Chinese-Character-Recognition
A TensorFlow CNN implementation for Chinese character recognition, achieving 92.5% top-1 accuracy with batch normalization.
What is Chinese-Character-Recognition?
Chinese-Character-Recognition is a TensorFlow-based project that implements a convolutional neural network (CNN) for recognizing handwritten Chinese characters. It solves the complex problem of Chinese character recognition, which involves distinguishing between thousands of characters compared to just 10 digits in MNIST. The project includes a clean codebase with batch normalization and achieves 92.5% top-1 accuracy.
Machine learning practitioners, students, and researchers interested in computer vision, particularly those working on optical character recognition (OCR) for non-Latin scripts like Chinese.
Developers choose this project for its clean, modular implementation that outperforms previous versions, its inclusion of batch normalization for better generalization, and the availability of preprocessed datasets and trained checkpoints for quick experimentation.
Overview
This project shows how to use CNN to perform Chinese character recognition, a much more complicated task compared to MNIST digit recognition.
Use Cases
Best For
- Learning CNN architectures for complex character recognition tasks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
