This paper presents an objective comparative evaluation of page segmentation and region classification methods for documents with complex layouts. It describes the competition (modus operandi, dataset and evaluation methodology) held in the context of ICDAR2017, presenting the results of the evaluation of seven methods – five submitted, two state-of-the-art systems (commercial and open-source). Three scenarios are reported in this paper, one evaluating the ability of methods to accurately segment regions and two evaluating both segmentation and region classification (one focusing only on text regions). For the first time, nested region content (table cells, chart labels etc.) are evaluated in addition to the top-level page content. Text recognition was a bonus challenge and was not taken up by all participants. The results indicate that an innovative approach has a clear advantage but there is still a considerable need to develop robust methods that deal with layout challenges, especially with the non-textual content.
展开▼
