OCR Module
Document Actions
The Optical Character Recognition (OCR) module provides interactive or batch conversion of raster images or regions to text entities. It is used to populate index fields, detect table of content, page numbers, paragraph text etc.. The converted text entities can be corrected or left uncorrected. In batch conversion, the paragraph text is saved as hidden text. These hidden text entities can be later used for searching and locating of the content.
- High accuracy OCR engine with fixed recognition engine (no learning mode)
- Interactive OCR correction when used to extract OCR values for fields
- Generates Image + Text PDF files when used in conjunction wth the PDF conversion module
- OCR engine operates as a service to other application to avoid interruption of large batch jobs
- Comprehensive log generation for accounting and error checking
- OCR cache generation for reuse of OCR results for several tasks