Papyrus Document Capture System 7

Product Information: Papyrus Document Capture System 7

FILE SOCIAL WEB Papyrus Capture/ MOBILE SCAN EMAIL FAX Papyrus WebRepository Scan-/File-/ XML-/Email- Automated processing Receiver Any image format, PDF or Recognition File System native MS Oﬃce documents Images to Server Manual processing Index & Images object structure Classify doc type, recognize and Validation extract index Batch/Detail data Check extracted Validation data with Client business rules External or Perform manual Supervisor internal database correction and Client Lookup for validate document data validation Perform special correction of documents

File System Data Archive & Export: Export validated data as XML, CSV or TXT and additional binary data as TIFF or PDF XML data

Concept Outline Every day a company receives a multitude of different documents - letters, image The Papyrus Document data, PDF and Office documents - all of which must be processed quickly and for- warded to the right place. Therefore, the configuration and operation of a capture Capture concept provides an system must be fast and efficient, regardless of document types, capture hardware integrated corporate solution and operating systems used. for powerful and efficient Based on the Papyrus Business Application Platform, ISIS Papyrus has developed the development, operation and most powerful tools for building document capture applications. Large banks, insur- ance companies, government organizations, industry and service companies have management of document one thing in common, they need fast development, elimination of programming ef- capture systems. fort and absolute independence from operating systems and scanners - all inherent to the Papyrus Document Capture System.

Contact Europe America Asia Pacific Email & Web © 2020, ISIS Papyrus, T: +43-2236-27551 T: 817-416-2345 T: +65-6339-8719 [email protected] replaces all previous F: +43-2236-21081 F: 817-416-1223 F: +65-6336-6933 www.isis-papyrus.com documentation. Product Information: Papyrus Document Capture System 7

The Capture Applications Papyrus Client/Capture for Windows The Papyrus Client/Capture is the interface for all kinds of user The ISIS Papyrus Document Capture System covers the entire interactions within a document capture system. It enables, spectrum of possible inbound applications: Scanning or im- among other things, the completion and correction of classi- porting documents, classifying and extracting indexes and fication and extraction results with all necessary display and data, post-processing the results and transferring documents validation functions. and data to any business application. This includes the recognition of document layouts as well as the extraction of specific Papyrus Scan for Windows contents under consideration of definable document logic, in- Papyrus Scan is the Papyrus WebRepository-based application for terfaces for data validation and highly functional masks for the scanning documents and automatic import of scanned images completion of the data. into the Depot Nodes of the Papyrus WebRepository. It supports Twain and EMC Captiva ISIS PixTools scanner interfaces and can Since all recognition engines are already available during be used with both document and barcode scanners. design time, capture quality and results can be verified right Papyrus WebRepository for z/OS Unix, z/Linux, HP-UX from the beginning. Additional tools for the high-volume Itanium, AIX, Solaris, Linux and Windows benchmarking of detection and rejection rates guarantee op- The Papyrus WebRepository is the core component of the Pa- timal preparation before going live. pyrus Objects Business Application Platform. It enables the control of all applications and document types across all plat- Additional tools for high volume benchmarking of automation forms and output channels, for both online and offline users. and rejection rates guarantee optimal production preparation It provides customizable audit and reporting capabilities and before going live. These frameworks include all necessary doc- Papyrus Adapters (e.g. Scan, Fax, Email, SOAP, REST) enable ument and data field definitions as well as ready-made views seamless integration with other business applications. for business administration and workflow design. Papyrus WebArchive for z/OS native, z/OS Unix, z/Linux, Papyrus Capture Products HP-UX Itanium, AIX, Solaris, Linux and Windows The Papyrus WebArchive offers an integrated archiving solution Papyrus Capture Recognition Server for Windows and Linux consisting of a central or distributed short-term and/or long- Papyrus Recognition Server is the technological basis for the term archive for all incoming and outgoing document types in development of self-learning modules to classify business any format. Optionally, the storage of associated business cas- documents and extract their data. Recognition Server offers a es is also possible. It offers a document query and retrieval user wide range of document capture and extraction methods for interface that integrates with other Papyrus business applica- structured, semi-structured and completely unstructured doc- tions via the Papyrus EYE Widgets technology, a web browser or uments. It also includes automated sorting and distribution of the Papyrus Enterprise Mobile App for iOS and Android devices. electronic documents (PDF, Office formats, image formats), fax and paper mail. Prerequisites Papyrus Capture Designer for Windows Windows Vista/7/8/10/Server 2008/Server 2012/Server 2016 The Papyrus Capture Designer is an application used by the Papyrus Capture Recognition Server is also available for Linux. Capture application developer for the design and development of elaborate data extraction projects. It features FixForm and FreeForm® technologies which enable the creation of extraction definitions for data from structured, semi-structured as well as unstructured documents. Its sophisticated, user-friendly interface enables the smooth development of hierarchically organized definitions for the extraction of document fields.

