IP Library Granted Patent US 12,430,948
Granted Patent B2
US 12,430,948 · App. 18/088,018 · Granted Sep 30, 2025

Apparatus and method for emotion estimation

Inventors: Masahiro Ishihara (Tokyo-to, JP); Yuki Horiuchi (Tokyo-to, JP); Yuji Yamanishi (Tokyo-to, JP); Taku Mitsumori (Kariya, JP); Yuki Takeda (Kariya, JP)
Assignees: TOYOTA JIDOSHA KABUSHIKI KAISHA; AISIN CORPORATION
G06V40/174G06V20/597
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,430,948
App. No.
18/088,018
Granted
Sep 30, 2025
Kind
B2
Abstract

An apparatus for emotion estimation sets a face feature threshold based on a plurality of face features indicating a deviation from a reference state of a predetermined part of a face detected from each of a plurality of face images representing a face of a driver of a vehicle generated by a camera mounted on the vehicle in a predetermined time range, specifies face features larger than the face feature threshold among the plurality of face features detected from each of the face images generated by the camera at a time not included in the predetermined time range, and estimates an emotion of the driver by using normalized features obtained by normalizing the specified face features downward.

Claims (13)

1. An apparatus for emotion estimation comprising a processor configured to:

set a face feature threshold, based on a plurality of values of a plurality of face features, to a first value, the face feature threshold indicating one or more of the plurality of face features deviating from a reference state of a predetermined part of a face detected from each of a plurality of face images representing a face of a driver of a vehicle generated by a camera mounted on the vehicle at a time included in a predetermined time range;

specify one or more second values of one or more face features, among the plurality of face features from each of the face images generated by the camera at a time not included in the predetermined time range, being larger than the face feature threshold; and

estimate an emotion of the driver using normalized features obtained by normalizing the one or more second values of the one or more face features downward by changing each of the one or more second values larger than the face feature threshold so that a first range from the face feature threshold to a maximum value of the one or more second values larger than the face feature threshold corresponds to a second range from a minimum value of the one or more second values larger than the face feature threshold to the maximum value of the one or more second values larger than the face feature threshold.

2. The apparatus for emotion estimation according to claim 1 , wherein the predetermined time range includes a time immediately after the apparatus is activated.

3. The apparatus for emotion estimation according to claim 1 , wherein the processor is further configured to, at the setting of the face feature threshold, set the first value to a value of the plurality of values of the plurality of face features that is located at a predetermined ratio from a minimum value of the plurality of values of the plurality of face features, in a state in which the plurality of values of the plurality of face features detected from each of the face images generated at a time included in the predetermined time range are arranged in ascending order.

4. The apparatus for emotion estimation according to claim 1 , wherein the processor is further configured to:

set the first value for each of a plurality of facial action units included in each of the plurality of face images, the plurality of facial action units being a plurality of predetermined parts of the face of the driver of the vehicle; and

specify, for each of the plurality of facial action units, the one or more second values of the one or more face features larger than the first value.

5. A method for emotion estimation, comprising:

setting a face feature threshold, based on a plurality of values of a plurality of face features, to a first value, the face feature threshold indicating one or more of the plurality of face features deviating from a reference state of a predetermined part of a face detected from each of a plurality of face images representing a face of a driver of a vehicle generated by a camera mounted on the vehicle at a time included in a predetermined time range;

specifying one or more second values of one or more face features, among the plurality of face features from each of the face images generated by the camera at a time not included in the predetermined time range, being larger than the face feature threshold; and

estimating an emotion of the driver using normalized features obtained by normalizing the one or more second values of the one or more face features downward by changing each of the one or more second values larger than the face feature threshold so that a first range from the face feature threshold to a maximum value of the one or more second values larger than the face feature threshold corresponds to a second range from a minimum value of the one or more second values larger than the face feature threshold to the maximum value of the one or more second values larger than the face feature threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 23, 2022
From: ISHIHARA, MASAHIRO; HORIUCHI, YUKI; YAMANISHI, YUJI; MITSUMORI, TAKU; TAKEDA, YUKI
To: TOYOTA JIDOSHA KABUSHIKI KAISHA; AISIN CORPORATION
Reel/Frame 062194/0928 →
Priority Claims (1)
JP 2021-213429 · Dec 27, 2021 · national
Continuity (1)
Related Publication 20230206690A1 · Jun 29, 2023
References Cited (24)
US 8743125B2 · Omote · 2014 [cited by examiner]
US 9956963B2 · Vijaya Kumar · 2018 [cited by examiner]
US 10963678B2 · Kim · 2021 [cited by examiner]
US 11113890B2 · Joseph · 2021 [cited by examiner]
US 11302124B2 · Zhang · 2022 [cited by examiner]
US 11314389B2 · You · 2022 [cited by examiner]
US 11453401B2 · Yamauchi · 2022 [cited by examiner]
US 11462027B2 · Sano · 2022 [cited by examiner]
US 11935306B2 · Goto · 2024 [cited by examiner]
US 12122392B2 · Ren · 2024 [cited by examiner]
US 20060115157A1 · Mori et al. · 2006 [cited by applicant]
US 20100296706A1 · Kaneda et al. · 2010 [cited by applicant]
US 20110235919A1 · Morita · 2011 [cited by examiner]
US 20170311863A1 · Matsunaga · 2017 [cited by examiner]
US 20180178766A1 · Oba · 2018 [cited by examiner]
US 20200410217A1 · Sugimoto · 2020 [cited by applicant]
US 20210261050A1 · Sobhany · 2021 [cited by examiner]
US 20210326586A1 · Sorci · 2021 [cited by examiner]
US 20220172527A1 · Kim · 2022 [cited by examiner]
US 20240286613A1 · Fujino · 2024 [cited by examiner]
US 20250014470A1 · Liu · 2025 [cited by examiner]
JP 200556388A · 2005 [cited by applicant]
JP 2010271872A · 2010 [cited by applicant]
WO 2019193781A1 · 2019 [cited by applicant]