[2009.09941] PP-OCR: A Practical Ultra Lightweight OCR System

The Optical Character Recognition (OCR) systems have been widely used in various of application scenarios, such as office automation (OA) systems, factory automations, online educations, map productions etc. However, OCR is still a challenging task due to the various of text appearances and the demand of computational efficiency. In this paper, we propose a practical ultra lightweight OCR system, i.e., PP-OCR. The overall model size of the PP-OCR is only 3.5M for recognizing 6622 Chinese characters and 2.8M for recognizing 63 alphanumeric symbols, respectively. We introduce a bag of strategies to either enhance the model ability or reduce the model size. The corresponding ablation experiments with the real data are also provided. Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17.9M images are used). Besides, the propos

1 mentions: @Nextremer_nb_o
Date:

Referring Tweets

@Nextremer_nb_o
@Nextremer_nb_o これやってみて、PaddleOCRの論文見始めた。 まずはPP-OCRv1。 テキスト位置の検出→矩形を回転させたときのテキスト向き検出→文字認識 ここのモデルを組み合わせているんだな。PP-OCRはそれぞれを軽量・最適化している。なるほど〜。 t.co/O4olXdb6FP t.co/5llcTU9SyA

Related Entries

GitHub - google-coral/aiy-maker-kit: Simple Python API for ML inferencing with TF Lite and Coral Edg...
Read more GitHub - google-coral/aiy-maker-kit: Simple Python API for ML inferencing with TF Lite and Coral Edg...
0 users, 1 mentions 2022/05/17 13:37
GitHub - NobuoTsukamoto/meta-tensorflow-lite at coral_edgetpu
Read more GitHub - NobuoTsukamoto/meta-tensorflow-lite at coral_edgetpu
0 users, 1 mentions 2022/07/04 13:38
GitHub - opencv/cvat: Annotate better with CVAT, the industry-leading data engine for machine learni...
Read more GitHub - opencv/cvat: Annotate better with CVAT, the industry-leading data engine for machine learni...
0 users, 1 mentions 2022/09/12 22:37
GitHub - cvat-ai/cvat-opencv: Annotate better with CVAT, the industry-leading data engine for machin...
Read more GitHub - cvat-ai/cvat-opencv: Annotate better with CVAT, the industry-leading data engine for machin...
0 users, 1 mentions 2022/09/12 22:37
GitHub - imaginationtech/PaddlePaddle_Model_zoo: Imagination Technologies model zoo for Paddle Paddl...
Read more GitHub - imaginationtech/PaddlePaddle_Model_zoo: Imagination Technologies model zoo for Paddle Paddl...
0 users, 1 mentions 2022/09/28 00:09
models/official/projects/mosaic at master · tensorflow/models · GitHub
Read more models/official/projects/mosaic at master · tensorflow/models · GitHub
0 users, 1 mentions 2022/11/07 13:37

ML-Newsについて

機械学習の技術に関する情報は流速も早いし、分野も多様でキャッチアップが大変です。Twitterで機械学習用のリストを作っても、普段は機械学習以外の話題が多く流れており、効率的に情報収集するのは困難です。

ML-NewsはSNSを情報源とした機械学習に特化したニュースサイトです。機械学習に関する論文ブログライブラリコンペティション発表資料勉強会などの最新の情報を効率的に収集できます。

機械学習を応用した自然言語処理、画像認識、情報検索などの分野の情報や機械学習で必要になるデータ基盤やMLOpsの話題もカバーしています。
安定したサイト運営のためにGitHub sponsorを募集しています。

お知らせ

  • 2021/12/31: デザインを刷新しました
  • 2021/04/08: 日本語Kaggleのカテゴリを新設しました