Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Soft Pen Chinese Character Transformation Method Based on Writing Feature Editing

A Chinese character editing technology, applied in the field of soft pen Chinese character writing feature editing, can solve problems such as the difficulty in expressing the soft pen Chinese character calligraphy characteristics, and the inability of image processing technology to effectively describe the soft pen Chinese character writing characteristics, etc.

Active Publication Date: 2018-12-11
BEIHANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is in order to overcome above-mentioned deficiency, solves the shortcoming that existing image processing technology can't effectively characterize soft pen Chinese character writing feature, solves the problem that soft pen Chinese character calligraphy characteristic expression is difficult, realizes the style transformation of soft pen Chinese character

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Soft Pen Chinese Character Transformation Method Based on Writing Feature Editing
  • A Soft Pen Chinese Character Transformation Method Based on Writing Feature Editing
  • A Soft Pen Chinese Character Transformation Method Based on Writing Feature Editing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Such as figure 1 Shown, a kind of soft pen Chinese character transformation method based on writing feature editing of the present invention adopts the following steps:

[0028] Step 1. Image preprocessing:

[0029] (1) Median filtering. For each pixel point in the image, take the value of the pixel point in its adjacent area, and sort it according to the degree of difficulty. Set the difficulty value of the point to the gray median value of the adjacent area. Through median filtering, isolated noise pixels can be better removed.

[0030] (2) Binarization. The local optimal threshold is calculated by iteratively calculating the midpoint of the average value of the local area. If the pixel value is greater than the optimal threshold, the pixel color is set to 1, otherwise the pixel color is set to 0.

[0031] (3) The contour is smooth. This step mainly deals with the punctures and holes in the outline turnover of Chinese characters. Use the mask matrix to judge th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a soft-pen Chinese character transformation method based on writing feature editing. This method can be used to extract the writing features of Chinese characters in inscriptions or soft-pen copybooks and to generate soft-pen Chinese characters with customized writing features. First, appropriate noise reduction algorithms, binary operations, and contour smoothing methods are selected to preprocess the original inscription image to enhance its contrast relative to the background. And through segmentation and normalization operations, the positioning of individual Chinese characters is achieved. Secondly, a stroke extraction optimization algorithm based on contour triangulation is implemented, and a triangular grid of Chinese characters is constructed based on preprocessing to identify stroke segments. At the same time, stroke sets are divided according to writing characteristics. Finally, a deformed Chinese character generation algorithm based on stroke features is proposed. Combining the customized feature matrix consisting of stroke centerline, width, contraction speed, curvature, etc. with the input deformation requirements, the feature matrix is ​​modified to generate Chinese character images with different writing characteristics.

Description

technical field [0001] The invention belongs to the fields of computer image processing and computer vision. Specifically, it is a method for editing soft-pen Chinese characters, which can be used for style transformation of ancient soft-pen Chinese characters such as inscriptions and copybooks. Background technique [0002] The culture of a country can largely be revealed from its text. Chinese characters are a great invention of our country, not only because they are the language carrier of the nation, but also because of the artistic value of Chinese characters. After thousands of years of accumulation and precipitation, the brush calligraphy art in our country has formed many different styles of writing art forms such as Yan style, official script, small seal script, and cursive script. The difference in objective conditions such as the spatial structure of strokes, the thickness of brush and ink, and the trend of brush movement, shows a completely different aesthetic ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/00
CPCG06T3/04
Inventor 齐越张石磊谢招楷杨光郝世昱李巧
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products