Correlation Propagation Networks for Scene Text Detection

TL;DR

This paper introduces Correlation Propagation Networks, a novel end-to-end trainable framework for scene text detection that effectively handles multi-scale and multi-oriented texts with high efficiency.

Contribution

The paper presents a hybrid CNN-based method utilizing correlation propagation for flexible, scale-varying, and rotated text detection without predefined templates, improving accuracy and efficiency.

Findings

Achieves state-of-the-art performance on public benchmarks.

Significantly outperforms existing methods in multi-scale and multi-oriented text detection.

Offers a computationally efficient and highly parallelizable approach.

Abstract

In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN). It is an end-to-end trainable framework engined by advanced Convolutional Neural Networks. Our CPN predicts text objects according to both top-down observations and the bottom-up cues. Multiple candidate boxes are assembled by a spatial communication mechanism call Correlation Propagation (CP). The extracted spatial features by CNN are regarded as node features in a latticed graph and Correlation Propagation algorithm runs distributively on each node to update the hypothesis of corresponding object centers. The CP process can flexibly handle scale-varying and rotated text objects without using predefined bounding box templates. Benefit from its distributive nature, CPN is computationally efficient and enjoys a high level of parallelism. Moreover, we introduce deformable convolution to the backbone network to enhance the adaptability to long texts. The evaluation on public benchmarks shows that the proposed method achieves state-of-art performance, and it significantly outperforms the existing methods for handling multi-scale and multi-oriented text objects with much lower computation cost.