Sliding Line Point Regression for Shape Robust Scene Text Detection

TL;DR

This paper introduces Sliding Line Point Regression (SLPR), a novel method for detecting arbitrary-shaped scene text by regressing edge points to outline text, adaptable to various detection architectures and achieving competitive results.

Contribution

The paper proposes SLPR, a new flexible approach for shape-robust scene text detection that efficiently regresses edge points using sliding lines and integrates with existing detection frameworks.

Findings

Achieved competitive results on ICDAR2015 benchmark.

Effective detection of curved and arbitrary-shaped text.

Reduced system parameters and improved regularity of detected polygons.

Abstract

Traditional text detection methods mostly focus on quadrangle text. In this study we propose a novel method named sliding line point regression (SLPR) in order to detect arbitrary-shape text in natural scene. SLPR regresses multiple points on the edge of text line and then utilizes these points to sketch the outlines of the text. The proposed SLPR can be adapted to many object detection architectures such as Faster R-CNN and R-FCN. Specifically, we first generate the smallest rectangular box including the text with region proposal network (RPN), then isometrically regress the points on the edge of text by using the vertically and horizontally sliding lines. To make full use of information and reduce redundancy, we calculate x-coordinate or y-coordinate of target point by the rectangular box position, and just regress the remaining y-coordinate or x-coordinate. Accordingly we can not only reduce the parameters of system, but also restrain the points which will generate more regular polygon. Our approach achieved competitive results on traditional ICDAR2015 Incidental Scene Text benchmark and curve text detection dataset CTW1500.