FIELD: image processing.
SUBSTANCE: invention relates to image processing, in particular to a method and a system for recognizing user gestures. Method is carried out by at least one computing device and comprises steps of: obtaining at least two user images for a given time interval; performing user hand area selection on each obtained image using a first machine learning model based on a neural network, trained to recognize user hand areas, gesture class is recognized, on each obtained image using a second machine learning model based on a neural network trained to recognize static gestures, a gesture sequence is formed, a gesture type is determined from the gesture sequence, and a user gesture is recognized.
EFFECT: high accuracy of recognizing user gestures.
12 cl, 6 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD AND SYSTEM FOR SEARCHING GRAPHIC IMAGES | 2022 |
|
RU2807639C1 |
| METHOD FOR ISOLATING AND CLASSIFYING BLOOD CELL TYPES USING DEEP CONVOLUTION NEURAL NETWORKS | 2019 |
|
RU2732895C1 |
| DETECTING AND IDENTIFYING OBJECTS ON IMAGES | 2020 |
|
RU2726185C1 |
| METHOD FOR IMAGE GENERATION BASED ON USER PREFERENCE ANALYSIS | 2023 |
|
RU2812413C1 |
| REPRODUCING AUGMENTATION OF IMAGE DATA | 2018 |
|
RU2716322C2 |
| METHOD OF TEXT GENERATION BASED ON MACHINE LEARNING | 2023 |
|
RU2821835C1 |
| METHOD OF RECOGNIZING ASSIGNED BOTTOM OBJECT | 2022 |
|
RU2818184C1 |
| METHOD AND SYSTEM FOR IDENTIFYING NEW GROWTHS ON X-RAY IMAGES | 2020 |
|
RU2734575C1 |
| METHOD OF MULTIMODAL CONTACTLESS CONTROL OF MOBILE INFORMATION ROBOT | 2020 |
|
RU2737231C1 |
| IMAGE RECOGNITION SYSTEM: BEORG SMART VISION | 2020 |
|
RU2777354C2 |
