Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition

TL;DR

Total-Text is a new dataset designed to include curved, multi-oriented, and horizontal scene texts, filling a significant gap in existing datasets, and it enables evaluation of segmentation-based text detection methods on curved text.

Contribution

The paper introduces Total-Text, a comprehensive dataset with diverse text orientations including curved text, and benchmarks segmentation-based detection methods on it.

Findings

DeconvNet performs robustly on curved text in Total-Text.

Total-Text dataset contains diverse orientations, with over half of images having multiple orientations.

Segmentation-based methods are effective for curved text detection.

Abstract

Text in curve orientation, despite being one of the common text orientations in real world environment, has close to zero existence in well received scene text datasets such as ICDAR2013 and MSRA-TD500. The main motivation of Total-Text is to fill this gap and facilitate a new research direction for the scene text community. On top of the conventional horizontal and multi-oriented texts, it features curved-oriented text. Total-Text is highly diversified in orientations, more than half of its images have a combination of more than two orientations. Recently, a new breed of solutions that casted text detection as a segmentation problem has demonstrated their effectiveness against multi-oriented text. In order to evaluate its robustness against curved text, we fine-tuned DeconvNet and benchmark it on Total-Text. Total-Text with its annotation is available at https://github.com/cs-chan/Total-Text-Dataset