Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

TL;DR

This paper introduces a novel scene text detection method combining corner localization and region segmentation, effectively handling arbitrary orientations and large aspect ratios without complex post-processing.

Contribution

The proposed approach uniquely integrates corner detection with region segmentation to improve accuracy and efficiency in multi-oriented scene text detection.

Findings

Achieves an F-measure of 84.3% on ICDAR2015

Performs better or comparable to state-of-the-art methods

Handles long oriented text naturally

Abstract

Previous deep learning based state-of-the-art scene text detection methods can be roughly classified into two categories. The first category treats scene text as a type of general objects and follows general object detection paradigm to localize scene text by regressing the text box locations, but troubled by the arbitrary-orientation and large aspect ratios of scene text. The second one segments text regions directly, but mostly needs complex post processing. In this paper, we present a method that combines the ideas of the two types of methods while avoiding their shortcomings. We propose to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions. In inference stage, candidate boxes are generated by sampling and grouping corner points, which are further scored by segmentation maps and suppressed by NMS. Compared with previous methods, our method can handle long oriented text naturally and doesn't need complex post processing. The experiments on ICDAR2013, ICDAR2015, MSRA-TD500, MLT and COCO-Text demonstrate that the proposed algorithm achieves better or comparable results in both accuracy and efficiency. Based on VGG16, it achieves an F-measure of 84.3% on ICDAR2015 and 81.5% on MSRA-TD500.