Image superimposition system and image superimposition method

Patent metadata

Field	Value
Publication number	US-2024303776-A1
Application number	US-202118574735-A
Country	US
Kind code	A1
Filing date	Jun 28, 2021
Priority date	Jun 28, 2021
Publication date	Sep 12, 2024
Grant date	—

Abstract

An image superimposition system ( 100 ) according to the present disclosure includes: a control device ( 4 ) that generates face region image information indicating a face region image obtained by trimming a face region (R 1 ) in a captured image, and generates superimposition object region image information indicating a superimposition object region image obtained by trimming a superimposition object region (R 2 ) in a captured image; a face recognition device ( 2 ) that recognizes a face image and generates face image information indicating the face image; a superimposition object recognition device ( 3 ) that recognizes a superimposition image corresponding to the superimposition object region image; and a combining device ( 5 ) that detects the face image of the user from a combining region image that is an image of a combining region (R 3 ) larger than the face region (R 1 ) and the superimposition object region (R 2 ) in a captured image, and generates combined image information indicating a combined image formed by superimposing the superimposition image on the face image.

First claim

1 . An image superimposition system comprising a processor configured to execute operations comprising:
generating face region image information indicating a face region image obtained by trimming a face region in a first captured image imaging a user in a first stage; generating superimposition object region image information indicating a superimposition object region image obtained by trimming a superimposition object region in a second captured image imaging a superimposition object in the first stage; recognizing a face image of the user included in the face region image; generating face image information indicating the face image; recognizing a superimposition image corresponding to the superimposition object region image; and detecting a face image of the user on a basis of the face image information from a combining region image that is an image of a combining region larger than the face region and the superimposition object region in a third captured image imaging the user in a second stage after the first stage; and generating combined image information indicating a combined image formed by superimposing the superimposition image on the face image.

2 . The image superimposition system according to claim 1 , wherein the generating superimposition object region image information further comprises:
determining the superimposition object region on a basis of the face image, and generating the superimposition object region image information indicating the superimposition object region image obtained by trimming the superimposition object region in the captured image.

3 . An image superimposition method comprising:
generating face region image information indicating a face region image obtained by trimming a face region in a captured image obtained by an imaging device imaging a user in a first stage; generating superimposition object region image information indicating a superimposition object region image obtained by trimming a superimposition object region in a captured image obtained by the imaging device imaging a superimposition object in the first stage; recognizing a face image of the user included in the face region image, and generating face image information indicating the face image; recognizing a superimposition image corresponding to the superimposition object region image; detecting a face image of the user on a basis of the face image information from a combining region image that is an image of a combining region larger than the face region and the superimposition object region in a captured image obtained by the imaging device imaging the user in a second stage after the first stage; and generating combined image information indicating a combined image formed by superimposing the superimposition image on the face image.

4 . The image superimposition method according to claim 3 , further comprising
determining the superimposition object region, on a basis of the face image included in the face region image, wherein the generating the superimposition object region image information further comprises generating the superimposition object region image information indicating the superimposition object region image obtained by trimming the superimposition object region in the captured image.

5 . The image superimposition system according to claim 1 , wherein the superimposition object includes a mask of a kumadori makeup for exaggerating facial expression in Kabuki.

6 . The image superimposition method according to claim 3 , wherein the superimposition object includes a mask of a kumadori makeup for exaggerating facial expression in Kabuki.

7 . A computer-readable non-transitory recording medium storing a computer-executable program instructions that when executed by a processor cause a computer to execute operations comprising:
generating face region image information indicating a face region image obtained by trimming a face region in a first captured image imaging a user in a first stage; generating superimposition object region image information indicating a superimposition object region image obtained by trimming a superimposition object region in a second captured image imaging a superimposition object in the first stage; recognizing a face image of the user included in the face region image; generating face image information indicating the face image; recognizing a superimposition image corresponding to the superimposition object region image; and detecting a face image of the user on a basis of the face image information from a combining region image that is an image of a combining region larger than the face region and the superimposition object region in a third captured image imaging the user in a second stage after the first stage; and generating combined image information indicating a combined image formed by superimposing the superimposition image on the face image.

8 . The computer-readable non-transitory recording medium according to claim 7 ,
wherein the generating superimposition object region image information further comprises: determining the superimposition object region on a basis of the face image, and generating the superimposition object region image information indicating the superimposition object region image obtained by trimming the superimposition object region in the captured image.

9 . The computer-readable non-transitory recording medium according to claim 7 ,
wherein the superimposition object includes a mask of a kumadori makeup for exaggerating facial expression in Kabuki.

Assignees

• Nippon Telegraph & Telephone

Inventors

• Urata Masakazu
• Sakuma Satoshi
• Chigira Hiroshi
• Matsui Tatsuya
• Suzuki Masafumi
• Iwamoto Hideaki

Classifications

• G06T5/50 Primary

  using two or more images, e.g. averaging or subtraction · CPC title

• G06V40/161 Primary

  Detection; Localisation; Normalisation · CPC title

• G06T2207/20221

  Image fusion; Image merging · CPC title

• G06T2207/20132

  Image cropping · CPC title

• G06T7/00

  Image analysis · CPC title