Papyrus Business Designer/Capture for Windows The Papyrus Business Designer/Capture is the core interface Order Information allowing business users to work with the document capture The ISIS Papyrus Document Capture System consists solution. It employs user-trained algorithms to continuously of independent components. Even though these are improve the capture results of the powerful OCR engines (for completely integrated, most of them can be used machine writing) and ICR engines (for hand writing) during standalone if required. content and case management operations, such as ad-hoc and on-the-fly extraction/indexing of documents in a busi- Maintenance ness case. This is possible because the Papyrus Business De- signer/Capture does not require IT-involvement but gives all The Terms and Conditions for ISIS Papyrus Software the power into the hands of the actual business user. Products apply. Free service period is 6 months after installation. A maintenance agreement is offered optionally for updates and hotline. Product Information: Papyrus Designer/Capture

Papyrus Designer/Capture

Product Description The Papyrus Designer/Capture is a very powerful toolkit to define classification and data extraction setups for automated data recognition of different kinds of documents.

Papyrus Designer/Extract component helps to easily create definitions of scanned or electronic unsorted business documents with unknown structure and layouts such as invoices, lists and complex tables. It also provides all necessary tools for a prompt definition of Unmatched power to data extraction parameters to process all kinds of structured form layouts. define classification and Papyrus Designer/Classify component supports a self-learning module for classification of data extraction on all documents that offers a broad range of possibilities for application in the field of automated sorting and distribution of electronic documents, fax and paper mail. types of documents.

Accepting a challenge of the modern world to extract only business relevant content out of high volume inbound paper and digital correspondence, the Papyrus Designer/Capture is much more than just a text recognition design tool. It has an excellent capability to identify required business content by means of pattern recognition, keywords, relative positions, rules etc. and a powerful mixture of these means.

