Geometry Normalization Networks for Accurate Scene Text Detection
This work addresses the problem of detecting text in scenes with varying orientations and scales for computer vision applications, offering a novel module that improves accuracy over existing methods.
The paper tackles the challenge of large geometry variances in scene text detection by proposing a Geometry Normalization Module (GNM) that normalizes text instances to a canonical geometry range, resulting in state-of-the-art F-scores of 88.52 on ICDAR 2015 and 74.54 on ICDAR 2017 MLT benchmarks.
Large geometry (e.g., orientation) variances are the key challenges in the scene text detection. In this work, we first conduct experiments to investigate the capacity of networks for learning geometry variances on detecting scene texts, and find that networks can handle only limited text geometry variances. Then, we put forward a novel Geometry Normalization Module (GNM) with multiple branches, each of which is composed of one Scale Normalization Unit and one Orientation Normalization Unit, to normalize each text instance to one desired canonical geometry range through at least one branch. The GNM is general and readily plugged into existing convolutional neural network based text detectors to construct end-to-end Geometry Normalization Networks (GNNets). Moreover, we propose a geometry-aware training scheme to effectively train the GNNets by sampling and augmenting text instances from a uniform geometry variance distribution. Finally, experiments on popular benchmarks of ICDAR 2015 and ICDAR 2017 MLT validate that our method outperforms all the state-of-the-art approaches remarkably by obtaining one-forward test F-scores of 88.52 and 74.54 respectively.