The Clustering Illusion

The clustering illusion is the human tendency to expect random events to appear more regular or uniform than they are in reality, resulting in the assumption that clusters in the data cannot be caused by chance alone. An important example of this is that the stars in the night sky seem clumped together in some regions, while… read more


Submitted on 5 March 2014

Valentine Filtering


Happy Valentine’s Day! This is a bit of a trick post; after luring you in with the cute heart, I’ll explain in this article how image filtering can be implemented in frequency space… read more

Submitted on 12 February 2014

Gaussian Noise is Added, Poisson Noise is Applied

Poisson and Gaussian noise, pixel values 0 to 5

There is a fundamental difference between adding Gaussian noise and applying Poisson noise. In practice, people often talk about adding Poisson noise anyway, but this is not accurate. I will be looking at this from the image processing perspective in this article, and I’ll show purely visual examples. An application of this could be… read more

Submitted on 11 January 2014

Why is Deconvolution Difficult?

Lena convolved with the Airy pattern

When taking a picture with a camera, the “true” image is convolved with the point spread function (PSF) of that camera, potentially producing a blurred image. Deconvolution is the process of removing the effect of this PSF again. In this article, I demonstrate that this is not an easy thing to do… read more

Submitted on 24 December 2013

Brandenburger TorPhoto Page

Brandenburger Tor

This is a detail of the Brandenburger Gate (Brandenburger Tor in German) in Berlin, Germany. It is difficult to make an original photo of the thing, since there are so many already, but this is my attempt at one… read more


Subscribe to RSS