Multi-finger detection using ellipse fitting and histogram analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional touch signal processing techniques for portable devices with touch sensors and touch-screen displays struggle to accurately track and interpret multi-finger gestures due to reliance on temporal domain prediction or boundary noise, leading to unreliable gesture recognition and tracking.
Innovation Solution
The implementation of a multi-finger detection and component resolution method using a statistical framework that analyzes single-frame data to identify individual contacts within a connected component on a touch-screen display, employing an ellipse model and histogram functions to separate finger inputs, thereby eliminating timing dependency and boundary noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If temporal domain prediction is used for multi-finger gesture detection, then gesture tracking can be performed, but the detection reliability deteriorates due to finger touch timing dependency
Solution Approach 1:
The patent replaces temporal domain prediction (time-based mechanical system) with spatial domain analysis using histogram functions and ellipse fitting on single-frame sensor data. This substitution eliminates timing dependency while maintaining gesture tracking capability, directly resolving the contradiction between productivity and reliability.
2Difficulty of detecting and measuring
If component contour determination is used for finger separation, then individual contacts can be identified, but measurement precision deteriorates due to boundary noise in touch input sensor data
Solution Approach 1:
The patent extracts the essential geometric features (ellipse parameters, histogram distribution) from the noisy component contour data. By projecting sensor data elements onto the ellipse axes and analyzing the histogram function, the method separates individual contacts based on spatial distribution rather than noisy boundaries, thereby improving measurement precision while maintaining detection capability.
Solution Approach 2:
The patent transforms the problem from boundary-based detection to parameter-based detection by fitting an ellipse to the connected component and analyzing the histogram function of projected data. This parameter transformation (from contour coordinates to ellipse parameters and histogram bins) filters out boundary noise and improves contact detection precision.
3Speed
If conventional touch signal processing is used, then processing speed can be maintained, but gesture recognition accuracy deteriorates for multi-finger gestures
Solution Approach 1:
The patent performs preliminary action by fitting an ellipse to the connected component and projecting data onto the ellipse axes before histogram analysis. This pre-processing step organizes the spatial data in a way that facilitates rapid and accurate finger separation, maintaining processing speed while improving gesture recognition accuracy through better spatial utilization.
Data Source
AI summary
In embodiments of multi-finger detection and component resolution, touch input sensor data is recognized as a component of a multi-finger gesture on a touch-screen display. An ellipse is determined that approximately encompasses the component, and the ellipse has a primary axis and a secondary axis that are orthogonal. A distribution is then generated that projects sensor data elements from the primary axis based on detected intensity of the touch input sensor data. A histogram function can then be generated based on the distribution, where the histogram function indicates individual contacts of the component and separation of the individual contacts.