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

Chinese ink painting style rendering technology of digital image

An ink and style technology, applied in the application field of convolutional neural network, can solve the problems of difficult to master artistic conception creation and inability to learn picture style, and achieve the effect of satisfying aesthetic needs, novelty and high quality of works.

Inactive Publication Date: 2018-07-20
NANJING UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, Western oil paintings are appreciated and accepted by more and more Chinese people. The traditional Chinese ink painting is gradually declining. Compared with the realistic style of oil painting, the artistic conception creation of ink painting is difficult for ordinary people to grasp.
Some existing image processing software can only simply and mechanically change the background color and background image of the picture, and cannot learn the style of the picture like a human, including detailed features such as texture and strokes

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
  • Chinese ink painting style rendering technology of digital image
  • Chinese ink painting style rendering technology of digital image
  • Chinese ink painting style rendering technology of digital image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0014] refer to figure 2 , image 3 , build the overall software and hardware operating environment, the operation of the hardware environment requires the support of high-performance GPU, equipped with NVIDIA parallel computing platform CUDA8.0, and related operation library Cudnn5.0, so that the GPU has large-scale data acceleration computing capabilities. The software runs based on the Linux system, uses Python as the development language, Protocol Buffer is responsible for data exchange, Tensorflow is used as the core framework of deep learning, Numpy and Scipy provide specific operation functions for matrix operations and images.

[0015] refer to Figure 4 , do preprocessing for the ink picture set, select the main features of pictures of...

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 Chinese ink painting style rendering technology of a digital image based on deep learning and convolutional neural network. Present image processing software can change the background color and scene of a picture simply, and provides only a few of fixed simple styles for selection. According to the method of the invention, a Chinese ink painting picture set is used to train a convolutional neural network model, the trained model is used to process Chinese ink painting pictures, a Gramian matrix is used to quantify characteristics of the Chinese ink painting pictures,a reverse spreading algorithm is used, loss of a gradient decrease algorithm is reduced by iterative training of a computer, and characteristics of Chinese ink paintings are extracted. The style of the Chinese ink painting is rendered into a random picture, and an exquisite Chinese ink painting is generated.

Description

technical field [0001] The invention relates to the application of digital image processing and deep learning in image, and the application of convolutional neural network. Background technique [0002] In March 2016, Google's artificial intelligence Alpha Go defeated the human Go champion, marking that artificial intelligence technology represented by machine learning and deep learning has entered a new stage of development. With the development of artificial intelligence, artistic creation, which has long been a unique talent of human beings, is slowly being mastered by computers and capable of simple artistic creation. [0003] At present, Western oil paintings are appreciated and accepted by more and more Chinese people. The traditional Chinese ink painting is gradually declining. Compared with the realistic style of oil painting, the artistic conception creation of ink painting is difficult for ordinary people to grasp. Some existing image processing software can only ...

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 Applications(China)
IPC IPC(8): G06T15/00G06N3/04G06N3/08
CPCG06T15/005G06N3/08G06N3/045
Inventor 李盛超陈颖葛云
Owner NANJING 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

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