Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

Abstract

We introduce a new top-down pipeline for scene text detection. We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization. The CCTN fast detects text regions roughly from a low-resolution image, and then accurately localizes text lines from each enlarged region. We cast previous character based detection into direct text region estimation, avoiding multiple bottom- up post-processing steps. It exhibits surprising robustness and discriminative power by considering whole text region as detection object which provides strong semantic information. We customize convolutional network by develop- ing rectangle convolutions and multiple in-network fusions. This enables it to handle multi-shape and multi-scale text efficiently. Furthermore, the CCTN is computationally efficient by sharing convolutional computations, and high-level property allows it to be invariant to various languages and multiple orientations. It achieves 0.84 and 0.86 F-measures on the ICDAR 2011 and ICDAR 2013, delivering substantial improvements over state-of-the-art results [23, 1].

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Robust Text Detection in Natural Scene Images
• Text-Attentional Convolutional Neural Networks for Scene Text Detection

Cited by in corpus (18)

• A Survey of Deep Learning-based Object Detection
• Single Shot Text Detector with Regional Attention
• Character Region Awareness for Text Detection
• Industrial Scene Text Detection with Refined Feature-attentive Network
• PixelLink: Detecting Scene Text via Instance Segmentation
• WordSup: Exploiting Word Annotations for Character based Text Detection
• An end-to-end TextSpotter with Explicit Alignment and Attention
• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
• A pooling based scene text proposal technique for scene text reading in the wild
• Detecting Text in Natural Image with Connectionist Text Proposal Network
• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• WeText: Scene Text Detection under Weak Supervision
• WordFence: Text Detection in Natural Images with Border Awareness
• Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
• Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
• Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
• A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping