{"url":"/method/pp-ocr","slug":"pp-ocr","name":"PP-OCR","full_name":"PP-OCR","full_name_withheld":false,"description_markdown":"**PP-OCR** is an OCR system that consists of three parts, text detection, detected boxes rectification and text recognition. The purpose of text detection is to locate the text area in the image. In PP-OCR, Differentiable Binarization (DB) is used as text detector which is based on a simple segmentation network. It integrates feature extraction and sequence modeling. It adopts the Connectionist Temporal Classification (CTC) loss to avoid the inconsistency between prediction and label.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PP-OCR: A Practical Ultra Lightweight OCR System","paper":"/paper/pp-ocr-a-practical-ultra-lightweight-ocr","first_author":"Yuning Du","n_authors":11,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pp-ocr-a-practical-ultra-lightweight-ocr"},"source":{"url":"https://arxiv.org/abs/2009.09941v3","title":"PP-OCR: A Practical Ultra Lightweight OCR System","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"OCR Models","url":"/methods/category/ocr-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":null,"title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","date":"2025-02-25","arxiv_id":"2502.18148","n_code_links":0,"syntology":null},{"paper":null,"title":"OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst","date":"2024-06-14","arxiv_id":"2406.09779","n_code_links":0,"syntology":null},{"paper":"/paper/pp-ocrv2-bag-of-tricks-for-ultra-lightweight","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","date":"2021-09-07","arxiv_id":"2109.03144","n_code_links":3,"syntology":{"ran":0,"of":6,"unverified":6,"pointer_only":0}},{"paper":"/paper/pp-ocr-a-practical-ultra-lightweight-ocr","title":"PP-OCR: A Practical Ultra Lightweight OCR System","date":"2020-09-21","arxiv_id":"2009.09941","n_code_links":10,"syntology":{"ran":0,"of":12,"unverified":12,"pointer_only":0}}],"papers_shown":4,"tasks":[{"task":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","papers":4},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition","papers":3},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/language-identification","name":"Language Identification","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/transliteration","name":"Transliteration","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pp-ocr"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}