IP Library › Granted Patent US 9,959,454
Granted Patent B2
US 9,959,454 · App. 15/407,239 · Granted May 1, 2018

Face recognition device, face recognition method, and computer-readable recording medium

Inventor: Toshiro Ohbitsu (Akishima, JP)
Assignee: FUJITSU LIMITED
G06K9/00268G06K9/00255G06K9/00288G06T7/74H04N5/23293G06T2207/30201
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 9,959,454
App. No.
15/407,239
Granted
May 1, 2018
Kind
B2
Abstract

A face recognition device includes a processor configured to: extract a plurality of feature points of a face included in an input image; detect a first and a second feature points that are paired from among the plurality of the feature points, a third feature point that is away from a straight line that connects the first and the second feature points, and two inter-feature vectors starting from the third feature point to the respective first the second feature points; calculate a feature angle formed by the two detected inter-feature vectors; and perform face recognition based on the feature angle formed by the two inter-feature vectors included in face information that is previously set as the face targeted for recognition and based on the calculated feature angle.

Claims (22)

1. A face recognition device for matching a face included in an input image with face information that is previously set with respect to a targeted face targeted for recognition, the face recognition device comprising:

a processor configured to:

extract a plurality of feature points of the face included in the input image;

detect first and second feature points that are paired from among the plurality of the feature points, a third feature point that is away from a straight line that connects the first and the second feature points, and two inter-feature vectors starting from the third feature point to the respective first and the second feature points;

calculate a feature angle formed by the two detected inter-feature vectors;

calculate, based on two inter-feature vectors of the targeted face in a predetermined orientation included in the face information and based on the detected two inter-feature vectors of the face in the input image, an inclination angle that indicates the rotation of the face in the input image about three axes and that is with respect to the orientation of the targeted face associated with the face information; and

perform face recognition based on whether a positional relationship of the two detected inter-feature vectors formed by the calculated feature angle matches a positional relationship of the two inter-feature vectors formed by a feature angle formed by the two inter-feature vectors in the face information, in a case where the orientation of the face in the input image is the orientation of the targeted face associated with the face information, based on the calculated inclination angle.

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

display a guide image that guides the orientation of the face included in the input image with respect to a camera to a predetermined orientation; and

acquire an image captured by the camera and set the face information that includes therein the two inter-feature vectors detected from the image and the feature angle calculated from the two detected inter-feature vectors.

3. A face recognition method for matching a face included in an input image with face information that is previously set with respect to a targeted face targeted for recognition, the face recognition method comprising:

extracting a plurality of feature points of the face included in the input image, by a processor;

detecting first and second feature points that are paired from among the plurality of the feature points, a third feature point that is away from a straight line that connects the first and the second feature points, and two inter-feature vectors starting from the third feature point to the respective first and the second feature points, by the processor;

calculating a feature angle formed by the two detected inter-feature vectors, by the processor;

calculating, by the processor based on two inter-feature vectors of the targeted face in a predetermined orientation included in the face information and based on the detected two inter-feature vectors of the face in the input image, an inclination angle that indicates the rotation of the face in the input image about three axes and that is with respect to the orientation of the targeted face associated with the face information; and

performing face recognition based on whether a positional relationship of the two detected inter-feature vectors formed by the calculated feature angle matches a positional relationship of the two inter-feature vectors formed by a feature angle formed by the two inter-feature vectors in the face information, in a case where the orientation of the face in the input image is the orientation of the targeted face associated with the face information, based on the calculated inclination angle, by the processor.

4. A non-transitory computer-readable recording medium storing a face recognition program for matching a face included in an input image with face information that is previously set with respect to a targeted face targeted for recognition, the face recognition program causing a computer to execute a process comprising:

extracting a plurality of feature points of the face included in the input image;

detecting first and second feature points that are paired from among the plurality of the feature points, a third feature point that is away from a straight line that connects the first and the second feature points, and two inter-feature vectors starting from the third feature point to the respective first and the second feature points;

calculating a feature angle formed by the two detected inter-feature vectors;

calculating, based on two inter-feature vectors of the targeted face in a predetermined orientation included in the face information and based on the detected two inter-feature vectors of the face in the input image, an inclination angle that indicates the rotation of the face in the input image about three axes and that is with respect to the orientation of the targeted face associated with the face information; and

performing face recognition based on whether a positional relationship of the two detected inter-feature vectors formed by the calculated feature angle matches a positional relationship of the two inter-feature vectors formed by a feature angle formed by the two inter-feature vectors in the face information, in a case where the orientation of the face in the input image is the orientation of the targeted face associated with the face information, based on the calculated inclination angle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 20, 2017
From: OHBITSU, TOSHIRO
To: FUJITSU LIMITED
Reel/Frame 041439/0093 →
Continuity (2)
Continuation PCTJP2014069622 · Jul 24, 2014
Related Publication 20170124383A1 · May 4, 2017