IP Library Granted Patent US 12700132
Granted Patent B2
US 12700132 · App. 17/639,955 · Granted Aug 4, 2026

Information processing system, information processing apparatus, information processing method, and recording medium

Inventors: Yuka Ogino (Tokyo, JP); Takahiro Toizumi (Tokyo, JP)
Assignee: NEC CORPORATION
G06T7/74G06V10/761G06V40/193G06V40/197G06T2207/20081G06T2207/30201
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 12700132
App. No.
17/639,955
Granted
Aug 4, 2026
Kind
B2
Abstract

An information processing system includes: an acquisition unit that obtains a both-eye image, which is an image of a face containing both eyes, from a target; and a detection unit that detects an eye position of the target in the both-eye image on the basis of a result of learning that uses a one-eye image containing only one of the eyes and the both-eyes image. According to such an information processing system, the eye position of the target contained in the both-eye image can be detected with high accuracy.

Claims (34)

1 . An information processing system comprising:

at least one memory that is configured to store information; and

at least one processor configured to execute instructions to:

obtain a both-eye image, which is an image of a face containing both eyes, from a target, and

detect an eye position of the target in the both-eye image based on a result of learning that uses a one-eye image containing only one eye of the target and the both-eye image,

wherein the at least one processor is further configured to execute the instructions to:

generate a similarity map by using a feature of the one-eye image and a feature of the both-eye image of the target, and

detect the eye position of the target based on the similarity map.

2 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:

in a case in which the one-eye image is a right-eye image, generate a similarity map for a right eye by using a feature of the right-eye image containing the right eye and the feature of the both-eye image of the target, and in a case in which the one-eye image is the left-eye image, generate a similarity map for a left eye by using a feature of the left-eye image containing the left eye and the feature of the both-eye image of the target, and

detect a position of the right eye of the target based on the similarity map for the right eye, and detect a position of the left eye of the target based on the similarity map for the left eye.

3 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to store the feature extracted from the one-eye image in advance and generate the similarity map by using the stored feature.

4 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to generate the similarity map by using the one-eye image and the both-eye image having a same eye size.

5 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to generate the similarity map that indicates a similarity between the feature of the one-eye image and a subspace of the feature of the both-eye image.

6 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to highlight the eye position detected, on the similarity map.

7 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to superimpose and display the eye position detected, on the both-eye image of the target.

8 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to allow learning by generating a loss function based on the similarity map and minimizing the loss function.

9 . The information processing system according to claim 8 , wherein the at least one processor is further configured to execute the instructions to perform learning on which a load is applied to reduce a similarity of a part corresponding to the eye position in the similarity map.

10 . The information processing system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:

obtain a visible-light face image by imaging the face of the target with a visible-light camera; and

detect the eye position of the target in the visible-light face image based on the visible-light face image.

11 . The information processing system according to claim 10 , wherein the at least one processor is further configured to execute the instructions to output a warning information when the eye position of the target detected in the both-eye image is different from the eye position of the target detected in the visible-light face image.

12 . An information processing method executed by at least one computer, comprising:

obtaining a both-eye image, which is an image of a face containing both eyes, from a target; and

detecting an eye position of the target in the both-eye image based on a result of learning that uses a one-eye image containing only one eye of the target and the both-image,

wherein the information processing method further comprises:

generating a similarity map by using a feature of the one-eye image and a feature of the both-eye image of the target, and

detecting the eye position of the target based on the similarity map.

13 . A non-transitory recording medium on which a computer program that allows at least one computer to execute an information processing method is recorded, the information processing method including:

obtaining a both-eye image, which is an image of a face containing both eyes, from a target; and

detecting an eye position of the target in the both-eye image based on a result of learning that uses a one-eye image containing only one eye of the target and the both-eye image,

wherein the information processing method further comprises:

generating a similarity map by using a feature of the one-eye image and a feature of the both-eye image of the target, and

detecting the eye position of the target based on the similarity map.