公开(公告)号：US20230186047A1

公开(公告)日：2023-06-15

申请号：US18063897

申请日：2022-12-09

Applicant: SEIKO EPSON CORPORATION

Inventor： Hikaru KURASAWA ,  Yuki URUSHIBATA ,  Ryoki WATANABE ,  Shin NISHIMURA ,  Eiichiro YAMAGUCHI

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: An evaluation method for a trained machine learning model includes the steps of (a) inputting evaluation data to the trained machine learning model to generate first explanatory information used for an evaluation of the machine learning model, (b) using a value indicated by each piece of information included in the first explanatory information to generate second explanatory information indicating an evaluation of the trained machine learning model, and (c) outputting the generated second explanatory information.

公开(公告)号：US20210037198A1

公开(公告)日：2021-02-04

申请号：US16941704

申请日：2020-07-29

Applicant: Seiko Epson Corporation

Inventor： Teruyuki NISHIMURA ,  Ryoki WATANABE ,  Hikaru KURASAWA

IPC: H04N5/33 ,  G01J3/36 ,  G01J3/28

Abstract: An image processing method includes: an image pickup step of picking up an RGB image of a target object to be picked up, and picking up a spectroscopic image of the target object in a predetermined wavelength range and thus acquiring spectroscopic information peculiar to the target object in the wavelength range; and a display step of displaying a complemented image complemented by superimposing the spectroscopic information on the RGB image.

公开(公告)号：US20200240843A1

公开(公告)日：2020-07-30

申请号：US16774020

申请日：2020-01-28

Applicant: Seiko Epson Corporation

Inventor： Masashi KANAI ,  Eiji OSAWA ,  Ryoki WATANABE

IPC: G01J3/28 ,  G01B17/02 ,  G01J3/50 ,  B41J29/38

Abstract: A media type determination device includes: a light detector that detects light from a target object; a sensor that transmits an ultrasonic wave to the target object and performs an ultrasonic measurement for receiving the ultrasonic wave transmitted through the target object; and one or a plurality of processors. The one or plurality of processors are programmed to execute a method including: acquiring light information corresponding to the light from the target object, from the light detector; acquiring ultrasonic wave information corresponding to an ultrasonic wave via the target object from the sensor, and determining a type of target object based on the light information and the ultrasonic wave information.

公开(公告)号：US20220197572A1

公开(公告)日：2022-06-23

申请号：US17645069

申请日：2021-12-20

Applicant: SEIKO EPSON CORPORATION

Inventor： Takahiro KAMADA ,  Satoru ONO ,  Yuko YAMAMOTO ,  Ryoki WATANABE ,  Mitsuhiro YAMASHITA ,  Kenji MATSUZAKA

IPC: G06F3/12 ,  G06K15/10

Abstract: A printing condition setting method is a printing condition setting method of setting printing conditions in a printing apparatus, including a learning step of performing machine learning by using ink physical characteristics and ink type information, a similarity score calculation step of calculating a similarity score indicating a similarity of a use ink used for printing in the printing apparatus with respect to a learned ink learned in the learning step, and a printing condition setting step of setting the printing conditions according to the use ink based on the similarity score.

公开(公告)号：US20220159140A1

公开(公告)日：2022-05-19

申请号：US17523984

申请日：2021-11-11

Applicant: SEIKO EPSON CORPORATION

Inventor： Yuko YAMAMOTO ,  Takahiro KAMADA ,  Mitsuhiro YAMASHITA ,  Shotaro MATSUDA ,  Ryoki WATANABE ,  Kenji MATSUZAKA

IPC: H04N1/23 ,  B41J29/38 ,  G06F3/12 ,  G06N20/00

Abstract: For a plurality of types of print media, a pre-trained model is prepared, the pre-trained model being generated by machine learning based on spectroscopic information of an unprinted area on the print medium and an identifier indicating the type of the print medium and using the identifier as a trainer. The spectroscopic information of the unprinted area on the print medium to print on is acquired. The acquired spectroscopic information is applied to the pre-trained model. Using a result thereof, auxiliary information about the type of the print medium is outputted. A specification of the type of the print medium using the outputted auxiliary information is accepted. When the type of the print medium is thus specified, printing is performed using a print condition suitable for the print medium.

