TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
This addresses a key limitation in scene text detection for real-world applications where curved text is common, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles the problem of detecting free-form text like curved text in natural images, which existing methods struggle with due to limited representations, and proposes TextSnake, a flexible representation that achieves state-of-the-art or comparable performance on benchmarks, including a more than 40% improvement in F-measure on Total-Text.
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.