TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade

Abstract

We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images. (2) The extracted contour information can be used for better scene text detection. We propose two ways for learning the contour task together with the scene text detection: (1) as an auxiliary task and (2) as multi-task cascade. Extensive experiments with different benchmark datasets demonstrate that both designs improve the performance of a state-of-the-art scene text detector and that a multi-task cascade design achieves the best performance.

arXiv comment9 pages(including references); WACV 2019

References in corpus (10)

• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Richer Convolutional Features for Edge Detection
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Multi-Oriented Text Detection with Fully Convolutional Networks
• Single Shot Text Detector with Regional Attention
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• PixelLink: Detecting Scene Text via Instance Segmentation
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks