PSIGEN provides trusted capture, Enterprise Content Management (ECM,) document management, and cloud solutions to help you meet your business needs while reducing costs. PSI Capture is our advanced document capture and data extraction and classification platform that integrates with any scanning device and more than 60 ECM systems.
No matter the size and scope of an organization, whether it has 10 employees in one office or 500 scattered across several locations, PSIcapture will make document processes easy and efficient.
Competitively priced, truly scalable and uniquely versatile, PSIcapture is the ideal document capture solution. A single capture platform designed to meet all the needs of an organization, including document scanning and import, forms processing, data capture, OCR/ICR data extraction and the ability to migrate the information into a document repository.
Document capture is the first step in any workflow. It provides integration with direct-connect scanners, multifunction printers (MFPs) and network-based image folders. Capture can be used interactively or it can be automated by using the auto-import feature, which allows automatic import from hot folders, SharePoint Document Libraries, RightFax Servers or FTP/SFTP servers.
Once documents are imported, QA allows the user to review the pages to verify image quality. Unsatisfactory pages can be replaced, missing pages inserted, and pages requiring rotating or cropping can be changed to suit the user’s needs. Image processing also allows pages to be manipulated to improve poor quality images.
OCR provides a powerful feature set that allows the conversion of images to a number of standard formats, such as PDF, PDF/A, HTML 4, XML, TXT. Other features of OCR include multiple page recognition, Zone OCR—which provides the ability to split files based on key terms—PDF field population, and more. OMR provides the ability to intelligently read check boxes or bubble sheets and convert the results into meaningful data. OMR can be used for anything from test grading to determining results of polls and surveys.
ICR converts hand-printed text on forms into index field data. The indexed data can then be routed to the document management system as metadata, making the form searchable by the information that was originally hand-printed data.
ADE is an advanced data extraction and parsing engine that can intelligently apply scripting or pattern matching logic to metadata, which provides greater accuracy to OCR, ICR, manual data entry and auto populated fields. ADE virtually eliminates the need for hand-keying information, increases accuracy and reduces the time required for the metadata capture process.
PSIcapture’s document classification feature set allows intelligent classification of forms and documents utilizing the OCR and ADE technologies. Through our forms processing engine, you can auto-extract complex data structures and information from disparate documents.
The Accelerated Classification Engine (ACE) is cutting-edge technology that allows users to build Classification rules in the middle of a workflow. Instead of configuring rules for Classification prior to running the workflow, ACE automatically classifies never-before-seen documents. All the end-user must do is verify that the automatic Classification is correct. Taking it a step further, ACE can access existing sets of indexed information, such as a database, find their location on the document and extract the data you are looking for. With ACE, users can simply validate the Classification and Data Extraction that has been intelligently identified, reducing a process that once took hours to under a minute.
PSIcapture’s Table Extraction provides a powerful line-item extraction technology to speed up the
extraction of invoice data and allow AP personnel to quickly and easily verify and validate data. Table Extraction can span multiple pages and be configured to suit your business’s unique structure and needs. Table Extraction works hand in hand with Classification, so when invoices get processed through the Classification step, the vendor is identified and the line-item data is automatically extracted. Classification will also determine if the invoice contains a table, and if so, Table Extraction will only be used on applicable documents.
The invoices and data will then be moved into the Quality Assurance step, where your AP personnel can verify the data collected then send it on to the migration step, publishing it to whatever repository or accounting program your business uses.
Table extraction is also useful in processing other documents classifications such as Purchase Orders, Transcripts, and Explanations of Benefits.
Once your documents have been fully processed, the final step in the workflow is Migration, which provides connectivity to your ECM system. PSIGEN supports migration, sometimes referred to as publication, to more than 67 ECM systems, allowing for the seamless transfer of your documents and indexed data into your repository. An updated list is kept at www.PSIGEN.com.