Keyboard Gesture Recognition Using Key Position Reference

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing keyboard gesture recognition systems often incorrectly determine gestures due to lack of reference to key positions on a physical keyboard, leading to erroneous instructions.

Innovation Solution

A method and computer program product that utilize a physical keyboard with sensors to convert operating position images into data, recognizing gestures by comparing detected values with defined conditions, and executing corresponding instructions based on key positions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If a camera is used to capture gestures above the keyboard without referencing key positions, then the gesture operation range is expanded, but the accuracy of gesture recognition deteriorates

Engineering Contradiction:
Improvegesture operation rangeVSAvoidgesture recognition accuracy
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent introduces key positions on the physical keyboard as an intermediary reference framework between the camera and the gesture recognition system. The processor maps captured gesture coordinates to the keyboard layout, using key positions as a mediator to translate arbitrary spatial gestures into meaningful keyboard-based commands. This resolves the contradiction by maintaining the expanded camera capture area while improving recognition accuracy through the reference framework.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms the gesture recognition approach by changing the reference parameter from absolute camera coordinates to keyboard-relative coordinates. By mapping gesture positions to key positions and using the keyboard layout as a reference framework, the system converts spatial coordinates into meaningful gesture instructions. This parameter transformation enables accurate gesture recognition regardless of the camera's capture area.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If key positions are used as a reference for gesture recognition, then the accuracy of gesture determination is improved, but the device complexity increases

Engineering Contradiction:
Improvegesture determination accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the existing physical keyboard serve a dual function: both as a traditional input device for typing and as a reference framework for gesture recognition. The keyboard's key positions are reused as spatial references for the camera-based gesture system, eliminating the need for separate reference markers or additional hardware. This multi-functionality approach improves gesture determination accuracy without significantly increasing device complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses the keyboard's own key positions to serve the gesture recognition function. Instead of requiring external reference objects or complex calibration procedures, the keyboard automatically provides its key layout as the reference framework. The processor leverages the existing keyboard structure to enable accurate gesture mapping, allowing the system to self-configure without additional complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10365726B2Keyboard gesture instruction generating method and computer program product and non-transitory computer readable storage medium thereof
Publication Date: 2019.07.30 MITAKE INFORMATION
  • US10365726B2 patent drawing
  • US10365726B2 patent drawing
  • US10365726B2 patent drawing

AI summary

A keyboard gesture instruction generating method includes: loading an instruction condition definition table, where the instruction condition definition table includes a plurality of gesture instructions, and each gesture instruction includes a plurality of instruction conditions, and each instruction condition has a corresponding defined value; reading an operating position image obtained by a sensor; converting the operating position image into an operating position data, where the operating position data includes relative position data of keys which are referenced; recognizing a gesture event according to multiple sets of the successive operating position data; obtaining a plurality of detected values of the gesture event and comparing the detected values with these defined values; if these detected values match with the defined values of all the instruction conditions of one of the gesture instructions, stopping tracking of the gesture event; and executing the matching gesture instruction.