: Unicode character recognition.


You know what some character looks like, but you've forgotten its name or its Unicode code point. Now what do you do? Shapecatcher is a new website, that helps you to find specific Unicode characters, just by sketching their shape. Currently about 10000 of the most important Unicode characters are compared to your sketch and are analysed for similarities.

Under the hood, Shapecatcher uses so called "shape contexts" to find similarities between two shapes. Shape contexts, a robust mathematical way of describing the concept of similarity between shapes, is a feature descriptor first proposed by Serge Belongie and Jitendra Malik.

You can find an indepth explanation of the shape context matching framework that I used in my Bachelor thesis ("On the Security of reCATPCHA"). In the end, it is quite a bit different from the matching framework that Belongie and Malik proposed in 2000, but still based on the idea of shape contexts.

The engine that runs this site is a rewrite of what I developed during my bachelor thesis. To make things faster, I used CUDA to accelereate some portions of the framework. This is a fairly new technology that enables me to use my NVIDIA graphics card for general purpose computing. Newer cards are quite powerful devices!

Each query on this website is processed by a graphics card, making the comparsion process over 15 times faster than on my CPU. In essence, CUDA makes it possible to provide a near realtime expierence and to handle higher loads on this website.