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

Novel font special effect rendering method

A font and special effect technology, applied in the computer field, can solve problems such as incomplete style rendering and wrong rendering area, and achieve the effect of reducing incomplete rendering style and wrong selection of rendering area

Pending Publication Date: 2019-10-08
NANJING UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of incomplete style rendering and wrong rendering area in the font special effect rendering task, the present invention proposes a method based on the strongest gravity based on semantics, and designs the strongest gravity loss function to replace the pixel-by-pixel loss in the original algorithm and the global loss function

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
  • Novel font special effect rendering method
  • Novel font special effect rendering method
  • Novel font special effect rendering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] This embodiment proposes a font special effect rendering method based on the strongest gravitational force, applies a stylization method to perform special effect migration on the font special effect style, and realizes conversion from a content map to a special effect map. Such as figure 1 As shown, it mainly includes the following steps:

[0048] Step 1: Random initialization to generate image g, that is, a white noise image of randomly selected pixels and used as the input of VGG-19; the full name of VGG is Visual Geometry Group, which belongs to the convolutional network model released by the Department of Science and Engineering of Oxford University, which can be applied to human It has good performance in face recognition, image classification, etc.;

[0049] Step 2: Extract the high-dimensional content feature points of the font image c in the conv4_2 layer of VGG-19, and calculate the strongest gravitational content loss L between the generated image g and the ...

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 relates to a novel font special effect rendering method. The method comprises the following steps of randomly initializing a generated image, that is, randomly selecting a white noise map of pixels and using the white noise map as input of VGG-19; extracting high-dimensional content feature points of a font image in a conv4_2 layer of VGG-19, and calculating the strongest gravitational content loss of a generated image and a font image; extracting high-dimensional style feature points of style images of conv3_2 and conve_4 layers of the VGG-19 and calculating the strongest gravitational content loss of the generated image and the font image; solving a function of strongest gravitational content loss; minimizing value of a total loss function; concluding iteration if the valueconverages or is less than an appointed threshold value; skipping to the step 2 otherwises. The method can reduce the possibility of incomplete rendering styles and wrongful rendering areas during arendering process.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a novel font special effect rendering method. Background technique [0002] Artificial intelligence has become one of the hottest technologies in tech circles in recent years. With the gradual maturity of artificial intelligence technology, deep learning has begun to exert its strength in the field of image processing. In some large-scale image recognition competitions, some algorithms based on deep learning have emerged. Convolutional Neural Network (CNN) is one of the most representative network structures in deep learning technology, which is more efficient and superior than previous image processing methods. The design process of traditional font effects is usually done manually, which consumes a lot of manpower and material resources. There is also a shortcoming of artificially designed word art, the style of a certain font designed cannot be transferred to another font...

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
IPC IPC(8): G06T3/00
CPCG06T3/18Y02D10/00
Inventor 帅仁俊徐泽刘开凯
Owner NANJING UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com