Open Images V5 Text Annotation and Yet Another Mask Text Spotter
arXiv:2106.12326
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 ICDAR2013, ICDAR2015 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.
References in corpus (6)
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Detecting Curve Text in the Wild: New Dataset and New Solution
- An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
- UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
- Character Region Attention For Text Spotting
- MANGO: A Mask Attention Guided One-Stage Scene Text Spotter