Calligraphy evaluation method, calligraphy evaluation device and electronic equipment

An evaluation method and calligraphy technology, applied in the field of image processing, can solve problems such as low efficiency and poor accuracy, and achieve the effect of automatic evaluation of accurate calligraphy

Active Publication Date: 2020-09-01
BEIJING HUAWENZHONGHE TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, for the former, the method of expert review is accurate and reliable, but the efficiency is not high; for the latter, the review method based on the comparison of lattice approximation, due to the writing style problems of calligraphy, etc. , the accuracy of this method is relatively poor

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
  • Calligraphy evaluation method, calligraphy evaluation device and electronic equipment
  • Calligraphy evaluation method, calligraphy evaluation device and electronic equipment
  • Calligraphy evaluation method, calligraphy evaluation device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] The following takes the copying scene as an example to describe. Among them, the original material that the writer wants to copy is called a "template", and the source of the template is generally a digital rubbing or a picture of a single character written by a famous artist. The individual characters in the template are the example characters mentioned above. The content written by the writer is called "work", that is, the current calligraphy work mentioned above.

[0090] After the writer completes the copying, the image of his work can be captured as a digital work by means of a video camera or camera or scanning.

[0091] Then, a geometric correction (for example, keystone correction may be used) may be performed on the digitized work to make it free from geometric distortion.

[0092] The digitized work can then be reduced or enlarged so that it is the same size as the template.

[0093] Then, the digitized work can be binarized, that is, converted into a black...

Embodiment 2

[0107] Take the copying scene as an example to describe. The collection and preprocessing of works are completed in the same process as in preferred embodiment 1.

[0108] In addition, the training process of the neural network is completed in advance, and the training process can adopt the following steps 2.1-2.5:

[0109] 2.1 Accumulate single-character materials (i.e., example character images) as training samples, and collect as many example character images of various styles and styles as possible, such as example characters on inscriptions and example characters from contemporary calligraphers.

[0110] 2.2 Example word preprocessing. Trim all the example word images into black characters on a white background, and store them in a uniform size.

[0111]2.3 Each example word is scored by experts. The better the written example, the higher the score.

[0112] 2.4 Build a neural network. Train examples and scores. For example, CNN convolutional neural network is selec...

Embodiment 3

[0136] Take the copying scene as an example to describe. The collection and preprocessing of works are completed in the same process as in preferred embodiments 1 and 2.

[0137] Using a process similar to that of the preferred embodiment 1 to obtain the area score of each single-character image in the work as the first type of score.

[0138] Adopt similar processing as preferred embodiment 2 to obtain the artificial intelligence score of each single character image in the work, as the second type of score.

[0139] Through weighted calculation, the weighted average value (or weighted sum) of the first-type score and the second-type score of each single-character image is obtained as the score of each single-character image. Wherein, the weights of the first type of scoring and the second type of scoring are both 1, for example.

[0140] Through weighted calculation, the weighted average (or weighted sum) of the ratings of all single-character images in the work is obtained...

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 present disclosure provides a calligraphy evaluation method, a calligraphy evaluation apparatus, and electronic equipment. The calligraphy evaluation method comprises: obtaining a plurality of single-word images corresponding to a current calligraphic work; ranking the plurality of single-word images; and calculating a total score of the current calligraphic work according to at least scores of the plurality of single-word images. According to the calligraphy evaluation method, the calligraphy evaluation apparatus, and the electronic equipment provided by the present disclosure, calligraphy automatic evaluation can be efficiently and accurately performed, and the problem that the prior art cannot take both efficiency and accuracy into consideration is solved.

Description

technical field [0001] The disclosure relates to the field of image processing, and in particular to a calligraphy evaluation method, a calligraphy evaluation device and electronic equipment. Background technique [0002] At present, for the evaluation of the level of calligraphy learners' works, calligraphy experts usually manually review and evaluate their works. In addition, there are still some that use computer automatic review, and the general method is to compare the dot matrix similarity with the standard word. The higher the dot matrix similarity, the higher the score. [0003] However, for the former, the method of expert review is accurate and reliable, but the efficiency is not high; for the latter, the review method based on the comparison of lattice approximation, due to the writing style problems of calligraphy, etc. , but the accuracy of this method is relatively poor. Contents of the invention [0004] A brief summary of the present disclosure is given b...

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): G06K9/62
Inventor 向大凤
Owner BEIJING HUAWENZHONGHE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap