Rover: a visualization and analysis tool

To use the ground truth data available in XML format along with the corresponding TIFF image, this tool is provided to allow researchers to:

· Load a TIFF image and the corresponding XML file into an application, and display the XML data, where appropriate, overlaid on the image.
· Modify and add new ground truth data.
· Compare the results of new algorithms against the ground truth data.

Rover’s design is based on TrueViz, a public domain tool developed at the University of Maryland by Dr. Tapas Kanungo and colleagues, for visualizing, creating and editing ground truth and metadata. It is implemented in Java and works on Windows and Unix platforms (specifically, it has been successfully tested in the Windows 2000 and Sun Solaris 2.6 environments). It reads and stores ground truth and metadata in XML format, and reads the corresponding TIFF images. It allows the user to inspect ground truth data at many levels, viz., at the page, zone, line, word, and character levels, and provides pertinent information at each level. For example, at the character level, such information includes the character code, font type and style, and bounding box (x1,y1,x2,y2) coordinates.

There will be occasions where there is new ground truth data to add or existing data to modify. Rover is capable of doing this graphically or you can modify the XML data directly using any editor capable of reading and writing XML data.

If you have any special features you would like to see added to Rover please email me by clicking here.

Future Plans

When fully developed, Rover is intended to serve as an effective analysis assistant, by extending TrueViz to provide researchers the capability to compare their XML data to ground truth XML data graphically, and thereby enable an iterative refinement of their algorithms. In addition, Rover will provide statistics and visual presentations on specified areas. For example, the user would be able to use Rover to compare all characters in the dataset that are bold, and to enumerate errors. Rover would visually locate the mistakes and report statistics on the query. In this example, it would report the number of bold characters, the number detected correctly, and the number detected incorrectly, both as absolute numbers and as percentages. Rover would also export this information to a database or spreadsheet for further analysis.

Rover History | Rover Application

U.S. National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894
National Institutes of Health | U.S. Dept. of Health and Human Services
Copyright information | Privacy policy | NLM Accessibility