ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene

TL;DR

This paper introduces ArbText, a novel detector for arbitrary-oriented text in natural scenes, using circle anchors and pyramid pooling to improve robustness and accuracy in challenging conditions.

Contribution

The paper proposes a new text detection method with circle anchors and pyramid pooling, enhancing robustness to orientation and scale variations in unconstrained scenes.

Findings

Outperforms state-of-the-art on ICDAR 2015 dataset

Achieves superior results on MSRA-TD500 dataset

Demonstrates robustness to orientation and illumination variations

Abstract

Arbitrary-oriented text detection in the wild is a very challenging task, due to the aspect ratio, scale, orientation, and illumination variations. In this paper, we propose a novel method, namely Arbitrary-oriented Text (or ArbText for short) detector, for efficient text detection in unconstrained natural scene images. Specifically, we first adopt the circle anchors rather than the rectangular ones to represent bounding boxes, which is more robust to orientation variations. Subsequently, we incorporate a pyramid pooling module into the Single Shot MultiBox Detector framework, in order to simultaneously explore the local and global visual information, which can, therefore, generate more confidential detection results. Experiments on established scene-text datasets, such as the ICDAR 2015 and MSRA-TD500 datasets, have demonstrated the supe rior performance of the proposed method, compared to the state-of-the-art approaches.