstract: An endoscope includes: a distal end rigid portion that configures a distal end portion of an insertion portion of an endoscope and has a through hole; an LED ceramic substrate including an LED light source mounted on a distal end side thereof, and arranged in the through hole so as to emit light from the through hole; an LED cable configured to be inserted in the insertion portion of the endoscope and to supply electric power to the LED light source; a ceramic cutout portion that configures a proximal end side of the LED ceramic substrate, and allows a conductive pattern for electrically connecting the LED light source and the LED cable to be exposed from inside the LED ceramic substrate and connected to the LED cable; and a reinforcement member having rigidity and fixed to the LED ceramic substrate and configured to cover the ceramic cutout portion.Type: GrantFiled: April 12, 2013Date of Patent: August 12, 2014Assignee: Olympus Medical Systems Corp.Inventor: Akira Kudo
-
Patent number: 8596032Abstract: In an embodiment, a core-sheath type conjugated yarn includes a core portion containing a double-prepolymer type polyurethane and a sheath portion containing an elastomer. The double-prepolymer comprises a prepolymer having terminal isocyanate groups obtained from reacting a polyol and a diisocyanate, and a prepolymer having terminal hydroxyl groups obtained from reacting a polyol, a diisocyanate, and a low-molecular weight diol. In other embodiments, a method of producing the core-sheath type conjugated yarn using conjugate spinning conditions provides a conjugated yarn with a fineness of 18 to 110 dtex, a weight ratio of the core portion to the sheath portion of 95/5 to 60/40, and a drawing ratio of 1.5 to 4.0.Type: GrantFiled: June 15, 2010Date of Patent: December 3, 2013Assignee: Nisshinbo Textile, Inc.Inventors: Shigeaki Seno, Akira Kudo
-
Publication number: 20130265798Abstract: An endoscope includes: a distal end rigid portion that configures a distal end portion of an insertion portion of an endoscope and has a through hole; an LED ceramic substrate including an LED light source mounted on a distal end side thereof, and arranged in the through hole so as to emit light from the through hole; an LED cable configured to be inserted in the insertion portion of the endoscope and to supply electric power to the LED light source; a ceramic cutout portion that configures a proximal end side of the LED ceramic substrate, and allows a conductive pattern for electrically connecting the LED light source and the LED cable to be exposed from inside the LED ceramic substrate and connected to the LED cable; and a reinforcement member having rigidity and fixed to the LED ceramic substrate and configured to cover the ceramic cutout portion.Type: ApplicationFiled: April 12, 2013Publication date: October 10, 2013Inventor: Akira KUDO
-
Patent number: 8333694Abstract: An illumination unit includes a distal end frame member having a through opening, a plurality of illumination sections, and a holding member which is arranged in the through opening and holds the illumination sections to incline the illumination sections at a desired angle with respect an opening surface of the through opening and to form a cascade along the axial direction of the through opening. The illumination unit includes a reflective member which is configured to reflect the illumination light emitted from the illumination sections toward the opening surface, the reflective member being held by the holding member to face the illumination sections and to apply the illumination light externally emitted from the illumination sections from the inside of the through opening via the opening surface.Type: GrantFiled: April 11, 2011Date of Patent: December 18, 2012Assignee: Olympus Medical Systems Corp.Inventors: Akira Kudo, Takeshi Oue
-
Publication number: 20120209072Abstract: An endoscope includes: a distal end rigid member to which an observation optical portion is fixedly provided; a distal end cover fixed to the distal end rigid member in an integrated manner, and including an illuminating window portion and a light-emitting device installing hole; a light-emitting device arranged in the light-emitting device installing hole and including a light-emitting portion that faces the illuminating window portion included in the distal end cover, and a conductive portion opposed to the opening of the light-emitting device installing hole; a substrate having thermal conductance and combining as a heat dissipating portion, and connected to the conductive portion of the light-emitting device, a power supply cable being connected thereto; and a heat dissipation member having thermal conductance, an end side of which being connected to the substrate and another end side projecting relative to the substrate to dissipate heat conducted to the substrate.Type: ApplicationFiled: April 25, 2012Publication date: August 16, 2012Applicant: OLYMPUS MEDICAL SYSTEMS CORP.Inventors: Takeshi OUE, Akira KUDO, Yosuke SATO
-
Publication number: 20120152018Abstract: An atmospheric pressure estimation method is disclosed. The method includes: controlling an oscillation frequency of a predetermined oscillator to match an oscillation frequency of an atmospheric pressure measurement oscillator; detecting a phase difference between an oscillation signal of the predetermined oscillator and an oscillation signal of the atmospheric pressure measurement oscillator; and estimating atmospheric pressure using the oscillation frequency of the predetermined oscillator and the phase difference.Type: ApplicationFiled: December 16, 2011Publication date: June 21, 2012Applicant: SEIKO EPSON CORPORATIONInventors: Akira Kudo, Chen Qian
-
Publication number: 20120036899Abstract: Provided is a novel conjugated yarn which: has excellent stretchability; is provided with a sufficient strength; shows high transparency; provides a good tactile sense; and has moderate fit power. Also provided are a knitted fabric knitted by using such conjugated yarn and a clothing product using such knitted fabric. Also provided is a method of producing a novel conjugated yarn which: has excellent stretchability; is provided with a sufficient strength; shows high transparency; provides a good tactile sense; and has moderate fit power.Type: ApplicationFiled: June 15, 2010Publication date: February 16, 2012Inventors: Shigeaki Seno, Akira Kudo