[visionlist] Two PhD studentship at School of Computing Sciences, UEA, UK

[Michal Mackiewicz (CMP)]

The first PhD studentship is a rare fully funded studentship that is open to international applicants.
Application deadline: 1st April 2013
Project Name: Visualizing High Dimensional Image Data

Project description: Probably, we have all seen CSI and other forensics based dramas where some indelible piece of evidence leads to a serious criminal being caught. Often the piece of evidence is not visible to the naked eye it may only become apparent if viewed under, for example, Ultra Violet Light. Like these popular fictional dramas this project is concerned with making the invisible visible.

However, we are interested in the problem of augmenting the visible information (with detail that is invisible to the naked eye). This problem occurs in many problem domains but here we will focus on visualising multispectral Satellite Data[1]. Often satellite images have 100s of image channels and yet only 1 (grey scale) or 3 (colour) can be viewed by an image analyst at any one time. In an attempt to maximize the amount of data that can be summarised in a reproducible image, a pseudo colour representation is often proposed[2]. However, when pseudo colour is used the cognitive link to what an observer might see in the same situation is lost. A second problem with many existing visualization methods is that they often introduce artefacts into the image[3] (details that do not appear in any of the channels of the multispectral image).

In this project we will first seek methods to, so far as it is possible, render all the spectral information in a single ‘true’ colour image without artefact. Specifically, we propose augmenting the visible colour image (which is generally available) with the contrast that is invisible. Second, we are interested in using this visualization as a window which helps to navigate the observer back to particular hyperspectral image planes of interest. Lastly, we will test the developed platform through user studies to establish how much the developed platform aids the observer locating information of interest.

The successful applicant will also have the opportunity to work with Spectral Edge Ltd (a recent Norwich Research Park spin out company in the area of image fusion).

Funding Notes: Funding for this project is specifically being offered to International candidates. However, applications are welcome from Home/EU candidates who are able to secure their own source of funding. Funding includes full tuition fees as well as an annual stipend of £13,726 for 3 years.

References:

[1] Unsalan, C. and Boyer, K., “Multispectral Satellite Image Understanding,”, Springer, 2003.
[2] ] Tsagaris, V. et al., “Fusion of hyperspectral data using segmented PCT for enhanced color representation‖,” IEEE Transactions on Geosciences and Remote Sensing, vol. 43, no. 10, pp. 2365-2375, 2005.
[3] Socolinsky, D.A and Wolff, L.B., “Multispectral image visualization through first-order fusion,” IEEE Transactions on Image Processing 11(8): 923-931 (2002)

For details and how to apply see: http://www.findaphd.com/search/ProjectDetails.aspx?PJID=43918&LID=434


The second PhD studentship is also fully funded and open to UK/EU applicants.
Application deadline: 1st March 2013

Project Name: Making the Invisible Visible

Probably, we have all seen CSI and other forensics based dramas where some indelible piece of evidence leads to a serious criminal being caught. Often the piece of evidence is not visible to the naked eye it may only become apparent if viewed under, for example, Ultra Violet Light. Like these popular fictional dramas this project is concerned with making the invisible visible.

However, we are interested in the problem of augmenting the visible information (with detail that is invisible to the naked eye). As an example, the image taken with a thermal camera (which measures heat) is bright wherever people appear in a scene. If we fuse the thermal image with a normal colour photo (of the same scene), the position of people ‘pops out’[1]. Making people ‘pop out’ is tremendously useful in applications such as surveillance and tracking. However, ideally, the fused image should still look, more or less, like a normal photo. Otherwise the image could look weird and any weirdness may be more difficult to interpret the image (in technical terms, by augmenting the visible image we do not wish to add to an observer’s cognitive load[2]).

In the proposed PhD project, the successful applicant will develop an imaging system where visible imagery is fused with the output of an Near Infra-Red Camera. The aim is, though image fusion, to provide a modified augmented colour image with respect to which it is ‘easier’ for people and machines to pinpoint the location of any faces that may be present. To test face detection in people, a psychophysical detection experiment will be carried out (we would like to test the hypothesis that observers will be able to find faces more quickly in the augmented image). The machine-intelligent system will, as a first step, test recognition by incorporating image fusion into a standard face classifier[3].

There will be scope in this project to apply the developed techniques to other domains including forensic imaging. The successful applicant will also have the opportunity to work with Spectral Edge Ltd (a recent UEA spin out company in the area of image fusion).

Minimum entry requirements: 2:1 Computer Science, Physics, Mathematics, Psychology or other numerate discipline

Funding Notes:

Funding is available to EU students. If funding is awarded for this project it will cover tuition fees and stipend for UK students. EU students may be eligible for full funding, or tuition fees only, depending on the funding source.

References:
Jonson, M.J. and Bacjsy, P. (2008), “Integration of thermal and visible imagery for robust foreground detection in tele-immersive spaces,” Information Fusion, 1-8.
Matsukura, M., Brockmole, J. R., Boot, W. R, & Henderson, J. M. (2011). Oculomotor capture during real-world scene viewing depends on cognitive load. Vision Research, 51, 546-552.
Viola, P.A., Jones M.J. (2004), “:Robust Real-Time Face Detection,” International Journal of Computer Vision 57(2): 137-154.

For details see and how to apply: http://www.findaphd.com/search/ProjectDetails.aspx?PJID=41606&LID=434
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist/attachments/20130222/29aae36a/attachment-0001.htm>