Personal Font Generation via Representative Trace Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pen input methods struggle with producing aesthetically pleasing handwriting due to noise and variability in input devices, and users seek to personalize their text with unique fonts for digital platforms.
Innovation Solution
An apparatus and method that includes a character input unit, character recognition unit, representative trace generation unit, and trace modification unit to receive and modify handwriting inputs by generating a representative trace and combining it with the input trace using weight values, allowing for the creation of personalized fonts based on the user's handwriting style.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a user inputs handwriting through a pen input device, then the user can transfer information using their own handwriting style, but the handwriting trace becomes uneven and noisy due to input device limitations and handwriting variability
Solution Approach 1:
The patent introduces a representative trace as an intermediary between the noisy input trace and the final output. The representative trace captures the essential characteristics of the user's handwriting style while filtering out noise and irregularities. This mediator allows the system to preserve the user's personal style while eliminating the harmful variability in the raw input trace.
Solution Approach 2:
The patent changes the parameter representation of the handwriting trace by extracting key features and representing them in a simplified form. Instead of using the raw coordinate data which contains noise, the system transforms the trace into a representative form that captures essential stylistic parameters while removing unwanted variability.
2Manufacturing precision
If the user writes clearly, then the handwriting trace quality is good, but not all users can write clearly and some users have hand trembling or poor input device sensitivity
Solution Approach 1:
The system performs self-correction by automatically processing the input trace to generate a representative trace. The algorithm independently identifies and corrects noise, irregularities, and inconsistencies in the handwriting trace without requiring the user to rewrite or correct their handwriting. This self-service approach maintains ease of operation while improving trace quality.
Solution Approach 2:
The patent converts the harmful noise and variability in the input trace into beneficial information. By analyzing the variations in the raw handwriting trace, the system extracts meaningful stylistic characteristics that define the user's personal handwriting style, transforming what was previously harmful noise into useful data for personalization.
3Productivity
If the system uses the raw input trace directly, then the process is simple, but the output lacks elegance and user satisfaction
Solution Approach 1:
The patent performs preliminary processing of the input trace by generating a representative trace before final font creation. This preliminary action of extracting essential characteristics and removing noise early in the process simplifies subsequent processing steps while ensuring high-quality output. The representative trace serves as a refined foundation for generating elegant fonts.
Data Source
AI summary
An apparatus and method of generating personal fonts is provided, which can modify a trace of handwriting inputted by a user into an elegant one and generate diverse personal fonts in accordance with user's style of handwriting. The apparatus for generating personal fonts includes a character input unit to receive an input of a character trace from a user, a character recognition unit to recognize a representative character corresponding to an input character from the input character trace, a representative trace generation unit to generate a representative trace expressing a trace of the representative character, and a trace modification unit to modify the trace of the input character by combining a weight value of the generated representative trace with the trace of the input character.