Key Benefits Papyrus Designer/Classify • Compare the results with previous generated “golden files” of intended • Content digitizing: extraction The Papyrus Designer/Classify is used extract data. definition of business relevant to define categories to be classified, content out of high volumes of the extraction of feature sets and the Various display support tools enable inbound data classification strategy. you to define new documents fast: • Classification and extraction • Display candidates for extraction definition for both FixForm and The Designer/Classify supports • Show regions and coherences FreeForm® documents automation of several definition steps. • Convenient tag tools • Support of documents from all It also enables the easy handling of common inbound channels and file sample data. The Designer/Classify is The Papyrus Capture/Extract formats fully integrated into Papyrus Objects. module provides a possibility for • Powerful set of classification and document reclassification definition extraction definition features Supported classification steps based on: or classification definition based on • Support of diverse recognition • Keywords and its combination the very deep document structure engines for different kinds of content • Layouts analysis. This gives a big flexibility for • In collaboration with Papyrus • Advanced text the document design and processing Recognition Server, provides a high- • Logos definitions of complex documents. level automated setup for content digitizing Before you start working with the • Fast definition and testing of new Designer/Classify, the required Data Formats document types document categories have to be • TIFF 6.0 or higher (also multi-page) defined. With a number of sample • JPEG, JPEG 2000, BMP, GIF, PNG Features documents (a few dozen) for each • HTML, CSV, TXT (plain text) category the system is trained in order • PDF 1.4 or higher, PDF/A (ISO 19005) Package Components to learn the specific properties of each • AFP • Papyrus Designer/Extract document class. New categories can • Office formats: • Papyrus Designer/Classify also be added easily and conveniently. • DOC/DOCX/DOCM/ODT • PPT/PPTX/PPTM/ODP Image Preprocessing The Papyrus Designer/Extract • XLS/XLSX/XLSM/ODS Papyrus Designer Capture allows component empowers classification automatic or adjusted preparation of capabilities by letting to define some the image data for optimal recognition Prerequisites classification logic even on a later stage results. This is especially important for • Windows 7 or later; Windows Server – during extraction. scanned and photo images. 2012 or later • Standard office PC • Dirt removal, Despeckle Papyrus Designer/Extract • Papyrus WebRepository • Punch hole removal To discover relevant content the • Papyrus Capture /Office-In for office • Automatic rotation following main possibilities and formats support • Binarize their mixture are usually used in the • Papyrus PDF-in for native PDF • Convert color to gray extraction definition support • Box, line, grid and combs remover • Patterns • Drop out color • Keywords • Dilate • Regions • Erode • Positions • Deskew on border • Anchor points Order Information • Deskew on content • Rules Papyrus Designer/Capture • Layout for Windows Recognition Engines • Logo Content of preprocessed images is recognized by a powerful set of Basic Definition Process Structure Training recognition engines belonging to the • Define all document types that occur ISIS Papyrus offers in-house following main groups: • Define the elements of interest on workshops and standard courses • Optical character recognition (OCR) – each document type for user training. machine written text • Define for each data element: • Intelligent Character Recognition • General attributes Maintenance (ICR) – hand written text • Related anchors The Terms and Conditions for ISIS • Optical Mark Recognition (OMR) – • Patterns that apply to the element Papyrus Software Products apply. check boxes • Condition (rules) that have to be Free service period is 6 months • Bar code, QR code, DataMatrix fulfilled after installation. A maintenance • Logo • Test the definitions with various agreement is offered optionally documents for updates and product support. Product Information: Papyrus Business Designer Business Document Capture Administration

Papyrus Business Designer User trained Capture, teaching the machine

Product Description The Papyrus Business Designer is a modern WYSIWYG design tool for easy definitions when digitizing business content with a self-learning user trained capture capability. Document structures and extraction definitions can be created faster and better than ever before.

It specializes in supporting business capture and OCR needs during content and case-management operations, such as extracting/indexing documents in the business case (on the fly, on demand), but also lifting fields from arbitrary documents, again ad-hoc and on the fly. This is possible because the Papyrus Business Designer/Capture does not require IT involvement, it gives all the power into the hands of the actual users of the application.

Any document can be extracted on the fly, regardless whether a document template has been created for it or not. Extraction definitions created by one user can be shared with other users or entire departments.

To lift a field from a document, the business user simply drags the text/area that is to be extracted from the document onto a pane. For its OCR/ICR/Classification capabilities the Papyrus Business Designer relies on the IDEX-Engine, also used in the Papyrus Recognition Server, which is a prerequisite for the deployment of Papyrus Business Designer.

