Eye-Typing Term Recognition via Gaze Sample Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional eye-typing methods require prolonged fixation on each key, leading to user fatigue and inefficiency, especially for users without physical or on-screen keyboards, or those with medical conditions that hinder traditional typing.
Innovation Solution
Eye-typing method that processes a plurality of gaze samples to determine intended terms by utilizing pattern recognition and fuzzy matching, allowing users to quickly gaze over an on-screen keyboard, with sensors collecting gaze data to identify likely words and phrases, enabling efficient text entry without prolonged key fixation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional eye-typing methods are used with prolonged fixation on each key, then text input can be achieved without physical keyboards, but user fatigue increases and typing efficiency decreases
Solution Approach 1:
The patent segments the text input process into multiple phases: initialization phase where the user gazes at a trigger key to start typing, data collection phase where gaze samples are gathered as the user looks across the keyboard, and processing phase where the gaze data is analyzed to determine the typed term. This segmentation allows the system to collect multiple gaze samples without requiring prolonged fixation on each individual key, thereby maintaining typing efficiency while enabling text input without physical keyboards.
Solution Approach 2:
The patent implements preliminary action by requiring the user to gaze at a trigger key before the actual typing process begins. This preliminary action initializes the eye-typing session and sets the system in the correct state for data collection. By performing this preparatory step, the system can then efficiently collect gaze samples during the typing process without requiring prolonged fixation, thus resolving the contradiction between enabling text input and maintaining typing efficiency.
2Measurement precision
If conventional eye-typing methods require prolonged fixation on each key, then accurate term recognition can be achieved, but user fatigue increases
Solution Approach 1:
The patent implements continuity of useful action by collecting multiple gaze samples continuously as the user gazes across the keyboard during the typing process, rather than requiring discrete prolonged fixations on each key. The system continuously monitors gaze position and accumulates data points throughout the typing action. This continuous data collection maintains term recognition accuracy by gathering sufficient information about the user's intended input while avoiding the fatigue associated with prolonged fixation on individual keys.
Solution Approach 2:
The patent applies partial action by collecting a plurality of gaze samples that may include more data points than strictly necessary for basic recognition. The system gathers excessive gaze data during the typing process, then processes this data to determine the most likely term. This approach ensures accurate term recognition by having more data to work with, while the actual processing time remains short because the user doesn't need to maintain prolonged fixation - they can gaze naturally across the keyboard.
3Productivity
If multiple gaze samples are collected and processed to determine likely terms, then typing efficiency improves, but system complexity increases
Solution Approach 1:
The patent implements self-service by having the system automatically process the collected gaze samples without requiring additional user input or intervention. Once the user completes the typing action and gazes at the trigger key to initiate processing, the system autonomously analyzes the plurality of gaze samples, determines the likely terms, and presents the results. This self-service approach improves typing efficiency by automating the complex data processing tasks, thereby managing system complexity without requiring the user to understand or manage the underlying processing complexity.
4Ease of operation
If eye-typing allows quick gazing over the keyboard, then user fatigue decreases, but term recognition accuracy may be compromised
Solution Approach 1:
The patent merges multiple gaze samples collected during the typing process into a unified term recognition decision. Instead of requiring accurate identification from a single brief gaze, the system combines information from multiple gaze samples taken at different time points as the user gazes across the keyboard. This merging of data compensates for the reduced precision of individual brief gazes, maintaining term recognition accuracy while allowing the user to gaze quickly without prolonged fixation, thereby reducing user fatigue.
Data Source
AI summary
Various embodiments related to entering text into a computing device via eye-typing are disclosed. For example, one embodiment provides a method that includes receiving a data set including a plurality of gaze samples, each gaze sample including a gaze location and a corresponding point in time. The method further comprises processing the plurality of gaze samples to determine one or more likely terms represented by the data set.