Location-Aware Feature Selection Network for Multi-Oriented Scene Text Detection

Direct Regression-based text detection methods have already achieved promising performances with simple network structure. However, there still leaves improvement room in terms of regression accuracy, especially for long and large text instances, which hinders their applicability in some realistic scenarios that need recognition of the detected text. To address this issue, we propose a novel Location Aware feature Selection text detection Network (LASNet) which selects suitable features from different locations to separately predict each component of a bounding box and gets the final bounding box through the combination of them. 1As a result, LASNet predicts the more accurate bounding boxes by effectively making use of features with a learnable feature selection way. The experimental results demonstrate that our LASNet achieves state-of-the-art performance with single model and single-scale testing.