Towards End-to-End Unified Scene Text Detection and Layout Analysis
This work addresses the need for integrated text understanding in images, offering a unified approach that could benefit applications like document analysis and scene interpretation, though it appears incremental by combining existing tasks.
The paper tackles the problem of unifying scene text detection and layout analysis, which were previously separate tasks, by introducing a hierarchical dataset and a novel method that simultaneously detects text and forms clusters, achieving state-of-the-art results on multiple datasets without complex post-processing.
Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The first hierarchical scene text dataset is introduced to enable this novel research task. We also propose a novel method that is able to simultaneously detect scene text and form text clusters in a unified way. Comprehensive experiments show that our unified model achieves better performance than multiple well-designed baseline methods. Additionally, this model achieves state-of-the-art results on multiple scene text detection datasets without the need of complex post-processing. Dataset and code: https://github.com/google-research-datasets/hiertext and https://github.com/tensorflow/models/tree/master/official/projects/unified_detector.