This document provides an agenda and overview for a webinar presented by Fujitsu and ReadSoft on document capture, classification, and automation. The webinar covers using Fujitsu scanners and ReadSoft software for invoice processing, the importance of document classification, trends toward higher resolution scanning, and information extraction techniques. An overview of the ReadSoft DOCUMENTS software suite and questions from attendees are also on the agenda.
[2024]Digital Global Overview Report 2024 Meltwater.pdf
Fujitsu & Readsoft Forms Classification and Document Automation Webinar
1. Fujitsu Scanners/ReadSoft Forms
Classification and Document Automation
Webinar
Kevin Neal
Product Manager – Production Scanners
Fujitsu Computer Products of America, Inc.
Imaging Products Group (IPG)
January 17, 2007
2. Agenda
• Introductions of Fujitsu and ReadSoft
– Kevin Neal, Fujitsu presenter
– Megan Fowler, Fujitsu moderator
– Bob Fresneda, ReadSoft presenter
• Document Capture
• Fujitsu scanners and ReadSoft DOCUMENTS for Invoices
• Document Classification considerations
• Trend toward Higher Resolution scanning
• Information Extraction techniques
• ReadSoft overview
– DOCUMENTS overview
– DOCUMENTS for Mailrooms
– DOCUMENTS for Invoices
– Corporate overview
• Questions and Answers
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
3. Document Capture
• Document Capture directly effects the entire automation workflow
• Document Capture begins with High Quality electronic images
• High Quality electronic images improve automation success
• Automation Success leads to improved business productivity
• Business Productivity reduces costs and improves process
• Improved Process creates a Business Advantage
Document Capture is the on-ramp to Automation
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
4. Invoice Processing
Paped-based challenges
• Manual sorting of documents
• Keying/miskeying data into backend systems
• Physical routing of documents/making copies
• Lost/misplaced copies of invoices
• Missing out on early pay discounts due to delays
• Accidentally paying same invoice more than once
• Faxing and/or shipping costs to route invoices
Preparation Input Capture Processing Presentation
Doc Prep High-Speed OCR, OMR Storage Access
Staples Image Quality Forms Processing Database Empower
Paperclips Integration Validate/Verify Archiving Efficient
Solving invoice challenges with Fujitsu and ReadSoft DOCUMENTS for Invoices
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
5. Fujitsu/ReadSoft DOCUMENTS for Invoices
Invoices
Doc Prep
Structure
Color Scanning
Paper Size
Image Quality
Quality
Paper Handling
Font Type
300dpi Speeds
ERP System
Electronic Images
Metadata
Database
ReadSoft DOCUMENTS
SAP
for Invoices
Understand
Oracle
Financials
Capture
Process
Client Workstations
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
6. Importance of Document Classification
Security = Rules based access or restriction of information
Information Silos
Searchability = Narrow searches enable more relevant data
Retention = Adhere to business policy or compliance regulations
Human Resources
Human Resources
Accounting
Accounts Payable
Records Managers
Shipping/Receiving
Business Management
Sales/Marketing
Customer Service
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
7. Higher Resolution for Forms Processing
“Scanning at true 300 dpi optical resolution is very important. Scanning at a lower resolution
and then using scanner software to increase the dpi later on does nothing for OCR. In
cases where the font size of characters on an image are very small ( point size of 4 or
less), scanning images in at 400 dpi can improve character recognition. This again would
require a scanner that supports true 400 dpi optical resolution.”
Source: http://www.primerecognition.com/augprime/ocr_faq.htm
“The accuracy of the OCR systems declined dramatically when the resolution of the images
was reduced from 300 to 200 dpi…”
Source: The Fourth Annual Test of OCR Accuracy ( http://www.isri.unlv.edu/downloads/AT-1995.pdf )
“Scan resolution: The number of dots per inch can affect the clarity of the image and accuracy
of OCR. Recent tests found that reducing from 300 dpi to 200 dpi increased the OCR error
rate for a complex document by 75%…”
Source: http://www.collectionscanada.ca/9/1/p1-236-e.html
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
8. Trends toward Higher Resolution Scanning
• Increased accuracy
• More automation techniques
• Decreased storage costs
– Affordability of magnetic storage, DVD, optical, etc.
• Document Classification intelligence
– Instructed Invoices
– Semi-Structured Accounts Payable documents
– Handprint Recognition
• Rated scanning speeds – No speed degradation
– No longer need to sacrifice throughput at 300 dots per inch
• Bandwidth and Network Infrastructure
– Corporate T1, OC3, DSL, Cable Modem, Wireless
• Improved image compression
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
9. Information Extraction
Optical Mark Recognition
Imaging Database fields
(OMR) index fields
Intelligent Character Recognition
(ICR) index fields
Optical Character Recognition (OCR)
makes documents fully searchable
Legible signature
SSN and contact information
sent to database field
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
10. Importance of Image Quality
• Anchor points to identify know form types
• Forms processing accuracy
– Optical Character Recognition
• 300dpi drastically increases accuracy
Anchor Points for
– Intelligent Character Recognition Forms Identification
– Optical Mark Recognition
• Database validation
– Automatic record matching
• Lack of Human Intervention
• More accurate electronic reproduction of original documents
• Image Enhancement
– Automatic Orientation
– Noise Removal
– Deskew, Cropping, Intelligent Blank Page Removal, etc.
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
11. Color Documents
• Dropout Color options
– Color reduction (background washout)
– Forms outline removal
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar
12. Distributed or Centralized Scanning
Applications
Way Bills Legal Documents
Bills of Lading Employee Records
Proof of Delivery HR Forms
Shipping Logs
HR
TeleCommuter
Warehouse Shipping
AP General
Field Sales Person Remote Office
Expense Receipts
Invoices
Customer Contracts
Freight Bills
Credit Applications
Centralized Scanning Scenario Scan to E-mail
Business Agreements
Document Distribution
Fujitsu Scanners/ReadSoft Forms Classification and Document Automation Webinar