Open Images V5 Text Annotation and Yet Another Mask Text Spotter

Ilya Krylov (Intel)*; Sergei Nosov (Intel); Vladislav Sovrasov (Lobachevsky State University of Nizhny Novgorod)

---

PMLR Page

Abstract

A large scale human-labeled dataset plays an important role in creating high quality deep learning models. In this paper we present text annotation for Open Images V5 dataset. To our knowledge it is the largest among publicly available manually created text annotations. Having this annotation we trained a simple Mask-RCNN-based network, referred as Yet Another Mask Text Spotter (YAMTS), which achieves competitive performance or even outperforms current state-of-the-art approaches in some cases on ICDAR 2013, ICDAR 2015 and Total-Text datasets. Code for text spotting model available online at: https://github.com/openvinotoolkit/training_extensions. The model can be exported to OpenVINO-format and run on Intel ® CPUs.