Key Benefits Classification Prerequisites • User trained capture capability • Classify new document samples • Windows 7 or later, Windows Server • Increased efficiency for content • Correct document sample categories 2012 or later digitizing: document types and • Standard office PC extraction definition can be created Change Management • Minimum display resolution of faster and better than ever before. 1280x1024 • Manage full life cycle of document • Easy and clear application for • Papyrus WebRepository structure and extraction definition business users supported by user- • Papyrus Recognition Server • Define change management process: trained technologies to create an • Papyrus Capture /Office-In for office private and group development extraction definition formats support • Deactivate or restore document • Excellent tool for both business and IT • Papyrus PDF-in for native PDF and extraction definitions to last allowing a perfect collaboration support productive version • Optimal collaboration and assuring • Anonymized document samples for • Delete not productively used the best results by utilizing Papyrus training (GPDR conform) document definitions change management • Recognition quality assurance supported by automatic evaluation of Recognition quality the extraction results for supervisor assurance decision making • Recognition results representation for the trained document samples Functions • Automatic compare with the • Document types and extraction reference data from the previous definitions for business users productive version of the extraction • User trained extraction with sample definition documents • Representation of the extraction and • Change and release management of comparison results in the optimal document definitions way to the supervisor • Recognition quality evaluation Integration Document Extraction Papyrus Business Designer/Capture Definitions is natively integrated within Papyrus Adaptive Case Management (ACM) and • Upload document samples is fully supported by it. • Create new document types • Create new data fields and UI form IT-experts can do extensions of the elements: specify element type, created extraction definition also with region, keywords, etc. the Papyrus Designer Capture in case • Create new table data fields: specify complex extraction logic is required. column element type, table header keywords etc. • Extract and paste document content Formats into an existing form or table field by • TIFF 6.0 or higher (also multi-page) drag and drop • JPEG Order Information • User trained document definitions • BMP fully compatible with Papyrus • GIF Papyrus Business Designer Capture Designer allowing to refine • PNG for Windows certain field definitions by extraction • PDF 1.4 or higher development experts for best • PDF/A (ISO 19005) Training performances • Office formats: ISIS Papyrus offers in-house • Rearrange or delete fields from form, • DOC/DOCX/DOCM/ODT workshops and standard courses delete table columns • PPT/PPTX/PPTM/ODP for user training. • XLS/XLSX/XLSM/ODS Training Maintenance • Create implicit training data during The Terms and Conditions for ISIS creation of new fields Papyrus Software Products apply. • Train extraction definitions with Free service period is 6 months training data collected during fields after installation. A maintenance manipulations (creation or update) agreement is offered optionally • Refine extraction definitions by for updates and product support. deleting training data and retraining Product Information: Papyrus Client/Capture

Papyrus Client/Capture

Product Description Papyrus Client/Capture is the Papyrus EYE Widgets based Papyrus Client/Capture can handle expanded requirements end-user interface for all kinds of user interactions within a for manual input processing such as rearranging the sequence document capture system. It enables the completion and cor- of sheets or exchanging pages between documents. rection of classification and extraction results with all necessary display and validation functions:

• Uniform handling of all incoming documents Document Verification and • Interactive check and correction of extraction results • Immediate verification of corrected data Correction Interface for Capture • Flexible image display Operator Powered by Validation • Information messages indicating recognition errors and rule violations • Administrator and operator views

Benefits Document Workplace View • Easy access to all documents via The Papyrus Client/Capture provides Papyrus Desktop/EYE Widgets or a the business user with a Document web-browser connected to a Papyrus Workplace view which enables the busi- WebPortal ness user to easily manage and manip- • One user interface for all types of ulate all processed inbound documents: documents and all tasks • classify documents manually • Workplaces with pre-configured • split and combine documents views for capture operators and • rotate, move and delete pages administrators • move images to a clipboard • Customizable to your individual • scan/import additional pages needs without programming • Ergonomic screen designs Prerequisites Core Features • Windows 7 or later, Windows Server • Display, view and edit all types of 2012 or later processed inbound documents • Standard office PC • Handling of virtually any document • Papyrus WebRepository format – images (TIFF, JPEG, BMP, GIF, • Papyrus Capture /Office-In for office PNG), HTML, CSV, TXT, native PDF and formats support PDF/A, AFP as well as all common office formats. • Fine-tuned search function for Cap- ture documents – search for document type, status, priority and name • Thumbnails Viewer with integrated document manipulation functions • Image Viewer with convenient zoom- ing and printing functions • Image Detail Viewer and color highlighting for areas of special interest • Variable color highlighting for data validation • Visual marking of rejected characters • Freely configurable masks for data display • Online validation with assistant for substitution lookup

Capture Framework Integration For rapid start-up the Papyrus Client/ Capture includes so-called capture Order Information workplaces with pre-configured views Papyrus Client/Capture 7 for capture operators and administra- for Windows tors, which provide a complete set of functionalities required for a successful Training capture project. ISIS Papyrus offers in-house work- • The Capture Workplace provides shops and standard courses for views for scanning, document man- user training. agement and document completion • The Capture Administration Work- place offers views for administrative Maintenance tasks such as queue and adapter con- The Terms and Conditions for ISIS trol, process monitoring and keeping Papyrus Software Products apply. track of tasks in the workflow Free service period is 6 months after installation. A maintenance agreement is offered optionally for updates and hotline. Product Information: Papyrus Recognition Server

Papyrus Recognition Server

Classification and Extraction Definition

Inound Document Document Type: Invoice FA MOBIE Customer Name: EMAI James Taylor Street: 10th Avenue 6649

