公开(公告)号：US11373448B2

公开(公告)日：2022-06-28

申请号：US16977463

申请日：2018-10-25

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Takashi Sugimoto

IPC: G06K9/00 ,  G06V40/16 ,  G06F3/01 ,  G06T7/00

Abstract: An emotion inference device includes: an obtainer that obtains a second evaluation value group and then a first evaluation value group each including evaluation values corresponding to emotion attributes of classified emotions of a subject; a processor that, when a difference under the same emotion attribute between corresponding evaluation values in the first and second evaluation value groups does not exceed a predetermined criterion, performs a correction process to reduce the evaluation value corresponding to the same emotion attribute in the first evaluation value group, and performs an inference process to infer the emotion of the subject based on the corrected first evaluation value group, in which an emotion attribute having a relatively higher evaluation value is inferred relatively more strongly as the emotion of the subject; and an outputter that outputs a result of the inference process performed by the processor.

公开(公告)号：US12205352B2

公开(公告)日：2025-01-21

申请号：US18264717

申请日：2022-02-16

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Takashi Sugimoto

IPC: G06V10/77 ,  G06T5/60 ,  G06V10/26 ,  G06V10/774 ,  G06V10/776 ,  G06V20/40

Abstract: An image identifying apparatus includes: an obtainer that obtains image data; an image processor that generates test image data by performing resizing to reduce the image data with predetermined aspect ratio distortion; a storage unit that stores a machine learning model used to identify attribute information of the test image data; and an identifier that identifies the attribute information of the test image data, using the machine learning model. The machine learning model includes trained parameters that have been adjusted through machine learning using a training data set including items of second training image data obtained through application of one or more types of aspect ratio distortion including the predetermined aspect ratio distortion to each of items of first training image data, and items of attribute information associated with the items of second training image data.