Correlation Propagation Networks for Scene Text Detection
This addresses the problem of detecting multi-scale and multi-oriented text in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles scene text detection by proposing a Correlation Propagation Network (CPN), which uses a hybrid method combining top-down and bottom-up cues with a spatial communication mechanism to handle scale-varying and rotated text objects efficiently, achieving state-of-the-art performance on public benchmarks with lower computation cost.
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.