Purely vision-based segmentation of web pages for assistive technology
详细信息 查看全文
- 作者：Michael Cormier ; a ; m4cormie@uwaterloo.ca" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Karyn Moffattb ; karyn.moffatt@mcgill.ca" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Robin Cohena ; rcohen@uwaterloo.ca" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Richard Manna ; mannr@uwaterloo.ca" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Webpage segmentation ; Edge detection ; Assistive technology for the visually impaired ; the ageing population and those with cognitive deficit
- 刊名：Computer Vision and Image Understanding
- 出版年：2016
- 出版时间：July 2016
- 年：2016
- 卷：148
- 期：Complete
- 页码：46-66
- 全文大小：5329 K
文摘
- •
We use a novel vision-based method to analyze the layout of a web page.
- •
Our method produces a hierarchical segmentation of the page reflecting its structure.
- •
Vision-based methods are not sensitive to implementation language or complexity.
- •
The visual presentation of a page provides rich information about semantic structure.
- •
This structure can help create modified presentations for users with assistive needs.