- Identifying natural images from human brain activity
- Interacting with Computers using Gaze
- Interactive
Image
Editing
- Content-based
Image Indexing and Retrieval
- Computational
Photography or Making Beautiful Pictures
- Interactive Fat
and Organ Segmentation
- Object (Face and
Car) Detection
|
|
Identifying natural images from human brain
activity
Is mind (brain) reading possible? Well,
the technology is getting closer. In this project, we will try to
implement such a system, e.g., this
method.
Interacting with Computers using
Gaze
In this project, we will use eye tracking
techniques to interact with computers. Using gaze and eye movements
instead of traditional keyboard and mouse to interact with computers
can open up new applications, for example, to assist motor impaired
people to use a computer.
Video/Photo Mashup
Mashup (Wiki)
is
a web application that combines data from more than one source into
a single integrated tool.
Here are some examples
Flickrvision (http://flickrvision.com/)
More examples here (http://mashupawards.com/)
There are many possibilities, and you can develop some very interesting
and useful tools.
Colorization
Given a black and white (old) photo, a user scribbles a few "seed"
colours, a computational algorithm will solve the colorization
problem in "closed form". More information
....
References
[1] A. Levin, D. Lischinski and Y. Weiss, “Colorization using
optimization”, SIGGRAPH 2004
[2] G. Qiu and J. Guan, "Color by Linear Neighborhood Embedding",
ICIP2005, IEEE International Conference on Image Processing, Genova,
Italy, September 11 - 14, 2005
Interactive Image
Editing
A user scribbles a few pixels belong to the foreground and background,
a computational algorithm will separate the foreground from the
background and produce an "alpha matte". The extracted foreground
objects can then be placed in a new background to synthesize a
new image.
References
J. Guan and G. Qiu, "Interactive image segmentation using optimization
with statistical priors", International Workshop on The Representation
and Use of Prior Knowledge in Vision, In conjunction with ECCV 2006,
May 13 2006, Graz, Austria
Content-based
Image Indexing and Retrieval
Managing large image database is very challenging. We take a
content-based approach and want to develop systems that will enable
users to query image databases by visual examples or visual features
such as colour and texture.
More information can be found in these links
http://www.viplab.cs.nott.ac.uk/research1.html
http://www.viplab.cs.nott.ac.uk/research2.html
http://www.viplab.cs.nott.ac.uk/research3.html
If you are interested in doing a project in this area, please come to
see
me, there will be many fun things you can do.
Computational
Photography or Making Beautiful Pictures
Have you ever wondered why the picture quality of some of the photos
you took with
your digital camera was so bad, like the left photo in the follwing
image
Well, by doing this project you will know why, and learn how to correct
this using computational approaches, to produce a "beautiful" picture
like the one on the right in the above image.
Interactive Fat
and Organ Segmentation
In medical research, it is often necessary to segment out various
organs and tissues. In this project, you will develop interactive
computational approaches to image segmentation. Please come to see me
if you are interested in this project.
Object (Face
and Car) Detection
In this project, you will learn how to detect specific types of objects
in still images and in videos.
More information can be found in this link http://www.viplab.cs.nott.ac.uk/research7.html
or come to see me if you are interested in this project.
|
|
|