FIELD: computer engineering.
SUBSTANCE: invention relates to computer engineering for determining synthetically altered images of faces on video. Technical result is achieved by a method in which: an image is obtained from a video; identifying images of faces on said image; calculating a vector representation of the geometric characteristics of the detected face images; using frame-by-frame video analysis, calculating the spatial-temporal significance of each face image of each person on said image and a vector representation of the temporal characteristic of the face image; calculating a vector of estimates of the probability of synthetic changes for images of human faces; calculating an overall estimate of the probability of synthetic changes; generating a final assessment of the presence of a synthetic face image change on the video; forming an integral estimate of the presence of a synthetically changed face image on the video at least one final estimate of the model and generating a notification on the presence of the synthetically changed face in the video.
EFFECT: high accuracy and efficiency of detecting synthetic change in images of human faces in video.
20 cl, 10 dwg, 2 tbl
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD AND SYSTEM FOR DETERMINING SYNTHETIC CHANGES OF FACES IN VIDEO | 2021 |
|
RU2774624C1 |
| METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE | 2022 |
|
RU2791415C1 |
| METHOD AND SYSTEM FOR VIDEO SCENES SEGMENTATION | 2022 |
|
RU2783632C1 |
| METHOD AND SYSTEM FOR EVALUATING QUALITY OF CUSTOMER SERVICE BASED ON ANALYSIS OF VIDEO AND AUDIO STREAMS USING MACHINE LEARNING TOOLS | 2018 |
|
RU2703969C1 |
| METHOD AND SYSTEM FOR DETECTING ALARM EVENTS WHEN INTERACTING WITH SELF-SERVICE DEVICE | 2019 |
|
RU2713876C1 |
| METHOD AND SYSTEM FOR ANALYZING VOICE CALLS FOR SOCIAL ENGINEERING DETECTION AND PREVENTION | 2022 |
|
RU2790946C1 |
| METHOD AND SYSTEM FOR ANALYSIS OF VOICE CALLS FOR SOCIAL ENGINEERING DETECTION AND PREVENTION USING VOICE BOT ACTIVATION | 2023 |
|
RU2802533C1 |
| METHOD OF COMPARING FACE OF PERSON BY MEANS OF DIGITAL TWO-DIMENSIONAL FACIAL IMAGE OR FACIAL IMAGE FROM ONE OR MORE STEREO CAMERAS WITH TWO-DIMENSIONAL FACIAL IMAGE FROM DATABASE | 2014 |
|
RU2578806C1 |
| RAPID TWO-LAYER NEURAL NETWORK SYNTHESIS OF REALISTIC IMAGES OF A NEURAL AVATAR BASED ON A SINGLE IMAGE | 2020 |
|
RU2764144C1 |
| MULTI-FRAME TRAINING OF REALISTIC NEURAL MODELS OF SPEAKERS HEADS | 2019 |
|
RU2720361C1 |
