PP-OCR: A Practical Ultra Lightweight OCR System

By Yuning Du, Chenxia Li, Ruoyu Guo, Xiaoting Yin, Weiwei Liu, Jun Zhou, Yifan Bai, Zilin Yu, Yehua Yang, Qingqing Dang and 1 more. arXiv.org, 2020

321 citations recorded by the source corpus.

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 proposed PP-OCR are also verified in several other language recognition tasks, including French, Korean, Japanese and German. All of the above mentioned models are open-sourced and the codes are available in the GitHub repository, i.e., this https URL.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/da7bbf5b56921e4f4a0c6a51d0a53df8feac11e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yu Liu
2. Guanglu Song
3. Hao Shao
4. Hongsheng Li
5. Shengju Qian
6. Zhuofan Zong
7. Han Xiao
8. Letian Wang

In Media Technology

1. Yu Liu
2. Hongsheng Li

Citations in the corpus

• Step1X-Edit: A Practical Framework for General Image Editing (2025, unknown): “We use PPOCR [10], which focuses on recognizing correct characters, alongside the Step-1o model to distinguish correct and incorrect regions of text.”
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning (2024, methodology): “For the visual annotations, we choose PaddleOCR [12], an efficient and accurate tool for optical character recognition.”
• CogAgent: A Visual Language Model for GUI Agents (2023, unknown): “We collect natural images from COYO [6] and LAION-2B [32] and employ Paddle-OCR [13] to extract the texts and their bounding boxes, and filter out images with no text boxes.”
• Monkey: Image Resolution and Text Label are Important Things for Large Multi-Modal Models (2023, unknown): “…each bringing its own strength to the process: BLIP2 [27], which provides a deep understanding of the relationship between images and text; PPOCR [14], a strong performer in optical character recognition; GRIT [50], specializing in detailed image-text matching; SAM [24], focused on semantic…”