Touch Screen Finger Recognition via Three-Descriptor Space
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing touch screen technologies struggle to accurately distinguish between finger touches and unintentional contacts, activating functionalities prematurely and failing to effectively recognize the presence and number of fingers, especially when fingers are close or interacting in complex patterns.
Innovation Solution
A supervised classification system using a three-descriptor space invariant to translation and rotation, which processes touch map data to differentiate between finger and non-finger touches by transforming raw data into a new space with descriptors such as the number of local peaks, maximum absorbed pixels, and delta values, enabling accurate discrimination of multiple fingers and rejecting unintentional touches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional touch detection methods are used, then the system responds to any contact on the screen, but it cannot distinguish between intentional finger touches and unintentional contacts, leading to false activations
Solution Approach 1:
The touch detection system segments the touch contact into multiple analysis dimensions: shape characteristics, size parameters, pressure distribution, and contact duration. By dividing the touch event into these separable features, the system can analyze each aspect independently and combine them for accurate finger identification, effectively distinguishing intentional touches from unintentional contacts.
Solution Approach 2:
The patent introduces additional analytical dimensions beyond simple contact detection, including spatial distribution of touch pressure, geometric shape of the contact area, and temporal patterns of touch application. This multi-dimensional approach transforms the detection problem from a single threshold-based decision into a comprehensive pattern recognition task, significantly improving accuracy.
2Measurement precision
If the system uses simple contact detection, then the processing is fast and simple, but it fails to recognize the presence and number of multiple fingers touching the screen simultaneously
Solution Approach 1:
The system segments multi-touch events into individual finger contacts by identifying separate contact regions and their respective characteristics. Each finger touch is analyzed as an independent entity with its own shape, size, and position parameters, allowing the system to accurately count and track multiple fingers simultaneously while maintaining manageable processing complexity.
Solution Approach 2:
The patent applies partial analysis to each touch contact, focusing on the most discriminative features (such as contact area shape and pressure distribution) rather than analyzing every possible parameter. This selective approach enables multi-finger recognition without requiring excessively complex processing for each individual contact point.
3Speed
If the touch detection is sensitive to approach, then fingers approaching the screen can activate functions, but this causes premature activation before actual touch intent is confirmed
Solution Approach 1:
The system performs preliminary analysis of approaching contacts by evaluating shape characteristics and pressure distribution patterns before full activation. This preliminary action allows the system to prepare for potential touch events while maintaining the ability to confirm or reject activation based on whether the contact pattern matches intentional finger touch profiles, preventing premature activation.
Solution Approach 2:
The patent implements feedback mechanisms that continuously monitor contact development as the finger approaches and makes contact with the screen. The system adjusts its response based on real-time feedback from pressure sensors, confirming touch intent through progressive validation of contact characteristics rather than triggering immediately on initial contact.
Data Source
AI summary
An embodiment of a method of recognizing finger detection data in a detection data map produced by a touch screen includes converting the data from the x, y, z space into a three-descriptor space including: a first coordinate representative of the number of intensity peaks in the map, a second coordinate representative of the number of nodes (i.e., pixels) absorbed under one or more of the intensity peaks. A third coordinate may be selected as the angular coefficient or slope of a piecewise-linear approximating function passing through points having the numbers of nodes absorbed under the intensity peaks ordered in decreasing order over said intensity peaks, which permits singling out finger data with respect to non-finger data over the whole of the touch screen. The third coordinate may be also selected as an adjacency value representative of the extent the intensity peaks are adjacent to one another, which permits singling out finger data produced over a portion of the touch screen with respect to non-finger data produced over another portion of the touch screen.