公开(公告)号：US20190271624A1

公开(公告)日：2019-09-05

申请号：US16291051

申请日：2019-03-04

Applicant: Seiko Epson Corporation

Inventor： Ryoki WATANABE ,  Kanechika KIYOSE

IPC: G01N11/00

Abstract: A sonic speed measurement device includes a reception array in which a plurality of reception elements which output reception signals in response to reception of an ultrasonic wave are disposed in one direction, a phase difference detection portion that detects a phase difference between the reception signals output from the reception elements adjacent to each other in a case where the plurality of reception elements receive the ultrasonic wave which propagates in a spherical wave shape from a target point, and a sonic speed calculation portion that calculates a sonic speed of the ultrasonic wave on the basis of the phase difference.

公开(公告)号：US20230169307A1

公开(公告)日：2023-06-01

申请号：US18058862

申请日：2022-11-26

Applicant: SEIKO EPSON CORPORATION

Inventor： Tomomasa USUI ,  Ryoki WATANABE ,  Hikaru KURASAWA ,  Shin NISHIMURA

IPC: G06N3/04 ,  G06V10/774

CPC classification number: G06N3/04 ,  G06V10/774

Abstract: A method according to the present disclosure includes (a) generating N pieces of input data from one target object, (b) inputting the input data to a machine learning model and obtaining M classification output values, one determination class, and a feature spectrum, (c) obtaining a similarity degree between a known feature spectrum group and the feature spectrum for the input data, and obtaining a reliability degree with respect to the determination class as a function of the reliability degree, and (d) executing a vote for the determination class, based on the reliability degree with respect to the determination class, and determining a class determination result of the target object, based on a result of the vote.

公开(公告)号：US20220305804A1

公开(公告)日：2022-09-29

申请号：US17656246

申请日：2022-03-24

Applicant: SEIKO EPSON CORPORATION

Inventor： Mitsuhiro YAMASHITA ,  Takahiro KAMADA ,  Kenji MATSUZAKA ,  Satoru ONO ,  Ryoki WATANABE

IPC: B41J2/195

Abstract: A print condition setting method for setting a print condition in a printer includes: an ink type learning step of executing machine learning of an ink type discriminator using physical property information of ink and an ink type identifier; a medium type learning step of executing machine learning of a medium type discriminator using characteristic information of a medium and medium type identification information; and a print condition setting step of setting the print condition according to an ink type discriminated by the ink type discriminator and a medium type discriminated by the medium type discriminator.

公开(公告)号：US20220194099A1

公开(公告)日：2022-06-23

申请号：US17645324

申请日：2021-12-21

Applicant: SEIKO EPSON CORPORATION

Inventor： Takahiro KAMADA ,  Ryoki WATANABE ,  Satoru ONO ,  Kenji MATSUZAKA

IPC: B41J11/00 ,  G06N20/00 ,  B41J11/42

Abstract: A method for executing a discrimination process of a printing medium includes a step (a) of preparing N machine learning models when N is an integer of 1 or more, a step (b) of acquiring target spectral data which is a spectral reflectance of a target printing medium, and a step (c) of discriminating a type of the target printing medium by executing a class classification process of the target spectral data using the N machine learning models.

公开(公告)号：US20220164658A1

公开(公告)日：2022-05-26

申请号：US17535256

申请日：2021-11-24

Applicant: SEIKO EPSON CORPORATION

Inventor： Kana KANAZAWA ,  Hikaru KURASAWA ,  Ryoki WATANABE

IPC: G06N3/08 ,  G06N3/04 ,  G06V10/82 ,  G06V10/74

Abstract: A method causes one or more processors to execute a method in which a machine learning model of a vector neural network type is used. The model is learned to reproduce correspondence between first images and a pre-label corresponding to each of the first images, and includes one or more neuron layers. First intermediate data output by the one or more neurons when the first images are input to the learned model is stored in one or more memories in correlation with the neurons. The method includes inputting a second image of an object to the machine learning model and acquiring second intermediate data based on at least one of a second vector and a second activation included in the one or more neurons, calculating a similarity degree between the first and second intermediate data, generating an evidence image corresponding to the similarity degree, and displaying the generated evidence image.