-
ICDAR-2015 Robust Reading Competition
The ICDAR-2015 Robust Reading Competition dataset contains images with text in various fonts, sizes, and orientations. -
ICDAR 2013
ICDAR 2013 consists of 229 training images and 233 testing images, and similar to ICDAR 2015, it also provides "Strong", "Weak" and "Generic" lexicons for text spotting task.... -
SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition
The proposed model performs OCR at paragraph level, without any prior segmentation stage. -
ICDAR 2013 Robust Reading Competition
The ICDAR 2013 robust reading competition dataset. -
OCR dataset
The OCR dataset is a dataset of handwritten digits, each image is an 8x16 binary image, and there are 52152 samples in total.
