Chinese Character Font Conversion via Stroke Spatial Distribution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Designing new Chinese character fonts is labor-intensive and time-consuming due to the large quantity of characters, necessitating a method for efficient font conversion in images.

Innovation Solution

A method and system that acquire the stroke and spatial distribution information of a Chinese character in an image, using deep learning networks to generate the character in a target font by matching and identifying strokes with standard font information, reducing labor and time through automated font conversion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual design methods are used to create personalized Chinese character fonts, then font customization and personalization can be achieved, but the process becomes labor-intensive and time-consuming

Engineering Contradiction:
Improvefont personalizationVSAvoidfont design efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent uses template matching to copy standard Chinese character fonts and adapt them to personalized styles. By matching strokes against standardized templates, the system can generate customized fonts efficiently without manual redrawing of each character, thus achieving both personalization and high productivity

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system changes parameters of existing font templates (such as stroke width, curvature, spacing) to create personalized fonts. By adjusting these parameters automatically through image processing, the system maintains design versatility while dramatically improving design efficiency

Inventive Principle:
Principle #35Parameter changes

2Productivity

If automated font conversion is implemented using deep learning networks, then conversion timeliness and efficiency are improved, but the complexity of the system increases

Engineering Contradiction:
Improvefont conversion speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the font conversion process into distinct modules: stroke detection, template matching, parameter extraction, and font generation. This segmentation allows each module to be independently optimized and managed, reducing overall system complexity while maintaining high conversion speed through parallel processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces intermediate representations (stroke features, spatial distribution data) that bridge the input image and output font. These intermediaries simplify the transformation process by breaking down the complex conversion into manageable steps, reducing system complexity while improving conversion efficiency

Inventive Principle:
Principle #24Intermediary (Mediator)

3Manufacturing precision

If stroke matching and identification is performed with high precision, then font conversion accuracy is improved, but the processing time increases

Engineering Contradiction:
Improvestroke identification accuracyVSAvoidprocessing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary processing of stroke data before full matching, including preprocessing to extract key features and pre-sorting templates by relevance. This preliminary action reduces the search space for accurate matching, maintaining high precision while minimizing processing time through early elimination of unlikely candidates

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11587343B2Method and system for converting font of Chinese character in image, computer device and medium
Publication Date: 2023.02.21 BOE TECHNOLOGY GROUP CO LTD
  • US11587343B2 patent drawing
  • US11587343B2 patent drawing
  • US11587343B2 patent drawing

AI summary

A method and a system for converting a font of a Chinese character in an image, a computer device and a medium are disclosed. A specific implementation of the method includes: acquiring a stroke of a to-be-converted Chinese character in the image and spatial distribution information of the stroke; and generating a Chinese character in a target font that corresponds to the to-be-converted Chinese character in the image according to the stroke of the to-be-converted Chinese character, the spatial distribution information of the stroke and standard stroke information of the target font, to replace the to-be-converted Chinese character.