Calligraphy restoration method based on crowdsourcing
A restoration method and calligraphy technology, applied in image data processing, instruments, character and pattern recognition, etc., can solve the problems of relying on real data, loss of calligraphy font characteristics, loss of calligraphy font details, etc., to achieve high restoration efficiency and improve construction Model and operation efficiency, and the effect of improving repair efficiency
Pending Publication Date: 2022-04-12
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Compared with manual restoration, automated restoration is more efficient and does not require professional skills, but the restoration results often lose the characteristics of calligraphy fonts, such as "dry pen", "flying white", etc.
In addition, automatic restoration, especially the restoration method based on deep learning, relies on a large amount of real data, and is not suitable for restoring the fonts of calligraphers with few surviving works
[0006] Therefore, it is urgent to develop a repair method that can avoid long time-consuming, the repaired font loses the details of calligraphy fonts, and the repair process relies on a large amount of real data.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0059] The present invention provides a calligraphy restoration method based on crowdsourcing, such as figure 1 As shown, the specific steps are: perform calligraphy font segmentation on the calligraphy image to be repaired. Due to the complexity of running script calligraphy rules, it is difficult for automatic methods to accurately identify fonts for segmentation. The present invention uses human-computer cooperation, such as figure 2 As shown, the image denoising algorithm of Guide-filter is used to denoise the first calligraphy image to be repaired, and then the third calligraphy image to be repaired is obtained through expert repair, and the binarization threshold is determined by the OTSU algorithm. Based on the binarization threshold, Binarize the third calligraphic image to be repaired to obtain the second calligraphic image to be repaired, segment the second calligraphic image to be repaired using a connected area detection algorithm, and obtain the first complete str...
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
Login to View More Abstract
The invention discloses a crowdsourcing-based calligraphy restoration method, which comprises the following steps of: separating complete-structure fonts and incomplete-structure fonts from a to-be-restored calligraphy graph, and restoring the incomplete-structure fonts by utilizing an expert crowdsourcing method to obtain a restored font set, screening repaired fonts similar to the convex hull contour of the incomplete structure through a convex hull contour feature module to obtain a second repaired font set, and screening a third repaired font set similar to the stroke feature of the complete structure from the second repaired font set through a stroke feature module, and screening a final repair font close to the incomplete structure key position area from the three-repair font set through a font structure distribution feature module to complete repair of the incomplete structure font. According to the method, less real data is needed, the repairing efficiency is high, and the fonts repaired through the method have good detail features of the calligraphy fonts.
Description
technical field [0001] The invention belongs to the technical field of text image restoration, and in particular relates to a calligraphy restoration method based on crowdsourcing. Background technique [0002] Calligraphy is considered a form of expression of great artistic value in cultures around the world. In the 5,000-year history of Chinese civilization, culture is an indispensable part of communication. Our country's history and culture have a long history, and multi-ethnic cultures are integrated with each other. There was once a glorious moment when a hundred schools of thought contended and a hundred flowers bloomed. In the long years, our Among the historical relics discovered today, there are many incomplete and damaged situations. As an important form of cultural transmission, calligraphy characters protect historical relics, protect the characters in incomplete historical relics, and restore the characters in incomplete historical relics to their original Tha...
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
Login to View More IPC IPC(8): G06V30/244G06T5/00
Inventor 杨昌源尤伟涛韩开鑫胡子衿孙凌云
Owner ZHEJIANG UNIV