Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Cartoon image page identification method and system based on dialogue and storyboard united identification

A recognition method and dialogue technology, applied in the fields of image processing and computer vision, can solve problems such as large limitations, low efficiency, and inability to handle complex situations, and achieve the effect of improving accuracy and strong versatility

Active Publication Date: 2016-05-11
PEKING UNIV
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is entirely dependent on experience, has too many limitations, and requires 2N morphological operations, which is relatively inefficient.
In addition, the above-mentioned segmentation and dialogue extraction methods are completed independently through each module, which often produces some false alarms and cannot handle some complicated situations

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
  • Cartoon image page identification method and system based on dialogue and storyboard united identification
  • Cartoon image page identification method and system based on dialogue and storyboard united identification
  • Cartoon image page identification method and system based on dialogue and storyboard united identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0054] The invention takes the page images of comic publications as the processing object, learns from the current natural image understanding methods, makes full use of the energy minimization model and its graph segmentation optimization algorithm, and provides a method for automatically extracting structural information of such complex document images. The recognition method of various image constituent objects (scenes, dialogues, or dialogue bubbles) also proposes to jointly recognize objects according to the logical structural relationship between constituent objects, and judge the order of reading.

[0055] In the present invention, the comic content is mainly a comic image obtained by scanning a comic book page by page. The user first obtains comic electronic files in image format (for example...

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 cartoon image page identification method and system based on dialogue and storyboard united identification. A carton image is divided into a storyboard layer and a dialogue layer. The method comprises following steps: extracting to obtain storyboards in a carton image page; extracting to obtain dialogues in the carton image page; carrying out storyboards, dialogues, and storyboard and dialogue united identification; building an energy minimized function, obtaining marking results of a storyboard polygon and a dialogue surrounding fence through optimally solving the energy minimized function; identifying a reading sequence according to the geometric position relation of the polygon, thus finishing the carton image identification. According to the method and the system of the invention, the limitations of an identification method which only pays attention to independent extraction of composite objects and ignores the relation among the objects are broken through; the storyboard identification accuracy is improved; and the method and the system have relatively strong universality.

Description

technical field [0001] The invention belongs to the field of image processing and computer vision, and relates to a comic image layout recognition method and system based on the joint recognition of dialogue and split mirror. Background technique [0002] In recent years, with the popularity of various mobile terminals such as smart phones, tablet computers, and e-book readers, mobile reading has developed rapidly and is gradually becoming an indispensable part of our lives. Due to the improvement of various terminal hardware manufacturing processes and the continuous decline in manufacturing costs, mobile reading has entered the era of "content is king". How to make content suitable for reading on mobile terminals is one of the key issues facing mobile reading. The invention starts from the mobile reading of comics and improves the reading experience of users. [0003] Comics are a relatively special type of publication, and their pages are usually divided into several ind...

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): G06K9/20G06K9/62
CPCG06V10/22G06F18/2411
Inventor 周亚峰王勇涛汤帜
Owner PEKING 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
Eureka Blog
Learn More
PatSnap group products