Geometry Normalization Networks for Accurate Scene Text Detection

Abstract

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.

arXiv commentICCV 2019

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• EAST: An Efficient and Accurate Scene Text Detector
• DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
• Single Shot Text Detector with Regional Attention
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
• WordSup: Exploiting Word Annotations for Character based Text Detection
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• Shape Robust Text Detection with Progressive Scale Expansion Network
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• Boosting up Scene Text Detectors with Guided CNN

Cited by in corpus (5)

• Fourier Contour Embedding for Arbitrary-Shaped Text Detection
• MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
• Batch Group Normalization
• Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
• TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection