Methodology for flexible and efficient analysis of the performance of page segmentation algorithms

The paper presents part of a new DIA performance analysis framework aimed at layout analysis algorithm developers. A new region representation scheme (an interval based description of isothetic polygons) and a corresponding comparison approach are introduced. These enable fast and accurate geometric comparison of ground truth with results of page segmentation, improving on current evaluation methods. Complex layouts are accurately described and layout analysis methods that handle them can be effectively evaluated. A further benefit of the new approach is that it measures the accuracy of the description of regions, an issue which is important for complex layouts involving non text regions