METHOD FOR DETERMINING FACE AUTHORITY BY SEGMENTATION MASKS Russian patent published in 2021 - IPC G06K9/50 G06T7/194 

Abstract RU 2758966 C1

FIELD: computing.

SUBSTANCE: technical solution relates to the field of computing. The effect is achieved by implementing a method for determining the identity of a subject's face on access control and management systems using segmentation masks, containing the stages at which: from a broadcast video stream sent from a stationary camera located on an access control and management system, the image is captured and stored the subject on which the foreground and background plans are captured; on the saved image, the position of the subject's face is determined by means of the face detection module; the subject silhouette extraction model is used to extract the subject silhouette segmentation mask on the saved image; by means of the model of extracting the silhouette of the hands of the subject, extracting the mask of the segmentation of the silhouette of the hands of the subject on the saved image; the foreground extraction model extracts the foreground segmentation mask on the saved image; the extracted segmentation masks are combined into one set and passed to the input of the authentication model, through which the final calculations are performed to determine the authenticity of the subject's face.

EFFECT: increasing the accuracy of determining the identity of the subject's face on control systems.

1 cl, 3 dwg

Similar patents RU2758966C1

Title Year Author Number
METHOD FOR VISUALIZING A 3D PORTRAIT OF A PERSON WITH ALTERED LIGHTING AND A COMPUTING DEVICE FOR IT 2021
  • Sevastopolskij Artem Mikhajlovich
  • Lempitskij Viktor Sergeevich
RU2757563C1
TRAINING GAN (GENERATIVE ADVERSARIAL NETWORKS) TO CREATE PIXEL-BY-PIXEL ANNOTATION 2019
  • Galeev Danil Fanilievich
  • Sofiyuk Konstantin Sergeevich
  • Rukhovich Danila Dmitrievich
  • Konushin Anton Sergeevich
  • Romanov Mikhail Viktorovich
RU2735148C1
REPEATED SYNTHESIS OF IMAGE USING DIRECT DEFORMATION OF IMAGE, PASS DISCRIMINATOR AND COORDINATE-BASED REMODELLING 2019
  • Sevastopolsky Artem Mikhailovich
  • Grigoriev Artur Andreevich
  • Lempitsky Victor Sergeevich
  • Vakhitov Alexander Timurovich
RU2726160C1
SIMULTANEOUS UNCONTROLLED SEGMENTATION OF OBJECTS AND DRAWING 2019
  • Ostyakov Pavel Aleksandrovich
  • Suvorov Roman Evgenievich
  • Logacheva Elizaveta Mikhailovna
  • Khomenko Oleg Igorevich
  • Nikolenko Sergey Igorevich
RU2710659C1
RAPID TWO-LAYER NEURAL NETWORK SYNTHESIS OF REALISTIC IMAGES OF A NEURAL AVATAR BASED ON A SINGLE IMAGE 2020
  • Zakharov Egor Olegovich
  • Ivakhnenko Aleksei Aleksandrovich
  • Shysheya Aliaksandra Petrovna
  • Lempitsky Victor Sergeevich
RU2764144C1
NEURAL NETWORK TRANSFER OF THE FACIAL EXPRESSION AND POSITION OF THE HEAD USING HIDDEN POSITION DESCRIPTORS 2020
  • Burkov Egor Andreevich
  • Pasechnik Igor Igorevich
  • Lempitsky Victor Sergeevich
RU2755396C1
SEGMENTATION AND PREDICTION OF TIME PATTERNS OF LOW LEVEL TRAILS 2020
  • Uajting, Ozge Ken
  • Ambati, Radzhiv Bkhatt
  • Uzunbas, Mustafa Gekkhan
  • Khoang, Tkhaj
RU2783420C1
METHOD FOR INTERACTIVE SEGMENTATION OF OBJECT ON IMAGE AND ELECTRONIC COMPUTING DEVICE FOR REALIZING SAID OBJECT 2020
  • Sofiiuk Konstantin Sergeyevich
  • Petrov Ilia Alekseevich
  • Barinova Olga Vyacheslavovna
  • Konushin Anton Sergeyevich
RU2742701C1
METHOD, EQUIPMENT AND ELECTRONIC DEVICE FOR DETECTING A FACE VITALITY 2018
  • Ma, Chenguang
RU2714096C1
METHOD OF TRAINING A CONVOLUTION NEURAL NETWORK TO CARRY OUT TELEROENTGENOGRAM MARKINGS IN A DIRECT AND LATERAL PROJECTIONS 2019
  • Muraev Aleksandr Aleksandrovich
  • Kibardin Ilia Alekseevich
  • Oborotistov Nikolai Iurevich
  • Muraeva Polina Aleksandrovna
RU2717911C1

RU 2 758 966 C1

Authors

Grinchuk Oleg Valerevich

Rybalchenko Denis Vyacheslavovich

Dates

2021-11-03Published

2021-05-13Filed