Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

Abstract

Previous deep learning based state-of-the-art scene text detection methods can be roughly classified into two categories. The first category treats scene text as a type of general objects and follows general object detection paradigm to localize scene text by regressing the text box locations, but troubled by the arbitrary-orientation and large aspect ratios of scene text. The second one segments text regions directly, but mostly needs complex post processing. In this paper, we present a method that combines the ideas of the two types of methods while avoiding their shortcomings. We propose to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions. In inference stage, candidate boxes are generated by sampling and grouping corner points, which are further scored by segmentation maps and suppressed by NMS. Compared with previous methods, our method can handle long oriented text naturally and doesn't need complex post processing. The experiments on ICDAR2013, ICDAR2015, MSRA-TD500, MLT and COCO-Text demonstrate that the proposed algorithm achieves better or comparable results in both accuracy and efficiency. Based on VGG16, it achieves an F-measure of 84.3% on ICDAR2015 and 81.5% on MSRA-TD500.

arXiv commentTo appear in CVPR2018

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Synthetic Data for Text Localisation in Natural Images
• Multi-Oriented Text Detection with Fully Convolutional Networks
• Instance-sensitive Fully Convolutional Networks
• Single Shot Text Detector with Regional Attention
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• WordSup: Exploiting Word Annotations for Character based Text Detection
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
• Point Linking Network for Object Detection
• WeText: Scene Text Detection under Weak Supervision
• Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification

Cited by in corpus (7)

• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• MSR: Multi-Scale Shape Regression for Scene Text Detection
• Geometry Normalization Networks for Accurate Scene Text Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• A Machine Learning Framework for Data Ingestion in Document Images