FIE SOCIA City: New Orleans

ZIP code: 70116 SCA Country: United States of America

WEB Phone: +15046218927

Email: [email protected]

Website: www.isis-papyrus.com

Number: JT70116

Ordered by: James Taylor

Order number: MDO12709

Order date: 2019/05/02

Papyrus Invoice number: MDI29249 Recognition Invoice date: 2 May 2019 Server Payment due: 2019/06/02 Amount Taxable Amount 16,67 Total amount: 20,00

Product Description Papyrus Recognition Server applies classification and extraction definitions created with the Papyrus Designer Papyrus Recognition Server is a powerful tool for automated Capture or Papyrus Business Designer /Capture to acquire the high volume business content digitizing what is key for tight required business content from the inbound business mails. SLAs (service level agreements) in the modern business world.

The Recognition Server offers a broad range of possibilities for Key Benefits application in the field of automated sorting and distribution • Automated high volume content digitizing to keep of electronic documents, fax and paper mail. For data business SLAs extraction, the Recognition Server can identify unstructured • Powerful classification and extraction of business relevant and structured documents with great reliability. Various types content out of high volume of inbound data of content: whether machine or hand written text, check • Excellent results for both FixForm and FreeForm® documents boxes or diverse bar codes, QR codes, DataMatrixes - can • Support of documents from all common file formats and be recognized and identified as business related content inbound channels such as scan, e-mail, mobile/photos, web by means of powerful document analysis using pattern and social media. recognition, keywords, relative positions, voting algorithms, • Support of diverse recognition engines for different kinds of layout analysis and rules. content, powerful preprocessing and extraction defined with Papyrus Designer Capture and Papyrus Business Designer.

Features Document structure analysis Document Classification To discover relevant content the follow- The purpose of the Papyrus Recognition ing main possibilities and their mixture Server for document classification is to can be applied during the extraction enable an automated process of judg- process based on the prepared ex- ing incoming documents according traction definition: to selected criteria, sorting them into • Patterns freely definable categories – thereby • Keywords making information actually accessible • Regions for the company – and forwarding them • Positions accurately to those who are in charge of • Anchor points the issue. • Rules • Layout Documents which could not be • Logo assigned to a class unequivocally are separated and presented to the admin- Data formats istrator or clerk for further assessment. The Papyrus Recognition Server can process the following data formats: Data Extraction • TIFF 6.0 or higher (also multi-page) The Papyrus Recognition Server ex- • JPEG and JPEG 2000 tracts and reads all necessary field data • BMP from the identified document class. • GIF This process can include unstructured • PNG layouts and structured forms with key- • HTML words at predefined positions. • CSV • TXT (plain text) Image Preprocessing • PDF 1.4 or higher According to the applied classification • PDF/A (ISO 19005) and extraction definitions the following • AFP image pre-processing can be used: • Office formats: • Dirt removal, Despeckle • DOC/DOCX/DOCM/ODT • Punch hole removal • PPT/PPTX/PPTM/ODP • Automatic rotation • XLS/XLSX/XLSM/ODS • Binarize • Convert color to gray • Box, line, grid and combs remover Prerequisites • Drop out color • Windows 7 or later; Windows Server • Dilate 2012 or later • Erode • Linux (SLES 11 or later, RHEL 5 or later) • Deskew on border • Papyrus WebRepository • Deskew on content • Papyrus Capture /Office-In for office formats support Recognition engines • Papyrus PDF-in for native PDF sup- Content of pre-processed images can port be recognized by a powerful set of • Papyrus Designer Capture or Papyrus Order Information recognition engines belonging to the Business Designer Papyrus Recognition Server for following main groups: Windows and Linux • Optical character recognition (OCR) – machine written text Training • Intelligent Character Recognition ISIS Papyrus offers in-house work- (ICR) – hand written text shops and standard courses for • Optical Mark Recognition (OMR) – user training. check boxes • Bar code, QR code, DataMatrix • Logo Maintenance • Signature The Terms and Conditions for ISIS Papyrus Software Products apply. Free service period is 6 months after installation. A maintenance agreement is offered optionally for updates and hotline.