Gesture Recognition Using Concentric Circle Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gesture recognition methods face challenges in reducing data processing complexity and noise-to-signal ratio, leading to inefficiencies in human-computer interaction.
Innovation Solution
A method involving the capture of hand images, calculation of a geometric center, deployment of concentric circles, and determination of feature vectors based on intersection points to simplify gesture recognition, using a processor and storage device to compare with standard gestures and vectors for accurate identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image pre-processing methods (image thresholding and background eliminating) are used to collect and analyze hand position and gesture information, then gesture recognition can be achieved, but the data processing complexity increases and the noise-to-signal ratio becomes relatively high
Solution Approach 1:
The patent segments the hand image processing into distinct concentric circular regions centered at the hand's geometric center. By dividing the image space into multiple concentric circles with different radii, the method analyzes intersection points of hand contours with these circles to extract gesture features. This segmentation approach simplifies the processing complexity while maintaining recognition accuracy by focusing on radial distance patterns rather than full image pre-processing.
2Measurement precision
If traditional image pre-processing methods are used to collect and analyze gesture information, then gesture recognition can be performed, but the processing time increases, reducing the instantaneity of human-computer interaction
Solution Approach 1:
The patent extracts only the essential features needed for gesture recognition by calculating the geometric center of the hand and analyzing the intersection points of hand contours with concentric circles. This extraction method bypasses time-consuming traditional pre-processing steps like image thresholding and background elimination, significantly reducing processing time while maintaining the ability to accurately recognize gestures through the extracted radial distance features.
Data Source
AI summary
A method for recognizing a gesture adopted by an electronic device to recognize a gesture of at least a hand. In the method, a hand image of the hand is captured and the hand image includes a hand region. A geometric center of the hand region is calculated. At least a concentric circle is disposed on the hand region with the geometric center as the center of the concentric circles. A number of intersection points of each concentric circle and the hand region is calculated respectively to determine a feature vector of the gesture. According to the feature vector, a hand recognition is performed to recognize the gesture of the hand.