Bar charts are crucial to summarize and present multi-faceted data sets in biomedical publications. Quantitative information carried by bar charts is of great interest to scientists and practitioners, which make it valuable to parse bar charts. This fact together with the abundance of bar chart images and their shared common patterns gives us a good candidates for automated image mining and parsing. We demonstrate a workflow to analyze bar charts and give a few feasible solutions to apply it. We are able to detect bar segments and panels with a promising performance in terms of both accuracy and recall, and we also perform extensive experiments to identify the entities of bar charts in the images of biomedical literature collected from PubMed Central. While we cannot provide a complete instance of the application using our method, we present evidence that this kind of image mining is feasible.