{"url":"/dataset/mle2e","name":"MLe2e","full_name":null,"description_markdown":"MLe2 is a dataset for the evaluation of scene text end-to-end reading systems and all intermediate stages such as text detection, script identification and text recognition. The dataset contains a total of 711 scene images covering four different scripts (Latin, Chinese, Kannada, and Hangul).\r\n\r\nSource: [A fine-grained approach to scene text script identification](https://arxiv.org/abs/1602.07475)","description_withheld":null,"homepage":"https://github.com/lluisgomez/script_identification","introduced_date":"2016-02-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-fine-grained-approach-to-scene-text-script","title":"A fine-grained approach to scene text script identification","first_author":"Lluis Gomez","url":null},"license":null,"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"},{"name":"Scene Text Recognition","url":"/task/scene-text-recognition","datasets_with_task":"/datasets/task/scene-text-recognition"}],"languages":[],"variants":["MLe2e"],"data_loaders":[{"repo":"https://github.com/lluisgomez/script_identification","url":"https://github.com/lluisgomez/script_identification","frameworks":[]}],"num_papers_in_archive":6,"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."}