8 datasets found

Formats: JSON Tags: Text Recognition

Filter Results

  • Total-Text

    Total-Text is a dataset for word-level arbitrary-shaped English text detection, containing 1,255 images for training and 300 images for testing.

  • SVTP

    Recognizing text with perspective distortion in natural scenes

  • Focusing Attention: Towards Accurate Text Recognition in Natural Images

    Focusing attention: Towards accurate text recognition in natural images.

  • CUTE80

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

  • SVT Perspective

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

  • ICDAR 2015

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

  • STRAug

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

  • TextZoom

    Scene text image super-resolution (STISR) has been regarded as an important pre-processing task for text recognition from low-resolution scene text images.
You can also access this registry using the API (see API Docs).