TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

Abstract

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the representations (axis-aligned rectangles, rotated rectangles or quadrangles) adopted to describe text, existing methods may fall short when dealing with much more free-form text instances, such as curved text, which are actually very common in real-world scenarios. To tackle this problem, we propose a more flexible representation for scene text, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms. In TextSnake, a text instance is described as a sequence of ordered, overlapping disks centered at symmetric axes, each of which is associated with potentially variable radius and orientation. Such geometry attributes are estimated via a Fully Convolutional Network (FCN) model. In experiments, the text detector based on TextSnake achieves state-of-the-art or comparable performance on Total-Text and SCUT-CTW1500, the two newly published benchmarks with special emphasis on curved text in natural images, as well as the widely-used datasets ICDAR 2015 and MSRA-TD500. Specifically, TextSnake outperforms the baseline on Total-Text by more than 40% in F-measure.

arXiv comment17 pages, accepted to ECCV2018

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Robust Text Detection in Natural Scene Images
• Learning Deconvolution Network for Semantic Segmentation
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Detecting Curve Text in the Wild: New Dataset and New Solution
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• WeText: Scene Text Detection under Weak Supervision

Cited by in corpus (6)

• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Character Region Awareness for Text Detection
• Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
• SwapText: Image Based Texts Transfer in Scenes
• On Vocabulary Reliance in Scene Text Recognition
• Scene Text Detection with Selected Anchor