Gesture Recognition Using Neural Networks on Resistive Touch Panels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gesture recognition systems on touch panels, particularly those using resistive technology, are limited to single-touch detection and struggle to recognize complex gestures or simulate multi-touch actions, lacking the capability to distinguish between various motions like lines, circles, and complex gestures.
Innovation Solution
A computer-implemented method and apparatus utilizing a neural network to record and calculate angles as a user moves their finger on a screen, comparing these angles with ideal angles to recognize gestures, and allowing for user-defined actions, enabling simulation of multi-touch actions on resistive overlays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If resistive touch panel overlays are used, then device cost is reduced, but gesture recognition capability is limited to single-touch detection
Solution Approach 1:
The system transforms the touch panel's output parameters from simple touch coordinates to calculated angle data between sequential touch points. By changing how touch information is processed (from direct coordinate reading to angle calculation), the system enables complex gesture recognition on resistive panels without requiring hardware upgrades to capacitive technology.
Solution Approach 2:
The patent introduces an intermediary processing layer that calculates angles between sequential touch points. This intermediary computation layer acts as a mediator between the simple resistive touch input and complex gesture recognition output, enabling multi-touch simulation through mathematical transformation of single-touch data sequences.
2Adaptability or versatility
If capacitive technology is used, then multiple touch points can be detected, but device cost increases
Solution Approach 1:
The system creates a computational copy of multi-touch functionality through angle-based gesture recognition. Instead of requiring physical multi-touch detection hardware, the patent replicates multi-touch capabilities by analyzing sequences of single-touch points and calculating angles between them, effectively copying the functional behavior of capacitive multi-touch systems.
Solution Approach 2:
The patent replaces the physical/mechanical multi-touch detection mechanism (capacitive sensing) with a computational/mathematical system. By substituting hardware complexity with software-based angle calculation algorithms, the system achieves multi-touch simulation without the associated cost and complexity of capacitive technology.
3Device complexity
If simple touch detection is used, then device complexity is reduced, but ability to recognize complex gestures is limited
Solution Approach 1:
The patent segments the gesture recognition process into distinct computational steps: recording initial touch point, recording subsequent touch points, calculating angles between sequential points, and comparing angle sets against ideal gestures. This segmentation of the recognition process enables complex gesture analysis through a series of simple, manageable computational operations.
Solution Approach 2:
The system adds an angular dimension to the basic touch coordinate data. By calculating angles between sequential touch points and comparing sets of angles against ideal gesture patterns, the patent transforms simple 2D coordinate detection into sophisticated gesture recognition capability, adding a new dimension of analysis to the touch interaction.
Data Source
AI summary
An apparatus, method, and a computer program is provided for gesture recognition using neural networks. An initial point is recorded when a user presses a finger on a screen. Subsequent points are recorded and an angle is calculated from point to point as the user periodically moves the finger. A set of the calculated angles are compared with an ideal angle in order to recognize the gesture.