PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System

TL;DR

PP-OCRv2 is an improved ultra lightweight OCR system that employs various training tricks to enhance accuracy while maintaining high efficiency, making it suitable for real-world applications.

Contribution

The paper introduces PP-OCRv2, incorporating multiple novel training techniques to significantly boost OCR accuracy without increasing inference costs.

Findings

PP-OCRv2 achieves 7% higher precision than PP-OCR at the same inference cost.

The system's accuracy is comparable to server-based models using ResNet backbones.

All models and code are open-sourced in PaddleOCR GitHub repository.

Abstract

Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to balance the accuracy against the efficiency. In order to improve the accuracy of PP-OCR and keep high efficiency, in this paper, we propose a more robust OCR system, i.e. PP-OCRv2. We introduce bag of tricks to train a better text detector and a better text recognizer, which include Collaborative Mutual Learning (CML), CopyPaste, Lightweight CPUNetwork (LCNet), Unified-Deep Mutual Learning (U-DML) and Enhanced CTCLoss. Experiments on real data show that the precision of PP-OCRv2 is 7% higher than PP-OCR under the same inference cost. It is also comparable to the server models of the PP-OCR which uses ResNet series as backbones. All of the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.