# Deep learning-enabled hybrid systems for accurate recognition of text in seal images

## TL;DR

This paper presents a hybrid system using deep learning to accurately recognize text on Chinese seals, which are often challenging due to noise and minimal image features.

## Contribution

The novel contribution is a hybrid model combining preprocessing, deep learning, and text unwrapping techniques for improved Chinese seal text recognition.

## Key findings

- A color-based method effectively removes background text on seals.
- A deep learning-based angle prediction network improves seal image positioning.
- Polar coordinate transformation enhances text recognition accuracy.

## Abstract

Chinese seals are widely used in various fields within Chinese society as a tool for certifying legal documents. However, recognizing text on these seals presents challenges due to background text, high noise levels, and minimalistic image features. This paper introduces a hybrid model to address these difficulties in Chinese seal text recognition. Our model integrates preprocessing techniques tailored for real seals, a deep learning-based position correction model, a circular text unwrapping model, and OCR text recognition. First, we apply a color-based method to effectively remove the black background text on seals, eliminating redundant information while retaining crucial features for further analysis. Next, we introduce an innovative image denoising algorithm to significantly improve the system's robustness in processing noisy seal images. Additionally, we develop a deep learning-based angle prediction network and create synthetic datasets that mimic real seal scenes, enabling optimal seal image positioning for enhanced text flattening and recognition, thus boosting overall system performance. Finally, polar coordinate transformation is employed to convert the circular seal into a rectangular image for more efficient text recognition. Experimental results indicate that our proposed methods effectively enhance the accuracy of seal text recognition.