CCOCR is a Quick Server Extension Module designed to address the needs of production based Optical Character and Optical Mark Sense applications. CCOCR includes the ability to configure confidence levels to deal with the desire to route OCR exceptions to a user queue for review, applying character sets to look for white listed characters or character combinations. CCOCR also helps to detect the content of a checkbox, fill-in-area , multiple choice examination form, or any area where highlighting is required to indicate a certain choice. Check boxes, filled in circles or square, etc. similar to that of SCANTRON standardized test forms or surveys.
CCOCR contains the following features:
• Unicode Support.
• Multi-thread Support.
• Character recognition confidence.
• Retrieve character location.
• Output text.
• Support for PDF/A OCR generation (PDF Image + hidden searchable text).
• Support for near 40 languages such as English, French, Italian, German, Spanish, Brazilian Portuguese, Vietnamese, Chinese, Russian, Polish, Dutch, etc.
• Can recognize only digits, only alpha or only "white listed" characters.
• OCR context support. Defines if the engine is processing document, single word, single character, text block, vertical text etc...
• Fast area processing.
• Document orientation detection.