Touchscreen Keyboard Finger Differentiation via Image Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Touch typing on mobile computing devices is inefficient due to the need for physical keyboards, which occupy valuable space, and existing touchscreen input methods lack precision and usability.
Innovation Solution
A touchscreen system that generates finger contact images using technologies like surface acoustic wave, capacitive, infrared, and optical sensing, classifies these images to determine finger probabilities, and converts them into character probabilities for accurate text input, allowing for improved typing precision and usability without a physical keyboard.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a physical keyboard is used for touch typing, then typing precision and speed are improved, but device space is consumed
Solution Approach 1:
The patent creates a virtual copy of the physical keyboard as a touchscreen display. The system captures images of finger contacts on the touchscreen and classifies them to determine which virtual key was pressed, replicating the functionality of a physical keyboard without occupying physical space. This allows users to maintain typing precision and speed while eliminating the need for a physical keyboard hardware component.
2Area of stationary object
If a touchscreen without physical keyboard is used, then device space is saved, but input precision deteriorates
Solution Approach 1:
The patent replaces the mechanical detection of physical key presses with an optical imaging system. The touchscreen captures images of finger contacts and uses image classification algorithms to determine input intent, substituting mechanical sensing with optical sensing and computational analysis. This enables precise input recognition without physical keyboard mechanics.
Solution Approach 2:
The patent introduces an intermediary processing layer between the touchscreen contact and the input output. The system captures the contact image, classifies it to determine which key was pressed, and then executes the corresponding output. This intermediary classification step ensures accurate input recognition by mediating between the physical touch and the digital input signal.
3Measurement precision
If finger contact images are classified to determine finger probabilities, then input accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent segments the finger contact image into distinct regions corresponding to different fingers. By dividing the contact area into segments and analyzing each segment's characteristics, the system can identify which specific finger made the contact and determine the probability distribution across possible fingers. This segmentation approach improves identification accuracy while managing processing complexity through structured analysis.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the precision and speed of text input on touchscreens by accurately identifying intended characters and executing outputs, thereby improving the overall usability of mobile computing devices.
Implementation Method 1
The image is generated using one or more technologies including surface acoustic wave sensing
Implementation Method 2
The image is generated using one or more technologies including capacitive sensing
Implementation Method 3
The image is generated using one or more technologies including infrared sensing
Implementation Method 4
The image is generated using one or more technologies including optical sensing
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Implementations of the present disclosure include actions of displaying a plurality of keys on a touchscreen of a computing device, receiving user input to the touchscreen, the user input including a contact with the touchscreen, in response to receiving the user input, determining spatial information associated with the contact and generating an image of the contact, determining an output based on the image and the spatial information, and executing the output.