IP Library › Granted Patent US 12,657,955
Granted Patent B2
US 12,657,955 · App. 18/495,417 · Granted Jun 16, 2026

Apparatus for identifying a face and method thereof

Inventors: Kyung Hwan Cho (Anyang-si, KR); Moon Sub Jin (Yongin-si, KR); Ji Won Kim (Suwon-si, KR); Hyeon Seok Jung (Suwon-si, KR); Keon Ho Lee (Incheon, KR)
Assignees: Hyundai Motor Company; Kia Corporation
G06V40/172G06V10/761G06V10/955G06V40/165G06V40/171G06V40/50
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 12,657,955
App. No.
18/495,417
Granted
Jun 16, 2026
Kind
B2
Abstract

Embodiments relate to a face identification apparatus and a method thereof. An exemplary embodiment face identification apparatus includes a processor configured to extract face information and person information from image data and to identify a face using the face information and the person information and a storage configured to store data and algorithms to be driven by the processor.

Claims (61)

1 . A face identification apparatus comprising:

a processor configured to:

extract face information and person information from image data to identify a face using the face information and the person information;

detect a person area and a face area from the image data;

create a first bounding box in the person area and assign a person ID for tracking;

create a second bounding box in the face area and assign a face ID for tracking; and

determine whether the person ID and the face ID are registered in a face person matching table; and

a storage configured to:

store data and algorithms to be driven by the processor;

store the face person matching table, wherein the face person matching table is configured to store the face ID, a face expressor, the person ID, a person expressor, and an integrated ID.

2 . The apparatus of claim 1 , wherein, in response to a case that the person ID and the face ID are registered in the face person matching table, the processor is configured to identify the face using the IDs registered in the face person matching table.

3 . The apparatus of claim 2 , wherein the processor is configured to:

in response to a case that both the face area and the person area are detected in a first frame of the image data but the face area is not detected in a second frame of the image data, inquire whether the person ID of the person area detected in the second frame is registered in the face person matching table; and

in response to a case that the person ID of the person area detected in the second frame is registered in the face person matching table, identify a face with a corresponding ID.

4 . The apparatus of claim 3 , wherein the processor is configured to:

assign a new face ID to the face area that is detected again in a third frame of the image data; and

update the face ID registered in the face person matching table to the new face ID.

5 . The apparatus of claim 2 , wherein the processor is configured to:

in response to a case that both the face area and the person area are detected in a first frame of the image data but the person area is not detected in a second frame of the image data, inquire whether the face ID of the face area detected in the second frame is registered in the face person matching table; and

in response to a case that the face ID of the face area detected in the second frame is registered in the face person matching table, identify a face with a corresponding ID.

6 . The apparatus of claim 5 , wherein the processor is configured to:

assign a new person ID to the person area that is detected again in a third frame of the image data; and

update the person ID registered in the face person matching table to the new person ID.

7 . A face identification apparatus, the apparatus comprising:

a processor configured to:

extract face information and person information from image data;

identify a face using the face information and the person information;

detect a person area and a face area from the image data;

create a first bounding box in the person area and assign a person ID for tracking;

create a second bounding box in the face area and assign a face ID for tracking;

determine whether the person ID and the face ID are registered in a face person matching table; and

in response to a determination that the person ID and the face ID are not registered in the face person matching table, extract the person information from the person area and extract the face information from the face area to determine whether the person information and the face information are information of a same person; and

a storage configured to:

store data and algorithms to be driven by the processor; and

store the face person matching table, wherein the face person matching table is configured to store the face ID, a face expressor, the person ID, a person expressor, and an integrated ID.

8 . The apparatus of claim 7 , wherein the processor is configured to determine whether the information is of the same person by determining whether a pixel distance difference between a face position extracted from the person information and a face position extracted from the person area is smaller than a predetermined first threshold.

9 . The apparatus of claim 8 , wherein the processor is configured to determine whether the information is of the same person by determining whether a difference between a distance from a camera to the person area and a distance from the camera to the face area is smaller than a predetermined second threshold.

10 . The apparatus of claim 9 , wherein the processor is configured to determine whether the information is of the same person by determining whether a size of an overlapped area between the first bounding box of the person area and the second bounding box of the face area is greater than a predetermined third threshold.

