Shape Robust Text Detection with Progressive Scale Expansion Network

TL;DR

This paper introduces PSENet, a novel text detection method that accurately detects arbitrary-shaped text instances and effectively separates close text objects using progressive scale expansion.

Contribution

The paper proposes a new segmentation-based network that generates multi-scale kernels and progressively expands them to improve arbitrary-shaped text detection and separation of close instances.

Findings

Achieves 74.3% F-measure on CTW1500 at 27 FPS

Outperforms state-of-the-art algorithms by 6.6% F-measure

Validates effectiveness on multiple challenging datasets

Abstract

Scene text detection has witnessed rapid progress especially with the recent development of convolutional neural networks. However, there still exists two challenges which prevent the algorithm into industry applications. On the one hand, most of the state-of-art algorithms require quadrangle bounding box which is in-accurate to locate the texts with arbitrary shape. On the other hand, two text instances which are close to each other may lead to a false detection which covers both instances. Traditionally, the segmentation-based approach can relieve the first problem but usually fail to solve the second challenge. To address these two challenges, in this paper, we propose a novel Progressive Scale Expansion Network (PSENet), which can precisely detect text instances with arbitrary shapes. More specifically, PSENet generates the different scale of kernels for each text instance, and gradually expands the minimal scale kernel to the text instance with the complete shape. Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances. Extensive experiments on CTW1500, Total-Text, ICDAR 2015 and ICDAR 2017 MLT validate the effectiveness of PSENet. Notably, on CTW1500, a dataset full of long curve texts, PSENet achieves a F-measure of 74.3% at 27 FPS, and our best F-measure (82.2%) outperforms state-of-art algorithms by 6.6%. The code will be released in the future.