DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images

Abstract

In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN). First, we propose the inception region proposal network (Inception-RPN) and design a set of text characteristic prior bounding boxes to achieve high word recall with only hundred level candidate proposals. Next, we present a powerful textdetection network that embeds ambiguous text category (ATC) information and multilevel region-of-interest pooling (MLRP) for text and non-text classification and accurate localization. Finally, we apply an iterative bounding box voting scheme to pursue high recall in a complementary manner and introduce a filtering algorithm to retain the most suitable bounding box, while removing redundant inner and outer boxes for each text instance. Our approach achieves an F-measure of 0.83 and 0.85 on the ICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous state-of-the-art results.

arXiv comment12 pages, 4 figures, 3 tables

References in corpus (4)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Robust Text Detection in Natural Scene Images
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

Cited by in corpus (24)

• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• 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
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
• Shape Robust Text Detection with Progressive Scale Expansion Network
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• WeText: Scene Text Detection under Weak Supervision
• Feature Enhancement Network: A Refined Scene Text Detector
• Geometry Normalization Networks for Accurate Scene Text Detection
• WordFence: Text Detection in Natural Images with Border Awareness
• Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
• Deep Scene Text Detection with Connected Component Proposals
• ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
• RRPN++: Guidance Towards More Accurate Scene Text Detection
• Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
• Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification
• Learning Robust Feature Representations for Scene Text Detection
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• RFBTD: RFB Text Detector
• Research on Fast Text Recognition Method for Financial Ticket Image