Detecting Multi-Oriented Text with Corner-based Region Proposals
This work addresses scene text detection for applications like image analysis, but it is incremental as it builds on existing region-based approaches.
The paper tackles the problem of detecting multi-oriented text in scenes by introducing a two-stage region-based method that uses corner detection and linking for adaptive quadrilateral proposals, achieving comparable performance with state-of-the-art methods on public benchmarks.
Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriented text without any prior knowledge regarding the textual shape. In the first stage, we estimate the possible locations of text instances by detecting and linking corners instead of shifting a set of default anchors. The quadrilateral proposals are geometry adaptive, which allows our method to cope with various text aspect ratios and orientations. In the second stage, we design a new pooling layer named Dual-RoI Pooling which embeds data augmentation inside the region-wise subnetwork for more robust classification and regression over these proposals. Experimental results on public benchmarks confirm that the proposed method is capable of achieving comparable performance with state-of-the-art methods. The code is publicly available at https://github.com/xhzdeng/crpn