WO2023008811A3 - Method for reconstructing masked face image by using neural network model - Google Patents

Method for reconstructing masked face image by using neural network model Download PDF

Info

Publication number
WO2023008811A3
WO2023008811A3 PCT/KR2022/010569 KR2022010569W WO2023008811A3 WO 2023008811 A3 WO2023008811 A3 WO 2023008811A3 KR 2022010569 W KR2022010569 W KR 2022010569W WO 2023008811 A3 WO2023008811 A3 WO 2023008811A3
Authority
WO
WIPO (PCT)
Prior art keywords
face image
masked face
reconstructing
neural network
network model
Prior art date
Application number
PCT/KR2022/010569
Other languages
French (fr)
Korean (ko)
Other versions
WO2023008811A2 (en
Inventor
이광희
Original Assignee
이광희
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from KR1020220075569A external-priority patent/KR102547630B1/en
Application filed by 이광희 filed Critical 이광희
Publication of WO2023008811A2 publication Critical patent/WO2023008811A2/en
Publication of WO2023008811A3 publication Critical patent/WO2023008811A3/en

Links

Classifications

    • G06T5/77—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • G06T5/60—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Abstract

According to one embodiment of the present disclosure, disclosed is a masked face image reconstruction method performed by means of one or more processors of a computing device. The method may comprise the steps of: identifying a masked face image included in an image to be reconstructed; acquiring a non-masked face image of a person associated with the identified masked face image; and combining the acquired non-masked face image with the identified masked face image.
PCT/KR2022/010569 2021-07-29 2022-07-20 Method for reconstructing masked face image by using neural network model WO2023008811A2 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
KR10-2021-0100100 2021-07-29
KR20210100100 2021-07-29
KR10-2022-0075569 2022-06-21
KR1020220075569A KR102547630B1 (en) 2021-07-29 2022-06-21 Method for restoring a masked face image by using the neural network model

Publications (2)

Publication Number Publication Date
WO2023008811A2 WO2023008811A2 (en) 2023-02-02
WO2023008811A3 true WO2023008811A3 (en) 2023-03-23

Family

ID=85087063

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/010569 WO2023008811A2 (en) 2021-07-29 2022-07-20 Method for reconstructing masked face image by using neural network model

Country Status (2)

Country Link
KR (1) KR20230095902A (en)
WO (1) WO2023008811A2 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170085477A (en) * 2014-08-04 2017-07-24 페이스북, 인크. Method and system for reconstructing obstructed face portions for virtual reality environment
CN108205659A (en) * 2017-11-30 2018-06-26 深圳市深网视界科技有限公司 Face occluder removes and its method, equipment and the medium of model construction
JP2019102081A (en) * 2017-12-05 2019-06-24 富士通株式会社 Data processing apparatus and data processing method
CN110728628A (en) * 2019-08-30 2020-01-24 南京航空航天大学 Face de-occlusion method for generating confrontation network based on condition
CN112633130A (en) * 2020-12-18 2021-04-09 成都三零凯天通信实业有限公司 Face mask removing method based on key point restoration image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170085477A (en) * 2014-08-04 2017-07-24 페이스북, 인크. Method and system for reconstructing obstructed face portions for virtual reality environment
CN108205659A (en) * 2017-11-30 2018-06-26 深圳市深网视界科技有限公司 Face occluder removes and its method, equipment and the medium of model construction
JP2019102081A (en) * 2017-12-05 2019-06-24 富士通株式会社 Data processing apparatus and data processing method
CN110728628A (en) * 2019-08-30 2020-01-24 南京航空航天大学 Face de-occlusion method for generating confrontation network based on condition
CN112633130A (en) * 2020-12-18 2021-04-09 成都三零凯天通信实业有限公司 Face mask removing method based on key point restoration image

Also Published As

Publication number Publication date
KR20230095902A (en) 2023-06-29
WO2023008811A2 (en) 2023-02-02

Similar Documents

Publication Publication Date Title
Park et al. Lip movements entrain the observers’ low-frequency brain oscillations to facilitate speech intelligibility
Yamaguchi et al. Judgment of gender through facial parts
Sagiv et al. Structural encoding of human and schematic faces: holistic and part-based processes
CN109924990A (en) A kind of EEG signals depression identifying system based on EMD algorithm
SG10201801885QA (en) Non-invasive method and system for estimating blood pressure from photoplethysmogram using statistical post-processing
Hammal et al. Interpersonal coordination of headmotion in distressed couples
WO2020087494A1 (en) Video collection emotion generation method
CN105551499A (en) Emotion visualization method facing voice and facial expression signal
DE602004007930D1 (en) TOMOGRAPHIC FOURIER IMAGE RECONSTRUCTION PROCESS FOR fan beam DATA
Dubey et al. A multi-smartwatch system for assessing speech characteristics of people with dysarthria in group settings
WO2023008811A3 (en) Method for reconstructing masked face image by using neural network model
Mullins Age progression and regression
Chou et al. FPGA implementation of EEG system-on-chip with automatic artifacts removal based on BSS-CCA method
CN110141244A (en) Electrocardiogram personal identification method
Arppana et al. Real time heart beat monitoring using computer vision
Phillips Skeletal remains identification by facial reconstruction
CN114067398A (en) Autistic child communication disorder assisting method based on facial expression recognition
JP2016182504A5 (en)
Kawamura et al. Smiling reduces masculinity: principal component analysis applied to facial images
Drack et al. The apex of happy laughter: A FACS-study with actors
US20100145886A1 (en) Evaluation and Selection Process for Consumer Products
JPWO2021161387A5 (en) Processing device, processing method and program
Donner et al. Biomechanical comparison of American Sign Language interpretation and conversation
MX2021003154A (en) Compositions and methods for treating cellulite.
AU2021105454A4 (en) Acoustic concentration decoding from electroencephalography based on long squat term recollection network

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22849787

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE