About Us

Studentship Vacancies

 

What makes a good picture?

This PhD project aims at uncovering the secrets of a good photograph. You are expected to develop computational algorithms that can set aside the very best photos of a set of similar photos - based on photographic design principles, trained with decisions taken by users, and based on learning from user comments on public photo sharing sites such as flickr and picassa. You will research and derive suitable high and low-level features from digital images that allow classification of photos as "good" and that allow categorisation of the emotive content of a digital image. You might use principles of simplicity (objects can easily be separated from the background), realism (eg, particular use of colour palette), basic techniques (right exposure, have areas with distinct focus, suitable colour, intensity and sharpness contrast) and composition principles. Armed with these features you will study, deploy, devise and modify machine learning algorithms that predict which photos make good representatives out of a bigger set of photographs.

Full Details

For further information, or informal discussion about the position, please contact: Professor Stefan Rüger.

---

Visual Digital Libraries

The overall aim of the project is to facilitate visual access to digital libraries through novel visual search paradigms in additional to the traditional text search approach. You will research (and develop) new search engines based on visual retrieval methods: For example, the user submits an image of an oil painting to retrieve all documents in the digital library that depict (and discuss) the very same painting. This task, also known as near identical search, should be able to recognise images, where the query is only part of an image, say the head of a particular person.

Full Details

For further information, or informal discussion about the position, please contact: Professor Stefan Rüger or Dr Suzanne Little.

---

Visual interfaces for search engines using query by example

The overall aim of the project is to facilitate visual access to digital libraries through novel browsing, search and visualisation paradigms in addition to the traditional text search approach. You will research (and develop) new interfaces for search engines based on visual retrieval methods. Rather than typing a text query the user is enabled to submit pictures and/or video clips; the novel interfaces make use of the screen to display results in an intuitive way for navigation, change of the visual query and browsing with a view to visually explore the digital library.

Full Details

For further information, or informal discussion about the position, please contact: Professor Stefan Rüger or Dr Suzanne Little.