Method and device for caricature segmentation

A technology for manga and image segmentation, applied in the field of manga segmentation methods and devices, can solve the problem of inability to accurately segment manga texture regions

Inactive Publication Date: 2017-11-28
SHENZHEN RES INST THE CHINESE UNIV OF HONG KONG
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the comic texture area cannot be accurately segmented in the prior art, this application provides a method and device for segmenting comics

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
  • Method and device for caricature segmentation
  • Method and device for caricature segmentation
  • Method and device for caricature segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] This embodiment provides a method for segmenting comics, which includes the following steps. The flowchart is as follows: figure 2 Shown.

[0027] S100: Divide the input image area.

[0028] In this step, the input image is divided into regions based on user input and texture features, and the region of the input image is divided into an initial region and a non-initial region, where the user input includes at least one stroke, and the initial region is the region where the user input strokes The area with similar texture, the non-initial area is the area with dissimilar texture to the area where the user entered the stroke; that is, the user only needs to draw one or a few strokes in the area that he wants to divide, and this step can realize the user The area you want to divide is divided into initial areas, and other areas are divided into non-initial areas.

[0029] Specifically, step S100 includes the following steps, and the flowchart is as follows: figure 2 Shown.

[...

Embodiment 2

[0082] Based on the comic segmentation method provided in the first embodiment, this example applies it specifically to Figure 5 Image segmentation shown.

[0083] The system enters a comic picture, such as Figure 5 As shown in (a), the user uses the brush tool of the system to draw a stroke in the area he wants to segment in the comic picture, such as Figure 5 (b) shows that the user is Figure 5 (b) Draw a stroke on the moon to indicate that the user wants to Figure 5 The moon in (a) is segmented, and based on the user's input strokes, using steps S101 to S103 of the first embodiment to perform texture feature analysis on the comic picture first to obtain a texture similarity map, such as Figure 5 As shown in (c), the initial area and non-initial area are obtained through the image segmentation algorithm, such as Figure 5 (d) shows, where, Figure 5 The white area in (d) is the initial area, and the black area is the non-initial area. Since the initial area segmented based o...

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

A comic segmentation method, comprising the steps of: dividing the input image area: dividing the input image into areas according to user input and based on texture features, and dividing the area of ​​the input image into initial areas and non-initial areas; smoothing the input image: smoothing based on texture The algorithm smoothes the input image to obtain a smooth map of the input image; extending the initial region: extending the initial region based on the smooth map to obtain a smooth connected map; segmenting the smooth connected map: using an image segmentation algorithm Segment the smooth connected graph and obtain the precisely segmented textured regions of the input image. Due to the comprehensive use of texture features and texture smoothing algorithms to segment images, the comic segmentation method of this application not only has the ability to distinguish textures, but also can obtain relatively accurate edges, so that accurate texture regions can be segmented from comic images.

Description

Technical field [0001] The present invention relates to the field of image segmentation, in particular to a method and device for segmenting comics. Background technique [0002] With the development and popularization of electronic devices, more and more people are no longer limited to traditional comic books, but are getting used to reading comics with electronic devices. Electronic comics, as a new form of comics, gradually occupy an increasing market share. Comic companies and cartoonists also began to produce electronic comics in electronic form, and converted comic books made in traditional ways into electronic comics. It is worth noting that converting comic books into electronic comics is more than just a simple scan. Different from comic books of a certain size, electronic devices such as computers, tablets, and mobile phones have display screens of various sizes. Therefore, comic pages need to be enlarged or reduced to fit different sizes of display screens. It is c...

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): G06T7/11G06T7/187
Inventor 黄田津刘雪婷
Owner SHENZHEN RES INST THE CHINESE UNIV OF HONG KONG
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