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.
翻译:大型人类标签数据集在创建高品质深层学习模型方面发挥了重要作用。 在本文中, 我们为开放图像V5数据集提供文本说明。 据我们所知, 这是公开手动创建的文本说明中最大的。 有了这种说明, 我们训练了一个简单的Mask- RCNN 网络, 称为“ 另类面具文本显示器 ” (YAMTS), 取得竞争性的性能, 甚至在某些情况中, ICDAR2013、 ICDAR2015 和 Total-Text 数据集的当前最先进方法超前。 文本识别模型的代码可以在以下网址上查到: https://github.com/ openvinotoolkit/ training_ extensions。 该模型可以导出到 OpenVINO- 格式, 并在 Intel CPUs 上运行 。