公开(公告)号：US20200167915A1

公开(公告)日：2020-05-28

申请号：US16637216

申请日：2018-08-06

Applicant: KOWA COMPANY, LTD.

Inventor： Reiko ARITA ,  Katsumi YABUSAKI

IPC: G06T7/00 ,  A61B3/00 ,  A61B5/00

Abstract: Provided are a method, a computer program and a device for noninvasively evaluating a state of a tear fluid and a tear fluid amount of a tear meniscus.Included are a binarization step of binarizing a tear meniscus image, obtained by capturing at least a part of a tear meniscus of a subject, using a predetermined threshold value; an extraction step of extracting a high luminance region indicating a tear meniscus part from the binarized image; and an evaluation step of evaluating a tear fluid state on the basis of the high luminance region.

公开(公告)号：US20230025493A1

公开(公告)日：2023-01-26

申请号：US17788949

申请日：2020-12-23

Applicant: Kowa Company, Ltd.

Inventor： Reiko ARITA ,  Katsumi YABUSAKI ,  Miyako SUZUKI

IPC: G06T7/00 ,  G06V10/44 ,  G06T7/13

Abstract: An ophthalmic image of an evaluation target is acquired, a plurality of subsection images is extracted from the ophthalmic image, a state of a subject's eye is predicted for each of the subsection images based on a learned model in which learning has been performed in advance regarding extracting a plurality of subsection images from an ophthalmic image for learning, and predicting a state of a subject's eye for the each of subsection image by machine learning using correct answer data related to a state of each subsection image, and the subsection image is extracted from the ophthalmic image so as to have an image size corresponding to a state of a subject's eye of an evaluation target.

公开(公告)号：US20210212561A1

公开(公告)日：2021-07-15

申请号：US16976375

申请日：2019-03-01

Applicant: KOWA COMPANY, LTD.

Inventor： Reiko ARITA ,  Katsumi YABUSAKI

IPC: A61B3/10 ,  A61B3/14 ,  A61B3/00 ,  G06K9/46 ,  G06K9/62

Abstract: In classifying images by machine learning, provided are an image classification method, device, and program for classifying the image from which the feature difference is hardly detected, in particular, classifying the interference fringe image of tear fluid layer by the dry eye types. The method includes a step of acquiring a feature value from an interference fringe image of tear fluid layer for learning, a step of constructing a model for classifying an image from the feature value acquired from the interference fringe image of tear fluid layer for learning, a step of acquiring the feature value from an interference fringe image of tear fluid layer for testing, and a step of performing classification processing for classifying the interference fringe image of tear fluid layer for testing by types of dry eye using the model and the feature value acquired from the interference fringe image of tear fluid layer.