FormsRec®
The solution FormsRec® is capable of reading and processing a large volume of documents and automatically extracting data from these documents. The data gained in this way is then exported for further processing in the related systems, in this case there is an assumption of connection to the information system of the customer. FormsRec® also connects the processes for processing of hardcopy and electronic documents with the use of the latest technology such as fuzzy logic and fuzzy database. Even poorly legible documents can be identified well and display a very low error rate during subsequent processing. Missing or incomplete parts of records in the processed documents are automatically replaced with the correct values, and thus a high level is achieved for the quality of the results of the extracted data from the documents processed in this way.
FormsRec® is a scalable and expandable solution and it thus allows the processing of thousands of documents every day.
Main properties of the solution FormsRec®:
- Identification of several languages, use of Latin script
- Special version for Eastern European languages
- Function Auto-analysis for automatic calculation and optimisation of classification of forms
- Identification of all common barcodes
- Identification of handwritten text (block capitals)
- Reading of graphic symbols
- Automatic comparison at the level of the database - fully integrated TCL programming language allowing performance of adjustments and adaptation in all process states
- Implemented voting mechanisms for designation of optimal results in the case of differing results of the individual OCR systems
- Integrated verification procedures
- Function of transfer of resultant data to associated (for example, DMS) and archiving systems
- Automatic function for reading and processing of faxes
