Tag Archives: Research

Experiment #1 - JavaSIFT

Just tried to do a first experiemnt using the ImageJ plugin JavaSIFT.

I took nine pictures* of my house with my smartphones camera. The goal was to let JavaSIFT reigster some interest points and then to see what I can do with that (JavaSIFT has some "align images" function). Turned out that the plugin is kind of broken: it does find interest points but right after that it stops with an MethodNotFound exception.

First experiment: failed.

I guess I'm not going to dive into the code to find out what the problem is. Eventually I'll play around a little with ImageJ (there are some dependencies, maybe they weren't loaded properly or so).

* thesis/experiment 1/foto set 1

Stephan Saalfeld - ImageJ Plugins - JavaSIFT.


SURF (Speeded Up Robust Features) is a robust image detector & descriptor, first presented by Herbert Bay et al. in 2006, that can be used in computer vision tasks like object recognition or 3D reconstruction. It is partly inspired by the SIFT descriptor. The standard version of SURF is several times faster than SIFT and claimed by its authors to be more robust against different image transformations than SIFT. SURF is based on sums of approximated 2D Haar wavelet responses and makes an efficient use of integral images.

via SURF (Wikipedia)