Datatset Summarisation Tool Prototype

This prototype dataset summarisation tool is based on research on creating more useful dataset summaries. The aim is to help and guide publishers through the process of writing a meaningful dataset summary so that other people can make sense of the dataset before downloading it. Imagine searching for data and seeing a text summary that tells you what you need to know!

Piechart or Pizza?

This tool is part of our work in which we seek to learn to identify images of charts as they are posted on social media. We have adapted the VGGNet architecture proposed by Simonyan and Zisserman to the requirements of our chart identification problem. The system is trained on a dataset consisting of chart images from the ReVision corpus and general-purpose images from ILSVRC-2012.

You can use our pre-trained model to identify whether an image on the web displays a data visualisation or not. In case it does, our model will try to predict the depicted chart type.