12 datasets found

The Multi-Lingual dataset is a benchmark for scene text recognition, containing 9,000 images with 9 languages.

CUTE is released by Risnumawan et al. There are only 288 word images in this dataset, but most of them are seriously curved.

SVT is a very challenging dataset collected by Wang et al. from the Google Street View.

The OCR and MT datasets are used to train the OCR and MT models respectively.

Scene text recognition using higher order language priors

SynthText dataset is proposed by Gupta et al. for scene text detection. The original dataset is composed of 800,000 scene text images, each with multiple word instances.

Diffusion Model for Scene Text Recognition

Scene text recognition with sliding convolutional character models.

Scene text recognition using higher order language priors.

Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. The proposed...

The dataset contains images of text in natural scenes, including street signs, logos, and product labels.

Scene text recognition (STR) is a challenging task in computer vision due to the large number of possible text appearances in natural scenes.