Thank you for your interest in our research. We are developing a method for digital image enhancement that employs an optimisation technique known as interactive evolutionary computation. Please help us assess our method by taking part in our online experiment.

Instructions

• Start the experiment using the link below
  • On 'start-up' you may be asked to install the latest version of Java Virtual Machine and accept a certificate from Ben George
• You will then be presented with four images of the same object containing differing amounts of image degradation.
  • The degradation is characterised by small coloured dots often referred to as 'salt and pepper' noise and/or 'block' artefacts in the object itself.
  • Use the 'select' button to choose the best image that has the smallest amount of degradation then use the 'next' button to display four new images.
• Repeat the above step until you are notified that the experiment has finished.
  • Note that the image object and initial amount of image degradation is chosen at random at the start of the experiment. If you begin a new experiment it is probable that you will be presented with a different object that exhibits a different amount of initial degradation to your first experiment. Feel free to repeat the experiment as many times as you like.

To start the experiment click on the link below which will launch a Java applet.

Image Enhancement Experiment

Note: The applet requires Java 1.4.2

Evolutionary algorithms are search techniques inspired by evolutionary biology and employing operations such as inheritance, mutation, selection and crossover. Evolution starts from a population of randomly generated individuals and occurs over a number of generations. At each generation, the individuals that best solve the problem are selected and recombined to form new individuals that can represent better solutions.

Contact

For further information, contact Ben George - bg37@kent.ac.uk or Dr Stuart Gibson - s.j.gibson@kent.ac.uk

References

Breukelaer, R.; Emmerich, M. & Bäck, T. (2006), On Interactive Evolution Strategies, in 'Applications of Evolutionary Computing: Evo Workshops 2006 (EvoIASP)'.

Cree, M. J. (2004), 'Observations on Adaptive Vector Filters for Noise Reduction in Color Images', IEEE Siganl Processing Letters 11(2), 140-143.

Herdy, M. (1996), Evolution Strategies with Subjective Selection, in 'Parallel Problem Solving from Nature, PPSN IV', pp. 22-31.

Jaksa, R.; Nakano, S. & Takagi, H. (2003), Image Filter Design with Interactive Evolutionary Computation, in 'IEEE International Conference on Computational Cybernetics (ICCC2003)'.

Lukac, R.; Plataniotis, K. & Venetsanopoulos, A. (2005), 'Color image denoising using evolutionary computation', IJIST 15(5), 236-251.

Lukac, R.; Smolka, B.; Plataniotis, K. & Venetsanopoulos, A. (2004), 'Selection weighted vector directional filters', CVIU 94(1-3), 140-167.