Classification within PSIcapture is comprised of a whole series of features and functions that provide the next level of seamless automation. The Classification Module is a core piece of the overall system that allows automatic identification, separation and assembly of forms and disparate types of documents. Once documents are classified, they are assigned a record type which facilitates specific extraction methods for that form or type of document. This guide will provide an overview of the theory and functions of classification within PSIcapture, as well as a basic configuration overview.
Classification in PSIcapture provides the following core functionality:
- Classification/Identification of Forms and Documents
- Intelligent Separation (Document Splitting) based on classified forms within the scan stream
- Intelligent merging of document pages
- Page count validation
- Automatic Record Type designation
- Data Extraction based on record type rule sets