{"url":"/dataset/imgur5k","name":"Imgur5K","full_name":null,"description_markdown":"**Imgur5k** is a large-scale handwritten in-the-wild dataset, containing challenging real world handwritten samples from nearly 5K writers. It consists of ~135K handwritten English words from 5K different images. As opposed to existing dataests for OCR which have limited variability in their images, the images in Imgur5K contain a diverse set of styles.","description_withheld":null,"homepage":"https://github.com/facebookresearch/IMGUR5K-Handwriting-Dataset","introduced_date":"2021-06-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/textstylebrush-transfer-of-text-aesthetics","title":"TextStyleBrush: Transfer of Text Aesthetics from a Single Example","first_author":"Praveen Krishnan","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://github.com/facebookresearch/IMGUR5K-Handwriting-Dataset/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Imgur5K"],"data_loaders":[{"repo":"https://github.com/sandhyasharma24/TrOCR_Model","url":"https://github.com/sandhyasharma24/TrOCR_Model","frameworks":["pytorch"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}