Data Extraction from Charts via Single Deep Neural Network
This addresses the challenge of extracting data from charts for applications in data analysis and visualization, but it is incremental as it builds on existing object detection and text recognition methods.
The paper tackled the problem of automatic data extraction from charts by proposing a single deep neural network framework that handles bar and pie charts, achieving success rates of 79.4% on simulated bar charts and 88.0% on simulated pie charts, though performance degraded for out-of-domain charts.
Automatic data extraction from charts is challenging for two reasons: there exist many relations among objects in a chart, which is not a common consideration in general computer vision problems; and different types of charts may not be processed by the same model. To address these problems, we propose a framework of a single deep neural network, which consists of object detection, text recognition and object matching modules. The framework handles both bar and pie charts, and it may also be extended to other types of charts by slight revisions and by augmenting the training data. Our model performs successfully on 79.4% of test simulated bar charts and 88.0% of test simulated pie charts, while for charts outside of the training domain it degrades for 57.5% and 62.3%, respectively.