IP Library Granted Patent US 11,055,513
Granted Patent B2
US 11,055,513 · App. 16/079,814 · Granted Jul 6, 2021

Face recognition system, face recognition method, and storage medium

Inventors: Noriaki Hayase (Tokyo, JP); Hiroshi Tezuka (Tokyo, JP)
Assignee: NEC CORPORATION
G06K9/00288G06F21/32G06K9/00228G06T7/00G06T7/38G06T2207/30201
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 11,055,513
App. No.
16/079,814
Granted
Jul 6, 2021
Kind
B2
Abstract

A face recognition system, a face recognition method, and a storage medium that can perform face matching smoothly in a short time are provided. The face recognition system includes: a face detection unit that detects a face image from an image including an authentication subject as a detected face image; a storage unit stores identification information identifying the authentication subject and a registered face image of the authentication subject in association with each other; and a face matching unit that, in response to acquisition of the identification information identifying the authentication subject, matches, against the registered face image corresponding to the acquired identification information, the detected face image detected by the face detection unit from an image captured before the acquisition.

Claims (47)

1. A face recognition system comprising:

a memory comprising instructions; and

a processor configured to execute the instructions to:

detect a candidate face image of an authentication subject;

calculate a quality value of the candidate face image;

determine the candidate face image as a target face image based on the quality value of the candidate face image satisfying a threshold value;

determine a face feature amount of the target face image; and

match the target face image with a registered image based on the face feature amount of the target face image.

2. The face recognition system according to claim 1 , wherein the processor is further configured to execute the instructions to:

detect a plurality of candidate face images from a plurality of frames of images, and

match the plurality of candidate face images with the registered face image.

3. The face recognition system according to claim 2 , wherein the processor is further configured to execute the instructions to:

calculate a priority used for determining order of performing matching with the registered face image for the plurality of candidate face images; and

match the plurality of candidate face images with the registered face image in descending order of the priority calculated by the priority calculation unit.

4. The face recognition system according to claim 2 , wherein the processor is further configured to execute the instructions to:

classify the plurality of candidate face images on an identical person basis and calculate a priority for determining order of performing matching with the registered face image for the target face image classified into the identical person; and

match the target face image classified into the identical person with the registered face image in descending order of the priority.

5. The face recognition system according to claim 1 , wherein the processor is further configured to execute the instructions to:

register, as a new registered face image, the target face image in which matching with the registered face image is matched.

6. The face recognition system according to claim 1 , further comprising:

an image capturing unit that captures an image including the authentication subject; and

another image capturing unit that captures a face image of the authentication subject and acquires the face image of the authentication subject when matching of the target face image with the registered face image is not matched,

wherein the processor is further configured to execute the instructions to:

match, with the registered face image, the face image of the authentication subject acquired by the another image capturing unit.

7. The face recognition system according to claim 1 further comprising a display unit that displays the target face image and the registered face image.

8. The face recognition system according to claim 1 , wherein the processor is further configured to execute the instructions to:

acquire, offline, the registered face image to be matched with the target face image.

9. The face recognition system according to claim 1 further comprising an image capturing unit that captures an image including the authentication subject,

wherein the image capturing unit is installed in a vertical orientation so as to capture the image that is vertically long.

10. The face recognition system according to claim 1 , wherein the face feature amount of the target face image is a facial likeness score indicating a likelihood that the target face image is a face.

11. A face recognition method comprising:

detecting a candidate face image of an authentication subject;

calculate a quality value of the candidate face image;

determining the face image as a target face image based on the quality of the candidate face image satisfying a threshold value;

determining a face feature amount of the target face image; and

matching the target face image with a registered image based on the face feature amount of the target face image.

12. The face recognition method according to claim 11 further comprising:

detecting a plurality of candidate face images from a plurality of frames of images; and

matching the plurality of candidate face images with the registered face image.

13. The face recognition method according to claim 11 , wherein the face feature amount of the target face image is a facial likeness score indicating a likelihood that the target face image is a face.

14. A non-transitory storage medium in which a program is stored, wherein the program causes a computer to execute:

detecting a candidate face image of an authentication subject;

calculate a quality value of the candidate face image;

determining the face image as a target face image based on the quality of the candidate face image satisfying a threshold value;

determining a face feature amount of the target face image; and

matching the target face image with a registered image based on the face feature amount of the target face image.

15. The non-transitory computer readable medium of claim 14 , wherein the face feature amount of the target face image is a facial likeness score indicating a likelihood that the target face image is a face.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 24, 2018
From: HAYASE, NORIAKI; TEZUKA, HIROSHI
To: NEC CORPORATION
Reel/Frame 046699/0696 →
Priority Claims (1)
JP JP2016-036406 · Feb 26, 2016 · national
Continuity (1)
Related Publication 20190050631A1 · Feb 14, 2019