Deep Direct Regression for Multi-Oriented Scene Text Detection

Abstract

In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given point, while indirect regression predicts the offsets from some bounding box proposals. Then we analyze the drawbacks of the indirect regression, which the recent state-of-the-art detection structures like Faster-RCNN and SSD follows, for multi-oriented scene text detection, and point out the potential superiority of direct regression. To verify this point of view, we propose a deep direct regression based method for multi-oriented scene text detection. Our detection framework is simple and effective with a fully convolutional network and one-step post processing. The fully convolutional network is optimized in an end-to-end way and has bi-task outputs where one is pixel-wise classification between text and non-text, and the other is direct regression to determine the vertex coordinates of quadrilateral text boundaries. The proposed method is particularly beneficial for localizing incidental scene texts. On the ICDAR2015 Incidental Scene Text benchmark, our method achieves the F1-measure of 81%, which is a new state-of-the-art and significantly outperforms previous approaches. On other standard datasets with focused scene texts, our method also reaches the state-of-the-art performance.

9 pages, 9 figures

References in corpus (9)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• Text-Attentional Convolutional Neural Networks for Scene Text Detection
• Synthetic Data for Text Localisation in Natural Images
• DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
• Multi-Oriented Text Detection with Fully Convolutional Networks
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• Scalable Object Detection using Deep Neural Networks

Cited by in corpus (25)

• Object Detection in 20 Years: A Survey
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• PixelLink: Detecting Scene Text via Instance Segmentation
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• An end-to-end TextSpotter with Explicit Alignment and Attention
• Learning Markov Clustering Networks for Scene Text Detection
• Robust Classification with Convolutional Prototype Learning
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
• Scene Text Detection with Supervised Pyramid Context Network
• Rotation-Sensitive Regression for Oriented Scene Text Detection
• Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• MSR: Multi-Scale Shape Regression for Scene Text Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• FOTS: Fast Oriented Text Spotting with a Unified Network
• ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
• Sketch2code: Generating a website from a paper mockup
• Correlation Propagation Networks for Scene Text Detection
• Learning to Predict More Accurate Text Instances for Scene Text Detection
• A Machine Learning Framework for Data Ingestion in Document Images
• TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade