Gesture recognition method based on fused skin color region segmentation and machine learning algorithm and application thereof
A technology of area segmentation and machine learning, applied in the field of gesture recognition, can solve problems such as the inability to rule out the interference of human faces, lighting, skin color, etc., high computational complexity, and unfavorable human-computer interaction, so as to achieve natural and improved human-computer interaction. Interactive mode, improve the effect of interactive mode
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] see figure 1 with figure 2 The present invention discloses a gesture recognition method and its application based on the fusion of skin color region segmentation and machine learning algorithm, comprising the following steps:
[0035] (1) After collecting and preprocessing the gesture image, use the Otsu adaptive threshold algorithm to segment the skin color area in the YCbCr skin color space;
[0036] (2) Gestures are segmented by setting gesture area judgment conditions after segmentation, and the Hu moment feature and fingertip number are extracted as feature vectors on the gesture contour;
[0037] (3) Then use the SVM classifier to classify and recognize the 6 commonly used static gestures;
[0038] (4) Based on the Webots simulation environment, the gesture recognition results are converted into instructions to realize the real-time control simulation of the gesture on the robot NAO.
[0039] The present invention uses the algorithm developed under the Webots ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com