chineseocr is an end-to-end deep learning pipeline for detecting and recognizing Chinese and English text in images. The project combines text region detection using YOLOv3 with sequence-based recognition via Convolutional Recurrent Neural Networks (CRNN) and dense OCR models, forming a complete optical character recognition workflow.
The pipeline includes orientation detection to handle text rotated at 0, 90, 180, or 270 degrees before recognition, and supports structured field extraction from identity cards and train tickets. A multi-framework model converter enables trained models to be converted between darknet, Keras, and PyTorch formats for cross-framework deployment.
The system provides capabilities for text region detection using darknet, OpenCV DNN, or Keras backends, along with variable-length text recognition for both Chinese and English characters. The documentation covers model conversion tools and the end-to-end pipeline configuration.