11 . The apparatus of claim 7 , wherein in response to a case that the person information and the face information are determined to be information of the same person, the processor is configured to perform a similarity comparison between the extracted person information and the extracted face information and the person information and the face information registered in the face person matching table.

12 . The apparatus of claim 11 , wherein the processor is configured to perform the similarity comparison by using similarity between the person expressor of the extracted person information and the person expressor of the person information registered in the face person matching table, similarity between the face expressor of the extracted face information and the face expressor of the face information registered in the face person matching table, and a predetermined face weight and a predetermined person weight.

13 . The apparatus of claim 12 , wherein the processor is configured to increase the face weight and decrease the person weight as a difference between an input time of the face expressor of the extracted face information and a registration time of the face expressor of the face information registered in the face person matching table increases.

14 . The apparatus of claim 12 , wherein the processor is configured to increase the person weight and decrease the face weight as a distance from a camera to the person area increases.

15 . The apparatus of claim 12 , wherein the processor is configured to determine whether similarity between the extracted person information and the extracted face information and the person information and the face information registered in the face person matching table is greater than a predetermined similarity threshold.

16 . The apparatus of claim 15 , wherein the processor is configured to:

determine that the extracted person information and the extracted face information and the person information and the face information registered in the face person matching table are information of the same person in response to a case that the similarity between the extracted person information and the extracted face information and the person information and the face information registered in the face person matching table is greater than the predetermined similarity threshold; and

newly register the extracted person information and the extracted face information in the face person matching table in response to a case that the similarity between the extracted person information and the extracted face information and the person information and the face information registered in the face person matching table is equal to or smaller than the predetermined similarity threshold.

17 . A face identification method, the method comprising:

extracting face information and person information from image data;

detecting a person area and a face area from the image data;

creating a first bounding box in the person area and assigning a person ID for tracking;

creating a second bounding box in the face area and assigning a face ID for tracking;

determining whether the person ID and the face ID are registered in a face person matching table, wherein the face person matching table stores the face ID, a face expressor, the person ID, a person expressor, and an integrated ID, and wherein the face person matching table is stored in a storage; and

identifying a face using the face information, the person information, and information stored in the face person matching table.

18 . The method of claim 17 , further comprising identifying the face using the IDs registered in the face person matching table in response to determining that the person ID and the face ID are registered in the face person matching table.

19 . The method of claim 18 , further comprising:

determining whether both the face area and the person area are detected in a first frame of the image data but the face area is not detected in a second frame of the image data;

inquiring whether the person ID of the person area detected in the second frame is registered in the face person matching table in response to determining that both the face area and the person area are detected in the first frame but the face area is not detected in the second frame; and

identifying a face with a corresponding ID in response to the person ID of the person area detected in the second frame being registered in the face person matching table.

20 . The method of claim 19 , further comprising:

assigning a new face ID to the face area that is detected again in a third frame of the image data; and

updating the face ID registered in the face person matching table to the new face ID.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 26, 2023
From: CHO, KYUNG HWAN; JIN, MOON SUB; KIM, JI WON; JUNG, HYEON SEOK; LEE, KEON HO
To: HYUNDAI MOTOR COMPANY; KIA CORPORATION
Reel/Frame 065359/0902 →
Priority Claims (1)
KR 10-2023-0060088 · May 9, 2023 · national
Continuity (1)
Related Publication 20240378920A1 · Nov 14, 2024
References Cited (12)
US 10140726B2 · Nishino et al. · 2018 [cited by applicant]
US 20040197014A1 · Oohashi · 2004 [cited by examiner]
US 20190371080A1 · Sminchisescu et al. · 2019 [cited by applicant]
US 20210312166A1 · Yuan · 2021 [cited by examiner]
US 20220165048A1 · Ham et al. · 2022 [cited by applicant]
JP 6730236B2 · 2020 [cited by applicant]
KR 101164228B1 · 2012 [cited by applicant]
KR 101680598B1 · 2016 [cited by applicant]
KR 102161476B1 · 2020 [cited by applicant]
KR 102187302B1 · 2020 [cited by applicant]
KR 102225613B1 · 2021 [cited by applicant]
KR 102533505B1 · 2023 [cited by applicant]