An image style migration and simulation method for gourd pyrography

An image and pyrography technology, which is applied in the image style transfer and simulation field of gourd pyrography, can solve the problems of generality and flexibility limitations, and achieve high ornamental, optimistic simulation effect and realistic effect

Pending Publication Date: 2019-05-03
YUNNAN UNIV
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this stage, based on NPR technology, it can simulate various styles of pictures such as Chinese calligraphy, sketch painting, pencil drawing and traditional pyrography, but the source images are basically painting images instead of ordinary photos, and manual selection control is required when generating gourd pyrography Points are deformed, therefore, the versatility and flexibility are limited

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
  • An image style migration and simulation method for gourd pyrography
  • An image style migration and simulation method for gourd pyrography
  • An image style migration and simulation method for gourd pyrography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The implementation of the present invention will be described in detail below in conjunction with the examples and drawings, so as to fully understand and implement the implementation process of how the present invention uses technical means to solve technical problems and achieve technical effects.

[0023] In recent years, deep neural networks (DNNs) have continued to develop in practical applications, especially breakthroughs have been made in the field of image processing. The implementation method in the present invention is proposed under this trend. This method firstly performs semantic segmentation on the target image, and then obtains an image mask; then transfers the style features of pyrography, so that the target image has both the style of pyrography and retains its content information, and makes the target image an ordinary photo ; Finally, deform and fuse the generated pyrography to obtain the final gourd pyrography.

[0024] Convolutional neural networks...

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

An image style migration and simulation method for the gourd pyrography comprises the steps of conducting semantic segmentation processing on a target image, and based on a CRF-RNN image semantic segmentation algorithm, obtaining a segmented image , and performing binarization processing on the segmented image in the P mode to obtain a corresponding image semantic mask; performing image multi-stylization processing with spatial control through the target image mask; carrying out image stylization processing on the foreground area and the background area of the target image by using different pyrograph styles respectively, and migrating the style of the source image to the target image, so that the target image has the pyrograph style and retains the content information of the source image,namely the stylized pyrograph image; A certain amount of coordinate points of the gourd pyrograph are selected according to spatial characteristics of the gourd pyrograph, the spatial hierarchical relation of the coordinate points is converted into a gourd posture heat map, the pyrograph image is migrated to a target area of the gourd pyrograph, the final gourd pyrograph is obtained, and the operation efficiency, flexibility and migration effect of image style migration are improved.

Description

technical field [0001] The invention belongs to the technical field of image style transfer, and in particular relates to an image style transfer and simulation method for gourd pyrography. Background technique [0002] Pyrography, also known as heat painting and fire brush painting, was called fire needle embroidery in ancient times. It is an extremely precious and rare painting in ancient China. , Tonal rich burn marks way to paint. Pyrography not only maintains the national style of traditional Chinese painting, but also has the rigorous realistic effect of Western painting, has its unique artistic charm, and has become an important folk art form. Among them, the pyrography gourd is a unique form of pyrography creation. The pyrography artist paints on the surface of the gourd. The painting is integrated with the gourd. It can be preserved and collected forever, and its artistic value is extremely high. [0003] In the field of non-photorealistic rendering (NPR) research...

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): G06T3/00G06T5/50G06T7/194G06T7/143G06N3/04G06N3/08
Inventor 徐丹吴航
Owner YUNNAN UNIV
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