Detecting Curve Text with Local Segmentation Network and Curve Connection

TL;DR

This paper introduces a novel framework combining local segmentation and curve connection to effectively detect horizontal, oriented, and curved text in real-world images, outperforming previous methods.

Contribution

The paper proposes a new framework with a local segmentation network and curve connection for robust curve text detection, addressing limitations of existing approaches.

Findings

Effective detection of various text orientations and shapes.

Outperforms previous methods on real-world datasets.

Demonstrates robustness in complex scenarios.

Abstract

Curve text or arbitrary shape text is very common in real-world scenarios. In this paper, we propose a novel framework with the local segmentation network (LSN) followed by the curve connection to detect text in horizontal, oriented and curved forms. The LSN is composed of two elements, i.e., proposal generation to get the horizontal rectangle proposals with high overlap with text and text segmentation to find the arbitrary shape text region within proposals. The curve connection is then designed to connect the local mask to the detection results. We conduct experiments using the proposed framework on two real-world curve text detection datasets and demonstrate the effectiveness over previous approaches.