A New Method for Hierarchical Image Segmentation from Visual Designs

Pavel Myznikov, Yan Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Hierarchical image segmentation recognizes and organizes image elements into a tree structure. The tree structure represents the semantic information of the image. It is one of the most fundamental computer vision problems. This paper focuses on the images that come from visual design such as graphic interfaces, posters, and presentations. Extracting hierarchical structure from such images allows quantitative analysis of visual design choices and reproducing designs from hand drawings or hard copies. We propose a more accurate method that incorporates the common design principles of visual designs. We compare our algorithm with seven existing approaches on the most popular websites screenshots ranked by Alexa. Our method outperforms the state-of-the-art methods in tree edit distance and F-score, and is comparable or better in the bottom-up distance.

Original languageEnglish
Title of host publication2020 54th Annual Conference on Information Sciences and Systems, CISS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728140841
DOIs
Publication statusPublished - Mar 2020
Event54th Annual Conference on Information Sciences and Systems, CISS 2020 - Princeton, United States
Duration: 18 Mar 202020 Mar 2020

Publication series

Name2020 54th Annual Conference on Information Sciences and Systems, CISS 2020

Conference

Conference54th Annual Conference on Information Sciences and Systems, CISS 2020
CountryUnited States
CityPrinceton
Period18.03.202020.03.2020

Keywords

  • image representation
  • image segmentation
  • pattern recognition

OECD FOS+WOS

  • 1.02 COMPUTER AND INFORMATION SCIENCES
  • 2.02 ELECTRICAL ENG, ELECTRONIC ENG
  • 5.09 OTHER SOCIAL SCIENCES

Fingerprint

Dive into the research topics of 'A New Method for Hierarchical Image Segmentation from Visual Designs'. Together they form a unique fingerprint.

Cite this