![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Thursday 08 June 2006, 14:15-15:00
Intelligent Compositing, Camera-Based Document Analysis and Preliminary Experiments on Sudoku
- đ¤ Speaker: Rahul Vohra
- đ Date & Time: Thursday 08 June 2006, 14:15 - 15:00
- đ Venue: Rainbow Room, Computer Laboratory
Abstract
In this talk I will cover two separate topics: compositing and camera-based document analysis.
1. I will begin with an overview of the material presented in “Cross Dissolve Without Cross Fade: Preserving Contrast, Color and Salience in Image Compositing”. Beautiful figures and videos can be found at http://www.cl.cam.ac.uk/Research/Rainbow/projects/compositing/.
2. I will then do an overview of Camera-Based Document Analysis. I intend to answer the questions: What is it? Why do we want it? Why is it hard? What can we do about it? I will then cover our preliminary experiments on the very specific case of taking photographs of Sudoku puzzles. I hope to finish with a live action demo of our camera phone based system.
Series This talk is part of the Rainbow Graphics Seminars series.
Included in Lists
Note: Ex-directory lists are not shown.