Simplified Chinese Language Support for OCRopus

Existing Open Source OCR Systems that Can Handle Simplified Chinese

Existing Commercial OCR Systems that Can Handle Simplified Chinese

• SunmiPage Chinese OCR API Engine - ~$40 (information in English)
• Readiris Pro 11 Asian Edition - $199.99 (information in English)
• Tsing-Hua OCR (information in English and Chinese)
• Hanvon Wenben Wang Wen Hao 7600 - USD $427 (information in Chinese )
• Hanvon Smart Reader Master (information in English)
• VIP Browser, browses scanned technical journals in Chinese, with integrated OCR feature (information in Chinese)
  

Technical Papers

• High Performance Chinese Ocr Based On Gabor Features, Discriminative Feature Extraction And Model Training (PDF)
• Zhang, et al. A Robust Approach for Recognition of Text Embedded in Natural Scenes (PDF)
  
• Neural Network Classifiers for Optical Chinese Character Recognition - With compiled binary demo (HTML, PDF)
• Optical Chinese Character Recognition using Probabilistic Neural Networks (HTML, PDF)

Ground-Truthed Simplified Chinese OCR Data (Scans + Transcription)

Simplified Chinese Dictionaries and Text Corpora (for Statistical Language Modeling)

Other Issues